Jurnal Politeknik Negeri Batam (PoliBatam)
Not a member yet
3001 research outputs found
Sort by
Analisis Perbandingan Teknik Optimasi Occlusion Culling & LOD Group Pada Game VR Mahakarya Vokasi Dengan Perangkat VR Oculus Quest 2
Get PDFPenelitian ini bertujuan untuk mengoptimalkan kinerja grafis dalam pengembangan game VR Mahakarya Vokasi dengan menggunakan teknik optimasi Occlusion Culling dan Level of Detail Group (LOD). Melalui analisis data menggunakan Profiler dan Profiler Analyzer, penulis menganalisis parameter rendering seperti Setpass Calls, Draw Calls, Batches, Triangles, Vertices, Used Texture, Render Texture, Used Buffers, dan lain-lain. Hasil penelitian menunjukkan bahwa penggunaan teknik optimasi Occlusion Culling dapat signifikan meningkatkan Frame Per Second (FPS) sebesar 13,26%, sementara teknik optimasi LOD tidak memberikan perubahan yang signifikan. Meskipun beberapa parameter tidak menunjukkan perubahan yang signifikan, penting untuk terus memantau dan mengoptimalkan parameter ini untuk menjaga kinerja game secara optimal. Penelitian ini memberikan panduan yang jelas bagi pengembang game VR dengan gameplay adventure dalam memilih teknik optimasi yang tepat untuk menciptakan pengalaman pengguna yang lebih stabil dan responsif
Analysis of the Use of MTCNN and Landmark Technology to Improve the Accuracy of Facial Recognition on Official Documents
Get PDFA face recognition system consists of two stages: face detection and face recognition. Detection of features such as eyes and mouth is important in facial image processing, especially for official documents such as identity cards. To ensure identification accuracy, this research applies facial landmark extraction technology and MTCNN (Multi-Task Cascaded Convolutional Neural Network). The purpose of this research is to evaluate the accuracy of MTCNN in detecting facial features at the Department of Population and Civil Registration (dukcapil) Palu City, using facial landmarks and waterfall methods as an application development methodology. The evaluation results show that MTCNN has high face recognition accuracy and good positioning ability regardless of what GPU in use as long have right CPU and System Operation. In comparison, the Viola-Jones algorithm is effective for high-speed applications, while SSD offers balanced performance with GPU device requirements for optimal performance. While MTCNN proved to be effective, challenges still exist, such as false positives and false negatives, especially in poor lighting conditions and extreme poses. Image and camera quality, including resolution and facial expression, also affects detection accuracy. These findings suggest that the application of MTCNN can improve face recognition accuracy for official documents, although it requires addressing existing challenges. With this technology, it is expected that errors in facial recognition can be minimized, resulting in more reliable data that meets the standards for issuing identity documents. This research contributes to the development of a more accurate and efficient face recognition system for personal identification applications
Optimization of Urban Waste Collection Routes Using the Held-Karp Algorithm in a Web and Mobile-Based System
Get PDFIn 2023, the Environmental Agency of Palu City recorded a total waste production of 97,492 tons, of which 10.4% was plastic waste. The Palu City Government operates a fleet of garbage trucks on a predetermined collection schedule. However, garbage bins frequently overflow before their scheduled pickup, resulting in extended waste accumulation and inefficiency. This study proposes a web and mobile-based system to enhance waste management by integrating bin condition reporting and shortest route calculation for collecting full bins. The Held-Karp algorithm is utilized to address the Travelling Salesman Problem (TSP) for determining optimal collection routes. The system was developed using Golang, Flutter, ReactJS, and a MySQL database. API functionality was validated using Postman, and overall system functionality was tested using the black-box method. A case study involving 8 test points (1 starting point, 10 waste collection points, and 1 endpoint) demonstrated that the proposed system reduces travel time by up to 21.74%, costs by 22.29%, fuel consumption by 21.16%, and distance traveled by 21.16% compared to conventional methods. These results highlight the potential of the system to significantly optimize waste collection operations and support sustainable urban waste management practices.In 2023, the Environmental Agency of Palu City recorded a total waste production of 97,492 tons, of which 10.4% was plastic waste. The Palu City Government operates a fleet of garbage trucks on a predetermined collection schedule. However, garbage bins frequently overflow before their scheduled pickup, resulting in extended waste accumulation and inefficiency. This study proposes a web and mobile-based system to enhance waste management by integrating bin condition reporting and shortest route calculation for collecting full bins. The Held-Karp algorithm is utilized to address the Travelling Salesman Problem (TSP) for determining optimal collection routes. The system was developed using Golang, Flutter, ReactJS, and a MySQL database. API functionality was validated using Postman, and overall system functionality was tested using the black-box method. A case study involving 8 test points (1 starting point, 10 waste collection points, and 1 endpoint) demonstrated that the proposed system reduces travel time by up to 21.74%, costs by 22.29%, fuel consumption by 21.16%, and distance traveled by 21.16% compared to conventional methods. These results highlight the potential of the system to significantly optimize waste collection operations and support sustainable urban waste management practices
