JITK (Jurnal Ilmu Pengetahuan dan Teknologi Komputer)

APPLICATION OF OWASP ZAP FRAMEWORK FOR SECURITY ANALYSIS OF LMS USING PENTEST METHOD

Rusydi Umar, Imam Riadi, Sonny Abriantoro Wicaksono — Mon, 18 Nov 2024 13:54:08 +0000

Learning Management System (LMS) is an application currently popular for online learning. The presence of LMS offers better prospects for the world of education, where its highly efficient use allows learning anywhere and anytime through the internet or other computer media. This study focuses on analyzing the security of the Learning Management System (LMS) on the domain e-learning.ibm.ac.id using the Pentest method with the Owasp Zap Framework. Security is a crucial step that needs to be considered by IBM Bekasi in protecting data and information from hacker threats. In this study, the method used is Pentest. Pentest is a series of methods used to test the security of a system by conducting literature studies, searching for data information, and domain information, followed by testing using Owasp Zap to find security-related vulnerabilities. The results of the testing using the Pentest method involve several stages of testing and scanning. The first step is checking domain information using Whois Lookup tools and then scanning using ZenMap on e-learning.ibm.ac.id. In this domain information search, the domain status serverTransferProhibited and clientTransferProhibited was found. The next stage is Vulnerability Analysis, where scanning is performed on the domain e-learning.ibm.ac.id using Owasp Zap tools. Based on the results from Owasp Zap scan, 16 vulnerabilities were found, with the breakdown being 2 high risk, 3 medium risk, 6 low risk, and 5 informational. In the exploitation stage using SQLMap, errors were found in the tested parameters, preventing injection.

UNDERSTANDING THE CONTINUANCE OF ELECTRONIC PAYMENTS USAGE AFTER COVID-19: A SURVEY IN INDONESIA

Maulyta Noer Fadilla, Nori Wilantika, Arfive Gandhi — Mon, 18 Nov 2024 13:54:51 +0000

During the ongoing pandemic with elevated COVID-19 cases, efforts to minimize direct physical contact for virus prevention have been heightened. Consequently, there has been a strong emphasis on adopting non-cash transactions, particularly electronic payments. As the Indonesian government revoked the social restriction policy on December 30, 2022, people gradually resumed normal activities such as work, school, and shopping. The question arises whether the widespread adoption of electronic payments will persist after COVID-19. To understand this and the factors influencing the sustained use of electronic payments, this study utilized the UTAUT, Trust, and Perceived Security as the research model. The findings indicate that all 920 survey participants maintain their electronic payment usage after COVID-19. Through PLS-SEM analysis, key factors contributing to the sustained use of electronic payment after COVID-19 include the intention to use electronic payments, user trust, performance expectations, facilitating conditions, and perceived security. Additional variables proposed in this research, user trust and perceived security, are proven to have an influence on users' intentions to continue using electronic payments.

The HYBRID CONTENT-BASED FILTERING AND CLASSIFICATION RNN WITH PARTICLE SWARM OPTIMIZATION FOR TOURISM RECOMMENDATION SYSTEM

Syahdan Naufal Nur Ihsan, Erwin Budi Setiawan — Mon, 18 Nov 2024 13:56:02 +0000

Economic recovery in the tourism sector after the COVID-19 pandemic is one of the main focuses of the Indonesian government at the moment, especially in Bandung City. This research aims to develop a personalized tourist spot recommendation system, by addressing the gaps in the existing literature through the integration of Content-Based Filtering (CBF) and Simple Recurrent Neural Network (RNN) methods that aim to improve recommendation accuracy. This study uses a hybrid approach that combines Term Frequency - Inverse Document Frequency (TF-IDF) and word embedding with the Robustly Optimized BERT (RoBERTa) model to identify similarities between tourist destinations based on their content characteristics. Simple RNN is used to analyze user preference patterns over time, which is then further optimized using Particle Swarm Optimization (PSO). As a result, the Simple RNN model that has been optimized with PSO shows an increased accuracy of up to 94.37%, outperforming other optimizations such as Adam and SGD. This research makes a novel contribution by applying advanced machine learning techniques to improve personalization in travel recommendation systems.

