cover
Contact Name
Eko Prasetyo
Contact Email
jeecs@ubhara.ac.id
Phone
+628819314737
Journal Mail Official
jeecs@ubhara.ac.id
Editorial Address
Faculty of Engineering, Universitas Bhayangkara Surabaya Jl. A. Yani 114, Surabaya
Location
Kota surabaya,
Jawa timur
INDONESIA
JEECS (Journal of Electrical Engineering and Computer Sciences)
ISSN : 25280260     EISSN : 25795392     DOI : https://doi.org/10.54732/jeecs
We aims to promote high-quality Electrical Engineering and Computer Sciences research among academics and practitioners alike, including power system, electrical engineering, industry automation, mechatronics, computer sciences, informatics, and information system. This journal is dedicated for the author or researcher who has focused in the field of technology and intending on publication and sharing knowledge the novel technology include, but are not limited to, the following topics: Data Mining, Informatics algorithm methodology, Mobile Computing, Automation, Power, Green Technology, Advanced Computer Networks, Image Processing, Computer Vision, Robotics Technology, Decision Support System, Big Data, Data Sciences, Internet of Things, Network Security, Virtual Reality, etc.
Articles 201 Documents
Comparison of SVM, Random Forest, and Logistic Regression Performance n Student Mental Health Screening Vannes Wijaya; Nur Rachmat
JEECS (Journal of Electrical Engineering and Computer Sciences) Vol. 9 No. 2 (2024): JEECS (Journal of Electrical Engineering and Computer Sciences)
Publisher : Fakultas Teknik Universitas Bhayangkara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54732/jeecs.v9i2.9

Abstract

Mental health is an essential aspect for university students, as undetected mental health disorders can have a significant impact on students' academic performance and well-being. This study contributes by evaluating Synthetic Minority Oversampling Technique (SMOTE)'s role in improving classification models' performance. Despite the increasing use of machine learning in mental health detection, limited research has addressed the challenges posed by imbalanced datasets, particularly in smaller student populations. This research aims to develop a mental health early detection system based on student data from Multi Data University Palembang using the Mental Health Scale (SKM)-12 mental health measurement. The system aims to remind students' awareness of the importance of mental health. To improve accuracy, this research compares the performance of three models, namely Support Vector Machine, Random Forest, and Logistic Regression, both with and without using SMOTE. The dataset obtained is 78 students, and SKM-12 consists of several groups, namely optimal mental health profile with symbol (+-), maximum mental illness profile with symbol (++), minimum mental illness profile with symbol (--), and minimal mental health profile with symbol (-+). The results of this study using the Logistic Regression method using SMOTE obtained better model performance compared to other methods, with an accuracy of 89.28%, an average class precision of 89.5%, an average class recall of 89.75%, and an average F1 - class score of 88.5%. This research shows that overcoming class imbalance using SMOTE can significantly improve the performance of mental health classification models.
Comparative Study of Obesity Levels Classification Syahrazad Syaukat Al Malaky; Alisya Akbar Choirun Nisa; Siti Armiyanti; Rizky Syahputra Setyawan
JEECS (Journal of Electrical Engineering and Computer Sciences) Vol. 10 No. 1 (2025): JEECS (Journal of Electrical Engineering and Computer Sciences)
Publisher : Fakultas Teknik Universitas Bhayangkara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54732/jeecs.v10i1.8