Comparison of EfficientNet-B0 and ResNet-50 for Detecting Diseases in Cocoa Fruit
Get PDFCocoa is a plant that is very susceptible to disease. One of the diseases that often attacks cocoa is black spots on the fruit. Detecting diseases in cocoa fruit is usually done manually by experts, which has limitations in providing information and is very expensive. this study proposes a model for detecting cocoa fruit diseases based on deep learning, namely convolution neural networks (CNN). This study compares CNN architectures, namely EfficientNetB0 and ResNet50 because these two architectures are very popular. EfficientNetB0 is known to be efficient in utilizing model parameters and the ability to achieve high accuracy, while ResNet50 uses Residual block recognition which allows deeper and more accurate model training. The dataset used is 3344 healthy cocoa fruit images, 943 black pod rot images and 103 pod borer images. From this study, the results for the accuracy of both methods are equally superior with an accuracy of 96% while for the precision of the EfficientNetB0 architecture is superior to ResNet50 with a value of 95.7% while for recall and f1-score ResNet50 is superior with a recall value of 94.7% and f1-score 93.3%. Based on the Confusion Matrix, it can be seen that ResNet50 is able to predict pod borer accurately so it can be concluded that in this study ResNet 50 is superior to EfficientNetB0. However, ResNet50 requires more parameters than EfficientNetB0 so ResNet50 requires a very large amount of data and when using a small amount of data EfficientNetB0 is more suitable for use.Cocoa is a plant that is very susceptible to disease. One of the diseases that often attacks cocoa is black spots on the fruit. Detecting diseases in cocoa fruit is usually done manually by experts, which has limitations in providing information and is very expensive. this study proposes a model for detecting cocoa fruit diseases based on deep learning, namely convolution neural networks (CNN). This study compares CNN architectures, namely EfficientNetB0 and ResNet50 because these two architectures are very popular. EfficientNetB0 is known to be efficient in utilizing model parameters and the ability to achieve high accuracy, while ResNet50 uses Residual block recognition which allows deeper and more accurate model training. The dataset used is 3344 healthy cocoa fruit images, 943 black pod rot images and 103 pod borer images. From this study, the results for the accuracy of both methods are equally superior with an accuracy of 96% while for the precision of the EfficientNetB0 architecture is superior to ResNet50 with a value of 95.7% while for recall and f1-score ResNet50 is superior with a recall value of 94.7% and f1-score 93.3%. Based on the Confusion Matrix, it can be seen that ResNet50 is able to predict pod borer accurately so it can be concluded that in this study ResNet 50 is superior to EfficientNetB0. However, ResNet50 requires more parameters than EfficientNetB0 so ResNet50 requires a very large amount of data and when using a small amount of data EfficientNetB0 is more suitable for use
Pembuatan Animasi 2D "Nampak Gonggong" sebagai Media Pengenalan Batik Gonggong
Get PDFThis research aims to introduce and preserve gonggong batik as one of the local cultural heritages of the Riau Islands through 2D animation media. The problem raised is the declining interest of the younger generation in gonggong batik, which is caused by a lack of promotion and understanding of its cultural value. This research uses a creative method, starting from visual observation of gonggong batik motifs and collecting related literature data. The production process includes pre-production stages (idea formulation, script writing, storyboarding, character design, and batik design), production (visual asset creation, rigging, animation with cut-out animation techniques, and adding visual effects), to post-production (compositing, editing, color correction, and adding audio). The final result is a 1 minute 14 second animated trailer video in Full HD resolution published on YouTube. Through 2D animation media that combines visual power and storytelling, this work is expected to be an interesting educational tool and support efforts to preserve gonggong batik, as well as contribute to the development of local cultural promotional media.Penelitian ini bertujuan untuk memperkenalkan dan melestarikan batik gonggong sebagai salah satu warisan budaya lokal Kepulauan Riau melalui media animasi 2D. Permasalahan yang diangkat adalah menurunnya minat generasi muda terhadap batik gonggong, yang disebabkan oleh kurangnya promosi dan pemahaman terhadap nilai budayanya. Penelitian ini menggunakan metode penciptaan, dimulai dari observasi visual terhadap motif batik gonggong serta pengumpulan data literatur terkait. Proses produksi meliputi tahap pra-produksi (perumusan ide, penulisan naskah, pembuatan storyboard, desain karakter, dan desain batik), produksi (pembuatan aset visual, rigging, animasi dengan teknik cut-out animation, serta penambahan efek visual), hingga pasca-produksi (compositing, editing, koreksi warna, dan penambahan audio). Hasil akhir berupa video trailer animasi berdurasi 1 menit 14 detik dalam resolusi Full HD yang dipublikasikan melalui YouTube. Melalui media animasi 2D yang memadukan kekuatan visual dan storytelling, karya ini diharapkan dapat menjadi sarana edukatif yang menarik dan mendukung upaya pelestarian batik gonggong, serta memberikan kontribusi dalam pengembangan media promosi budaya lokal