SENTIMENT ANALYSIS ON RENEWABLE ENERGY ELECTRIC USING SUPPORT VECTOR MACHINE (SVM) BASED OPTIMIZATION

Pungkas Subarkah, Bagus Adhi Kusuma, Primandani Arsi — Mon, 18 Nov 2024 13:58:47 +0000

Government policy regarding the discourse on the use of renewable energy in electricity, this discourse is widely discussed in the community, especially on social media twitter. The public's response to the implementation of the use of renewable energy varies, there are positive, negative and neutral responses to this government policy. Sentiment analysis is part of Machine Learning which aims to identify responses in the form of text. The data used in this study amounted to 1,367 tweets. The purpose of this study is to determine the sentiment analysis of government discourse related to the use of renewable energy using an optimisation-based Support Vector Machine (SVM) algorithm approach. This research involves several stages including data collection, data pre-processing, experiments and modelling and evaluation. The data is divided into 3 classes, 120 positive, 1221 neutral and 26 negative. In this research, there are five optimisation models used namely Forward Selection, Backward Elimination, Optimised Selection, Bagging and AdaBoost. The results obtained are the use of Optimised Selection (OS) optimisation with the Support Vector Machine (SVM) algorithm obtained an increase in accuracy from 93% to 96%. The increase in the use of SVM using selection optimization obtained the highest increase, because other optimization techniques only reached 1% and 2% of the original results using the SVM algorithm, namely the accuracy value of 93% to 96% (high accuracy). From the research that has been done, it is certainly important to understand public sentiment towards renewable energy policies, especially renewable energy electricity, the hope is that this research will become a reference for the government.

CRITICAL SUCCESS FACTORS OF AGILE SOFTWARE DEVELOPMENT IN WATERFALL PROJECT: A CASE STUDY APPROACH

Indra Bayu, Teguh Raharjo, Bob Hardian Syahbuddin — Mon, 18 Nov 2024 14:01:06 +0000

The evolution of software development methodologies has seen Agile rise in response to the limitations of traditional approaches like Waterfall, characterized by its iterative, collaborative, and adaptable nature. However, integrating Agile within the rigid, structured frameworks of organizations accustomed to Waterfall presents significant challenges. This study addresses how to effectively combine these methodologies to mitigate conflicts and achieve successful project outcomes by identifying and analyzing the Critical Success Factors (CSFs) that enable a harmonious integration of Agile into Waterfall environments. Conducted at PT ABC, a firm balancing formal client interactions and contract creation with internal adoption of Scrum, this research uses the Analytic Hierarchy Process (AHP) to systematically prioritize CSFs through literature review, questionnaire development, data collection, and pairwise comparison analysis. The findings reveal that "Communication and Team Environment" is the most influential factor, with a priority vector weight of 0.178, followed by "Project Management and Strategy," "Leadership and Management Support," and "User and Customer Engagement." These factors are pivotal in achieving a balance between control and flexibility in software development projects. The study's implications for PT ABC and other organizations, especially those handling multiple projects and requiring on-site presence while managing other projects, demonstrate how to leverage the strengths of both methodologies for optimal project outcomes. This research provides a model for other organizations striving for similar integrative efforts, showcasing practical strategies to enhance project flexibility and coordination.

COMPARISON OF PROFILE MATCHING AND MOORA METHODS IN DETERMINING LOAN ELIGIBILITY

Wayan Eka Ariawan, Gede Indrawan, I Gede Aris Gunadi — Mon, 18 Nov 2024 14:02:04 +0000

The objective of this research is to analyze the comparison between the profileimatching method and MOORA in supporting decision-making for loan approvals at the Widya Dharma Student Cooperative (KOPMA). The criteria used in this research include basic salary, length of service, loan duration, membership status, loan amount, and number of dependents. These two methods are compared based on their accuracy levels. The accuracy levels are obtained through testing with the Mean Average Precision (MAP) technique, which measures the accuracy in ranking. The testing is conducted by comparing the ranking results from the method calculations with the rankings from the KOPMA chairman. The analysis results show that the Profile Matching method has a higher accuracy rate, which is 67.83%, compared to the MOORA method, which has an accuracy rate of 45.46%. Besides method testing, system testing was also conducted using the User Acceptance Test (UAT) technique. The UAT results indicate that the developed system aligns with the business processes in determining loan eligibility, the menu layout and contents within the system are well-organized, the system features function properly and are easy to understand, and the system meets expectations.

