Jurnal Politeknik Negeri Batam (PoliBatam)
Not a member yet
3001 research outputs found
Sort by
Decoding Worldwide Trends on Cooperatives and their Economic Influence: A Bilbliometric Analysis from 2015-2025
No full textCooperatives play a crucial role in global economic development, contributing to financial stability, employment creation, and sustainable business practices. This study examines research trends on cooperatives using bibliometric analysis and a systematic literature review, focusing on key themes such as governance, economic resilience, and digital transformation. Findings indicate that cooperatives significantly contribute to GDP and job creation while demonstrating resilience during financial crises. Their role in sustainability is also expanding, with cooperatives driving environmentally friendly initiatives in various sectors. However, challenges such as regulatory constraints, market competition, and digital adaptation persist. Differences in legal frameworks hinder cooperative expansion, and limited technological resources slow digital transformation. To address these issues, stronger policies, financial support, and technological integration are needed. This study underscores the increasing importance of cooperatives in fostering economic resilience and sustainability while emphasizing the need for continued research on innovation and global collaboration to enhance cooperative effectiveness.Koperasi memainkan peran penting dalam pembangunan ekonomi global dengan berkontribusi pada stabilitas keuangan, penciptaan lapangan kerja, dan praktik bisnis berkelanjutan. Studi ini meneliti tren penelitian tentang koperasi menggunakan analisis bibliometrik dan tinjauan literatur sistematis, dengan fokus pada tema utama seperti tata kelola, ketahanan ekonomi, dan transformasi digital. Temuan menunjukkan bahwa koperasi secara signifikan berkontribusi terhadap PDB dan penciptaan lapangan kerja serta menunjukkan ketahanan selama krisis keuangan. Peran mereka dalam keberlanjutan juga semakin berkembang, dengan koperasi mendorong inisiatif ramah lingkungan di berbagai sektor. Namun, tantangan seperti kendala regulasi, persaingan pasar, dan adaptasi digital masih ada. Perbedaan dalam kerangka hukum menghambat ekspansi koperasi, sementara keterbatasan sumber daya teknologi memperlambat transformasi digital. Untuk mengatasi masalah ini, diperlukan kebijakan yang lebih kuat, dukungan finansial, dan integrasi teknologi. Studi ini menegaskan semakin pentingnya koperasi dalam mendorong ketahanan ekonomi dan keberlanjutan, serta menekankan perlunya penelitian berkelanjutan tentang inovasi dan kolaborasi global untuk meningkatkan efektivitas koperasi
Sosialisasi Bahaya JUDOL (Judi Online) Dalam Perspektif Ekonomi di SMKN 2 Sungailiat-Bangka
Get PDFOnline games are currently an alternative to gambling online in secret and have a dangerous impact on the economy and mental health of its players. The problem that occurs, with very easy digital access in various groups including teenagers, teenagers are unable to distinguish and identify online gambling with regular online games, coupled with fairly low digital literacy. This problem also occurs among teenagers at the vocational school level in Sungailiat which shows low knowledge about online gambling. For this reason, it is important to make community service efforts by conducting socialization to educate students about online gambling and its dangers from an economic perspective. The method used to carry out this community service is in the form of socialization starting from socialization preparation, program implementation to program evaluation which is carried out pre-test, post-test and qualitatively. The results show an increase in student knowledge about online gambling and its dangers to the economy and a decrease in student interest in carrying out activities related to online gambling.Online games are currently an alternative to gambling online in secret and have a dangerous impact on the economy and mental health of its players. The problem that occurs, with very easy digital access in various groups including teenagers, teenagers are unable to distinguish and identify online gambling with regular online games, coupled with fairly low digital literacy. This problem also occurs among teenagers at the vocational school level in Sungailiat which shows low knowledge about online gambling. For this reason, it is important to make community service efforts by conducting socialization to educate students about online gambling and its dangers from an economic perspective. The method used to carry out this community service is in the form of socialization starting from socialization preparation, program implementation to program evaluation which is carried out pre-test, post-test and qualitatively. The results show an increase in student knowledge about online gambling and its dangers to the economy and a decrease in student interest in carrying out activities related to online gambling
Penerapan Kincir Air Otomatis Berbasis Sensor Suhu untuk Meningkatkan Efisiensi Budidaya Ikan Nila di Kelompok Kegiatan Wildatul Sholihah, Bogor