Abstract

Obesity is a growing global health problem, requiring accurate data analysis to understand and address contributing factors. The level of obesity can be identified based on eating habits and physical conditions, which consist of several parameters. However, the performance of widely used machine learning methods has not provided satisfactory results. Therefore, this study analyzes obesity data using pre-processing methods to improve data quality before classifying data. The dataset used is 2111 data and includes 17 variables/features. The classification methods are Random Forest Classifier, Light Gradient Boosting Machine (LGBM) Classifier, Decision Tree Classifier, and Extra Tree Classifier. The process of data pre-processing involves data integration, data labeling, data transformation, normalization, and data cleansing. After pre-processing the data, four algorithms were used to identify patterns in the obesity data. The Random Forest Classifier is used for its ability to handle unbalanced data and reduce the risk of overfitting. The LGBM Classifier is used for a probabilistic approach to classification. The Decision Tree Classifier is applied for straightforward interpretation and clear understanding of patterns, while the Extra Tree Classifier is applied to improve the variety and accuracy of classification. The experimental results showed that a good data pre-processing method significantly improved the performance of the classification. Among the four algorithms tested, the Random Forest Classifier and Extra Tree Classifier performed best in accuracy and generalizability. Combining appropriate data pre-processing with powerful classification algorithms can provide deep insights to address obesity problems and formulate effective public health interventions.
Implementation of Internet Network Load Balancing at the Faculty of Computer Science UNUSIDA Using the ECMP Method Nida Aulina; Mochammad Machlul Alamin
JEECS (Journal of Electrical Engineering and Computer Sciences) Vol. 10 No. 1 (2025): JEECS (Journal of Electrical Engineering and Computer Sciences)
Publisher : Fakultas Teknik Universitas Bhayangkara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54732/jeecs.v10i1.7

Abstract

A stable internet speed is essential in supporting worker and student task completion. Slow internet connectivity can become a persistent hindrance if it occurs continuously. Previous research indicates that conventional load balancing methods still have limitations in handling uneven traffic loads. This study, therefore, explores methods to optimize internet link utilization by distributing traffic load evenly, known as load balancing, using the Equal Cost Multi-Path (ECMP) method. This approach aims to maintain maximum data/packet flow, thereby preventing overload on a single link or connection failure. Testing was conducted by comparing network performance before and after ECMP implementation on two different ISPs. The test results showed that before implementing the ECMP method load balancing, the internet speed of ISP 1 was 29 Mbps, and the speed of ISP 2 was 16 Mbps. While after implementing load balancing using the ECMP method, the internet speed was 63 Mbps. Therefore, it is proven that implementing load balancing using the ECMP method can maintain and increase connection speed and share the load on both gateways so that overload does not occur.
Alzheimer Disease Prediction Through Guided Predictive Modeling With Machine Learning Mahesa Pramudya Alfayat; Adithya Kusuma Whardana
JEECS (Journal of Electrical Engineering and Computer Sciences) Vol. 10 No. 1 (2025): JEECS (Journal of Electrical Engineering and Computer Sciences)
Publisher : Fakultas Teknik Universitas Bhayangkara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54732/jeecs.v10i1.5

Abstract

Alzheimer's disease is a progressive neurodegenerative disorder characterized by the accumulation of misfolded brain proteins, especially beta-amyloid plaques, resulting in cognitive deterioration and memory impairment. However, there has been no effort of early detection to facilitate prompt intervention and preventive strategies. This research fulfills this essential need by employing the Open Access Series of Imaging Studies (OASIS) dataset supplied by the Alzheimer's Disease Neuroimaging Initiative (ADNI). The research employs the Cross-industry Standard Process for Data Mining (CRISP-DM) methodology to create and assess a classification model utilizing Artificial Neural Networks (ANN). The model attains a remarkable accuracy rate of 96%, exhibiting elevated precision, recall, and F1-scores across all categories. A 10-fold cross-validation technique was utilized to assess the model's robustness, resulting in an average accuracy of 90.7%. These findings underscore the efficacy of artificial neural networks in identifying Alzheimer's disease in its initial phases. This research utilizes advanced data mining approaches to improve predictive capacities and highlights the promise of machine learning in tackling intricate healthcare issues.
Application of K-means Clustering Data Mining in Grouping Data of People with Disabilities Moh. Bahauddin; Zaehol Fatah
JEECS (Journal of Electrical Engineering and Computer Sciences) Vol. 10 No. 1 (2025): JEECS (Journal of Electrical Engineering and Computer Sciences)
Publisher : Fakultas Teknik Universitas Bhayangkara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54732/jeecs.v10i1.6