A SYSTEMATIC LITERATURE REVIEW ON ROLE OF PROJECT MANAGEMENT IN DIGITAL FORENSICS INVESTIGATION

Panji Zulfikar Sidik, Teguh Raharjo — Mon, 18 Nov 2024 14:03:15 +0000

The landscape of digital forensics has evolved significantly with the advent of sophisticated cybercrimes and the proliferation of digital devices. Digital forensics is a rapidly evolving discipline, characterized by unique challenges such as rapidly changing technology, large volumes of data, and stringent legal requirements. Effective project management in this context is crucial to ensure that investigations are conducted efficiently, accurately, and in compliance with legal standards. This systematic literature review aims to comprehensively analyze the role of project management practices in optimizing digital forensics investigations. Using established search protocols and selection criteria, we identified and analyzed relevant studies published between 2016 until 2023 that explored the application of project management methodologies, challenges, and best practices within the context of digital investigations. By applying effective project management strategies, investigators can ensure efficient, accurate, and legally sound digital investigations, ultimately contributing to successful criminal prosecutions and civil litigation outcomes.

ARCHITECTURE OF SMART TOURISM APPLICATION: A DEVELOPING COUNTRIES’ PERSPECTIVE A CASE STUDY IN INDONESIA

Ruci Meiyanti, Yuwan Jumaryadi, Riri Fajriah, Bagus Priambodo — Tue, 19 Nov 2024 01:23:16 +0000

Beautiful, comfortable, safe, and affordable tourist attractions are every tourist's dream. Meanwhile, tourism in developing countries, the authenticity and uniqueness of nature and culture are the main attractions for tourists. The lack of accurate information that can accommodate tourist locations, local culture, unique tourism, transportation, and accommodation of a tourist attraction for developing countries is an obstacle to the success of tourist visits. The role of technology and society can help the concept of smart tourism governance for developing countries. Therefore, a framework model is needed that can explore the advantages of tourism in developing countries. The success of Smart Tourism cannot be separated from the development of the application architecture that is used as the basis for developing the Smart Tourism system application. So, the purpose of this study is to create an informative, accurate, safe, and easy smart tourism application architecture. This study uses a qualitative method, namely with literature studies and in-depth interviews were also conducted with tourism and informatics experts. The Mc Farlan Matrix used in the Ward and Peppard method and the TOGAF framework are used in the formation of smart tourism applications. The results of this study are The results of this study are in the form of an application architecture that focuses on stakeholder interests in the form of Smart Tourism Service Application Architecture for various Stakeholders which is an integration of smart tourism organization, smart destination, smart service, smart decision, smart share, smart experience, smart recommendation.

IMPLEMENTATION OF MULTIPLE LINEAR REGRESSION ALGORITHM IN PREDICTING RED CHILI PRICES IN GARUT REGENCY

Yoga Handoko Agustin, Fitri Nuraeni, Rika Lestari — Tue, 19 Nov 2024 01:26:17 +0000

Vegetables, including red chili peppers, play an important role in food and economic balance. Significant price fluctuations and inflation are often problems for farmers and traders. Garut Regency, as the center of red chili production in West Java, faces similar challenges. This research aims to implement a Multiple Linear Regression algorithm to predict the price of red chili peppers in the Garut Regency, highlighting the novelty of using a combination of One Hot Encoding, Feature Engineering, Standard Scaler, and Hyperparameter Tuning techniques. The method used is CRISP-DM with 6 stages: Business Understanding, Data Understanding, Data Preparation, Modeling, Evaluation, and Deployment. The data used is the price and production of red chili peppers per week in 2018-2023, with a total of 702 records. This research involved 8 trials with data transformation and normalization scenarios. The model evaluation used MSE, RMSE, MAPE, R-squared, and statistical hypothesis testing metrics. Results showed 5 significantly influential attributes: year, month, production, net harvested area, and productivity. The best model yielded MSE 202,134,650, RMSE 14,217, MAPE 29.16%, and R-squared 0.320. This approach is simpler yet effective and is able to provide fairly accurate predictions. This research is expected to contribute to providing predictive models that help farmers and traders anticipate price fluctuations, as well as provide insights for policymakers in price management.

