Publication Search

Software development effort estimation is crucial as it is one of the key factors for successful software development. This research employs Random Forest to estimate software development effort. To achieve better results, the study combines the Random Forest method with Genetic Algorithm. The results show that the China dataset provides more accurate estimation compared to the Desharnais dataset, because the China dataset uses relevant feature selection for estimation.

Stunting and wasting are nutritional problems in toddlers that remain a double burden of malnutrition in Indonesia and have an impact on the quality of health and future human resource development. Monitoring the nutritional status of toddlers is generally carried out using anthropometric indicators, but the use of this data is still limited to descriptive analysis. This study aims to apply the K-Means algorithm in clustering infants vulnerable to stunting and wasting based on anthropometric indicators, so that groups of infants with different levels of nutritional vulnerability can be identified. The dataset used consists of infant data with variables of gender, age (months), height (cm), and weight (kg). The research stages included data preprocessing, encoding categorical variables, data normalization, determining the optimal number of clusters using the Elbow and Silhouette Score methods, and analyzing the characteristics of each cluster. The evaluation results showed that the optimal number of clusters was four. Each cluster has different anthropometric characteristics and distributions of stunting and wasting status, ranging from groups with relatively normal nutritional conditions, groups with a tendency toward overnutrition, to groups that are vulnerable to acute and chronic malnutrition. These clustering results provide a more comprehensive and segmented mapping of toddlers, which can be used as a basis for formulating more targeted and data-driven nutrition policies and interventions.

Managing Regional Public Service Agency (Badan Layanan Umum Daerah/BLUD) hospitals requires planning and budgeting processes that are accountable, measurable, and aligned with service performance. In practice, BLUD planning is still constrained by fragmented applications (hospital information system/SIMRS, finance, human resources, e-office, and procurement), duplicate data entry, approval delays, and limited monitoring of process compliance. This study aims to analyze requirements and design a web-based BLUD planning information system using an Enterprise Application Integration (EAI) approach through middleware to improve cross-system interoperability, data consistency, and the timeliness of executive reporting. The study adopts the Design Science Research (DSR) framework, comprising problem identification, definition of solution objectives, artifact design and development, demonstration, evaluation, and communication/report writing. The proposed system includes a unit-based budget proposal module and item management, a role-based approval workflow (RBAC) with SLA tracking, a budget ceiling (pagu) master to benchmark proposals, audit trails and report exports, and an executive dashboard integrating budget perspectives, service indicators (e.g., bed occupancy rate/BOR and patient visits), and process compliance. It also provides an integration design via middleware (ESB/message broker) supported by a canonical data model (CDM) and traceable logging (trace_id/correlation_id). Evaluation using black-box testing and API contract testing indicates that the main planning workflow operates as intended and the integration interfaces are consistently defined, providing a foundation for staged implementation and further performance evaluation.

Conventional management of sports services often leads to inefficiency and limited public access to experts and facilities. Reliance on manual systems poses a high risk of scheduling conflicts or human error. This study aims to develop the User Interface (UI) and User Experience (UX) design for the Movement and Athletic Talent Hub (MATCH) application as an integrative digital solution. The approach employed is the Design Thinking method, encompassing the stages of empathize, define, ideate, prototype, and testing. The design process resulted in an interactive prototype featuring key functions such as facility booking, trainer search, and a digital payment system. Evaluation was conducted using the System Usability Scale (SUS) method involving target users. The test results yielded an average score of 79.5, categorizing the MATCH application within the Good rating and Acceptable status. These findings indicate that the design is effective in meeting user needs and is viable for further development as a digital sports ecosystem.

