Feddy Setio Pribadi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Feddy Setio Pribadi has a total of 33 co-authors. Here are the top co-authors by number of shared publications:
- Arulita Ika Fibriana
Universitas Negeri Semarang
2 shared publications - Agus Suryanto
Department of Mathematics, Faculty of Mathematics and Natural Sciences, Universitas Brawijaya, Indonesia
1 shared publication Ahnaf Maulana
1 shared publication- Ali Masyhar
Faculty of Law, Universitas Negeri Semarang
1 shared publication - Arief Rahadian
Department of Biochemical, Faculty of Medicine, Universitas Islam Sultan Agung, Indonesia
1 shared publication - Arvina Rizqi Nurul’aIni
Universitas Negeri Semarang
1 shared publication
Latest Publications
- Open Access
- 20 July 2026
- Published by JMIR Publications Inc. in JMIR Preprints
Developing a Supervised Self-Assessment Psychosocial Stimulation Intervention to Enhance Cognitive Development among Stunted Children Under Five: A Study in Semarang, Indonesia (Preprint)
BACKGROUND Stunting remains a major public health problem worldwide and is strongly associated with impaired cognitive and language development. Although psychosocial stimulation has been shown to improve development, conventional interventions often require intensive supervision by health professionals and are difficult to sustain in community settings. Digital health technologies offer opportunities to enhance caregiver engagement; however, evidence on chatbot-based supervised self-assessment for psychosocial stimulation remains limited. OBJECTIVE This study aimed to develop and evaluate a WhatsApp® chatbot-based supervised self-assessment model using the Home Observation for Measurement of the Environment (HOME) Inventory to improve psychosocial stimulation practices and cognitive development among stunted children. METHODS This research and development study used the ADDIE (Analysis, Design, Development, Implementation, and Evaluation) model. During the analysis phase, a literature review and stakeholder focus group discussions were conducted to identify intervention needs. The intervention was then developed through a participatory process involving stakeholder consultation, expert validation, and iterative refinement to ensure its relevance, feasibility, and suitability for community-based child development programs. The final intervention integrated a WhatsApp® chatbot, the Home Observation for Measurement of the Environment (HOME) Inventory, educational videos, and a monitoring dashboard. This model enabled caregivers to conduct self-assessments while receiving ongoing supervision from health personnel. The model underwent expert validation and usability testing using the Usefulness, Satisfaction, and Ease of Use (USE) Questionnaire. Its effectiveness was subsequently evaluated in a randomized controlled trial involving caregivers of stunted children at four Rumah Pelita centers in Semarang, Indonesia. Children’s cognitive development was assessed before and after the intervention using the Capute Scales, comprising the Cognitive Adaptive Test (CAT) and the Clinical Linguistic and Auditory Milestone Scale (CLAMS). Quantitative data were analyzed using Cohen’s kappa coefficient, the Wilcoxon signed-rank test, the Sign test, and the Mann–Whitney U test; qualitative data were analyzed using content analysis. RESULTS The needs assessment identified the need for a practical digital intervention integrating psychosocial stimulation assessment, caregiver education, and continuous supervision. A WhatsApp® chatbot-based supervised self-assessment model was successfully developed and validated. The model demonstrated high usability, with an overall USE-score of 87.32%, indicating excellent user acceptance. The chatbot-based HOME-Inventory assessment showed good agreement with the conventional assessment. Compared with the control group, the intervention significantly improved children's developmental outcomes, including Developmental Quotient (DQ) CAT (Δ=7.14, p = 0.012), DQ CLAMS (Δ=4.62, p = 0.049), Full-Scale Developmental Quotient (FSDQ) (Δ=5.70, p = 0.007), expressive language (Δ=8.73, p = 0.004), receptive language (Δ=4.91, p = 0.007), and overall language development (Δ=6.27, p = 0.004). CONCLUSIONS The WhatsApp® chatbot-based supervised self-assessment model is a valid, feasible, and effective digital intervention for supporting psychosocial stimulation among caregivers of stunted children. Integrating standardized assessment, educational support, and continuous supervision into a widely accessible messaging platform could strengthen community-based child development programs, particularly in low-resource settings. CLINICALTRIAL N/A
- 20 July 2026
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessDeveloping a Supervised Self-Assessment Psychosocial Stimulation Intervention to Enhance Cognitive Development among Stunted Children Under Five: A Study in Semarang, Indonesia (Preprint)
