Sinkron : jurnal dan penelitian teknik informatika

Comparison of Performance of K-Nearest Neighbors and Neural Network Algorithm in Bitcoin Price Prediction

Eko Aziz Apriadi, Sriyanto, Sri Lestari, Suhendro Yusuf Irianto — Sun, 31 Mar 2024 00:00:00 +0000

This research evaluates and compares the performance of two prediction methods, namely K-Nearest Neighbors (K-NN) and Neural Network, in the context of Bitcoin price prediction. Historical Bitcoin price data is used as input to train and test both algorithms. Experimental results show that the K-NN algorithm produces a Root Mean Square Error (RSME) of 389,770 and a Mean Absolute Error (MAE) of 89,261, while the Neural Network has an RSME of 614,825 and an MAE of 284,190. Performance comparison analysis shows that, on this dataset, K-NN has better performance in predicting Bitcoin prices compared to Neural Network. These findings provide important insights for the selection of crypto asset price prediction models, especially Bitcoin, in financial and investment environments

Edge Detection Model Performance Using Canny, Prewitt and Sobel in Face Detection

I Wayan Rangga Pinastawa, Musthofa Galih Pradana, Khoironi — Sun, 31 Mar 2024 00:00:00 +0000

Detection of objects in the form of objects, humans and other objects at this time has been widely applied in many aspects of life. The help of this technology can facilitate human work, one of which is facial detection to get information about a person's identity. Face identification and detection is closely related to Data Mining science with Image Processing sub-science. This facial detection and recognition can use several technical approaches, one of which is to use edge detection. Edge detection is one of the basic operations of image processing. In the image classification process, edge detection is required before image segmentation processing. There are several methods that can be used to perform edge detection such as Canny, Prewitt and Sobel. These three methods are methods that have accurate and good detection results, with the advantages of each method having its own added value. From the results of previous studies that stated these three methods have good results, it became interesting to conduct a comparative study of these three methods in detecting edges in facial images. Edge detection applied to this study identifies facial images, and will get similarities with the original image from the result analysis process, and is reinforced by measurement results using the Mean Square Error error degree. The final result of this study states that this study the most optimal Mean Square Error measurement results obtained the final results in the Canny method of 10, the Prewitt method of 41 and Sobel of 29. These results show that the value of the Canny method has the smallest Mean Square Error value, which indicates that the Canny method on facial image edge detection has the most optimal results.

Optimizing Facial Expression Recognition with Image Augmentation Techniques: VGG19 Approach on FERC Dataset

Fahma Inti Ilmawati, Kusrini, Tonny Hidayat — Sun, 31 Mar 2024 00:00:00 +0000

In the field of facial expression recognition (FER), the availability of balanced and representative datasets is key to success in training accurate models. However, Facial Expression Recognition Challenge (FERC) datasets often face the challenge of class imbalance, where some facial expressions have a much smaller number of samples compared to others. This issue can result in biased and unsatisfactory model performance, especially in recognizing less common facial expressions. Data augmentation techniques are becoming an important strategy as they can expand the dataset by creating new variations of existing samples, thus increasing the variety and diversity of the data. Data augmentation can be used to increase the number of samples for less common facial expression classes, thus improving the model's ability to recognize and understand diverse facial expressions. The augmentation results are then combined with balancing techniques such as SMOTE coupled with undersampling to improve model performance. In this study, VGG19 is used to support better model performance. This will provide valuable guidelines for optimizing more advanced CNN models in the future and may encourage further research in creating more innovative augmentation techniques.

SIAKAD Mobile With API Service To Improve Academic Services

Sun, 31 Mar 2024 00:00:00 +0000

Developing SIAKAD (commonly called SIAM, Student Academic Information System) Mobile using API Service to improve academic services for students is the goal of researchers doing so because it supports the implementation of education to create better information distribution services for everyone who wants access to it. And this also has an impact on academic performance, it is easier to organize lecturer attendance schedules, value recapitulation, and so on. Conventional SIAKAD (SIAM) which can be accessed via a computer or laptop has limited accessibility and practicality, which can hinder students from accessing academic information flexibly. Therefore, after researchers have examined and paid attention to several systems that can be implemented to assist users in accessing them, the development of SIAKAD in the form of a mobile application is a solution to increasing accessibility and ease of access to academic information. The API service is used as a communication bridge between the SIAKAD mobile application and the backend system. Through this, the Mobile Application can communicate (send requests and receive responses from the backend system) quickly and efficiently. But to shorten the application development time we use the SCRUM method and for the business process model, we use BPMN to create, design and design this application. The results of this study the authors see a compare of the time that can increase after using Mobile in access SIAKAD (SIAM).

Extraction of Shape and Texture Features of Dermoscopy Image for Skin Cancer Identification

Febri Aldi, Sumijan — Sun, 31 Mar 2024 00:00:00 +0000

Skin diseases are increasing and becoming a very serious problem. Skin cancer in general there are 2, namely melanoma and non-melanoma. Cases that are often encountered are in non-melanoma types. A critical factor in the treatment of skin cancer is early diagnosis. Doctors usually use the biopsy method to detect skin cancer. Computer-based technology provides convenient, cheaper, and faster diagnosis of skin cancer symptoms. This study aims to identify the type of skin cancer. The data used in the study were 6 types of skin cancer, namely Basal Cell Carcinoma, Dermatofibroma, Melanoma, Nevus image, Pigmented Benign Keratosis image, or Vascular Lesion, with a total of 60 dermoscopy images obtained from the Kaggle site. Dermoscopy image processing begins with a pre-processing process, which converts RGB images to LAB. After that, segmentation is carried out to separate objects from the background. The method of extracting shape and texture features is used to obtain the characteristics of dermoscopy images. As many as 2 types of shape features, namely eccentricity and metric, and 4 types of texture features, namely contrast, correlation, energy, and homogeneity. The result of this study is that it can identify the type of skin cancer based on image features that have been extracted using a program from the Matlab application. The technique of extracting shape and texture features is proven to work well in identifying the type of skin cancer. In the future it is expected to use more data, and add color features in identifying dermoscopy images.

Integrated Selection of Permanent Teacher Appointments Recommended MCDM-AHP and WASPAS Methods

Sun, 31 Mar 2024 00:00:00 +0000

The teacher's role is very important in improving the national learning system. Many honorary teachers are empowered in curriculum development in a number of schools who want to collaborate in improving the quality of their students. The purpose of this research is to provide rewards to honorary teachers who have long served for the progress of the nation in the world of education to be appointed as permanent teachers. The selection method was carried out through a criteria weighting technique with the MCDM-AHP method which was integrated with the WASPAS method. The technique of developing the MCDM-AHP method as an eigenvector measurement concept with proof of optimization through mathematical algebra matrices that is correlated with the Expert Choice application to get optimal values. The result optimization value is integrated with the WASPAS method as a determinant of the ranking system for permanent teacher candidates. This method is a unification of the concepts of the weight product model and weight sum model methods, so that it has special stages to support decision making with the WASPAS method. The results of selecting twelve honorary teachers for appointment as permanent teachers can be seen from the acquisition of the Qi optimization value as a ranking. The results of support for decision making for permanent teacher appointments with the highest optimization value were given to TC04 with a weight of 0.878; followed by a significant difference in the next rank. The findings of this study provide evidence that the integration of the MCDM-AHP and WASPAS methods provides continuous optimization results for decision-making support.

Exploring Regional Development Patterns using Machine Learning: A Python-based Clustering Analysis of Human Development Index in West Java

Kartika Mariskhana, Ita Dewi Sintawati, Widiarina — Sun, 31 Mar 2024 00:00:00 +0000

Many local governments now prioritize human development when trying to raise the standard of living and welfare of their citizens. Developing effective development policies in West Java, one of Indonesia's most populous provinces, requires a thorough understanding of human development patterns in various districts and cities. Using the Human Development Index (HDI) as the primary indicator, we examine regional development patterns in this study using machine learning techniques, specifically clustering analysis. This study's scope includes an HDI analysis for each of West Java's 27 districts and cities from 2017 to 2022. Finding clusters of districts or cities with comparable human development traits and comparing and contrasting them are our primary goals. We provide a solution that allows for improved mapping and comprehension of human development patterns in West Java by utilizing the Python programming language as the primary tool and the K-Means clustering algorithm. The study's findings indicate that there are three major categories of districts and cities, each with a distinct human development pattern. By using clustering analysis, we can determine which districts or cities within each group have the highest and lowest levels of human development. This information helps policymakers plan more inclusive and sustainable development. In conclusion, a clustering analysis approach based on machine learning can be a helpful tool for understanding and creating more focused and efficient regional development policies in West Java and other areas.