The rapid development of information technology encourages the use of digital media as an educational tool in the health sector, particularly for pregnant women. One of the problems faced by Klinik Bidan Rima Pondok Meja is the limited use of conventional educational media, such as books and posters, which are considered less attractive and difficult to understand. This study aims to design and develop an Android-based Augmented Reality (AR) application as an educational medium for nutrition and fetal development for pregnant women. The application presents three-dimensional (3D) visualizations of fetal development from week to week, along with information on nutritional needs during pregnancy. The system development method used in this research is the Prototype model, while the Augmented Reality technology applies marker-based tracking. The development tools used include Unity, and Blender 3D. The result of this study is an Android-based AR application prototype that provides interactive and easily understandable information about fetal development and maternal nutrition. This application is expected to increase learning interest and understanding of pregnant women in maintaining a healthy pregnancy at Klinik Bidan Rima Pondok Meja.

Student selection for the National Student Sports Olympiad (O2SN), particularly in the karate category, is still largely conducted manually, which may lead to subjectivity and inconsistency in the assessment process. This study aims to design and develop a web-based Decision Support System (DSS) to assist schools in selecting the best students for the O2SN karate competition by applying the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) method at SMA Negeri 2 Muaro Jambi. The system was developed using the waterfall model, which consists of requirement analysis, system design, implementation, and testing stages. The student evaluation process is based on criteria referring to the official O2SN karate standards, including stance accuracy, techniques, movement transitions, timing and harmony, breathing control, focus (kime), conformity (consistency with ryu-ha/style), strength, speed, and balance. The developed system processes assessment data to generate preference values and student rankings, which are separated by male and female categories. The results indicate that the application of the TOPSIS method is able to support more objective decision-making and improve transparency and efficiency in the O2SN student selection process within the school environment.

The National Student Arts Festival and Competition (FLS3N) is an event aimed at developing students’ talents and achievements in the arts, including solo vocal competitions. The assessment process in this category involves multiple criteria, which may lead to subjectivity in decision-making. This study aims to design and develop a web-based Decision Support System (DSS) for selecting non-academic students in the FLS3N solo vocal category using the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) method. The assessment criteria are based on the 2025 FLS3N Technical Guidelines, consisting of voice quality, vocal technique, expression, and performance. The TOPSIS method is applied to generate alternative rankings based on the highest preference value. The system is developed using a web-based software development approach and tested using participant data from both male and female categories. The results indicate that the system can provide objective and consistent ranking recommendations, thereby assisting schools in selecting the best students to represent them in the FLS3N competition.

SMP Negeri 5 Merlung is a public junior high school in Merlung Subdistrict that has utilized the DAPODIK system for online data processing management, enabling efficient sending and receiving of information to the government. This research analyzes IT governance on the DAPODIK system using the COBIT 5 framework, specifically the MEA01 domain (Monitor, Evaluate and Assess Performance and Conformance), which focuses on monitoring and evaluating performance and conformance. The research background is based on the need to maximize the utilization of the system at the school level. The main objectives are to determine the current and expected capability levels, as well as to provide improvement recommendations to achieve higher process maturity. The research method applies Assessment Process Activities, covering observation, interviews, identification of findings, gap analysis, and recommendations. The results show that the current capability level is at level 3 (established process), while the expected capability level is directed toward level 4 (predictable process). The implications of these findings provide practical recommendations such as routine monitoring enhancements, staff training, and integration of automation tools to bridge the capability gap, thereby improving the effectiveness of IT governance at SMP Negeri 5 Merlung sustainably.

ARP spoofing attacks are a serious threat to network security, particularly in vulnerable Internet of Things (IoT) environments. This final project aims to detect ARP spoofing attacks on IoT net-works using a combination of Random Forest (RF) and Robust PCA methods. RF is chosen for its classification capabilities and handling of non-linear data, while Robust PCA is used for di-mensionality reduction and handling outliers in the data. The dataset used is "MITMArpSpoof-ing.pcap.csv," which contains network traffic data. The data is processed by performing prepro-cessing, feature scaling, and converting labels to binary (0 for benign, 1 for ARP spoofing). Subsequently, Robust PCA is applied to reduce data dimensions, and then the data is trained using the RF model. The test results show that the RF model with Robust PCA achieves an accu-racy of 96.02% in detecting ARP spoofing attacks. This method has proven effective in identify-ing and classifying ARP spoofing attacks on IoT networks.