BACKGROUND Stunting remains a major public health problem worldwide and is strongly associated with impaired cognitive and language development. Although psychosocial stimulation has been shown to improve development, conventional interventions often require intensive supervision by health professionals and are difficult to sustain in community settings. Digital health technologies offer opportunities to enhance caregiver engagement; however, evidence on chatbot-based supervised self-assessment for psychosocial stimulation remains limited. OBJECTIVE This study aimed to develop and evaluate a WhatsApp® chatbot-based supervised self-assessment model using the Home Observation for Measurement of the Environment (HOME) Inventory to improve psychosocial stimulation practices and cognitive development among stunted children. METHODS This research and development study used the ADDIE (Analysis, Design, Development, Implementation, and Evaluation) model. During the analysis phase, a literature review and stakeholder focus group discussions were conducted to identify intervention needs. The intervention was then developed through a participatory process involving stakeholder consultation, expert validation, and iterative refinement to ensure its relevance, feasibility, and suitability for community-based child development programs. The final intervention integrated a WhatsApp® chatbot, the Home Observation for Measurement of the Environment (HOME) Inventory, educational videos, and a monitoring dashboard. This model enabled caregivers to conduct self-assessments while receiving ongoing supervision from health personnel. The model underwent expert validation and usability testing using the Usefulness, Satisfaction, and Ease of Use (USE) Questionnaire. Its effectiveness was subsequently evaluated in a randomized controlled trial involving caregivers of stunted children at four Rumah Pelita centers in Semarang, Indonesia. Children’s cognitive development was assessed before and after the intervention using the Capute Scales, comprising the Cognitive Adaptive Test (CAT) and the Clinical Linguistic and Auditory Milestone Scale (CLAMS). Quantitative data were analyzed using Cohen’s kappa coefficient, the Wilcoxon signed-rank test, the Sign test, and the Mann–Whitney U test; qualitative data were analyzed using content analysis. RESULTS The needs assessment identified the need for a practical digital intervention integrating psychosocial stimulation assessment, caregiver education, and continuous supervision. A WhatsApp® chatbot-based supervised self-assessment model was successfully developed and validated. The model demonstrated high usability, with an overall USE-score of 87.32%, indicating excellent user acceptance. The chatbot-based HOME-Inventory assessment showed good agreement with the conventional assessment. Compared with the control group, the intervention significantly improved children's developmental outcomes, including Developmental Quotient (DQ) CAT (Δ=7.14, p = 0.012), DQ CLAMS (Δ=4.62, p = 0.049), Full-Scale Developmental Quotient (FSDQ) (Δ=5.70, p = 0.007), expressive language (Δ=8.73, p = 0.004), receptive language (Δ=4.91, p = 0.007), and overall language development (Δ=6.27, p = 0.004). CONCLUSIONS The WhatsApp® chatbot-based supervised self-assessment model is a valid, feasible, and effective digital intervention for supporting psychosocial stimulation among caregivers of stunted children. Integrating standardized assessment, educational support, and continuous supervision into a widely accessible messaging platform could strengthen community-based child development programs, particularly in low-resource settings. CLINICALTRIAL N/A
- Open Access
- 13 July 2026
- Published by Universitas Negeri Semarang in Journal of Law and Legal Reform
- Vol. 7 (3) , 1585-1626
Gamified Online Radicalization and Counterterrorism Law Reform for Indonesian Adolescents
Indonesia’s Counterterrorism Law (Law No. 5 of 2018) has not regulated one of the rapidly growing radicalization vectors: multiplayer online games, where recruitment is decentralized, extremist narratives are embedded in in-game content, and migration to encrypted platforms operates outside existing regulatory frameworks. This research addresses that normative gap by examining how extremist content is disseminated through online games played by Indonesian teenagers and identifying legal weaknesses that leave this vector unregulated. Using a normative-qualitative approach combining doctrinal analysis, literature review, and exploratory questionnaire data from 46 junior high school students (ages 12–15) in Gunungpati, Semarang, this study analyzes radicalization mechanisms—including narrative infiltration, extremist symbols, and in-game recruitment—through Moghaddam’s Staircase to Terrorism framework and Ware’s Third Generation of Radicalization. The findings indicate significant exposure to ideological recruitment through in-game social features and psychosocial vulnerabilities among respondents, strengthening the doctrinal urgency beyond generalized statistical claims. The doctrinal analysis identified three normative gaps in Law No. 5 of 2018: the absence of due diligence obligations for game operators, the lack of detection and school-based reporting mechanisms, and the failure to recognize children vulnerable to radicalization as subjects of legal protection rather than criminal responsibility. By integrating empirical evidence with doctrinal analysis, this study provides the first legal-empirical account linking online game–based radicalization to Indonesian counterterrorism law and highlights the need to shift from a repressive to a prevention-oriented legal framework through early intervention in digital radicalization.