Analyzing Public Sentiment Regarding the Qatar 2023 World Cup Debate Using TF-IDF and K-Nearest Neighbor Weighting

Sayyid Muh. Raziq Olajuwon, Kusrini, Kusnawi — Sun, 31 Mar 2024 00:00:00 +0000

This research aims to uncover the sentiment of Twitter users regarding the polemics surrounding the 2023 Qatar World Cup using a text-based sentiment analysis approach. The research methodology involves collecting data from Twitter posts, encompassing discussions, opinions, and responses related to the Qatar World Cup 2023. The TF-IDF weighting is applied to identify significant keywords in each post, while the K-Nearest Neighbor algorithm is employed to classify sentiments as positive, negative, or neutral. The findings reveal a comprehensive picture of how the public perceives the Qatar World Cup 2023 on the Twitter platform. The results not only cover positive and negative aspects of online discussions but also identify trends and patterns of sentiment that emerge during specific periods.The application of these methods provides valuable insights into understanding the dynamics of public opinion related to international sports events through the lens of social media. The results of the analysis demonstrate that a majority of Twitter users express positive sentiments towards the Qatar World Cup 2023, highlighting excitement and anticipation. However, some negative sentiments also arise, primarily related to controversies and concerns about the event. The research further identifies temporal variations in sentiment, reflecting changing public perceptions over time.This research contributes to the development of sentiment analysis methods by using a combination of TF-IDF weighting and the K-Nearest Neighbor algorithm to delve into Twitter users' perspectives. Consequently, the findings have practical applicability for further research and implementation in managing the social impact and public perception of major sporting events like the World Cup. .

Comparison Of Naïve Bayes And Decision Trees In Determining The Best Manager Of Nurul Jadid Islamic Boarding School Based On Forward Selection

Farhan Dardiri — Sun, 31 Mar 2024 00:00:00 +0000

In an effort to find a solution for determining the best administrators, Islamic boarding school administrators try to determine the nominations for the best administrators using existing service data and knowledge. The process of determining nominations for the best administrators is less accurate, requiring computational methods to classify which administrators fall into the best category. In the context of data mining, classification is an important aspect. One of the classification models used is Naïve Bayes which focuses on class probability, and Decision Tree C4.5 which produces a decision tree to determine the priority of indicators that are most influential in predicting the best management. Both of these algorithms have their respective advantages. This research aims to analyze and compare the performance of the Naïve Bayes and Decision Tree classification algorithms. The comparative results of testing the Naïve Bayes and C4.5 algorithms in determining the nominations for the best administrators at the Nurul Jadid Paiton Probolinggo Islamic Boarding School on 455 administrator data tested in this study show that there is a fairly large comparison of accuracy. Naïve Bayes with Forward Selection has an accuracy rate of 91.21%, higher than Naïve Bayes itself whose accuracy results are only 87.64%. there is a difference of 3.57%. Likewise, the accuracy of C4.5 with Forward Selection has an accuracy rate of 90.99%, higher than C4.5 alone which has an accuracy rate of 90.11%. there is a difference of 0.88%. So in the comparison between 4 algorithm model trials, Naïve Bayes and Forward Selection had the most dominant accuracy with an accuracy result of 91.21%.

C4.5 Forward Selection Based Algorithm For Class Level Classification Of Nurul Jadid Islamic Boarding School Students

Muhammad Isomul Irfan — Sun, 31 Mar 2024 00:00:00 +0000

Pesantren is an Islamic educational institution that plays a central role in the development of education in Indonesia. Although originally established for Islamic religious education (Pendidikan Agama Islam or PAI), pesantren has evolved into an educational institution that contributes to both scholarly and community service aspects. According to the regulations set by the Ministry of Religious Affairs of the Republic of Indonesia under Number 31 of 2020, pesantren is a community-based institution that upholds the teachings of Islam rahmatan lil'alamin (Islam as a blessing for all) and the noble values of the Indonesian nation. Pesantren education is efficient because it is conducted in a boarding school setting, which shapes the character of its students or 'santri.' However, the current method of determining the grade levels of santri is often inaccurate, relying solely on the average scores of entrance exams without considering essential aspects of subjects. This leads to a decrease in students' interest in learning and delays in achieving higher levels of education. By utilizing data mining techniques, such as the C4.5 algorithm based on Forward Selection, it is possible to address this issue and enhance the accuracy of placing santri into their appropriate grade levels at the Nurul Jadid Paiton Probolinggo pesantren. This improvement can make the pesantren education system more effective in managing student learning

GOVERNANCE EVALUATION ELECTRONIC SECURITY SYSTEM (ESS) (Case Study: ABC Central Bank)

RZ Abdul Aziz, Anas Ikhsanudin, M Said Hasibuan — Sun, 31 Mar 2024 00:00:00 +0000

As we know, the role of the security system has a very important role for a state institution to provide security and comfort in carrying out its functions, such as the ABC central bank. A good security system is a security system that is supported by a reliable electronic security system and is composed of several components such as a CCTV monitoring system, Access Control System (ACS), Security Alarm System (SAS), and Fire Alarm System (FAS). This system is very necessary to provide support for the duties of these state institutions to protect devices, data and electronic infrastructure from potential threats and security risks. The main functions of electronic security systems include prevention, detection, response to incidents, and recovery after disturbances/disasters. For this reason, efforts are needed to provide an evaluation of the system maturity level and information security management as a form of risk management to maintain the continuity of system use. This research uses the INDEKS KAMI 4.1 to map ESS governance maturity and the OCTAVE Allegro method to analyze information security management. From the analysis carried out, it has been concluded that the ESS implementation has been operated well in accordance with the security system requirements and has reached a good level of governance maturity. Information security management analysis carried out using the OCTAVE Allegro method has succeeded in identifying information security management with the result that information security management has been implemented well. This is proven by the existence of indicators, namely CCTV recording data, log systems as information assets that have been managed and distributed according to authority

Comparison of Naïve Bayes and SVM in Sentiment Analysis of Product Reviews on Marketplaces

Nurul Zalza Bilal Jannah, Kusnawi — Sun, 31 Mar 2024 00:00:00 +0000

At this time more and more people are switching to shopping online in existing marketplaces such as Shopee. Marketplaces provide various advantages and disadvantages to customers such as lower costs and goods sent not according to orders. Product reviews from customers greatly affect the sales level of business people so that sentiment analysis is carried out. The importance of conducting sentiment analysis of product reviews in the marketplace is to add an overview of how the product is received by users. This research uses Naïve Bayes and SVM algorithms for sentiment analysis of beauty care product review datasets obtained from Shopee scraping results. This research implements k fold cross validation for data splitting process of 10 folds. The Naïve Bayes algorithm obtained the highest accuracy value of 85.53% on fold 2 and the lowest accuracy value of 77.16% on fold 3. While the SVM algorithm obtained the highest accuracy value of 88.58% on fold 2 and the lowest accuracy value of 82.99% on fold 7. With this it is stated that SVM can work better for sentiment analysis of beauty care product reviews on the Shopee marketplace because it gets a higher average accuracy value of 86.14% compared to the Naïve Bayes algorithm.

Comparison of Smartphone Technology using AHP, ELECTRE, and PROMETHEE Methods

Akmaludin, Adhi Dharma Suriyanto , Nandang Iriadi, Kudiantoro Widianto — Sun, 31 Mar 2024 00:00:00 +0000

The progress of smartphone technology is now very rapid, supported by many renewable features, even many users are competing to get the latest products without regard to the costs that have been incurred. The problem that arises is that it is increasingly difficult to select technology-based products with many criteria. The purpose of writing this paper is to provide the best solution for selecting technology-based products with multi-criteria to suit user needs by taking into account the costs incurred effectively and the use of contradictory multi-criteria applications. The presence of technology products always has many criteria that make it more difficult for users to choose products as the right choice according to their needs, thus the right method is needed as a solution to obtain technology-based products such as smartphones. The Analytic Hierarchy Process (AHP) method is used for the evaluation and selection process. This AHP method will collaborate with the ELECTRE and PROMETHEE methods as a comparison solution for smartphone product selection. The resulting comparison will be an applied model for smartphone selection that produces the best decision-making support according to user needs. The results of the collaborative implementation process of the ELECTRE and PROMETHEE methods provide a decision on the rating system. The collaborative application of the AHP method to the ELECTRE and PROMETHEE methods provides optimal decision support for the selection process, so that this can be used as a comparison material in making decisions regarding the selection of smartphones as technology-based products.

