Jurnal Politeknik Negeri Batam (PoliBatam)
Not a member yet
3001 research outputs found
Sort by
Design of a Web-Based Geographic Information System for Mapping Coastal Areas and Fishermen\u27s Activities on Bintan Island
No full textCoastal ecosystems and small-scale fisheries in Pengudang Village, Bintan, play an essential role in supporting local livelihoods. However, integrated spatial information on benthic habitats, mangroves, and fishing activities remains limited. This study aims to map coastal ecological conditions and fishing grounds while developing an accessible Web-GIS system to support coastal management. A descriptive qualitative approach was employed. Sentinel-2 Level 2A imagery was analyzed using Maximum Likelihood Classification, supported by field surveys, ground truthing, and interviews with 20 active fishers. Mangrove density was assessed using NDVI analysis. Spatial data, combined with fishers’ activity information, were integrated into a Web-GIS developed using the SDLC Waterfall method. The classification generated four dominant benthic habitat classes including seagrass, sand, mixed substrate, and dead coral with algae. NDVI indicated varying mangrove density levels from low to very high. Fishing grounds were concentrated in shallow waters with seagrass and mixed substrates. Fishers predominantly used kelong and bubu, producing 5–20 kg catch per trip. The developed Web-GIS provides interactive maps, layer selection, and spatial search features. The system enhances accessibility to coastal spatial data and supports evidence-based decision-making for sustainable coastal resource management in Pengudang Village
ANALISIS PROSES PENGELASAN REPLATING LAMBUNG KAPAL PADA KONDISI FLOATING TERHADAP NILAI KEKERASANNYA: PENGELASAN LAMBUNG KAPAL
No full textReplating the ship’s hull is an essential repair process to ensure that a vessel remains operationally seaworthy. Replating welding can be performed under both docking and floating conditions. These differing conditions influence the cooling rate, which in turn can result in variations in hardness (HV). This study examines the effect of varying the distance from the waterline (30, 60, 100, and 130 mm) and water temperature (25°C, 28°C, 30°C, and 32°C) on the hardness values produced during welding under floating conditions.Each variation combination was tested using the Vickers method with three repetitions, and the reported HV values represent the average of those measurements. The results show that the highest hardness value under floating conditions reached 218.5 HV (30 mm, 25°C), while the lowest was 195.7 HV (130 mm, 32°C). All measured hardness values remained within the acceptable limits specified by BKI for low-carbon steel.This study demonstrates that the closer the weld groove is to the water surface and the lower the water temperature, the higher the resulting hardness due to increased cooling rates. The limitations of this study include the absence of microstructural data and the unavailability of individual measurement data for further statistical analysis.Replating kapal merupakan suatu hal penting dalam hal perbaikan kapal agar tetap dapat beroperasi sesuai fungsinya. Replating dapat dilakukan kondisi docking, serta dapat juga dilakukan kondisi floating. Laju pendinginan proses pengelasan kondisi floating berbeda dengan laju pendinginan pada pengelasan kondisi docking, sehingga hal tersebut mempengaruhi sifat mekanis dari material. Penelitian ini menggunakan empat variasi jarak antara garis las dengan garis air yaitu 30 mm, 60 mm, 100 mm, dan 130 mm, dan empat variasi temperatur air yaitu 25˚C, 28˚C, 30˚C dan 32˚C, yang nantinya akan dibandingkan hasilnya dengan pengelasan kondisi di darat. Pengujian kekerasan dilakukan untuk mengetahui sifat mekanis material. Hasil pengujian kekerasan menunjukkan bahwa terjadi penurunan nilai kekerasan pada setiap kenaikan variasi jarak garis air dengan garis las dan variasi temperatur air. Nilai kekerasan untuk seluruh variasi yang dilakukan pada penelitian ini memenuhi standard BKI. Sehingga berdasarkan penelitian ini, pengelasan dalam kondisi floating dengan minimal jarak antara garis air dengan garis las sebesar 30 mm, dan temperatur air antara 25˚C - 32˚C, dapat diaplikasikan dilapangan
UX Analysis of the Virtual Tour 360 Application at Universitas Dr. Soetomo Campus
Get PDFThis research investigates the effectiveness of the Virtual Tour 360 application implemented at Universitas Dr. Soetomo Campus, Surabaya, as a tool for enhancing prospective students\u27 understanding and familiarity with campus facilities. Focusing on user experience (UX), this study evaluates key aspects such as the flow of the virtual tour, camera height for indoor and outdoor captures, image resolution and file size, and overall application size for online accessibility. User feedback highlights a high level of satisfaction, with 85.1% finding the application beneficial, especially on mobile devices, the preferred access method. The immersive 360-degree campus visualizations and user-friendly navigation have received positive responses, effectively providing a favorable first impression of the university. To further enrich user experience, optimizing mobile display quality and enhancing navigation features are recommended to offer a more comprehensive and interactive campus introduction.This research investigates the effectiveness of the Virtual Tour 360 application implemented at Universitas Dr. Soetomo Campus, Surabaya, as a tool for enhancing