- 13 July 2026
- Published by Universitas Negeri Semarang in Journal of Law and Legal Reform
- Vol. 7 (3) , 1585-1626
Open AccessGamified Online Radicalization and Counterterrorism Law Reform for Indonesian Adolescents
Indonesia’s Counterterrorism Law (Law No. 5 of 2018) has not regulated one of the rapidly growing radicalization vectors: multiplayer online games, where recruitment is decentralized, extremist narratives are embedded in in-game content, and migration to encrypted platforms operates outside existing regulatory frameworks. This research addresses that normative gap by examining how extremist content is disseminated through online games played by Indonesian teenagers and identifying legal weaknesses that leave this vector unregulated. Using a normative-qualitative approach combining doctrinal analysis, literature review, and exploratory questionnaire data from 46 junior high school students (ages 12–15) in Gunungpati, Semarang, this study analyzes radicalization mechanisms—including narrative infiltration, extremist symbols, and in-game recruitment—through Moghaddam’s Staircase to Terrorism framework and Ware’s Third Generation of Radicalization. The findings indicate significant exposure to ideological recruitment through in-game social features and psychosocial vulnerabilities among respondents, strengthening the doctrinal urgency beyond generalized statistical claims. The doctrinal analysis identified three normative gaps in Law No. 5 of 2018: the absence of due diligence obligations for game operators, the lack of detection and school-based reporting mechanisms, and the failure to recognize children vulnerable to radicalization as subjects of legal protection rather than criminal responsibility. By integrating empirical evidence with doctrinal analysis, this study provides the first legal-empirical account linking online game–based radicalization to Indonesian counterterrorism law and highlights the need to shift from a repressive to a prevention-oriented legal framework through early intervention in digital radicalization.
- Open Access
- 24 May 2026
- Published by STKIP PGRI Tulungagung in JIPI (Jurnal Ilmiah Penelitian dan Pembelajaran Informatika)
- Vol. 11 (2) , 1566-1573
A Wind Speed Forecasting Model Using Bi-Directional LSTM
Accurate wind speed forecasting is essential for optimizing wind energy generation, ensuring grid reliability, and supporting meteorological planning. This study presents a wind speed forecasting model based on a Bi-Directional Long Short-Term Memory (Bi-LSTM) network to capture complex temporal dependencies in time series data. The Bi-LSTM model was trained on historical wind speed data and tested across various forecasting schemes with several evaluation metrics such as Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), and Coefficient of Determination (R²). The result in the 24-hour forecast shows that the model achieved an MSE of 0.0454, RMSE of 0.2131, MAE of 0.1700, MAPE of 0.0443, and R² of 0.7103. On the 48-hour forecast, the model recorded an MSE of 0.0326, RMSE of 0.1807, MAE of 0.1353, MAPE of 0.0378, and R² of 0.8564. The 72-hour forecast achieved an MSE of 0.0290, RMSE of 0.1702, MAE of 0.1302, MAPE of 0.0336, and R² of 0.9429. The model demonstrated strong generalization on the full testing set with an MSE of 0.1432, RMSE of 0.1959, MAE of 0.1423, MAPE of 0.0708, and R² of 0.9810. These findings highlight the Bi-LSTM model's effectiveness and robustness for wind speed forecasting, offering a valuable tool for wind energy management and operational planning.