Analyzing UI and UX of Verval PTK: Impact on Elementary School Data Precision

Shamsul Huda, Ari Eko Wardoyo, Henny Wahyu Sulistyo — Sun, 31 Mar 2024 00:00:00 +0000

This study explores the implementation of the Verval PTK application in elementary school data management in Kabupaten Jember, with emphasis on its impact and precision. The research methodology adopts a differential qualitative descriptive design, with the main focus on elementary schools in Kabupaten Jember that have integrated Verval PTK. Five Elementary Schools were involved in the study. Among others, SD Negeri Jember Lor 2, SD Negeri Kepatihan 1, SD Negeri Jember Kidul 2, SD Negeri Kebonsari 1, and SD Negeri Patrang 1. In the analysis, the study involved technical aspects such as usability tests, performance measurements using Lighthouse, and A/B tests. However, challenges related to platform accessibility and stability are still a concern. Performance measurement using Lighthouse shows excellent scores, although SEO scores require further attention to improve. A/B tests highlight significant improvements in time efficiency and data accuracy through Verval PTK implementations, but some low scores require more in-depth analysis. A number of technical recommendations were put forward to improve the security, stability, accessibility, and SEO optimization of Verval PTK. Regular software updates, efficient error management, and real-time performance monitoring are key focuses to support continuous development. This recommendation is directed to strengthen the role of Verval PTK in supporting efficient and accurate school data management.

Comparative Study: Preemptive Shortest Job First and Round Robin Algorithms

Rakhmat Purnomo, Tri Dharma Putra — Sun, 31 Mar 2024 00:00:00 +0000

Abstract: Operating system is a software acting as an interface between computer hardware and user. Operating system is known as a resource manager. The main responsibility of operating system is to handle resources of computer system. Scheduling is a key concept in computer multitasking and multiprocessing operating system design by switching the CPU among process. Shortest job first (SJF) and round robin are two wellknown algorithms in CPU processing. For shortest job first, this algorithm can be preemptived. In preemptive shortest job first, when a new process coming in, the process can be interupted. Where with round robin algorithm there will be time slices, context switching, or also called quantum, between process. In this journal we wil discuss comparative study between preemptive shortest job first and round robin algorithms. Three comparative studies will be discussed to understand these two algorithms more deeply. For all comparative study, the average waiting time and average turnaround time is more for round robin algorithm. In the first comparative study, we get average waiting time 52% more. For average turnaround time, 30% more. In second comparative analysis, we get 52 % average waiting time more and we get 35 % average turnaround time more. For third comparative analysis, average waiting time we get 50% more and for average turnaround time, we get 28% more. Thus it is concluded in our comparative study for these kind of data the preemptive shortest job first is more efficient then the round robin algorithm.

Keywords: comparative study, premptive shortest job first algorithm, round robin algorithm, turn around time, average waiting time, time slice

Feasibility Analysis of Bengkel Koding Website Using Black Box Testing and Boundary Value Analysis

Clara Edrea Evelyna Sony Putri, Ajib Susanto — Sun, 31 Mar 2024 00:00:00 +0000

In an era of rapid technological development, application development has become common, especially in coding. However, most websites do not give appropriate assignments and instructors to help improve coding skills. Because of this, the Bengkel Koding of Dian Nuswantoro University Semarang is a solution to improving the quality of coding learning. This research aims to identify the shortcomings in the website and ensure that the website functions as expected by the users. By testing the application like this, researchers can know which problems can affect the user experience. This research uses one of the frequently used tests, namely Black Box testing. The objective is to verify that the system's functions, inputs, and outputs align with the specified requirements. In addition to the Black Box method, this research uses a technique called Boundary Value Analysis. This technique is to identify errors or bugs that can affect the user experience by focusing on the input value boundary. The test results will use a quality ratio that will determine whether or not the system is suitable for use by users. Through 30 test cases, most website functions have been tested properly, with the feasibility level reaching 83.333%. Nonetheless, five errors or bugs were still found, emphasizing the need for further improvement. The results of this study provide valuable insights into improving the quality and convenience of users in accessing the Bengkel Koding website.

Comparison of CNN and SVM Methods on Web-based Skin Disease Classification Process

Ahmad Ilham Kushartanto, Fauziah, Rima Tamara Aldisa — Sun, 31 Mar 2024 00:00:00 +0000

Skin, as the outermost layer of the body, is often in contact with bacteria, germs and viruses because of its most external position. According to statistics from the 2009 Indonesian Health Profile, skin illness is the third most common ailment seen in outpatient settings across the country's hospitals. Therefore, maintaining healthy skin is important because it protects the body's internal organs from injury and attack by pathogens. The development of image classification, such as the classification of skin diseases, has become a focus in the health sector. This research analyses the performance of Convolutional Neural Network (CNN) and Support Vector Machine (SVM) in web-based skin disease classification and overcomes the problem of imbalanced training data. With data augmentation and preprocess, this research improves data generalization and compares performance metrics such as Recall, Accuracy, and F1 Score. The results show that the average accuracy of CNN is 83.8%, while SVM reaches 81%. Although both models have high metrics for the normal class, other more complicated classes can only be handled by CNN with a value of more than 0.9. Apart from that, the CNN method also provides a higher Confidence Score than SVM, as well as a faster execution time. In conclusion, the CNN method is superior and recommended for skin disease classification based on web applications based on various performance test results.

Development of an Intelligent Imaging System for Determining Maturity of Copra Flesh in Coconuts Using Shape and Texture Extraction

Yogi Wiyandra, Firna Yenila, Suci Wahyuni — Sun, 31 Mar 2024 00:00:00 +0000

Copra is dried coconut meat that is used to produce coconut oil. According to the Central Statistics Agency (BPS), Indonesia's copra production in 2020 reached 2.3 million tonnes. This is one form of the process of improving the economy of people living on the coast. This research was conducted to educate farmers in determining the level of maturity of the copra meat produced. This research was conducted using an extraction method that involves colour extraction and texture extraction. the method is used to provide convenience in seeing the level of maturity of the two characteristics of copra obtained in the field, namely texture and colour. The process obtained in the training with one of the images used as a test image in colour extraction produces area, perimeter, metric and eccentricity values in label 3 with values of 651.00, 184.69, 0.24 and 0.89. while in the feature extraction method the results are obtained with an average intensity value of 243.31, standard deviation of intensity 39.76 and entropy value of the tested image 4.57. The method is able to perform a detection process so that it can determine the level of maturity of copra seen from the existing types of copra such as asalan copra, regular copra, black copra and wet copra, each of which provides different functions in the copra processing stage. The process will be carried out using KNN which is seen from all test data and training data stored after the detection process. The results of the process carried out using digital images involving the extraction method for detection and KNN for classification are able to provide the right value. This is evidenced by the better accuracy value of 98%.

Clothing Recommendation System Using the K-Nearest Neighbor Method

Arya Maghrizal Putra, Muhamad Irsan, Muhammad Faris Fathoni — Sun, 31 Mar 2024 00:00:00 +0000

The world of fashion and the way we interact with it has been transformed by advances in information and communication technology. Clothing recommendation applications have become increasingly common, helping people choose clothes that suit their style and preferences. This study suggests using the KNN Method as a basis for building a more intelligent and personalized clothing recommendation system. To address the growing need for accurate clothing recommendations that match users' preferences, The goal of this research is to create a clothing recommendation system that can help users choose more appropriately because advances in technology have made it possible to gather and examine user data more thoroughly. In this study, the clothing recommendation system was implemented using the KNN Method. We ran simulations by setting the clothing dataset's parameter K value from 3 to 11. The simulation results show that the system's performance reaches its peak at parameter value K=8. We measured the system's accuracy, precision, and recall at this K value in order to assess its performance. The results show that the clothing recommendation system uses the KNN Method. A clothing recommendation system based on the KNN Method with the parameter K=8 has proven successful in classifying clothes with an accuracy of 83,67%.

Rice Plant Disease Detection System Using Transfer Learning with MobilenetV3Large

Rifqi Raenanda Faqih, Muhamad Irsan, Muhammad Faris Fathoni — Sun, 31 Mar 2024 00:00:00 +0000

In this study, we address that foliar diseases of rice (Oryza sativa L.) pose a serious threat to agricultural productivity and propose an effective method for disease detection using Convolutional Neural Network (CNN). We use transfer learning on the MobilenetV3Large model to improve the model's performance. Our study involves a curated dataset containing images of infected rice leaves, followed by a careful preprocessing step. This dataset is then used to train a CNN model. The results show a commendable accuracy rate of over 90% and almost reaching 95% when the model is trained over 200 epochs. The model performance graph shows a consistent upward trend in accuracy coupled with decreasing loss during the training process. Furthermore, the classification results highlight the ability of the model to discriminate between different types of diseases affecting rice leaves. This study demonstrates the effectiveness of our proposed method and positions it as a valuable tool for leaf disease detection in rice. By providing faster and more accurate control measures, our approach has the potential to significantly improve agricultural productivity. The successful application of the CNN model using MobilenetV3Large highlights its adaptability and robust performance in addressing the pressing problem of rice leaf diseases and provides a promising path for future advances in precision agriculture.