Abstract

Data mining is critical in enabling organizations to derive reliable insights from data. Social welfare remains a significant challenge in Indonesia, particularly for people with disabilities, emphasizing the need for targeted strategies. However, developing research has not used natural characteristics according to disability problems. This study utilizes the K-Means Clustering algorithm to analyze and categorize the population of people with disabilities in East Java. The attributes include the type of disability, population size, and regional distribution. We employs a dataset from the East Java Central Bureau of Statistics, comprising 342 data points across eight attributes, including region, disability type, and year. The analysis involves data preprocessing, transformation, clustering, and evaluation using the Davies-Bouldin Index (DBI). The results identify two optimal clusters, achieving the lowest DBI score of 0.097, indicating high cluster quality. Cluster 0 represents regions with fewer people with disabilities, while Cluster 1 highlights areas with higher populations. These findings provide a foundation for developing more focused and inclusive welfare programs tailored to regional needs, enhancing the quality of life for people with disabilities.
Sentiment Analysis Regarding the Indonesian House of Representatives Rejecting the Constitutional Court Decision from Social Media Using Naive Bayes Fahar Abdul Aziz; Lailan Sofinah Harahap
JEECS (Journal of Electrical Engineering and Computer Sciences) Vol. 10 No. 1 (2025): JEECS (Journal of Electrical Engineering and Computer Sciences)
Publisher : Fakultas Teknik Universitas Bhayangkara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54732/jeecs.v10i1.4

Abstract

This study analyzes public sentiment towards the HOR's rejection of the Constitutional Court's decision regarding the age limit for regional head candidates. Data was obtained from TikTok comments using scraping techniques with the Apify platform, resulting in 574 comments being analyzed. Sentiment labeling was automatically used VADER (Valence Aware Dictionary and Sentiment Reasoner), with positive, neutral, and negative sentiment categories. Text representation was carried out using TF-IDF, and sentiment classification using the Naive Bayes algorithm. The analysis results showed that most comments were neutral (42.0%) and positive (41.8%), while negative sentiment was only 16.2%. This study provides important insights into public perceptions of political issues involving the HoR and Constitutional Court decisions. By analyzing sentiment through comment data on TikTok, this study shows that lexicon-based approaches such as VADER can be used for automatic sentiment labeling, saving time compared to manual methods. In addition, classical algorithms such as Naive Bayes, combined with TF-IDF text representation, have proven effective in handling sentiment classification for short and informal texts such as social media comments.
Smoothing Algorithm Using Censor Distance on KRSRI ITN Malang Robot with Moving Average Method Waradana Adikasani; Sotyohadi Sotyohadi; M. Ibrahim Ashari
JEECS (Journal of Electrical Engineering and Computer Sciences) Vol. 10 No. 1 (2025): JEECS (Journal of Electrical Engineering and Computer Sciences)
Publisher : Fakultas Teknik Universitas Bhayangkara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54732/jeecs.v10i1.2