OPTIMIZATION IOT TECHNOLOGY IN WEATHER STATIONS FOR IMPROVE AGRICULTURAL SUCCESS DURING EL NIÑO ERA

Dodi Solihudin, Odi Nurdiawan, Rudi Kurniawan, Cep Lukman Rohmat — Tue, 19 Nov 2024 01:29:49 +0000

The El Niño phenomenon is significant to global weather patterns, particularly in Indonesia, which adversely affects the agricultural sector, especially rice production. El Niño causes drastic changes in rainfall patterns, making it difficult for farmers to determine the right planting time. Limited access to accurate weather information is a major obstacle for farmers in planning their agricultural activities. This research aims to develop an Internet of Things (IoT)-based weather station capable of providing real-time and accurate weather data to support farmers' decision-making in their land management. The research method starts with observation in Babakan Jaya Village, Gabuswetan District, Indramayu Regency, to understand the local weather conditions and specific challenges faced by farmers. Next, the construction and implementation of a weather station equipped with sensors to measure various weather parameters such as temperature, humidity, wind direction and speed, and rainfall. The weather data collected by these stations is then processed and presented in real-time through a cloud platform, which allows access from computer devices and smart phones. The observation results from 1 June to 27 July 2024 showed that the air temperature ranged from 29°C to 35°C, humidity between 55% to 90%, and wind speed ranged from 0 to 7 km/h, with sporadic rainfall patterns. The developed IoT weather station successfully provides relevant and accurate weather data, which can be accessed in real-time by farmers. With this data, farmers can make more informed decisions in their land management, hopefully improving the efficiency and success of farming practices, especially in the midst of erratic weather conditions due to El Niño.

AUTOMATION OF THE BERT AND RESNET50 MODEL INFERENCE CONFIGURATION ANALYSIS PROCESS

Medi Noviana, Sunny Arief Sudiro — Tue, 19 Nov 2024 01:34:11 +0000

Inference is the process of using models to make predictions on new data, performance is measured based on throughput, latency, GPU memory usage, and GPU power usage. The models used are BERT and ResNet50. The right configuration can be used to maximise inference. Configuration analysis needs to be done to find out which configuration is right for model inference. The main challenge in the analysis process lies in its inherent time-intensive nature and inherent complexity, making it a task that is not simple. The analysis needs to be made easier by building an automation programme. The automation programme analyses the BERT model inference configuration by dividing 10 configurations namely bert-large_config_0 to bert-large_config_9, the result is that the right configuration is bert-large_config_2 resulting in a throughput of 12.8 infer/sec with a latency of 618 ms. While the ResNet50 model is divided into 5 configurations, namely resnet50_config_0 to resnet50_config_4, the result is that the right configuration is resnet50_config_1 which produces a throughput of 120.6 infer/sec with a latency of 60.9 ms. The automation programme has the benefit of facilitating the process of analysing the inference configuration.

CONTENT-BASED FILTERING CULINARY RECOMMENDATION SYSTEM USING DEEP CONVOLUTIONAL NEURAL NETWORK ON TWITTER (X)

Zahwa Dewi Artika, Erwin Budi Setiawan — Tue, 19 Nov 2024 01:39:16 +0000

Along with the development of technology, social media has become integral to everyday life, especially for sharing content like culinary reviews. Social media platform X (formerly Twitter) is often used for sharing culinary recommendations, but the abundance of information makes it difficult for users to find relevant suggestions. In order to improve rating prediction performance, this study suggests a recommendation system model that is more thoroughly created utilizing Content-Based Filtering (CBF) combined with Deep Convolutional Neural Network (CNN) and optimised with Particle Swarm Optimization (PSO). Data was collected from PergiKuliner and Twitter, totaling 2644 reviews and 200 cuisines. The preprocessing involved text processing, translation, and polarity assessment. Post-labeling, 7438 data were labeled with 0 and 1562 with 1. Label 0 means not recommended while label 1 means recommended. The imbalance is handled by applying the SMOTE method after observing that the fraction of data labeled 0 and 1 is 65.2%. CBF employed TF-IDF feature extraction and FastText word embedding, while Deep CNN handled classification. PSO optimisation was applied to enhance the accuracy of culinary rating predictions. The results showed an initial accuracy of 76.32% with the baseline Deep CNN model, which increased to 86.06% after Nadam optimisation with the best learning rate, and further reached 86.18% after PSO optimisation on dense units. The 9.86% accuracy improvement from the baseline model demonstrates the effectiveness of the combined methods.