Optimizing Attendance Data Security by Implementing Dynamic AES-128 Encryption

Mukhsin Nuzula, Yuwaldi Away, Kahlil; Andri Novandri — Sun, 31 Mar 2024 00:00:00 +0000

The protection of data security is crucial, particularly when dealing with the transmission of sensitive information through communication networks. This article explores the Advanced Encryption Standard 128-bit (AES-128) algorithm as an effective and secure cryptographic solution. The paper proposes the dynamic development of the AES-128 cryptography method by implementing a dynamic key to enhance the security of employee attendance data. The dynamic key involves changing the encryption key every minute, providing an additional security layer and reducing the risk of decryption by unauthorized parties. Test results indicate that the dynamic AES-128 encryption algorithm demonstrates optimal performance. The consecutive encryption and decryption speeds for sending attendance data are 14656.78 bit/s and 21898.21 bit/s, respectively. The consistent duration of the encryption and decryption processes, at 6.66ms and 2.44ms, along with an Avalanche Effect rate of 50.73% and an Entropy of 6.67 bit/symbol, emphasizes the algorithm’s efficiency and stability. This research not only reinforces the desired level of security but also outperforms several previous studies. Analyzed performance data indicates that this method is not only efficient but also stable in maintaining data security, addressing significant variations in data length. Thus, the implementation of dynamic AES-128 cryptography in attendance systems provides a significant advantage in addressing information security challenges in the current digital era.

Sentiment Analysis of Mobile Provider Application Reviews Using Naive Bayes Algorithm and Support Vector Machine

Tiara Sari Ningsih; Teguh Iman Hermanto, Imam Ma'ruf Nugroho — Sun, 31 Mar 2024 00:00:00 +0000

To choose a mobile provider to use, prospective users often rely on reviews left by previous users of the mobile provider application. One source of information for finding reviews of cellular provider applications is the Google Play Store. The purpose of this research is to analyze user reviews of cellular provider applications and find out the comparison of the accuracy levels of the two algorithms to be used, namely the Naïve Bayes Classification (NBC) and Support Vector Machine (SVM) algorithms. The object of this research is focused on the three most popular applications in Indonesia, according to the Goodstate website, namely Telkomsel, IM3, and XL Axiata. After testing using the Naïve Bayes Clasification method, the accuracy value obtained in the MyTelkomsel application is 75%, MyIM3 is 80%, and MyXL is 72%. While the Support Vector Machine method obtained an accuracy value of 77% for MyTelkomsel, 80% for MyIM3, and 76% for MyXL.

Hybrid Analysis of Road Service Level Determination Decision Support System

Dodi Guswandi, Maiyozzi Chairi — Sun, 31 Mar 2024 00:00:00 +0000

Traffic congestion on the highway is one of the problems often faced by road users, as on the highway traffic in the city of Padang often experiences congestion due to the growth of several highways that are relatively smaller than the growth of traffic volume, causing a decrease in road service levels. This study aimed to determine the level of road services in several traffic lanes in the city of Padang. Data analysis using Hybrid Decision Support System (HDSS) modeling by combining the Analytical Hierarchy Process (AHP) method with the Weighted Aggregated Sum Product Assessment (WASPAS) This method is included in the Multi-Criteria Decision Making (MCDM) group. The AHP method can consistently determine the weight value of each criterion, and the WASPAS method can analyze alternative data to obtain decision results by ranking with the Weighted Sum Model (WSM) and Weighted Product Model (WPM) processes. The ranking results show that there are three types of road services in the city of Padang, namely B, C, and D with an accuracy rate of 0.6947%, this the results of this study using HDSS modeling can provide a better analysis process.

Classification of types Roasted Coffee Beans using Convolutional Neural Network Method

Halifa Sekar Metha, Kusrini, Dhani Ariatmanto — Sun, 31 Mar 2024 00:00:00 +0000

In the current digital era, the role of technology in the agricultural industry is very necessary to increase yields which can have an impact on the productivity and welfare of farmers. Coffee is a drink that has been very popular for many years. Due to the high demand for coffee beans, this research aims to develop a system that can classify types of roasted coffee beans based on images using the Convolution Neural Network (CNN) method. Coffee bean processing is the most important stage in the coffee industry, classifying coffee beans often requires more in-depth knowledge and extensive experience regarding coffee beans. Therefore, this system can be a more effective solution. The author collects a dataset containing types of roasted coffee beans, then the Convolutional Neural Network (CNN) can analyze in the form of visual patterns each type of coffee bean. This implementation is expected to help the coffee industry identify coffee beans quickly and accurately.

Face Detection in Complex Background using Scale Invariant Feature Transform and Haar Cascade Classifier Methods

Sun, 31 Mar 2024 00:00:00 +0000

Face detection is a process by a computer system that can find and identify human faces in digital images or videos. One of the main challenges faced in the face detection process is the complex background. Complex backgrounds, such as many color combinations in the image, can interfere with the detection process. To overcome this challenge, this research uses a combination of two methods: Scale Invariant Feature Transform (SIFT) and Haar Cascade Classifier. Scale Invariant Feature Transform (SIFT) is a method used in image processing to identify and describe unique features in an image. The SIFT method looks for keypoint descriptors in images that can be used as a reference in comparing different images. After the keypoint descriptor is found with SIFT, the Haar Cascade Classifier method is used to detect faces in the image. Haar Cascade Classifier is a practical algorithm for object detection in images. After facial features are extracted with these two methods, the results are compared with the K-Nearest Neighbor (KNN) approach. This research involves the introduction of 28 color images with complex backgrounds. The results of combining these two methods produce an accuracy of 81.75%. This shows that combining these two methods effectively overcomes complex background challenges in face detection.

Music Genre Classification Using K-Nearest Neighbor and Mel-Frequency Cepstral Coefficients

Tika Pratiwi, Andi Sunyoto , Dhani Ariatmanto — Sun, 31 Mar 2024 00:00:00 +0000

Music genre classification plays a pivotal role in organizing and accessing vast music collections, enhancing user experiences, and enabling efficient music recommendation systems. This study focuses on employing the K-Nearest Neighbors (KNN) algorithm in conjunction with Mel-Frequency Cepstral Coefficients (MFCCs) for accurate music genre classification. MFCCs extract essential spectral features from audio signals, which serve as robust representations of music characteristics. The proposed approach achieves a commendable classification accuracy of 80%, showcasing the effectiveness of KNN-MFCC fusion. Nevertheless, the challenge of overlapping genres, particularly rock and country, demands special attention due to their shared acoustic attributes. The inherent similarities between these genres often lead to misclassification, hampering accuracy. To address this issue, an enhanced feature engineering strategy is devised, leveraging deeper insights into the subtle nuances that differentiate rock and country music. Additionally, a refined KNN distance metric and neighbor selection mechanism are introduced to further refine classification decisions. Experimental results underscore the effectiveness of the refined approach in mitigating genre overlap issues, significantly enhancing classification accuracy for rock and country genres. This study contributes to the advancement of music genre classification techniques, offering an innovative solution for handling overlapping genres and demonstrating the potential of KNN-MFCC synergy in achieving accurate and refined genre classification.

Stability Analysis of Dapodik Website: A WebQual Efficiency Model Approach

Hadi Mulyono, Ari Eko Wardoyo, Luluk Handayani — Sun, 31 Mar 2024 00:00:00 +0000

This study aims to provide a deeper understanding of how Dapodik can play a role in supporting efficiency and improving the quality of education at the primary level. The research methodology adopts qualitative research design using WebQual 4.0 model. A qualitative approach was chosen to gain an in-depth understanding of user experience regarding the stability and effectiveness of Dapodik in the management of educational data. This study involved participants from two leading elementary schools in Kabupaten Jember, Jember Lor 3 State Elementary School and Al Furqon Elementary School. In its analysis, the research instrument covers three main aspects. The findings show fluctuations in usability scores that reflect application access and performance instability. Although Dapodik shows a good focus on search engine optimization with high SEO value and best practices, improvements to the Largest Contentful Paint (LCP) and page structure are needed to improve stability and responsiveness. The results of operator interviews show the adequacy of Dapodik information, however, more attention is needed in understanding the features of the application. User service responsiveness can be improved by minimizing delays in providing guidance. Suggestions for improvement include stabilization of applications and improved understanding of features, while continued research can explore the positive impact of Dapodik in the context of student learning in various educational environments.