Abstract

Distance sensors play a crucial role in robotic navigation systems, particularly in the Indonesian Search and Rescue Robot Contest (KRSRI). However, sensor readings often suffer from instability due to external disturbances such as robot leg movements and environmental interference. This research aims to address these issues by implementing a smoothing algorithm based on the Simple Moving Average (SMA) method to refine distance sensor readings from the GP2Y Infrared Proximity sensor, enabling the robot to detect obstacles more accurately. Experiments were conducted under various conditions, both with and without the smoothing algorithm, showing that the use of SMA significantly improves the stability and accuracy of sensor data. The results indicate that sensor readings with SMA exhibited minimal fluctuations, maintaining higher consistency around the actual measured distance, while readings without SMA showed significant variability and inaccuracies. The implementation of SMA successfully reduced measurement errors, with an average error reduction of 97.68% compared to the raw sensor data. This improvement ensures more reliable obstacle detection and navigation performance, thereby enhancing the robot’s effectiveness in competitions as well as search and rescue applications in real-world environments.
Solar-powered Mobile Robot for Monitoring Gas Distribution Pipe Leak Using IoT Application Richa Watiasih; Hasti Afianti; Arif Arizal; Ahmadi Ahmadi
JEECS (Journal of Electrical Engineering and Computer Sciences) Vol. 10 No. 1 (2025): JEECS (Journal of Electrical Engineering and Computer Sciences)
Publisher : Fakultas Teknik Universitas Bhayangkara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54732/jeecs.v10i1.10

Abstract

The constraints of gas distribution pipe leak monitoring robots in outdoor environments are the limited battery capacity and the method used as a monitoring system to assist the work of gas pipe leak inspection officers, which takes a long time. Therefore, the robot requires independent battery charging and real-time monitoring systems. This study resulted in a solar-powered gas distribution pipe leak monitoring robot that can provide real-time information on the robot's battery capacity and gas odor concentration data along the inspected gas distribution pipe. This robot can directly channel electrical power to the robot's battery using solar energy. This Mobile Robot uses a Photovoltaic (PV) module, Light Detection and Ranging (LiDAR), a Compass, a gas sensor, a voltage sensor, a current sensor, an ATMEGA 2560 Microcontroller, and Node MCU V3 ESP8266. The Internet of Things (IoT) application uses the Blynk application to monitor battery capacity and the concentration value of gas odor detected by the robot. The test results show that by using the PV + battery module, this mobile robot can work for more than 60 minutes compared to using only the battery for around 55 minutes. This work was successfully implemented based on IoT performance using the Blynk Application to monitor battery capacity conditions of voltage and current data and gas concentration data. It is also shown that the average delay time for sending data from voltage, current, and gas sensors to the Blynk application was around 0.226 seconds.
Strategy to Improve Operational Performance Efficiency through the Implementation of Management Information System Nining Ariati; Febri Pratama; Irfan Saputra; Melinda Kurnia Putri; Sultan Imam Fajri
JEECS (Journal of Electrical Engineering and Computer Sciences) Vol. 10 No. 1 (2025): JEECS (Journal of Electrical Engineering and Computer Sciences)
Publisher : Fakultas Teknik Universitas Bhayangkara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54732/jeecs.v10i1.1

Abstract

The rapid advancement of information technology has encouraged many companies to adopt Management Information Systems (MIS) to enhance operational performance. However, a significant number of organizations continue to experience suboptimal results due to inadequate employee training, inconsistent system maintenance, and weak managerial support. This indicates a critical gap between MIS implementation and its expected benefits, particularly in improving operational efficiency. This study aims to bridge that gap by investigating the impact of MIS implementation on operational performance and identifying key success factors that influence its effectiveness. Using a quantitative approach, the research involved a case study in a medium-sized manufacturing company, with data collected from 100 respondents across operational-related depart-ments through a structured questionnaire. The findings show that effective MIS implementation contributes substantially to operational efficiency by streamlining workflows, minimizing processing time, and enhancing resource allocation. Furthermore, success is strongly associated with comprehensive user training, consistent system maintenance, and committed managerial support. These findings offer practical insights for organizations seeking to maximize the benefits of MIS and can serve as strategic references for improving operational performance through targeted system implementation efforts.
Improving the Quality of X-Ray Images of the Lungs of COVID-19 and Healthy Patients Using the Contrast Limited Adaptive Histogram Equalization (CLAHE) Method in Batam Marisha Pertiwi; Fortia Magfira; Dwi Rahmaisyah; M. Hasbi Sidqi Alajuri
JEECS (Journal of Electrical Engineering and Computer Sciences) Vol. 10 No. 1 (2025): JEECS (Journal of Electrical Engineering and Computer Sciences)
Publisher : Fakultas Teknik Universitas Bhayangkara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54732/jeecs.v10i1.3