Student dropout remains a significant challenge for higher education institutions as it impacts academic quality, educational management efficiency, and students' success in completing their studies. Therefore, an approach that can identify students at risk of dropping out is necessary so that timely academic interventions can be made. This study aims to develop a dropout detection model using an Artificial Neural Network (ANN). The data used come from a publicly available higher education dataset, ensuring research reproducibility. Data preprocessing steps were carried out to improve data quality before modeling, and the Synthetic Minority Over-Sampling Technique combined with Edited Nearest Neighbors (SMOTE-ENN) was applied to address class imbalance issues. The ANN model's performance was evaluated using accuracy, precision, recall, F1-score, and area under the ROC curve (ROC-AUC). The test results show that the ANN model can provide excellent predictive performance in detecting at-risk students. The application of SMOTE-ENN also proved to enhance the model’s sensitivity toward the minority class, as indicated by improvements in recall and F1-score. These findings indicate that the developed ANN model has the potential to be used as a student dropout detection system to support data-driven decision-making and strategy development within higher education institutions.

Hypertension is a major global health risk that requires accurate early detection, yet conventional methods struggle with complex and imbalanced health datasets. This study aims to optimize hypertension prediction using a Logistic Regression model integrated with Borderline-SMOTE to enhance recall and provide model transparency through SHAP (Shapley Additive Explanations). The method utilizes the BRFSS dataset, applying Borderline-SMOTE to address class imbalance at the decision boundary and XAI techniques for global and local interpretation. The findings show that the model achieved an accuracy of 0.719, an AUC of 0.800, and a significantly improved recall of 0.756. SHAP analysis identified age, high cholesterol, and BMI as the most influential risk factors, while waterfall plots successfully clarified individual risk extremes, ranging from 1.72% to 99.43% probability. These results imply that the proposed approach provides a sensitive and transparent screening tool for public health practitioners, effectively balancing statistical efficiency with clinical accountability.

The fitness industry has shown rapid growth as public awareness of the importance of healthy lifestyles increases in today's world. Gyms no longer function solely as a place to exercise, but also offer value and a sustainable experience for their members. The ability to manage a gym and retain members in this increasingly competitive era encourages gym owners to be more sensitive to factors that could potentially affect member satisfaction and loyalty. To improve the quality of the gym, it is necessary to evaluate the price and quality offered in the form of well-maintained and complete facilities. The suitability of the price to the benefits felt by members will make them more loyal to training at the gym. Likewise, comfortable facilities can increase member loyalty, which in turn drives member satisfaction, especially at Velcro Gym.

The purpose of this study is to investigate the factors that lead to poverty in different Indonesian regions between 2018 up to 2024. The Gross Regional Domestic Product per capita, the Human Development Index, and the Open Unemployment Rate are the independent factors used in this study, whereas poverty levels are the dependent variable. The Central Statistics Agency provided secondary data that was used in a quantitative manner. Using EViews 12 software, panel regression techniques were used to process the data. The study's conclusions show that, at a significance level of less than 0.05, economic and human development factors simultaneously significantly affect poverty rates across Indonesian regions. The coefficient of determination indicates that the variables in the model can account for the majority of the variations in poverty levels. These findings demonstrate how important a region's economic status and level of human development are to efforts to reduce poverty. It is anticipated that this research will help the government develop more effective and long-lasting methods for reducing poverty.