LSB-2 Steganography with Brotli Compression and base64 Encoding for Improving Data Embedding Capacity

Sun, 31 Mar 2024 00:00:00 +0000

Steganography functions as a technique for embedding messages or data in various forms of media, such as images, audio, video, or text, with the aim of avoiding detection by unauthorized parties. Steganography techniques can be used as a solution to hide and protect data. In this research, steganography will be carried out using images as the transmission object. This research was conducted to offer a modification of the Least Significant Bit (LSB) steganography technique using the LSB-2 method with Brotli compression and base64 encoding. Modification and use of Brotli compression and base64 coding aims to increase the message capacity that can be embedded in a transmission object while maintaining the quality of the transmission object. Experiments using small data and big data. The experimental results will be presented in tabular form by comparing the original image with the steganographically processed image using metrics such as Mean Square Error (MSE), Peak Signal-to-Noise Ratio (PSNR), and Structural Similarity Index (SSIM) as a comparison. The experiments carried out resulted in an increase in image capacity by reducing capacity usage with an average of 47.13% for small data and an average of 71.34%. The big data experiment resulted in an increase in the PSNR value of around 3.49%, accompanied by a decrease in the average MSE value of 33.85%, and a constant SSIM value of 0.9999, thus proving that the proposed method was successful in increasing image capacity and improving stego-image quality. when embedding big data.

Depression Detection of Users in Social Media X using IndoBERTweet

Muhammad Fadhel, Warih Maharani — Sun, 31 Mar 2024 00:00:00 +0000

According to the Ministry of Home Affairs, the population of Indonesia stands at 273 million, Indonesia has approximately 167 million active subscribers to virtual entertainment platforms, including YouTube, Facebook, Instagram, and Twitter. The use of online entertainment is huge, particularly on Twitter, and has been associated with mental health implications, such as depression. This research objective is to do a comprehensive study about the IndoBertweet deep learning framework to investigate the prevalence of depression in social media, focusing on Twitter. Utilizing the DASS-42, the research estimates depression levels based on user interactions and reactions to tweets. The results of this research showed that the IndoBERTweet method achieved an accuracy rate of 82% in detecting depression using Twitter data. This research highlights the importance of intervention strategies to support the mental health of social media users, emphasizing the importance of proactive measures in addressing mental well-being issues in the digital space.

Laptop Recommender System Using the Hybrid of Ontology-Based and Collaborative Filtering

A. D. A. Putra, Z. K. A. Baizal — Sun, 31 Mar 2024 00:00:00 +0000

In the era of ever-evolving information technology, choosing the best laptop can be a complicated task for many users. The increasing complexity of technical specifications is often an obstacle, especially for users who need help understanding them. In addressing this challenge, we propose a solution: a laptop recommendation system that considers users' preferences and functional needs. We designed this system to help users choose a laptop that suits their daily functional needs. This system uses a form of Conversational Recommender System (CRS) by combining Ontology-Based Recommender System Filtering and Collaborative Filtering (CF). Ontology-Based Recommender System Filtering ensures a strong relationship between functional needs and technical specifications of laptops, making it easier for users to identify the right laptop. At the same time, Collaborative Filtering (CF) can provide diversity to the recommended products by using similar user preference data. We evaluate the accuracy of our system by calculating the success rate of recommendation accuracy with the accuracy metric, and the evaluation results show that the success rate of recommendation accuracy reaches 93.33%. Our system is highly effective in assisting users in choosing a laptop that suits their functional needs. With our laptop recommendation system, users can confidently select the correct laptop without being burdened by technical specifications, thus making their lives easier and more productive.

Implementation of App Engine and Cloud Storage as REST API on Smart Farm Application

Khoirul Azkiya, Muhamad Irsan, Muhammad Faris Fathoni — Sun, 31 Mar 2024 00:00:00 +0000

Smart Farm is an agricultural application that uses machine learning and cloud computing technology to improve efficiency in the farming process. Technological advancement and sustainable agriculture are two essential aspects of supporting global food security. This research investigates the implementation of App Engine and Cloud Storage in developing REST API in Smart Farm applications. By utilizing cloud computing technology, such as App Engine, and cloud storage, such as Cloud Storage, we can create efficient solutions to monitor and manage agriculture better. This research implements an App Engine and Cloud Storage to develop a REST API that allows Smart Farm application users to access data and control farming devices efficiently. The authors designed, developed, and tested this system to ensure optimal performance and reliability in agricultural data collection and distribution. This method has several significant advantages. First, App Engine allows for easy scalability, ensuring the system can handle increased data demand without disruption. Secondly, Cloud Storage provides secure and scalable storage for agricultural data, which can be accessed from anywhere. This provides easy and quick access to critical data for farmers. Moreover, the use of cloud technology also reduces infrastructure and maintenance costs. The developed system integrates the App Engine and Cloud Storage with the Smart Farm application. The App Engine is a processing engine that receives user requests via the REST API, processes the required data, and provides appropriate responses. Like image data, farm data is stored and managed on Cloud Storage. Users can access this data through the Smart Farm app or other devices, enabling better farming monitoring and decision-making.

An In-Depth Analysis of SIMPKB: Revealing Performance Tests and Efficiency from a User Experience

Hariono Ponco Adi, Ari Eko Wardoyo, Habibatul Azizah — Sun, 31 Mar 2024 00:00:00 +0000

This study comprehensively analyzes the performance and usability of the SIMPKB website in the context of teacher professional development. This research carries a qualitative descriptive approach with the aim of deeply understanding the performance and usability of the SIMPKB website. This research consists of two complementary stages, the first involves performance testing using GT Metrix software, and the second phase focuses on in-depth interviews with 5 driving teachers in Kabupaten Jember by applying the concept of the Five Dimensions of Usability (5E) model. Through performance testing using GT Metrix and 5E interviews with driving teachers, significant findings have been revealed. Although SIMPKB shows relatively good response speeds, there are areas of improvement that can be improved, especially in terms of loading times and Largest Contentful Paint (LCP). The 5E evaluation of the mobilizing teacher provides an in-depth perspective on the effectiveness, efficiency, engagement, errors, and ease of learning on the platform. The test and interview results complement each other, providing a holistic picture of SIMPKB's condition and potential improvement. Improvement recommendations, which involve improving response speed and improving usability, can be a foothold for improving the user experience. Further research is recommended to explore optimizing technical performance, implementing more intuitive interface designs, and evaluating the impact of implementing improvements on user effectiveness. By adopting these recommendations, SIMPKB can continue to develop as an effective, efficient, and user-friendly platform in supporting teacher professional development.

Effect of Epoch Value on the Performance of the RNN-LSTM Algorithm in Classifying Lazada App Review Sentiments

Maswan Pratama Putra, Yuliant Sibaroni — Sun, 31 Mar 2024 00:00:00 +0000

In today's development, the process of buying and selling transactions between sellers and buyers is so developed. not only done directly but can also be done online or can be called e-commerce. Which is where the development of technology is so fast that it indirectly encourages entrepreneurs to develop through e-commerce. Lazada is one of the online stores in Indonesia that has many users and Lazada makes it easy to shop without the need to come to the place or directly. However, purchasing goods using e-commerce has problems regarding the quality of the goods you want to buy, therefore purchasing goods can be seen through reviews of each one you want to buy. Sentiment analysis is carried out using the Recurrent Neural Network (RNN) method with Long Short Term Memory (LSTM). And using the Epoch value as a parameter in processing validation data and test data to produce the best accuracy value

Analysis of TF-IDF and TF-RF Feature Extraction on Product Review Sentiment

Keisha Priya Harmandini, Kemas Muslim L — Sun, 31 Mar 2024 00:00:00 +0000

Sentiment analysis of product reviews is critical in understanding customer views and satisfaction, especially in the context of e-commerce applications. A marketplace provides channels where users can submit reviews of the products they purchase. However, due to the large number of reviews in a marketplace, analyzing them is no longer feasible to be performed manually. This research proposes a machine learning implementation to perform sentiment analysis on product reviews. In this research, the product review dataset on Shopee marketplace is used for sentiment analysis by comparing TF-IDF and TF-RF feature extraction using the SVM algorithm with stages of dataset, labeling, feature extraction and accuracy results. The importance of the comparison between TF-IDF and TF-RF feature extraction in this research is related to the need to evaluate and determine which feature extraction method is most effective in increasing the accuracy of sentiment analysis. TF-IDF and TF-RF are two methods commonly used in text analysis, and a comparison of their performance can provide deep insight into the effectiveness of each in the context of product sentiment analysis.Thus, through this comparison, this research aims to determine the best approach that can provide the highest accuracy results, so that the results can serve as a guide for further research. Based on the evaluation, the highest accuracy value is achieved at 92.87% by using TF-IDF and SVM classifiers which outperformed previous research.