Abstract

X-ray imaging is a widely used technique for observing lung patients conditions. Compared to other radiographic methods, X-ray is more accessible, cost-effective, and commonly available in healthcare facilities. However, digital X-ray images often suffer from low quality, particularly in terms of image contrast, which complicates the process of identifying lung abnormalities accurately. In Embung Fatimah Hospital in Batam, X-ray imaging is routinely used to screen COVID-19 and healthy patients. To address the issue of poor image contrast, this study applies the Contrast Limited Adaptive Histogram Equalization (CLAHE) technique, aiming to enhance image clarity and support more effective analysis. The research involved 20 lung X-ray images, consisting of 10 from COVID-19 and 10 from healthy patients, retrieved from the hospital’s radiology department system. The images underwent digital processing using Matlab software. The workflow included converting the images to grayscale before applying contrast enhancement with the CLAHE method, using three different distribution types: Uniform, Rayleigh, and Exponential. Following enhancement, Peak Signal to Noise Ratio and Mean Square Error metrics were calculated for each distribution type to evaluate image quality improvement. The result shown that all three CLAHE methods effectively enhanced the visual contrast of the lung images. The average MSE values for COVID-19 images were 26.27, 25.25, and 25.62, while for healthy images they were 28.27, 27.35, and 27.44. Meanwhile, the average PSNR values for COVID-19 images reached 155.63, 196.58, and 180.58, with healthy images scoring 98.27, 122.22, and 118.97. Overall, the process achieved an accuracy of 100%.

Filter by Year

2016 2025


Filter By Issues
All Issue Vol. 10 No. 2 (2025): JEECS (Journal of Electrical Engineering and Computer Sciences) Vol. 10 No. 1 (2025): JEECS (Journal of Electrical Engineering and Computer Sciences) Vol. 9 No. 2 (2024): JEECS (Journal of Electrical Engineering and Computer Sciences) Vol. 9 No. 1 (2024): JEECS (Journal of Electrical Engineering and Computer Sciences) Vol. 8 No. 2 (2023): JEECS (Journal of Electrical Engineering and Computer Sciences) Vol. 8 No. 1 (2023): JEECS (Journal of Electrical Engineering and Computer Sciences) Vol. 7 No. 2 (2022): JEECS (Journal of Electrical Engineering and Computer Sciences) Vol. 7 No. 1 (2022): JEECS (Journal of Electrical Engineering and Computer Sciences) Vol. 6 No. 2 (2021): JEECS (Journal of Electrical Engineering and Computer Sciences) Vol. 6 No. 1 (2021): JEECS (Journal of Electrical Engineering and Computer Sciences) Vol. 5 No. 2 (2020): JEECS (Journal of Electrical Engineering and Computer Sciences) Vol. 5 No. 1 (2020): JEECS (Journal of Electrical Engineering and Computer Sciences) Vol. 4 No. 2 (2019): JEECS (Journal of Electrical Engineering and Computer Sciences) Vol. 4 No. 1 (2019): JEECS (Journal of Electrical Engineering and Computer Sciences) Vol. 3 No. 2 (2018): JEECS (Journal of Electrical Engineering and Computer Sciences) Vol. 3 No. 1 (2018): JEECS (Journal of Electrical Engineering and Computer Sciences) Vol. 2 No. 2 (2017): JEECS (Journal of Electrical Engineering and Computer Sciences) Vol. 2 No. 1 (2017): JEECS (Journal of Electrical Engineering and Computer Sciences) Vol. 1 No. 2 (2016): JEECS (Journal of Electrical Engineering and Computer Sciences) Vol. 1 No. 1 (2016): JEECS (Journal of Electrical Engineering and Computer Sciences) More Issue