UNLEASHING THE POWER OF SVM AND KNN: ENHANCED EARLY DETECTION OF HEART DISEASE

Jefri Junifer Pangaribuan, Ade Maulana, Romindo Romindo — Tue, 19 Nov 2024 01:44:52 +0000

Heart disease is a fatal illness responsible for approximately 36% of deaths in 2020. Therefore, it is important to pay attention to and better anticipate the risk of heart disease. One technological contribution that can be made is through information related to the risk of heart disease. Classification techniques in data mining can be used to diagnose and identify the risk of heart disease earlier by processing medical data and making predictions. This study compares the effectiveness of two classification algorithms, Support Vector Machine (SVM) and K-Nearest Neighbor (KNN), in predicting the risk of heart disease using a Kaggle dataset consisting of 303 records with 14 attribute columns. The data is divided into 70% for training and 30% for testing. The software used in this study is Orange Data Mining to build the SVM and KNN models. The results show that the SVM accuracy is 85.6%, while KNN achieves 81.1%. Based on the confusion matrix, the SVM algorithm has a lower error rate compared to KNN. In conclusion, the SVM algorithm is superior to KNN in predicting the risk of heart disease. These findings indicate that SVM has a better potential in identifying individuals at high risk of experiencing a heart attack. This research can contribute to the development of a more accurate medical decision support system for early detection of heart disease.

UTILIZING RETRIEVAL-AUGMENTED GENERATION IN LARGE LANGUAGE MODELS TO ENHANCE INDONESIAN LANGUAGE NLP

Herdian Tohir, Nita Merlina, Muhammad Haris — Tue, 19 Nov 2024 01:48:00 +0000

The improvement of Large Language Models (LLM) such as ChatGPT through Retrieval-Augmented Generation (RAG) techniques has urgency in the development of natural language translation technology and dialogue systems. LLMs often experience obstacles in addressing special requests that require information outside the training data. This study aims to discuss the use of Retrieval-Augmented Generation (RAG) on large-scale language models to improve the performance of Natural Language Processing (NLP) in Indonesian, which has so far been poorly supported by high-quality data and to overcome the limitations of traditional language models in understanding the context of Indonesian better. The method used is a combination of retrieval capabilities (external information search) with generation (text generation), where the model utilizes broader and more structured basic data through the retrieval process to produce more accurate and relevant text. The data used includes the Indonesian corpus of the 30 Juz Quran translation into Indonesian. The results of the trial show that the RAG approach significantly improves the performance of the model in various NLP tasks, including token usage optimization, text classification, and context understanding, by increasing the accuracy and relevance of the results

ANALYSIS STUDENT EMOTIONS AND MENTAL HEALTH ON CUMULATIVE GPA USING MACHINE LEARNING AND SMOTE

Fadhil Muhammad Basysyar, Gifthera Dwilestari, Ade Irma Purnamasari — Tue, 19 Nov 2024 01:51:54 +0000

This research investigates the impact of emotions and mental health on students' cumulative grade point average (CGPA) using machine learning classification algorithms while addressing data imbalances with the Synthetic Minority Oversampling Technique (SMOTE). Emotional well-being and mental health are acknowledged as vital determinants of academic achievement. Data imbalance, particularly in mental health metrics such as anxiety and depression, frequently compromises forecast accuracy. This study improves the accuracy of CGPA prediction based on emotional and mental health factors by utilizing SMOTE in machine learning models such as logistic regression and random forest. A dataset including 226 university students, including academic records and self-reported mental health evaluations, was evaluated. The random forest model attained an accuracy of 87.63%, exceeding the logistic regression model's accuracy of 86.56%. These findings emphasize the significant role of emotions and mental health in academic outcomes and validate SMOTE’s efficacy in addressing class imbalance. This work offers a fresh technique in educational data mining by revealing the possibility for improved academic achievement forecasts based on psychological characteristics, helping to the development of targeted therapies for students experiencing emotional issues. Implications for educational policy emphasize the significance of mental health support systems in promoting academic achievement. Subsequent research should investigate supplementary psychological variables and comprehensible models to improve predictive accuracy and facilitate evidence-based policymaking.

ENHANCING UNDERWATER IMAGE QUALITY: EVALUATING COMBINATIVE APPROACHES FOR EFFECTIVE IN SEAGRASS BED ECOSYSTEM

Sri Dianing Asri, SDA, Indra Jaya, IJ, Agus Buono, AB, Sony Hartono Wijaya, SHW — Tue, 19 Nov 2024 03:15:12 +0000