Sentiment Analysis of the 2024 Indonesia Presidential Election on Twitter

Lisyana Damayanti, Kemas Muslim Lhaksmana — Sun, 31 Mar 2024 00:00:00 +0000

This analysis enables the identification and a deeper understanding of the positive and negative sentiments reflected in online conversations, providing a comprehensive view of the direction of public support and preferences regarding presidential candidates. Sentiment analysis through machine learning can manage extensive sentiment data, ensuring time efficiency, and enhancing accuracy in swiftly and comprehensively comprehending people's opinions and preferences. With these advantages, machine learning-based sentiment analysis has gained popularity as an effective choice for understanding people's perspectives, preferences, and responses to various issues and events. Therefore, this research focuses on sentiment analysis regarding public opinions on the 2024 presidential election. The method employed in this research is the SVM algorithm with Word2Vec feature extraction. The researcher is interested in conducting a study related to sentiment analysis of the 2024 Indonesian Presidential election using the Support Vector Machine algorithm because of its high accuracy compared to other algorithms. The use of feature extraction aims to improve the performance and effectiveness of the algorithm, and Word2Vec is chosen because it can represent contextual similarity between two words in the generated vectors, enabling concise and improved text classification based on context. The results of this research indicate the best performance at 80:20 ratio with a precision score of 88,94%, Recall 93.08%, F1-score 90,43% and accuracy of 90,75%. This study's results outperform prior research using the SVM method, which achieved an 82,3% accuracy.

Prediction of Stunting in Toddlers Using Bagging and Random Forest Algorithms

Juwariyem, Sriyanto, Sri Lestari, Chairani — Sun, 31 Mar 2024 00:00:00 +0000

Stunting is a condition of failure to thrive in toddlers. This is caused by lack of nutrition over a long period of time, exposure to repeated infections, and lack of stimulation. This malnutrition condition is influenced by the mother's health during pregnancy, the health status of adolescents, as well as the economy and culture and the environment, such as sanitation and access to health services. To find out predictions of stunting, currently we still use a common method, namely Secondary Data Analysis, namely by conducting surveys and research to collect data regarding stunting. This data includes risk factors related to stunting, such as maternal nutritional status, child nutritional intake, access to health services, sanitation, and other socioeconomic factors. This secondary data analysis can provide an overview of the prevalence of stunting and the contributing factors. To overcome this, the right solution is needed, one solution that can be used is data mining techniques, where data mining can be used to carry out analysis and predictions for the future, and provide useful information for business or health needs. Based on this analysis, this research will use the Bagging method and Random Forest Algorithm to obtain the accuracy level of stunting predictions in toddlers. Bagging or Bootstrap Aggregation is an ensemble method that can improve classification by randomly combining classifications on the training dataset which can reduce variation and avoid overfitting. Random Forest is a powerful algorithm in machine learning that combines decisions from many independent decision trees to improve prediction performance and model stability. By combining the Bagging method and the Random Forest algorithm, it is hoped that it will be able to provide better stunting prediction results in toddlers. This research uses a dataset with a total of 10,001 data records, 7 attributes and 1 attribute class. Based on the test results using the Bagging method and the Random Forest algorithm in this research, the results obtained were class precision yes 91.72%, class recall yes 98.84%, class precision no 93.55%, class recall no 65.28%, and accuracy of 91.98%.

Diabetes Disease Detection Classification Using Light Gradient Boosting (LightGBM) With Hyperparameter Tuning

Sun, 31 Mar 2024 00:00:00 +0000

Diabetes is a condition caused by an imbalance between the need for insulin in the body and insufficient insulin production by the pancreas, causing an increase in blood sugar concentration. This study aims to find the best classification performance on diabetes datasets with the LightGBM method. The dataset used consists of 768 rows and 9 columns, with target values of 0 and 1. In this study, resampling is applied to overcome data imbalance using SMOTE and perform hyperparameter optimization. Model evaluation is performed using confusion matrix and various metrics such as accuracy, recall, precision and f1-score. This research conducted several tests. In hyperparameter optimization tests using GridSearchCV and RandomSearchCV, the LightGBM method showed good performance. In tests that apply data resampling, the LightGBM method achieves the highest accuracy, namely the LightGBM method with GridSearchCV optimization with the highest accuracy reaching 84%, while LightGBM with RandomSearchCV optimization reaches 82% accuracy.

Optimizing Iron Price Forecasting with Linear Regression Analysis and RapidMiner

Rahmatul Istiqomah, Rita Ambarwati — Sun, 31 Mar 2024 00:00:00 +0000

Competition in companies often occurs in price, advertising and promotion, and quality. Price is very influential on competition in a business. The price of a product is one of the things that influences buyers to want to buy a product or not; therefore, price is very important to determine. There are two objectives in this study; the first objective is to predict the right iron price to be used in the following year so that it can be used to increase the competitiveness of the company. The second objective is to determine the attributes that affect the price. This research uses a linear regression algorithm to predict prices and measure the attributes' relationship using the RapidMiner tool. RapidMiner is software that functions as a learning tool in data mining science in which various data processing models are ready to be used easily. From the test results on the training data, an accuracy value of 95% was obtained with a threshold value of 30, which stated that the results were accurate. Then, the factors that affect the price produce factors from the size variable (mm) and unit (kg); between the two variables that affect the price, there are results from the variables that most affect the price, namely size (mm). For the performance of the linear regression model calculated using the root mean square error (RMSE) produces a value of 199,291.

Designing an Application for Detecting Diseases of Rice Plants Using OOAD Method

Wijdan Khalil, Muhammad Irsan, Muhammad Faris Fathoni — Sun, 31 Mar 2024 00:00:00 +0000

Rice, as a key element of Indonesia's food security, plays a crucial role in agricultural ecosystems. Despite its high economic value, rice plants are susceptible to various diseases that can reduce productivity and harvest quality. Farmer's limited knowledge about disease types, identification, and proper handling poses a serious challenge to sustainable agriculture. Previous studies highlight farmers' inadequate understanding of pests and diseases in rice plants, leading to a high dependency on pesticides. Furthermore, lack of training data and a shallow understanding of rice diseases present significant challenges in disease management efforts. This research aims to develop an Android-based Smart Farm application. This application utilizes image processing and artificial intelligence technologies to assist farmers in identifying leaf diseases in rice plants. Requirements analysis involves literature review and field observations around Bandung Regency. It can be concluded; Smart Farm application has been successfully developed with three functional and two non-functional requirements. Validation testing indicates a 100% functionality rate and an 80% accuracy in disease detection. Nevertheless, further attention is required to enhance accuracy by providing more training data and improving image quality. The implications of this research extend to enhancing farmers' knowledge, reducing pesticide dependency, and supporting sustainable agriculture in the future.

Enhancing Cable News Network Comprehension: Text Rank Integrated Natural Language Processing Summary Algorithm

Duta Pramudya Ramadhan, Djarot Hindarto — Sun, 31 Mar 2024 00:00:00 +0000

In the online news space, timely content delivery has become essential due to the unavoidable information overload. This study investigates the use of Python-based text summarizing techniques on news sites, promoting the combination of Natural Language Processing approaches with the Text Rank summarization algorithm. The primary objective is to deliver automatic news article summaries while preserving pertinent information, this is confirmed by means of experimental testing. This study uses the Text Rank technique on a news platform to enhance summaries' readability and information absorption capacity. To test the Text Rank algorithm's capacity to provide enlightening summaries, two news stories from the Cable News Network were chosen for the experiment. The word "Trump" obtained the highest score of 16.52 when sentence scores were calculated using the Text Rank algorithm. "Former" came in second with a score of 1.95, "McCarthy" was third with a score of 1.31, and "President" and "Republican" were each awarded a score of 1.03. Furthermore, the terms "CNN" and "Establishment" received scores of 0.79 and 0.58, respectively, for "DeSantis" and "Endorsements." Reader accessibility and convenience can be improved by using a news summary algorithm on a Python-based platform to swiftly retrieve important information. This research emphasizes the critical role that summary algorithm technology plays in enabling efficient and easily accessible information consumption in the digital age, in addition to creating automated tools for news summaries.