- 24 May 2026
- Published by STKIP PGRI Tulungagung in JIPI (Jurnal Ilmiah Penelitian dan Pembelajaran Informatika)
- Vol. 11 (2) , 1566-1573
Open AccessA Wind Speed Forecasting Model Using Bi-Directional LSTM
Accurate wind speed forecasting is essential for optimizing wind energy generation, ensuring grid reliability, and supporting meteorological planning. This study presents a wind speed forecasting model based on a Bi-Directional Long Short-Term Memory (Bi-LSTM) network to capture complex temporal dependencies in time series data. The Bi-LSTM model was trained on historical wind speed data and tested across various forecasting schemes with several evaluation metrics such as Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), and Coefficient of Determination (R²). The result in the 24-hour forecast shows that the model achieved an MSE of 0.0454, RMSE of 0.2131, MAE of 0.1700, MAPE of 0.0443, and R² of 0.7103. On the 48-hour forecast, the model recorded an MSE of 0.0326, RMSE of 0.1807, MAE of 0.1353, MAPE of 0.0378, and R² of 0.8564. The 72-hour forecast achieved an MSE of 0.0290, RMSE of 0.1702, MAE of 0.1302, MAPE of 0.0336, and R² of 0.9429. The model demonstrated strong generalization on the full testing set with an MSE of 0.1432, RMSE of 0.1959, MAE of 0.1423, MAPE of 0.0708, and R² of 0.9810. These findings highlight the Bi-LSTM model's effectiveness and robustness for wind speed forecasting, offering a valuable tool for wind energy management and operational planning.
- Open Access
- 1 March 2026
- Published by Universitas Muhammadiyah Yogyakarta in Journal of Robotics and Control (JRC)
- Vol. 7 (2) , 3587-3597
Development of Adaptive Cruise Control for Cut-In Scenario Using Crow Search Algorithm
Cut-in maneuvers pose a major challenge for Adaptive Cruise Control (ACC) systems because they require rapid re-identification of the lead vehicle and immediate adjustment of longitudinal control to maintain safety. Conventional ACC controllers often struggle to respond quickly and smoothly under these abrupt disturbances. This study proposes the use of the Crow Search Algorithm (CSA) to optimize key ACC control parameters, enabling improved adaptability and stability during cut-in events. CSA is employed to tune the controller gains through an iterative search process that balances exploration and exploitation. Simulation experiments are conducted to evaluate the influence of iteration numbers and population sizes on optimization performance. The optimized ACC system is validated through a cut-in scenario, assessing relative distance error, velocity error, and recovery behavior after the disturbance. The results show that CSA significantly enhances the controller’s ability to reduce transient errors, stabilize inter-vehicle distance, and restore speed in a smooth and safe manner. These findings demonstrate that CSA is a promising metaheuristic for improving ACC robustness in highly dynamic traffic environments. Future extensions include testing in multi-scenario conditions, incorporating cooperative vehicle-to-vehicle communication, and integrating hybrid optimization methods to further enhance real-time performance.
- 1 March 2026
- Published by Universitas Muhammadiyah Yogyakarta in Journal of Robotics and Control (JRC)
- Vol. 7 (2) , 3587-3597
Open AccessDevelopment of Adaptive Cruise Control for Cut-In Scenario Using Crow Search Algorithm
Cut-in maneuvers pose a major challenge for Adaptive Cruise Control (ACC) systems because they require rapid re-identification of the lead vehicle and immediate adjustment of longitudinal control to maintain safety. Conventional ACC controllers often struggle to respond quickly and smoothly under these abrupt disturbances. This study proposes the use of the Crow Search Algorithm (CSA) to optimize key ACC control parameters, enabling improved adaptability and stability during cut-in events. CSA is employed to tune the controller gains through an iterative search process that balances exploration and exploitation. Simulation experiments are conducted to evaluate the influence of iteration numbers and population sizes on optimization performance. The optimized ACC system is validated through a cut-in scenario, assessing relative distance error, velocity error, and recovery behavior after the disturbance. The results show that CSA significantly enhances the controller’s ability to reduce transient errors, stabilize inter-vehicle distance, and restore speed in a smooth and safe manner. These findings demonstrate that CSA is a promising metaheuristic for improving ACC robustness in highly dynamic traffic environments. Future extensions include testing in multi-scenario conditions, incorporating cooperative vehicle-to-vehicle communication, and integrating hybrid optimization methods to further enhance real-time performance.