Comparison of Logistic Regression, Random Forest, Support Vector Machine (SVM) and K-Nearest Neighbor (KNN) Algorithms in Diabetes Prediction
Get PDFDiabetes mellitus is a prevalent chronic illness that continues to grow in incidence worldwide, placing significant strain on healthcare systems. The timely prediction of diabetes is crucial for early intervention and management. This study explores the comparative effectiveness of four machine learning algorithms Logistic Regression (LR), Random Forest (RF), Support Vector Machine (SVM), and K-Nearest Neighbors (KNN) in identifying diabetes cases using a large public dataset containing 100,000 patient records obtained from open source Kaggle. The dataset includes nine clinical variables, such as age, gender, body mass index (BMI), blood glucose level, and HbA1c levels, among others. To address class imbalance, which showed less than 10% positive (diabetic) cases initially, the Synthetic Minority Oversampling Technique (SMOTE) was applied exclusively to the training data after an 80:20 stratified split. All models were evaluated using 5-fold stratified cross-validation, measuring their performance through accuracy, precision, recall, F1-score, area under the ROC curve (AUC), and training time. Among the models, Random Forest achieved the highest classification accuracy (96.88%) and AUC (99.70%), indicating superior overall performance. Furthermore, McNemar statistical tests revealed that the differences in performance between Random Forest and the other models were statistically significant. An analysis of feature importance highlighted that HbA1c, glucose level, and BMI were the most influential predictors. These results demonstrate that Random Forest offers the most balanced combination of accuracy, interpretability, and robustness, making it highly suitable for real-world clinical screening scenarios where early detection of diabetes is critical.Diabetes mellitus is a prevalent chronic illness that continues to grow in incidence worldwide, placing significant strain on healthcare systems. The timely prediction of diabetes is crucial for early intervention and management. This study explores the comparative effectiveness of four machine learning algorithms Logistic Regression (LR), Random Forest (RF), Support Vector Machine (SVM), and K-Nearest Neighbors (KNN) in identifying diabetes cases using a large public dataset containing 100,000 patient records obtained from open source Kaggle. The dataset includes nine clinical variables, such as age, gender, body mass index (BMI), blood glucose level, and HbA1c levels, among others. To address class imbalance, which showed less than 10% positive (diabetic) cases initially, the Synthetic Minority Oversampling Technique (SMOTE) was applied exclusively to the training data after an 80:20 stratified split. All models were evaluated using 5-fold stratified cross-validation, measuring their performance through accuracy, precision, recall, F1-score, area under the ROC curve (AUC), and training time. Among the models, Random Forest achieved the highest classification accuracy (96.88%) and AUC (99.70%), indicating superior overall performance. Furthermore, McNemar statistical tests revealed that the differences in performance between Random Forest and the other models were statistically significant. An analysis of feature importance highlighted that HbA1c, glucose level, and BMI were the most influential predictors. These results demonstrate that Random Forest offers the most balanced combination of accuracy, interpretability, and robustness, making it highly suitable for real-world clinical screening scenarios where early detection of diabetes is critical
Evaluation of User Satisfaction on the Indonesian National Police Recruitment Website Using the EUCS Method
Get PDFThe digitalization of public services encourages government institutions to provide efficient and responsive information systems, including in the recruitment process of the Indonesian National Police (Polri). The Polri recruitment website was developed as an online registration platform to improve transparency, accessibility, and service effectiveness. However, systematic evaluations of user satisfaction with this website are still limited. This study aims to measure user satisfaction using the End User Computing Satisfaction (EUCS) model. A quantitative approach was applied, with data collected through questionnaires from 144 prospective applicants in the West Papua Regional Police area. Data were analyzed using the Partial Least Squares - Structural Equation Modelling (PLS-SEM) method. The findings reveal that ease of use and timeliness significantly influence user satisfaction, while content, accuracy, and format do not. This indicates that usability and information timeliness play a more critical role. The study encourages system developers to focus on enhancing functional and responsive features to improve digital public services.The digitalization of public services encourages government institutions to provide efficient and responsive information