No full textThis community service activity aims to improve the efficiency of tilapia pond management through the implementation of a manually operated waterwheel system for the Wildatul Sholihah Activity Group in Bojong Village, Bogor Regency. The partner’s challenges include fluctuating water temperatures, low oxygen levels, and limited manpower, as pond maintenance is only carried out on weekends. As an initial solution, the service team conducted training and installed a simple manually operated waterwheel unit. The activity took place on May 28, 2025, and involved several stages: coordination, module preparation, equipment assembly, technical training, and field testing. The results showed that the waterwheel successfully improved water circulation and temperature stability, while also reducing the frequency of manual water replacement. Training participants demonstrated increased technical understanding, high enthusiasm, and the ability to operate and maintain the device independently. This initiative had a tangible impact in supporting more efficient and sustainable tilapia farming. In the future, the system has the potential to be further developed with the integration of digital technologies such as IoT-based monitoring systemsKegiatan pengabdian kepada masyarakat ini bertujuan untuk meningkatkan efisiensi pengelolaan kolam ikan nila melalui penerapan kincir air manual di Kelompok Kegiatan Wildatul Sholihah, Desa Bojong, Kabupaten Bogor. Permasalahan yang dihadapi mitra meliputi fluktuasi suhu air, rendahnya kadar oksigen, serta keterbatasan tenaga dalam perawatan kolam yang hanya dilakukan pada akhir pekan. Sebagai solusi awal, tim pengabdian melakukan pelatihan dan instalasi unit kincir air sederhana yang dapat dioperasikan secara manual. Kegiatan dilaksanakan pada 28 Mei 2025 dan mencakup tahapan koordinasi, penyusunan modul, perakitan alat, pelatihan teknis, serta uji coba di lapangan. Hasil kegiatan menunjukkan bahwa kincir air berhasil meningkatkan sirkulasi dan kestabilan suhu air, sekaligus menurunkan frekuensi penggantian air secara manual. Peserta pelatihan menunjukkan peningkatan pemahaman teknis, antusiasme tinggi, dan kemampuan untuk mengoperasikan serta merawat alat secara mandiri. Kegiatan ini memberikan dampak nyata dalam mendukung budidaya ikan nila yang lebih efisien dan berkelanjutan. Ke depannya, sistem ini berpotensi dikembangkan menuju integrasi teknologi digital seperti sistem monitoring berbasis IoT.
 
Comparison of Support Vector Machine (SVM) and Random Forest (RF) Algorithm Performance with Random Undersampling Technique to Predict Gestational Diabetes Mellitus Risk
Get PDFGestational Diabetes Mellitus (GDM) is a condition of glucose intolerance that develops during pregnancy until the birth process, which is characterized by an abnormal increase in blood sugar levels. Accurate early diagnosis is very important to provide information that can accelerate the treatment process and reduce complications in the mother and baby. One of the machine learning methods that can be used to predict GDM is the Support Vector Machine (SVM) algorithm and the Random Forest (RF) algorithm. This study aims to compare, and evaluate GDM disease prediction models using the SVM and RF algorithms by balancing the target data using the Random Undersampling Technique. The approach using the random undersampling technique managed to increase accuracy by 18% from the accuracy before using the random undersampling technique. The SVM model in this study also uses hyperparameter tuning with kernel parameters, C (cost), and gamma, while the RF model uses Scoring Metrix and four other parameters, namely N_estimators, max_depth, min_samples_split, and min_samples_leaf. The best parameter search process is carried out using GridSearchCV on both models. The results of the study showed that the SVM classification model with random undersampling technique and hyperparameter tuning with K-Fold achieved an average accuracy of 100% with precision, recall, f1-score values also reaching 100%, with the Best Parameter Kernel Linear, C value = 0.1 and gamma value = 0.001 reaching the highest accuracy of 1.0, with a ROC-AUC value of 99% indicating very good prediction performance. While the RF model showed an accuracy result of 99%, tuning was also carried out using the appropriate parameters resulting in the same accuracy of 99%, with a ROC-AUC value of 99% as well. From both models, it shows that the SVM and RF algorithms have very good prediction performance in predicting DMG, but the SVM algorithm can predict DMG better than RF because the number of prediction errors is lower. Gestational Diabetes Mellitus (GDM) is a condition of glucose intolerance that develops during pregnancy until the birth process, which is characterized by an abnormal increase in blood sugar levels. Accurate early diagnosis is very important to provide information that can accelerate the treatment process and reduce complications in the mother and baby. One of the machine learning methods that can be used to predict GDM is the Support Vector Machine (SVM) algorithm and the Random Forest (RF) algorithm. This study aims to compare, and evaluate GDM disease prediction models using the SVM and RF algorithms by balancing the target data using the Random Undersampling Technique. The approach using the random undersampling technique managed to increase accuracy by 18% from the accuracy before using the random undersampling technique. The SVM model in this study also uses hyperparameter tuning with kernel parameters, C (cost), and gamma, while the RF model uses Scoring Metrix and four other parameters, namely N_estimators, max_depth, min_samples_split, and min_samples_leaf. The best parameter search process is carried out using GridSearchCV on both models. The results of the study showed that the SVM classification model with random undersampling technique and hyperparameter tuning with K-Fold achieved an average accuracy of 100% with precision, recall, f1-score values also reaching 100%, with the Best Parameter Kernel Linear, C value = 0.1 and gamma value = 0.001 reaching the highest accuracy of 1.0, with a ROC-AUC value of 99% indicating very good prediction performance. While the RF model showed an accuracy result of 99%, tuning was also carried out using the appropriate parameters resulting in the same accuracy of 99%, with a ROC-AUC value of 99% as well. From both models, it shows that the SVM and RF algorithms have very good prediction performance in predicting DMG, but the SVM algorithm can predict DMG better than RF because the number of prediction errors is lower.