Web Program Testing Using Selenium Python: Best Practices and Effective Approaches

Rusdiansyah, Nining Suharyanti, Hendra Supendar, Tuslaela Tuslaela — Sun, 31 Mar 2024 00:00:00 +0000

A critical component of software development is testing programs on websites to make sure they run, are secure, and meet user expectations. This article explores efficient methods and best practices for utilizing Selenium with the Python programming language to perform program testing on websites. This study shows the outcomes of Selenium WebDriver-based automated testing on two webpages: https://demoqa.com/text-box and https://demoqa.com/login. Testing was done to assess Selenium's dependability and performance when it comes to completing text fields and completing the login procedure. The goal of the study is to evaluate Selenium WebDriver's dependability and effectiveness in basic testing jobs while spotting any issues that may arise. Using the appropriate locator to fill in text boxes efficiently using Selenium WebDriver ensures that the operation proceeds without major hiccups. The effective completion of the login procedure on the https://demoqa.com/login page further demonstrates the dependability of Selenium WebDriver for handling increasingly complicated interactions, including login. According to the analysis's findings, Selenium WebDriver is a dependable and efficient solution for test automation that performs consistently and steadily under a range of conditions. The research's conclusions highlight how crucial it is to use automation technologies in order to ensure software quality and boost testing effectiveness. Software engineers can detect issues more rapidly and completely test the functionality of applications with Selenium WebDriver, which enhances the overall quality of software development

Analysis of The Use of Nguyen Widrow Algorithm in Backpropagation in Kidney Disease

Romanus Damanik, Muhammad Zarlis, Zakarias Situmorang — Sun, 31 Mar 2024 00:00:00 +0000

Fast and accurate diagnosis is very important for kidney disease. This research conducts and analyzes by using Nguyen Widrow Algorithm in Back Propagation method in artificial neural network for kidney disease diagnosis with the aim to improve the accuracy in predicting and time efficiency in diagnosing. The Nguyen Widrow algorithm is very capable of accelerating convergence and stabilizing the learning process in artificial neural networks, which is also expected to present a meaningful contribution to the handling of health data. This study uses MATLAB as a platform for algorithm implementation and a dataset of medical records of kidney disease patients collected from a hospital that specializes in treating kidney disease patients. The data pre-processing and artificial neural network modeling stages use the Nguyen Widrow algorithm, while the model training process uses the Back Propagation method. The results showed that the Nguyen Widrow algorithm was able to improve the accuracy of predicting someone suffering from kidney disease compared to using only the Back Propagation method. Analysis of the performance of the model shows a significant improvement in stability and convergence speed during the learning process. This indicates that data processing and medical decision making becomes more efficient. On the other hand, this research also studied the challenges and limitations that will be faced in terms of implementation of the Nguyen Widrow algorithm. Also the sensitivity of the initialization parameters, the need for the quality of the dataset to be used in training the model.
This research reveals the ability of the Nguyen Widrow algorithm to improve the performance of artificial neural networks in diagnosing kidney disease. By implementing this algorithm in MATLAB, the results show that the use of the latest data processing technology and analysis tools can provide significant improvements in accuracy and efficiency in the medical field. In addition, this research is expected to provide a new direction in the development of machine learning algorithms for applications in the healthcare field, especially for diagnosing kidney disease. By further utilizing this technology, it contributes significantly to improving the quality of healthcare and treatment outcomes for patients suffering from kidney disease.

K-Medoids Algorithm to Clustering COVID-19 Patients with Various Age Levels at Hospitals in Yogyakarta Province

Pratamasari Noor Insani, Endang Darmawan, Sugiyarto — Fri, 05 Apr 2024 00:00:00 +0000

COVID-19 causes a wide spectrum of symptoms, such as mild upper respiratory infection or life-threatening sepsis. From 20.2% of cases of COVID-19 progressed to severe disease with a mortality rate of 3.1% where 60%-90% of patients with comorbidities were hospitalized. The purpose of this study was to find out that cluster analysis using K-Medoids can distinguish COVID-19 patients at various age levels which analytical method has sensitivity and specificity values in analyzing clustering in COVID-19 patients. This study uses a cohort retrospective design conducted at five hospitals in Yogyakarta Province. The study used patient medical record data from March 2020 – September 2021 with a total of 916 patient data that met the inclusion criteria. Cluster analysis will be carried out using Google Colaboratory with the Python programming language. The clustering results are divided into 2 cluster groups where cluster 1 consists of 558 patients and cluster 2 consists of 358 patients with various age levels. The test resulted in 2 clusters with a DBI value of 5,191631. The results of statistical tests showed that there was a significant relationship (p-value = 0,023) between age, recovery rate, and patient mortality. From the test results, it can be seen that ages 50 to 59 years are suspected of COVID-19

Development of Machine Learning Model for Breast Cancer Prediction from Ultrasound Images

Djarot Hindarto, Ferial Hendrata — Fri, 05 Apr 2024 00:00:00 +0000

In the past decade, the revolution in information and computing technology has transformed approaches to breast cancer detection and treatment, with Machine Learning technologies offering significant potential in health data analysis. However, the development of accurate and reliable predictive models is faced with the challenges of data heterogeneity and complexity. This research proposes the development and validation of Machine Learning-based classification models using Support Vector Machine and Principal Component Analysis to address these issues, targeting improved accuracy in the early detection of breast cancer. The methodology applied involved the use of a breast cancer dataset from Kaggle, with data analysis conducted through inductive methods to identify relevant patterns. The combination of Support Vector Machine and Principal component Analysis achieved 89% accuracy in medical image classification, proving its efficacy in breast cancer diagnostics and providing a more reliable model for early detection. The implications of these findings are significant, both theoretically and practically, for the fields of Machine Learning and Breast Cancer, expanding the understanding of the applications of advanced data processing techniques. Although this study faces limitations in the variability of the dataset's patient characteristics, the results offer a basis for further development in diagnostic technology while recommending the integration of Deep Learning and Big Data analysis as a direction for future research.

Chatbot Design for Interview Questions Using Neural Network Models on the CarTech Website

Diko Pradana Sihotang, Syaiful Zuhri Harahap, Irmayanti — Fri, 05 Apr 2024 00:00:00 +0000

Abstract: This research focuses on analyzing interview questions using a neural network model, implemented on the CarTech website. With the main aim of optimizing the interaction between users and the system through the questions asked, this research takes an innovative step by utilizing Google Collab as a development platform. For this research, several paragraphs were carried out, namely problem scoping, data acquisition, data exploration, modeling, evaluation, and deployment. These stages were carried out so that this research could get good results, plus the integration between Google Collab and chatbot which made it possible for this research to get good results. Google Collab makes it easy to use neural network models and integrate with chatbots, enabling efficient and effective testing and deployment of models. The results of this study are quite impressive, with an accuracy of 92%, demonstrating the model's ability to process and understand interview questions with high precision. The aim of this research is not only to explore the potential of neural network models in automatically understanding questions and providing accurate responses, but also to show how this technology can be integrated into web applications to improve the quality of user interactions, making AI-based chatbots a viable solution and effective in improving user experience on the CarTech website. In conclusion, by utilizing AI you will also get good results. As in this research, AI can help analyze interview questions with neural network models.

An IoT-Enabled Smart Energy Management System to Improve Energy Efficiency in University Laboratory

Fitri Wibowo, Suheri, Pausta Yugianus — Sun, 07 Apr 2024 00:00:00 +0000

Efficient energy management remains a challenge in university laboratories. The aim of this study is to develop and deploy an Internet of Things (IoT) system that can automatically adjust electronic devices to improve the efficiency of power consumption in the university laboratory. An advanced system is urgently needed to support sustainable and effective energy management. A smart IoT-based energy management system can improve energy efficiency, reduce operating costs, and reduce negative environmental impacts. The system enables both human and automated control of lighting and air conditioning using scheduling and occupancy detection. This development-based research uses a product design methodology that includes both software and hardware. The software product in this research is an IoT platform website for managing IoT devices. The essential processes include defining project goals and requirements, designing a system architecture, creating a user experience design, developing and integrating components, and conducting tests. The system is successful in automatically monitoring and controlling electronic devices based on certain parameters such as scheduling and presence detection. The system meets most of the specified functional and non-functional requirements as demonstrated in experiments, although it is somewhat limited by hardware limitations. Ultimately, the system increases the energy efficiency of the laboratory and thus successfully fulfills the research goal. This innovative project could be a blueprint for other smart energy control efforts.