This study aims to analyze the influence of promotion, shopping convenience, advertising, recommendation, comment, and credibility factors on purchase intensity in the TikTok Shop platform among Indonesian households. The rapid development of social commerce services requires a deep understanding of factors driving online purchasing decisions, especially among families as primary users. A quantitative approach was employed, utilizing a Likert-scale questionnaire distributed online. The sample consisted of 150 active TikTok Shop users from various household backgrounds. Partial Least Squares Structural Equation Modeling (PLS-SEM) via SmartPLS was used to analyze the direct effects of each factor on purchase intensity. The results indicate that promotion, shopping convenience, and credibility significantly and positively influence purchase intensity, while advertising, recommendation, and comment have relatively weaker yet still relevant effects. These findings underscore the importance of effective promotional strategies, ease-of-shopping enhancements, and building platform credibility to boost purchase intensity within the household consumer segment. The practical implications can guide e-commerce practitioners and digital marketers in formulating adaptive marketing strategies in the era of social commerce.

The rapid growth of e-commerce platforms in Indonesia, particularly Tokopedia, has resulted in a large volume of consumer reviews containing valuable information regarding customer perceptions and satisfaction. However, manual analysis of such reviews is inefficient and prone to subjectivity, necessitating an automated approach based on machine learning. This study aims to classify the sentiment of sports product reviews on Tokopedia into positive, negative, and neutral categories by applying Logistic Regression, Support Vector Machine (SVM), and Random Forest using the Term Frequency–Inverse Document Frequency (TF-IDF) approach. The data were collected through web scraping of Indonesian-language sports product reviews and processed through several preprocessing stages, including data cleaning, case folding, tokenization, stopword removal, and stemming. Feature representation was performed using TF-IDF to transform textual data into numerical vectors, after which the dataset was divided into training and testing sets with an 80:20 ratio. Model performance was evaluated using accuracy, precision, recall, and F1-score metrics. The results indicate that the application of TF-IDF significantly improves the performance of all models, with SVM consistently achieving the most optimal performance compared to Logistic Regression and Random Forest. These findings demonstrate that classical machine learning algorithms combined with TF-IDF remain highly effective for sentiment analysis of Indonesian-language text. The implications of this study are expected to assist sellers in understanding customer opinions, support consumers in making informed purchasing decisions, and serve as a foundation for the development of sentiment analysis and recommendation systems on e-commerce platforms.

Information technology (IT) governance plays a strategic role in supporting the achievement of organizational goals, especially in higher education institutions. Adiwangsa University Jambi, as a private university, is required to manage IT effectively, efficiently, and in line with the institution's vision. This study aims to analyze the level of IT governance capabilities at Adiwangsa Jambi University using the COBIT 2019 framework with a focus on the EDM (Evaluate, Direct, Monitor) domain. The research method used is a descriptive quantitative method through data collection using questionnaires, interviews, and documentation studies. The results show that the level of IT governance capability in the EDM domain is at level 2 (Managed Process), indicating that the IT governance process is running but still needs improvement in several aspects, especially in monitoring and controlling IT performance. This study is expected to provide recommendations for Adiwangsa University Jambi in improving IT governance in a sustainable manner.

In the contemporary digital marketplace, consumers increasingly face diverse product choices and brand communications. Understanding the mechanisms through which product quality and brand perception influence customer loyalty remains critical for competitive advantage. The mediating role of customer trust in this relationship has received limited empirical attention within Indonesian market contexts. This research analyzes the direct and indirect effects of product quality and brand perception on customer loyalty, with customer trust as a mediating variable, using Partial Least Squares Structural Equation Modeling (PLS-SEM) methodology on 103 respondents. A quantitative cross-sectional survey design was employed, collecting data via Likert-scale questionnaires (1-5) with 15 measurement items across four latent constructs: Product Quality (5 items), Brand Perception (4 items), Customer Trust (3 items), and Customer Loyalty (3 items). Data analysis utilized PLS-SEM via SmartPLS 3.0, including assessment of measurement model validity (outer model), structural relationships (inner model), and mediation effects through bootstrapping (5000 iterations). The outer model demonstrated adequate validity with 12 of 15 indicators loading above 0.7, and all constructs meeting composite reliability (CR > 0.7) and average variance extracted (AVE > 0.5) criteria. The inner model revealed that product quality significantly influenced customer trust (β = 0.624, p < 0.001), while brand perception showed no significant direct effect (β = 0.045, p = 0.767). Customer trust strongly predicted loyalty (β = 0.650, p < 0.001). Product quality demonstrated a significant indirect effect on loyalty through trust (β = 0.405, p < 0.001), indicating full mediation. The model explained 43.5% of trust variance and 42.2% of loyalty variance. Product quality emerged as the dominant antecedent of customer trust and loyalty, while brand perception did not significantly contribute. Trust served as the critical mechanism translating quality into loyalty. These findings suggest that companies should prioritize quality assurance and consistent delivery over brand marketing campaigns for sustainable loyalty development. The research contributes to mediation theory in consumer behavior and provides actionable strategic guidance for practitioners in emerging markets.