Balancing CICIoV2024 Dataset with RUS for Improved IoV Attack Detection
Get PDFThis study addresses the cybersecurity challenges within the Internet of Vehicles (IoV) by exploring the efficacy of Random Under-Sampling (RUS) in balancing the class distribution of the CICIoV2024 dataset for improved intrusion detection. IoV technology connects vehicles to digital infrastructure, fostering communication and enhancing safety but is simultaneously vulnerable to cyber threats such as Denial of Service (DoS) and spoofing attacks. This research employed RUS to mitigate data imbalance within the CICIoV2024 dataset, which often impedes effective threat detection in machine learning models. Four machine learning classifiers Random Forest, AdaBoost, Gradient Boosting, and XGBoost were evaluated on both imbalanced and balanced datasets to compare their performance. Results demonstrated that RUS significantly enhances model accuracy, precision, recall, and F1-score, reaching perfect scores across all classifiers post-balancing. Additionally, RUS contributed to substantial reductions in training and testing times, thereby boosting computational efficiency. These findings underscore the potential of RUS in addressing data imbalance in IoV cybersecurity, establishing a foundation for future research aimed at safeguarding IoV systems against evolving cyber threats
The Application of Deep Learning for Skin Disease Classification Using the EfficientNet-B1 Model
Get PDFThe skin, being the largest organ in the human body, plays a vital role in protecting against various external threats. However, cases of skin diseases are steadily rising across countries, making it a significant global health concern. Diagnosis often faces challenges due to symptom variations and low public awareness, highlighting the need for automated technology in skin disease detection. This study developed an automated classification system for skin diseases using EfficientNet-B1, capable of categorizing five skin conditions: Acne and Rosacea, Eczema, Melanoma Skin Cancer Nevi and Moles, Normal, Vitiligo, Psoriasis pictures Lichen Planus and related diseases, Seborrheic Keratoses and other Benign Tumors, Tinea Ringworm Candidiasis and other Fungal Infections. The system utilized 1.571 plus 1641 JPG digital images resized to 224 x 224 pixels, with 80% of the data allocated for training and 20% for testing. The trained model achieved a high accuracy of 99%, demonstrating the system\u27s potential to support faster and more accurate diagnostic processes.The skin, being the largest organ in the human body, plays a vital role in protecting against various external threats. However, cases of skin diseases are steadily rising across countries, making it a significant global health concern. Diagnosis often faces challenges due to symptom variations and low public awareness, highlighting the need for automated technology in skin disease detection. This study developed an automated classification system for skin diseases using EfficientNet-B1, capable of categorizing five skin conditions: Acne and Rosacea, Eczema, Melanoma Skin Cancer Nevi and Moles, Normal, Vitiligo, Psoriasis pictures Lichen Planus and related diseases, Seborrheic Keratoses and other Benign Tumors, Tinea Ringworm Candidiasis and other Fungal Infections. The system utilized 1.571 plus 1641 JPG digital images resized to 224 x 224 pixels, with 80% of the data allocated for training and 20% for testing. The trained model achieved a high accuracy of 99%, demonstrating the system\u27s potential to support faster and more accurate diagnostic processes
Analysis of Marketing Stimuli Factors in Purchasing Decisions for Fast Fashion Items Among Generation Z in Batam
Get PDFThis study aims to analyze the marketing stimuli factors that influence the purchasing decisions of Generation Z in Batam City regarding fast fashion items. The research adopts a quantitative approach, utilizing factor analysis as the primary analytical method. Within the study, 19 variables were initially examined and subsequently reduced to several factors. The analysis revealed four key factors that drive purchasing decisions for fast fashion items among Generation Z in Batam City: Attractive Service, Marketing Excellence and Competitive Design, Value for Money, and Shopping Experience. The Attractive Service factor emerged as the most dominant, accounting for 24.192% of the variance in this study. This finding underscores the critical role of service quality in influencing consumer decisions in the competitive fast fashion industry. Brands should strengthen their digital presence through engaging social media content, and ensure up-to-date product designs to align with Generation Z’s preferences for developing competitive strategies. Additionally, improving the shopping experience through accessible store locations, strengthening brand reputation, and creating an inviting store atmosphere, can further attract and retain Generation Z consumers in Batam’s competitive market