- 31 December 2025
- Published by Echo Academic Publishing in Environmental Research and Technology
- Vol. 8 (4) , 1007-1017
Design of waste management area based on clustering and traveling salesman problem
Waste management in rural Indonesia faces significant challenges as the volume of household waste increases. Waste banks are proposed as a solution to overcome this problem. This study aims to design an efficient waste management area in Gondangmanis Village by determining the optimal location of waste collection points and the shortest waste pickup route using clustering and Travelling Salesman Problem (TSP) approaches. The K-Means clustering algorithm is used to form clusters and determine the center point of each cluster, where the K value is first optimized using a genetic algorithm. Furthermore, the genetic algorithm is also applied to optimize the TSP to find the most efficient waste pickup route. The data used includes 1181 coordinate points in the study area, with household waste production of 2.5 kg/day/house and the capacity of the waste collection bin. The results showed that placing a waste collection bin with a capacity of 0.8 m³ with 4 clusters was more effective than 3 clusters with a capacity of 1 m³. TSP optimization resulted in the shortest waste pickup route with 19581 km, thus reducing travel distance and operational time. This approach is expected to increase waste management efficiency in rural areas, support environmental conservation, and optimize waste bank operations.
- 31 December 2025
- Published by Echo Academic Publishing in Environmental Research and Technology
- Vol. 8 (4) , 1007-1017
Design of waste management area based on clustering and traveling salesman problem
Waste management in rural Indonesia faces significant challenges as the volume of household waste increases. Waste banks are proposed as a solution to overcome this problem. This study aims to design an efficient waste management area in Gondangmanis Village by determining the optimal location of waste collection points and the shortest waste pickup route using clustering and Travelling Salesman Problem (TSP) approaches. The K-Means clustering algorithm is used to form clusters and determine the center point of each cluster, where the K value is first optimized using a genetic algorithm. Furthermore, the genetic algorithm is also applied to optimize the TSP to find the most efficient waste pickup route. The data used includes 1181 coordinate points in the study area, with household waste production of 2.5 kg/day/house and the capacity of the waste collection bin. The results showed that placing a waste collection bin with a capacity of 0.8 m³ with 4 clusters was more effective than 3 clusters with a capacity of 1 m³. TSP optimization resulted in the shortest waste pickup route with 19581 km, thus reducing travel distance and operational time. This approach is expected to increase waste management efficiency in rural areas, support environmental conservation, and optimize waste bank operations.
- Open Access
- 28 September 2025
- Published by Ikatan Ahli Informatika Indonesia (IAII) in Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi)
- Vol. 9 (5) , 1030-1037
Stacking Ensemble Learning Model for Intrusion Detection in Electrical Substation
Electrical substations are crucial infrastructure in power transmission and distribution but are increasingly vulnerable to cyber threats. However, existing intrusion detection systems (IDS) face challenges such as high false positive rates, limited adaptability to emerging attack patterns, and imbalanced detection across different intrusion types. This study proposes a Stacking Ensemble Learning model to enhance intrusion detection accuracy in electrical substations. The proposed model integrates Logistic Regression (LR), Support Vector Machine (SVM), K-Nearest Neighbors (KNN), and XGBoost (XGB) as base models with XGB acting as the meta-model. A real-world electrical substation IEC 60870-5-104 network traffic dataset comprising 319,949 instances with multiple attacks, such as DoS, Port Scan, NTP DdoS, IEC 104 Starvation, Fuzzy Attack, Flood Attack, and MITM, was used for this study. The results showed that the stacking model had the best accuracy (0.99990), precision (0.99990), recall (0.99990), and F1-score (0.99990), beating out the base, Bagging, and Boosting models. T-test results further confirmed statistical significance, with p-values of 0.00428 (LR), 0.04237 (SVM), 0.00000 (XGB), 0.00057 (KNN), 0.00549 (Boosting), and 0.00000 (Bagging) reinforcing the superiority of the Stacking Ensemble Learning approach. These findings highlight the effectiveness of Stacking Ensemble Learning in enhancing the detection accuracy of IDS for electrical substations and outperforming traditional models and other ensemble learning methods by minimizing false positives and false negatives.