The Complex underwater characteristics, challenges for image processing tasks. These images often have poor visibility due to low contrast, light scattering and various types of interference. There is a lack of exploration into the effectiveness of existing underwater image enhancement methods, particularly in the context of seagrass ecosystems, allows for further investigation. This study aims to explore and evaluate the effectiveness of various methods in underwater image enhancement, including Colour Balanced, CLAHE, and Unsharp Masking and their combinations, starting with converting video data from UTS devices into two-dimensional images. Furthermore, the quality of images taken from underwater cameras placed in a complex and wild seagrass meadow environment was improved using the proposed method, and the quality was evaluated by the SSIM value. The results show that the CLAHE method has the highest average SSIM value of 0.898. Meanwhile, the combined Color Balanced-CLAHE method achieved an SSIM value of 0.683 in a separate evaluation. This combination is an innovative approach to address complex underwater image quality problems, providing a more specific and adaptive solution. Overall, the proposed method is able to improve the visual quality of images on aspects such as clarity, color, and visibility of objects in the image

ENHANCING USER EXPERIENCE (UX) IN BUS TICKET BOOKING: A CASE STUDY OF REDBus APPLICATION

Valencia Valencia, Lisana Lisana, Tyrza Adelia — Tue, 19 Nov 2024 06:02:26 +0000

In Indonesia, the number of buses has increased significantly, particularly in major cities. Along with the advancement of mobile technology, people can now purchase bus tickets online using mobile applications. One of the popular online bus ticket booking platforms is RedBus. As one of the widely used applications, it is crucial to focus on User Experience (UX) because it significantly influences user satisfaction, encouraging continued use of the application. However, usability testing of the current RedBus application revealed that users are experiencing several issues, including difficulties in using the app, which leads to low user motivation and dissatisfaction with RedBus services. As a result, a redesign was needed to improve the UX of the RedBus application. Therefore, this study aims to investigate how UX can be improved after a redesign of the application. The redesign process employed the Design Thinking method, which consists of five phases: Empathize, Define, Ideate, Prototype, and Test. UX was measured through usability testing, focusing on effectiveness, efficiency, and user satisfaction. The measurement results of the redesigned RedBus application showed a 44% increase in effectiveness, with efficiency reaching 0.079 goals per second. Additionally, user satisfaction improved by approximately 63% across all criteria. These findings provide practical insights for designers and developers looking to enhance UX in their applications. They underscore the importance of a user-centered approach and demonstrate the effectiveness of Design Thinking as a framework for successful redesigns. Moreover, this research offers a practical guideline on how to measure UX for digital products

MULTICLASS CLASSIFICATION FOR STUNTING PREDICTION USING DEEP NEURAL NETWORKS

Wulan Sri Lestari, Yuni Marlina Saragih, Caroline Caroline — Tue, 19 Nov 2024 06:32:29 +0000

Stunting is a chronic nutritional issue that hinders child growth and leads to serious long-term health and developmental impacts, particularly in developing countries. Therefore, early and accurate prediction of stunting is crucial for implementing effective interventions. This research aims to develop a multiclass classification model based on Deep Neural Networks (DNNs) to predict stunting status. The model is trained using a comprehensive dataset that encompasses various health variables related to stunting. The research process includes data collection, data preprocessing, dataset splitting, and training and evaluation of the DNNs model. The model can classify stunting status into four categories: stunted, severely stunted, normal, and tall. Further analysis is conducted to evaluate the influence of various parameters on the model's performance, including dataset splitting ratios (80:20 and 70:30) and learning rates (0.001, 0.0001, and 0.00001). The results show that a learning rate of 0.0001 yields the highest prediction accuracy, at 93.64% and 93.83% for the two data-splitting schemes. This indicates that this learning rate has achieved an optimal balance between convergence speed and the model's generalization capability. Additionally, the developed DNNs model can identify complex patterns hidden within the data without being affected by noise. These findings confirm that appropriate parameter selection, particularly the dataset splitting ratio and learning rate, can significantly enhance the DNNs model's ability to identify complex data patterns.