This research aims to analyze the public's perception of career women's efforts in achieving work-life balance, as well as its impact on the dual role experience. The research focus includes the view of society, obstacles experienced by women, and the social implications of the dual role of women. The results of the study based on the questionnaire showed that 74,94% of the people had a positive perception of career women and judged that the balance of work and life can be achieved through time management and family support, while 25,06% had a neutral to negative perception that considered that career women were not optimal in carrying out domestic roles, thus causing social pressure and role conflicts. This perception contributes to stress levels, emotional fatigue, and difficulties in achieving work-life balance. This finding also reveals that education factors, working experience with women, family roles, and social environment affect the formation of perceptions. This research is expected to contribute in increasing public understanding and encouraging policies that support women's careers both in social and work.

This study aims to compare the effectiveness of QRIS with other cashless payment methods in driving the development of the digital economy in Indonesia. The background to this study stems from the increasing use of digital transactions and the strategic role of QRIS as a national standard for QR-based payments. Google Forms was used to disseminate the survey online and successfully collected 100 respondents who were users of cashless digital payment services. A purposive sampling technique was used to ensure that respondents had experience using QRIS and other digital payment methods. Data were examined using the SmartPLS 4 program using a Partial Least Squares Structural Equation Modeling (PLS-SEM) approach to test the relationships between variables. The results indicate that perceived ease of use, transaction security, and influence on digital behavior have a positive or significant influence on QRIS effectiveness. However, availability and accessibility variables did not have a significant effect. This finding indicates that QRIS effectiveness is more influenced by user experience and perceptions, rather than availability or ease of access. This research is expected to contribute to the development of strategies to increase digital payment adoption in Indonesia.

The rapid development of artificial intelligence, particularly ChatGPT, has created new opportunities to support students’ academic activities in higher education. However, its utilization needs to be evaluated in terms of the alignment between academic task characteristics and technological capabilities to ensure optimal outcomes. This study aims to examine the feasibility of using ChatGPT in students’ academic activities by applying the Task–Technology Fit (TTF) model. This research employed a quantitative approach using Structural Equation Modeling based on Partial Least Squares (SEM-PLS). Data were collected through questionnaires distributed to university students and analyzed using SmartPLS 4 software. The variables examined included Task Characteristics, Technology Characteristics, Task–Technology Fit, Performance Impact, and Utilization. The results indicate that Task Characteristics and Technology Characteristics have a positive and significant effect on Task–Technology Fit. Furthermore, Task–Technology Fit significantly influences Performance Impact and Utilization. Performance Impact also shows a positive and significant effect on the utilization of ChatGPT by students. These findings suggest that the alignment between academic task requirements and the capabilities of ChatGPT plays a crucial role in improving students’ performance and encouraging sustained technology use. The implications of this study highlight the importance of selective and purposeful use of ChatGPT in higher education and provide a reference for higher education institutions in formulating policies related to the ethical and effective integration of artificial intelligence technologies as learning support tools.