- 28 September 2025
- Published by Ikatan Ahli Informatika Indonesia (IAII) in Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi)
- Vol. 9 (5) , 1030-1037
Open AccessStacking Ensemble Learning Model for Intrusion Detection in Electrical Substation
Electrical substations are crucial infrastructure in power transmission and distribution but are increasingly vulnerable to cyber threats. However, existing intrusion detection systems (IDS) face challenges such as high false positive rates, limited adaptability to emerging attack patterns, and imbalanced detection across different intrusion types. This study proposes a Stacking Ensemble Learning model to enhance intrusion detection accuracy in electrical substations. The proposed model integrates Logistic Regression (LR), Support Vector Machine (SVM), K-Nearest Neighbors (KNN), and XGBoost (XGB) as base models with XGB acting as the meta-model. A real-world electrical substation IEC 60870-5-104 network traffic dataset comprising 319,949 instances with multiple attacks, such as DoS, Port Scan, NTP DdoS, IEC 104 Starvation, Fuzzy Attack, Flood Attack, and MITM, was used for this study. The results showed that the stacking model had the best accuracy (0.99990), precision (0.99990), recall (0.99990), and F1-score (0.99990), beating out the base, Bagging, and Boosting models. T-test results further confirmed statistical significance, with p-values of 0.00428 (LR), 0.04237 (SVM), 0.00000 (XGB), 0.00057 (KNN), 0.00549 (Boosting), and 0.00000 (Bagging) reinforcing the superiority of the Stacking Ensemble Learning approach. These findings highlight the effectiveness of Stacking Ensemble Learning in enhancing the detection accuracy of IDS for electrical substations and outperforming traditional models and other ensemble learning methods by minimizing false positives and false negatives.
- Open Access
- 30 June 2025
- Published by Jurnal Rekayasa Elektrika (JRE) in Jurnal Rekayasa Elektrika
- Vol. 21 (2)
Hybrid Deep Learning Models Using LSTM with Random Forest for Radio Frequency-Based Human Activity Recognition in Line-of-Sight and Non-Line-of-Sight Environments
Human activity recognition (HAR) has become an important field of study because of its wide range of applications in healthcare, security, and smart living systems. Radio frequency (RF)-based HAR offers a non-invasive and privacy-preserving alternative to traditional vision-based systems. This study proposes a hybrid deep learning model combining long short-term memory (LSTM) networks with Random Forest classifiers for RF-based HAR, aiming to improve recognition accuracy across diverse environments. The model was evaluated using channel state information (CSI) and received signal strength indicator (RSSI) features under line-of-sight (LOS) and non-line-of-sight (NLOS) conditions. synthetic minority over-sampling technique (SMOTE) was integrated to balance the dataset and K-fold cross-validation was employed to assess robustness. The dataset included data from 8 subjects performing 10 different activities. The model achieved high classification accuracy, with 99.40% in Environment 1 (LOS), 97.58% in Environment 2 (LOS), and 98.30% in Environment 3 (NLOS), demonstrating the model’s adaptability and effectiveness. The results highlight the potential of the hybrid LSTM with random forest approach for scalable and reliable RF-based HAR systems that can be integrated into real-world Internet-of-Things (IoT) applications.
- 30 June 2025
- Published by Jurnal Rekayasa Elektrika (JRE) in Jurnal Rekayasa Elektrika
- Vol. 21 (2)
Open AccessHybrid Deep Learning Models Using LSTM with Random Forest for Radio Frequency-Based Human Activity Recognition in Line-of-Sight and Non-Line-of-Sight Environments
Human activity recognition (HAR) has become an important field of study because of its wide range of applications in healthcare, security, and smart living systems. Radio frequency (RF)-based HAR offers a non-invasive and privacy-preserving alternative to traditional vision-based systems. This study proposes a hybrid deep learning model combining long short-term memory (LSTM) networks with Random Forest classifiers for RF-based HAR, aiming to improve recognition accuracy across diverse environments. The model was evaluated using channel state information (CSI) and received signal strength indicator (RSSI) features under line-of-sight (LOS) and non-line-of-sight (NLOS) conditions. synthetic minority over-sampling technique (SMOTE) was integrated to balance the dataset and K-fold cross-validation was employed to assess robustness. The dataset included data from 8 subjects performing 10 different activities. The model achieved high classification accuracy, with 99.40% in Environment 1 (LOS), 97.58% in Environment 2 (LOS), and 98.30% in Environment 3 (NLOS), demonstrating the model’s adaptability and effectiveness. The results highlight the potential of the hybrid LSTM with random forest approach for scalable and reliable RF-based HAR systems that can be integrated into real-world Internet-of-Things (IoT) applications.