Fine-Grained Analysis of Coral Instance Segmentation using YOLOv8 Models

Wahyu Maulana Hassanudin, Victor Gayuh Utomo, Riski Apriyanto — Mon, 08 Apr 2024 00:00:00 +0000

Within the geographical boundaries of Indonesia, coral reefs flourish as intricate ecosystems bustling with a variety of marine creatures that play a crucial role, in preserving biodiversity. However this delicate harmony faces threats from climate change and human activities, leading to the risk of species loss. Despite growing awareness surrounding these challenges effectively and swiftly monitoring conditions remains a task. Existing methods for assessing corals often fall short due to requiring extensive specialist knowledge, lacking large-scale coverage, and being costly to implement. To tackle these obstacles this research suggests an approach for automated reef monitoring using instance segmentation with a YOLOv8 model. Leveraging YOLOv8 segmentation capabilities enables efficient analysis of corals. A systematic process is employed involving data collection, preparation (including techniques like Histogram Equalization), training the model on a reef dataset, model evaluation and enhancing the segmentation mask. The outcomes reveal the YOLOv8m Pp model with 96.7% precision 95.9% recall rate and a mean Average Precision (mAP50) score of 98.2%. This study demonstrates the potential of YOLOv8 to accurately segment instances for monitoring reefs in Indonesia, hence facilitating improved conservation strategies.

Optimization of the Artificial Neural Network Algorithm with Genetic Algorithm in Stroke Prediction

Serin Wulandari, Yogi Isro’ Mukti, Tri Susanti — Mon, 08 Apr 2024 00:00:00 +0000

This study aims to optimize Artificial Neural Network with Genetic Algorithm in predicting stroke. This research is motivated by health problems in the community that are less considered that cause a disease such as stroke. Factors of lifestyle, poor diet and other factors that can be the cause of stroke. Therefore, where later the data that has been obtained will be processed to see what factors determine the cause of stroke. The data used, namely kaggle and mendeley, will be processed using RapidMiner, with a development method (CRISP-DM) and a testing method using a Confusion Matrix. The results of this study, stroke disease classification model accuracy kaggle Artificial Neural Network dataset with Genetic Algorithm accuracy 95.13% and AUC 0.667 and mendeley dataset accuracy 98.20% and AUC 0.712. For model evaluation with Artificial Neural Network algorithm with Artificial Neural Network algorithm with kaggle dataset genetic algorithm using X-fold validation average accuracy of 95.14% and AUC 0.686.7 and mendeley dataset resulted in accuracy of 98.20% and AUC 0.712.5. So as to produce from an algorithm a new attribute from the results of the classification model that has been carried out, namely heart disease, ever married, work type and residence type

Application of Decision Tree Method in ECG Signal Classification For Heart Disorder Detection

Mon, 08 Apr 2024 00:00:00 +0000

Cardiovascular Disease (CVD) is a group of diseases that affect the heart and blood vessels, and it is the leading cause of death globally. In Indonesia, Coronary Heart Disease (CHD) is one of the most prevalent CVDs. However, due to the high cost of drugs, lengthy treatment duration, and various supporting examinations required, treating CHD can be very expensive. An obstacle to treating heart disease in Indonesia is the insufficient number of cardiologists and experts experienced in interventional cardiology. Along with technological developments, the computer science community is encouraged to contribute to the medical field. For instance, using an electrocardiogram (ECG) can help prevent and minimize problems arising from heart disease. An Electrocardiogram (ECG) is a medical test that measures and records the heart’s electrical activity using a machine that detects electrical impulses. The use of Artificial Intelligence (AI) in ECG is rapidly increasing and has shown to have great potential in improving the diagnosis and treatment of cardiac patients. AI has become a valuable tool in helping doctors diagnose, predict risk, and manage heart disease with greater accuracy, speed, and precision. One of the machine learning methods used in this research is the decision tree method, which is often employed to make decisions. The decision tree method exhibited promising results, with an accuracy rate of 99% in identifying heart defects at an early stage. This method has significant potential to assist doctors in diagnosing heart defects at an early stage with high accuracy.

Improving Digital Image Clarity: A Study on the Application of Histogram Equalization for Noise Correction

Surmayanti, Sumijan — Tue, 09 Apr 2024 00:00:00 +0000

This study aims to improve the clarity of digital images by examining the application of the histogram equalization method for noise correction. Noise in digital images is often a major challenge in maintaining the clarity and authenticity of visual information. Histogram equalization has been recognized as an effective method in improving image contrast and reducing the effects of noise. In this research, we conducted experiments by applying histogram equalization techniques to various types of digital images that are affected by noise. We analyzed the results by comparing the clarity and quality of the images before and after applying this method. The results of this research show that histogram equalization is able to significantly improve the clarity of digital images by reducing the effects of noise without sacrificing important details in the image. The implication of this discovery is the potential use of the histogram equalization method as an effective tool in improving the quality of digital images that are affected by noise.

Designing Integrated IT Architecture for Health Monitoring Internet of Things: Findings Exploratory Study

Sabrina Fajrul Ula Usman, Djarot Hindarto, Ririn Ikana Desanti — Tue, 09 Apr 2024 00:00:00 +0000

IT integration with healthcare, mainly through Internet of Things-based health monitoring systems, is crucial to improving healthcare management in the digital age. However, challenges remain in the design of an integrated IT architecture that can support the sustainability and effectiveness of IoT health monitoring systems, which still need to be addressed. The shortcomings in the literature related to the application of a holistic IT architecture framework to address these challenges indicate a knowledge gap that needs to be filled. Through the application of the TOGAF methodology, this research seeks to design and analyze an integrated IT architecture for IoT-based health monitoring systems in Indonesia, taking a qualitative approach through case studies, in-depth interviews, and document analysis. The main findings show that the application of the TOGAF framework successfully addresses the challenges of interoperability, data security, and system scalability by effectively integrating IoT technologies in the healthcare environment and considering the local social and infrastructural context. The implementation of the IT architecture developed based on the TOGAF methodology demonstrated improved coordination between IoT devices and backend systems, facilitated secure and real-time data flow, and accommodated the scalability and sustainability needs of the system. The findings have significant implications in supporting the development of more efficient and effective health monitoring systems, offering strategic guidance for system developers, policymakers, and IT practitioners within the healthcare sector.

Enterprise Architecture for Efficient Integration of IoT Lighting System in Smart City Framework

Nadia Amalia, Djarot Hindarto — Mon, 15 Apr 2024 00:00:00 +0000

This research investigates the influence of enterprise architecture design in integrating Internet of Things (IoT)-based street lighting systems into an innovative city framework, emphasizing the importance of efficient lighting infrastructure as a fundamental component of a creative urban ecosystem. With a focus on building an architectural model that supports the integration of IoT street lighting with other components of a smart city, this research addresses the knowledge gap in optimizing enterprise architecture design for integration efficiency, considering technological complexity and interoperability needs between systems. The methodology applied involved an in-depth analysis of the architectural components essential to facilitate the integration of IoT-based street lighting within the more extensive intelligent city infrastructure. The findings of this study show that a well-structured enterprise architecture model can significantly improve operational efficiency, reduce energy consumption, and provide a rich source of data for strategic decision-making regarding the management and maintenance of city infrastructure. Furthermore, these results emphasize the importance of an adaptive and unified architecture design, which not only improves the functionality of the lighting system but also strengthens the synergy between IoT technologies and innovative city operations. These discoveries have a wide range of repercussions and implications, offering new insights into designing enterprise architectures that can support the transition to more efficient and sustainable smart cities, thereby improving the quality of service for citizens.

Implementation of Cloud Run and Cloud Storage as REST API Service on OutfitHub Application

Derryl Reflando Tarigan, Muhammad Irsan, Muhammad Faris Fathoni — Sun, 31 Mar 2024 00:00:00 +0000

The development of Cloud Computing technology has progressed rapidly in recent years especially with the emergence of Google Cloud Services (GCR) which has become one of the leading cloud service providers. This research focuses on the OutfitHub application, which plays a role in assisting users in determining clothing styles using a personalized recommendation system. In developing this application, the research seeks to implement cloud computing services to improve application performance. The purpose of this research is to implement Cloud Computing, especially Cloud run and Cloud Storage services as Rest API in the Outfithub application. By implementing these two services, it is expected that there is no need to pay attention to the problem of Storage needs that are growing at any time and no need to worry about the need for server configuration because both of these things will be fully done by GCR. Implementing Cloud Computing will provide a variety of benefits in addition to those previously mentioned, such as: being able to access data from anywhere and at any time. This implementation is expected to be able to run OutfitHub applications in a Cloud environment in a serverless computing manner without requiring the design of unnecessary virtual machines.