The Influence of IT Governance Implementation on Firm Performance in Manufacturing Companies
Get PDFAbstract. This study aims to examine the effect of IT Governance implementation on firm performance in manufacturing companies listed on the Indonesia Stock Exchange for the years 2019-2020. The method used is quantitative descriptive method. This research will use multiple linear regression analysis. The research sample consists of manufacturing companies listed on the Indonesia Stock Exchange during the years 2019-2020. The independent variable studied is IT Governance with control variables being sales growth, advertising expense, research and development expense, and capital expenditure. The dependent variable is firm performance. The results obtained indicate that IT Governance does not influence firm performance. Sales growth has a negative but not significant effect on firm performance, while advertising expense has an influence on firm performance. However, research and development expense and capital expenditure do not have an influence on firm performance
An Audit Tata Kelola Teknologi Informasi di PT. SMOE Indonesia Menggunakan Framework COBIT 2019
No full textInformation technology governance is an important part of the Company. Every Company that has implemented information technology in its activities must have good IT governance so that the company\u27s business goals can be achieved with optimal utilization of information technology. This study examines the implementation of information technology governance at PT. SMOE Indonesia with the aim of improving information security. In this context, the information technology governance audit uses the COBIT 2019 framework. The audit was conducted to determine the domains and processes that exist at PT. SMOE Indonesia, the domains and processes used are APO13 and DSS05. The audit was conducted to determine the level of capability of each IT process running at PT. SMOE IndonesiaInformation technology governance is an important part of the Company. Every Company that has implemented information technology in its activities must have good IT governance so that the company\u27s business goals can be achieved with optimal utilization of information technology. This study examines the implementation of information technology governance at PT. SMOE Indonesia with the aim of improving information security. In this context, the information technology governance audit uses the COBIT 2019 framework. The audit was conducted to determine the domains and processes that exist at PT. SMOE Indonesia, the domains and processes used are APO13 and DSS05. The audit was conducted to determine the level of capability of each IT process running at PT. SMOE Indonesia
Comparative Performance Analysis of Optimization Algorithms in Artificial Neural Networks for Stock Price Prediction
Get PDFThis study aims to enhance price prediction accuracy using Artificial Neural Networks (ANN) by comparing three optimization methods: Stochastic Gradient Descent (SGD), Adam, and RMSprop. The research employs a systematic approach involving the design, training, and validation of ANN models optimized by these techniques. Performance metrics such as Mean Squared Error (MSE), Mean Absolute Error (MAE), and R Square are utilized to evaluate the effectiveness of each method. The results indicate that the Adam optimization method outperforms the others, achieving the lowest MSE of 0.0000503 and the lowest MAE of 0.0046, resulting in an impressive R Square value of 0.9989. Adam\u27s superior performance can be attributed to its adaptive learning rate mechanism, which effectively adjusts to the high volatility and noise characteristic of stock price data, enabling the model to converge faster and more accurately. In comparison, SGD produced a higher MSE of 0.0001208 and MAE of 0.0075, while RMSprop yielded an MSE of 0.0000726 and MAE of 0.0059. These findings highlight Adam\u27s ability to significantly enhance the predictive capabilities of ANN, particularly in dynamic and complex datasets, making it a preferred choice for this application. The novelty of this research lies not only in its comparative analysis of various optimization methods within the ANN framework but also in the exploration of unique ANN features and their application to a specific stock price prediction case study, providing deeper insights into the practical implications of optimization strategies. This study lays the groundwork for future research by suggesting the exploration of additional optimization algorithms and more complex neural network architectures to further improve prediction accuracy