A COMPARATIVE EVALUATING NUMERICAL MEASURE VARIATIONS IN K-MEDOIDS CLUSTERING FOR EFFECTIVE DATA GROUPING

Relita Buaton, Solikhun Solikhun — Tue, 19 Nov 2024 07:28:57 +0000

The K-Medoids Clustering algorithm is a frequently employed technique among researchers for data categorization. The primary difficulty addressed in this investigation pertains to the extent of optimality achieved when varying distance computation methodologies are applied within the framework of K-Medoids Clustering. This study is primarily concerned with the application of K-Medoids Clustering, employing a multitude of distance calculation methods, specifically those involving numerical metrics. The aim is to undertake a comparative analysis of Davies-Bouldin Index (DBI) values in order to ascertain the most productive distance calculation technique. In this research, the distance calculation methodologies include Manhattan Distance, Jaccard Similarity, Dynamic Time Warping Distance, Cosine Similarity, Chebyshev Distance, Canberra Distance and Euclidean Distance. The dataset consists of sales data from Devi Cosmetics, covering the period between January and April 2022 and comprising 56 distinct sales items. The research provides an exhaustive evaluation of numerical metrics concerning the K-Medoids Clustering algorithm. The findings indicate that the optimal clustering is achieved using the Chebyshev distance, resulting in 9 clusters with a DBI value of 166.632. The study's contribution is that it can improve more optimal data grouping to help make decisions correctly.

DESIGNING 'KIDDOCARE' APPLICATION FOR PEDIATRIC NURSING PRACTICE WITH USER CENTERED DESIGN (UCD)

Rifa Yanti, Dasril Aldo, Nursaka Putra, Dading Qolbu Adi, Miftahul Ilmi — Tue, 19 Nov 2024 08:42:10 +0000

This research aims to develop KiddoCare, a mobile-based pediatric nursing application designed using the User Centered Design (UCD) method. The methodology used in this study included interviews, questionnaire distribution, and documentation with the aim of filling the gap of tools and applications that specifically meet the unique needs in pediatric care. Interviews with health workers showed that one of the biggest challenges was the lack of efficient communication between nurses and parents, as well as difficult access to pediatric health information. Therefore, this app is designed to improve communication between nurses and pediatric patients and facilitate access to important health information. The UCD process includes understanding the user context, determining user needs, designing and producing solutions, and evaluating those needs. From the initial survey of 74 respondents, 50.56% agreed and 46.02% strongly agreed with the need for easier access to pediatric health information. A total of 74 respondents evaluated the app and gave positive feedback; 47.01% 'agreed', 41.17% 'strongly agreed' with the functionality of the app, and 11.82% 'moderately'. No respondents expressed 'disagree' or 'strongly disagree'. In conclusion, KiddoCare was rated as an effective and appropriate pediatric nursing tool, supporting flexible care that is adaptive to each child's individual needs.

EXPLORING AGILE EFFORT ESTIMATION ISSUES: A SYSTEMATIC LITERATURE REVIEW

Tetti Sinaga, Teguh Raharjo, Ni Wayan Trisnawaty — Wed, 20 Nov 2024 03:04:54 +0000

Effort estimation is crucial in software development, especially in Agile projects. The 2020 Standish Group survey found that only 31% of software projects success. The success of a software development project depends on the accuracy of effort estimation. This research aims to analyze studies related to effort estimation methods in Agile software development to identify related issues. A systematic literature review by Kitchenham was conducted across Emerald, Science Direct, Scopus, SpringerLink, and IEEE databases and identified 239 relevant studies from 2018 and 2023, ultimately focusing on 40 studies about effort estimation challenges in Agile software development. The research revealed 59 issues related to various estimation methods. The main challenge in effort estimation for Agile software development is team experience and limited knowledge about the domain, which results in inaccurate estimation result. Requirements’ details, tasks complexity, and lack of data will complicate problem-solving and the prediction of the duration of completion. Reliance on expert judgment will increase the risk of bias and inaccuracy in estimates. These challenges increase the likelihood of project failure due to a mismatch between initial planning and reality as development progresses.

USABILITY EVALUATION OF MOBILE MULTI-FACTOR AUTHENTICATION BASED ON FACE AUTHENTICATION, GEOLOCATION AND QR CODE

I Kadek Dendy Senapartha, Matahari Bhakti Nendya — Fri, 22 Nov 2024 11:21:59 +0000

The swift progress of information technology has led to the adoption of mobile-based multi-factor authentication (MFA) systems for attendance management, addressing inefficiencies, security issues, and errors inherent in traditional methods. By utilizing multiple layers of authentication—such as face recognition, geolocation, and QR code scanning—these systems significantly enhance security and reliability. This study evaluates the usability of a mobile MFA system, focusing on user-friendliness and learnability. Two iterations of the system were tested using cognitive walkthrough approaches, chosen for their effectiveness in simulating the experience of new users and identifying usability issues in system learnability. The initial version of the system utilized MobileFaceNet_v2, which had an input size of 112x112. This resulted in a false acceptance rate (FAR) of 0.26, a false rejection rate (FRR) of 0.2, and a half total error rate (HTER) of 0.23. Failures in face verifications and inadequate instructions led to significant user dissatisfaction. In the second iteration, improvements were made by providing better instructions during location and QR scan steps, adding a face capture confirmation screen, and increasing the input size of the face anti-spoof detection model to 224x224. This reduced the FAR to 0.11 but increased the FRR to 0.4, resulting in HTER to 0.25. While these updates improved security, usability issues such as ambiguous user feedback and inadequate instructions persisted. These results emphasize the need for an integrated approach that combines both technological improvements in authentication models and enhancements in UI design to create a more user-friendly experience