- Open Access
- 11 July 2024
- Published by State University of Medan in CESS (Journal of Computer Engineering, System and Science)
- Vol. 9 (2) , 814-822
Pengembangan Intelligent Electrocardiograph Portable untuk Pemantauan Detak Jantung: Systematic Literature Review
Kesehatan jantung menjadi faktor penting yang harus diperhatikan, terutama pada orang yang melakukan aktivitas fisik tinggi, seperti atlet. Untuk meningkatkan identifikasi dini penyakit jantung dan mengurangi bahaya kematian mendadak, perangkat elektrokardiogram (EKG) cerdas portabel telah banyak diusulkan untuk mendeteksi aktivitas jantung secara real-time. Penelitian ini bertujuan untuk memberikan informasi tentang klasifikasi sinyal jantung dengan memanfaatkan Filter Infinite Impulse Response (IIR) untuk menghilangkan noise sinyal dan Random Forest yang berguna untuk mengkategorikan masalah jantung secara cepat dan akurat. Referensi yang dirujuk, dipetakan berdasarkan sistematic literature review menggunakan metode preferred reporting items for systematic reviews and meta-analyses (PRISMA). Berdasarkan hasil ulasan yang telah dilakukan, terbukti EKG portable dengan filter IIR terbukti mampu membersihkan sinyal yang didukung dengan algoritma Random Forest untuk klasifikasi sehingga menghasilkan tingkat akurasi yang baik.
- 11 July 2024
- Published by State University of Medan in CESS (Journal of Computer Engineering, System and Science)
- Vol. 9 (2) , 814-822
Open AccessPengembangan Intelligent Electrocardiograph Portable untuk Pemantauan Detak Jantung: Systematic Literature Review
Kesehatan jantung menjadi faktor penting yang harus diperhatikan, terutama pada orang yang melakukan aktivitas fisik tinggi, seperti atlet. Untuk meningkatkan identifikasi dini penyakit jantung dan mengurangi bahaya kematian mendadak, perangkat elektrokardiogram (EKG) cerdas portabel telah banyak diusulkan untuk mendeteksi aktivitas jantung secara real-time. Penelitian ini bertujuan untuk memberikan informasi tentang klasifikasi sinyal jantung dengan memanfaatkan Filter Infinite Impulse Response (IIR) untuk menghilangkan noise sinyal dan Random Forest yang berguna untuk mengkategorikan masalah jantung secara cepat dan akurat. Referensi yang dirujuk, dipetakan berdasarkan sistematic literature review menggunakan metode preferred reporting items for systematic reviews and meta-analyses (PRISMA). Berdasarkan hasil ulasan yang telah dilakukan, terbukti EKG portable dengan filter IIR terbukti mampu membersihkan sinyal yang didukung dengan algoritma Random Forest untuk klasifikasi sehingga menghasilkan tingkat akurasi yang baik.
- Open Access
- 30 May 2023
- Published by Universitas Negeri Yogyakarta in Elinvo (Electronics, Informatics, and Vocational Education)
- Vol. 8 (1) , 86-95
Soybean Collect Recommender Based on Distance and Productivity Cluster Using K-means Clustering and Simple Addictive Weighting Method
Soybeans are an essential agricultural product that is one of the primary food sources in Indonesia, such as tempeh, tofu, soy milk, soy sauce, and other preparations. However, production yields, harvested land area, and soybean productivity in each district or city in Central Java Province vary widely. Differences in soybean productivity in each area are due to production factors such as area, use of fertilizers, seeds, and labor. This study tries to provide recommendations for soybean harvesting based on the distance and productivity of an area using K-means clustering and the simple addictive weighting method. In the Central Java Province, 35 regions will be divided into four clusters: the first with high productivity, the second with medium productivity; the third with low productivity; and the fourth with very low productivity. Additionally, based on the fourth cluster clustering results, it will be advised to take soybeans from other clusters by taking the closest distance and cluster members into account. According to the research, four clusters have formed: the first has five members, the second has fourteen, the third has nine, and the fourth has seven. The fourth cluster, which consists of seven members who do not grow soybeans, is advised to buy soybeans from the following regions: Kendal Regency, Klaten Regency, Magelang Regency, Batang Regency, and Brebes Regency.