systems, including in the recruitment process of the Indonesian National Police (Polri). The Polri recruitment website was developed as an online registration platform to improve transparency, accessibility, and service effectiveness. However, systematic evaluations of user satisfaction with this website are still limited. This study aims to measure user satisfaction using the End User Computing Satisfaction (EUCS) model. A quantitative approach was applied, with data collected through questionnaires from 144 prospective applicants in the West Papua Regional Police area. Data were analyzed using the Partial Least Squares - Structural Equation Modelling (PLS-SEM) method. The findings reveal that ease of use and timeliness significantly influence user satisfaction, while content, accuracy, and format do not. This indicates that usability and information timeliness play a more critical role. The study encourages system developers to focus on enhancing functional and responsive features to improve digital public services
Comparison of Support Vector Regression and Extreme Learning Machine Methods for Predicting Bitcoin Prices
Get PDFBitcoin can be used for transactions, mining, and investments. Transactions with Bitcoin are highly secure with the help of Bitcoin miner validation. Miners who validate transactions are rewarded with Bitcoins which then adds supply to the Bitcoin network. However, over time, these rewards will run out. The depletion of Bitcoin supply can affect the price of Bitcoin. In addition, investing in Bitcoin is very risky with the fluctuating price of Bitcoin. Therefore, it is necessary to predict the price. In this research, prediction is done using Support Vector Regression (SVR) and Extreme Learning Machine (ELM). The dataset for Bitcoin price (USD) comes from Yahoo Finance. The types of Bitcoin prices predicted are Open, High, Low, and Close prices. Across all series and both splits, ELM outperforms SVR. Under the 80/20 split, the average error of ELM is MAE 418.698 USD, RMSE 633.953 USD, R² of 0.987, versus SVR’s MAE 1061.449 USD, RMSE 1227.499 USD, R² of 0.955. A reduction of 60.6% (MAE) and 48.4% (RMSE). With the 60/40 split, ELM remains strong (MAE 550.783 USD, RMSE 850.656 USD, R² 0.989 while SVR deteriorates (MAE 1843.534 USD, RMSE 2093.542 USD, R² of 0.935, yielding 70.1% and 59.4% average reductions in MAE and RMSE, respectively. ELM consistently tracks both levels and day to day movements, with typical errors of only a few hundred dollars. These results indicate that ELM is the more reliable choice and is capable of capturing non-linearities for Bitcoin price prediction
Implementation of Green Logistics on the Development of Cargo Logistics in the Free Trade Zone Area: A Case Study of PT Bandara Internasional Batam
Get PDFThis study examines the implementation of green logistics at PT Bandara Internasional Batam to evaluate its role in supporting the development of cargo logistics in the Free Trade Zone (FTZ) area. Using a qualitative case study approach, data were collected through in-depth interviews with key informants, direct field observations, and document analysis. The data were analyzed using the Miles and Huberman model, which consists of data reduction, data display, and conclusion drawing. The findings reveal that the adoption of green logistics practices at PT Bandara Internasional Batam has not yet been fully optimized. Although initiatives such as a semi-automated Warehouse Management System (WMS) and document digitalization (paperless system) have been introduced, significant barriers remain, including high investment costs, limited infrastructure, and insufficient human resource capacity. The analysis highlights that outdated cargo facilities, low environmental awareness among workers and service users, and incomplete digital transformation contribute to the slow progress of green logistics implementation. Comparisons with practices in other international airports demonstrate the importance of modern technology adoption, stronger regulatory support, and cultural change in advancing sustainable logistics. This study contributes theoretically by expanding knowledge on the application of green logistics in the aviation sector within a developing country context. Practically, it provides actionable recommendations for PT Bandara Internasional Batam, policymakers, and industry stakeholders to enhance operational efficiency, reduce environmental impact, and strengthen competitiveness in the FTZ area
The Influence of Accountability, Transparency, and Internal Control on the Budget Implementation Performance of the Binjai City Regional Government
Get PDFThis study aims to examine the impact of accountability, transparency, and internal control on budget management performance. The population consists of four SKPDs (Regional Work Units) in Binjai City, with a sample of 90 respondents. Primary data were collected through questionnaires distributed to respondents, who included department heads, finance heads, and finance staff, with time provided for responses. The sampling method employed was purposive sampling, resulting in 90 respondents. The analysis utilized multiple linear regression with SPSS (Statistical Product and Service Solutions) version 25.0. The findings indicate that accountability, transparency, and internal control each have a positive effect on budget management performance in local government. These results support all the hypotheses formulated in the study