SOCIAL MEDIA COMMENTS FOR GOVERNMENT INSTITUTION VIDEO CLASSIFICATION USING MACHINE LEARNING

M. Faris Al Hakim, Subhan Subhan, Prasetyo Listiaji — Sat, 23 Nov 2024 09:13:25 +0000

YouTube is a social media site that is quite familiar and is used as a means of disseminating video-based information. With a fairly high number of users, YouTube can become a communication medium for audiences, including government agencies. The user’s responses in comments reflect the nuance of the presented video. This research aims to determine the best algorithm for classifying video types based on user comments. Several machine learning algorithms used to carry out classification are Decision Tree, Random Forest, K-Nearest Neighbor, Support Vector Machine, and Logistic Regression. K-Fold Cross Validation was chosen as a method to evaluate the performance of classification algorithms based on the accuracy values. of these algorithms in classifying YouTube videos based on comments. The first experiment with the highest ratio of training and test data for each algorithm was obtained at a ratio of 90:10, with respectively 78.99%, 86.21%, 84.01%, 72.72%, and 79.31%. In the second experiment with k-fold cross validation using a ratio of 90:10, the highest accuracy for each algorithm was obtained at a value of k = 10, which was respectively 74.39%, 81.34%, 78.05%, 85.21%, and 72.15%. From these results, it can be concluded that the most suitable algorithm for classifying YouTube videos based on comments is the Random Forest algorithm with a training and test data ratio of 90:10 and SVM with 10-cross-fold validation. These results show that a larger portion of data for learning has a positive impact on algorithm performance.

MOBILENET PERFORMANCE IMPROVEMENTS FOR DEEPFAKE IMAGE IDENTIFICATION USING ACTIVATION FUNCTION AND REGULARIZATION

Handrie Noprisson, Vina Ayumi, Mariana Purba, Nur Ani — Mon, 25 Nov 2024 09:11:53 +0000

Deepfake images are often used to spread false information, manipulate public opinion, and harm individuals by creating fake content, making developing deepfake detection technology essential to mitigate these potential dangers. This study utilized the MobileNet architecture by applying regularization and activation function methods to improve detection accuracy. ReLU (Rectified Linear Unit) enhances the model's efficiency and ability to capture non-linear features, while Dropout and L2 regularization help reduce overfitting by penalizing large weights, thereby improving generalization. Based on experimental results, the MobileNet model optimized with ReLU and Dropout achieved an accuracy of 99.17% in the training phase, 85.34% in validation, and 70.60% in testing, whereas the MobileNet model optimized with ReLU and L2 showed lower accuracy in the training and validation phases compared to Dropout but achieved higher accuracy in testing at 72.18%. This study recommends MobileNet with ReLU and L2 due to its better generalization ability when testing data (resulting from reduced overfitting).

SYSTEMATIC LITERATURE REVIEW: CHALLENGES AND SOLUTIONS ON AGILE PROJECT MANAGEMENT IN PUBLIC SECTOR

Handini Mekkawati, Teguh Raharjo, Rina Yuniarti — Tue, 26 Nov 2024 09:31:29 +0000

The public sector is transforming by adopting an agile approach to overcome bureaucratic rigidity and lagging the private sector. The aim is to overcome the limitations of traditional approaches by encouraging flexibility in planning, operations, and service delivery. In the face of diverse, agile characteristics, further research is required on the challenges and best practices other public sector organizations can adopt. This research identifies key challenges in agile implementation within the PMBOK 7th edition project performance domains with the most issues: Development Approach and Life Cycle and Project Work Domain. Using a systematic literature review (SLR), 35 of 680 reviewed papers were selected as references. The biggest challenges were in the Project Work Domain, dominated by the context of monitoring new work and changes, project processes, and procurement processes. Best practices were identified to address these challenges and guide other public sectors in supporting more flexible and responsive public service delivery.