- 30 May 2023
- Published by Universitas Negeri Yogyakarta in Elinvo (Electronics, Informatics, and Vocational Education)
- Vol. 8 (1) , 86-95
Open AccessSoybean Collect Recommender Based on Distance and Productivity Cluster Using K-means Clustering and Simple Addictive Weighting Method
Soybeans are an essential agricultural product that is one of the primary food sources in Indonesia, such as tempeh, tofu, soy milk, soy sauce, and other preparations. However, production yields, harvested land area, and soybean productivity in each district or city in Central Java Province vary widely. Differences in soybean productivity in each area are due to production factors such as area, use of fertilizers, seeds, and labor. This study tries to provide recommendations for soybean harvesting based on the distance and productivity of an area using K-means clustering and the simple addictive weighting method. In the Central Java Province, 35 regions will be divided into four clusters: the first with high productivity, the second with medium productivity; the third with low productivity; and the fourth with very low productivity. Additionally, based on the fourth cluster clustering results, it will be advised to take soybeans from other clusters by taking the closest distance and cluster members into account. According to the research, four clusters have formed: the first has five members, the second has fourteen, the third has nine, and the fourth has seven. The fourth cluster, which consists of seven members who do not grow soybeans, is advised to buy soybeans from the following regions: Kendal Regency, Klaten Regency, Magelang Regency, Batang Regency, and Brebes Regency.
- Open Access
Incidence of COVID-19 reinfection: an analysis of outpatient-based data in the United States of America
Objectives COVID-19 reinfection cases are evidence of antibody waning in recovered individuals. Previous studies had reported cases of COVID-19 reinfection both in hospital-based and community-based data. However, limited studies reported COVID-19 reinfection in large community-based data. The present study aimed to provide the incidence of COVID-19 reinfection based on secondary data in the U.S. Study design Cross-sectional study Methods A cross-sectional study was conducted using secondary data provided by COVID-19 Research Database, i.e., Healthjump. Reinfection were defined as diagnosed COVID-19 (U07.1= confirmed virus identified) twice with ≥90 days interval between diagnosis. Age, gender, and region data were also explored. A Chi-square test continued by a binary logistic regression was conducted to determine the association between parameters. Data collecting and processing were done in the Amazon workspace. Results The study revealed 3,778 reinfection cases of 116,932 COVID-19 infected cases (3.23%). Reinfection cases were more common in females (3.35%) than males (3.23%). Elderly subjects were the highest incidence (5.13%), followed by adult (4.14%), young adults (2.35%), and children (1.09%). Proportion in the region of living northeast was the highest (3.68%), compared to the south (3.49%), west (2.59%), and midwest (2.48%). Conclusion The incidence of COVID-19 reinfection was 3.23%, suggesting our concern with COVID-19 management and future research to understand COVID-19 reinfection better. The incident is more likely to occur in female and elderly patients.
Open AccessIncidence of COVID-19 reinfection: an analysis of outpatient-based data in the United States of America
Objectives COVID-19 reinfection cases are evidence of antibody waning in recovered individuals. Previous studies had reported cases of COVID-19 reinfection both in hospital-based and community-based data. However, limited studies reported COVID-19 reinfection in large community-based data. The present study aimed to provide the incidence of COVID-19 reinfection based on secondary data in the U.S. Study design Cross-sectional study Methods A cross-sectional study was conducted using secondary data provided by COVID-19 Research Database, i.e., Healthjump. Reinfection were defined as diagnosed COVID-19 (U07.1= confirmed virus identified) twice with ≥90 days interval between diagnosis. Age, gender, and region data were also explored. A Chi-square test continued by a binary logistic regression was conducted to determine the association between parameters. Data collecting and processing were done in the Amazon workspace. Results The study revealed 3,778 reinfection cases of 116,932 COVID-19 infected cases (3.23%). Reinfection cases were more common in females (3.35%) than males (3.23%). Elderly subjects were the highest incidence (5.13%), followed by adult (4.14%), young adults (2.35%), and children (1.09%). Proportion in the region of living northeast was the highest (3.68%), compared to the south (3.49%), west (2.59%), and midwest (2.48%). Conclusion The incidence of COVID-19 reinfection was 3.23%, suggesting our concern with COVID-19 management and future research to understand COVID-19 reinfection better. The incident is more likely to occur in female and elderly patients.