prospective students\u27 understanding and familiarity with campus facilities. Focusing on user experience (UX), this study evaluates key aspects such as the flow of the virtual tour, camera height for indoor and outdoor captures, image resolution and file size, and overall application size for online accessibility. User feedback highlights a high level of satisfaction, with 85.1% finding the application beneficial, especially on mobile devices, the preferred access method. The immersive 360-degree campus visualizations and user-friendly navigation have received positive responses, effectively providing a favorable first impression of the university. To further enrich user experience, optimizing mobile display quality and enhancing navigation features are recommended to offer a more comprehensive and interactive campus introduction
Application of Gated Recurrent Unit in Electroencephalogram (EEG)-Based Mental State Classification
Get PDFThe classification of mental states based on electroencephalogram (EEG) recordings has recently gained significant interest in cognitive monitoring and human-computer interaction fields. Due to high signal variability and sensitivity to noise, correct classification is still tricky, even with advances in the analysis of EEG signals. Among deep learning models, Gated Recurrent Unit (GRU) models have established great potential for sequential EEG data analysis. The applications of the GRUs are less reviewed in tasks concerning classification cases of mental states compared to hybrid and convolutional models. Based on this paper, we will propose a method for developing a model based on the GRU network trained with raw EEG data in the classification tasks of mental states of concentration and relaxed conditions. We analyzed 400 EEG recordings taken from 10 subjects within a controlled environment and collected using the Muse EEG Headband. The mean, standard deviation, skewness, kurtosis, power spectral density, zero-crossing rate, and root mean square were extracted as statistical features from the raw EEG data. After parameter tuning, the GRU-based model achieved an excellent average accuracy value of 95.94% and also yielded precision, recall, and F1-scores within the range of 0.95 to 0.97 over 5-fold cross-validation. This shows that GRU works well in classifying mental states based on the EEG data
Identification of Latent Dimensions of Digital Readiness and Typology of Districts/Cities in Indonesia Using PCA and K-Means Clustering
No full textDigital transformation is a key agenda in Indonesia’s national development that requires balanced readiness across regions. However, the level of digital readiness among districts and cities still varies widely, highlighting the need for a typology that can comprehensively describe existing disparities. This study aims to identify the latent dimensions of digital readiness and to develop a regional typology of Indonesian districts/cities using Principal Component Analysis (PCA) and K-Means clustering. The data were obtained from the 2024 Indonesian Digital Society Index (IMDI), which consists of four pillars—Infrastructure and Ecosystem, Digital Skills, Empowerment, and Employment—with ten sub-pillars. PCA reduced these correlated indicators into two main latent components, namely Digital Capacity and Participation and Digital Infrastructure Foundation, which together explain 70.4% of the total variance. Cluster validation using the Silhouette Score and Davies–Bouldin Index (DBI) showed that K = 2 yielded the best internal validity (Silhouette = 0.402; DBI = 0.906), but a three-cluster configuration (K = 3) was adopted to obtain a more interpretable typology of high-, medium-, and low-readiness regions (Silhouette = 0.346; DBI = 1.007). Spatial mapping reveals that high-readiness districts are concentrated in Java, Bali, and parts of Sumatra, whereas low-readiness areas dominate eastern Indonesia. These findings confirm persistent digital inequality across regions and provide a quantitative basis for targeted policy interventions, including infrastructure development, digital literacy programs, and innovation ecosystem strengthening, to support an inclusive digital transformation in Indonesia
A Comparative Study of Machine Learning and Deep Learning Models for Heart Disease Classification
No full textHeart disease remains one of the leading causes of mortality worldwide, necessitating accurate early detection. This study aims to compare the performance of several Machine Learning (ML) and Deep Learning (DL) algorithms in heart disease classification using the Heart Disease dataset with 918 samples. The methods tested included Naïve Bayes, Decision Tree, Random Forest, Support Vector Machine (SVM), Logistic Regression, K-Nearest Neighbor (KNN), and Deep Neural Network (DNN). Preprocessing included feature normalization, data splitting (80:20), and simple hyperparameter tuning for parameter-sensitive models. Evaluations were conducted using accuracy, precision, recall, F1-score, AUC, and confusion matrix analysis to identify error patterns. The results showed that SVM and DNN achieved the highest accuracies of 91.3% and 92.1%, respectively. However, DNN has higher computational costs and risks of overfitting on small datasets. These findings confirm that traditional ML models such as SVM remain highly competitive on tabular medical data.Heart disease remains one of the leading causes of mortality worldwide, necessitating accurate early detection. This study aims to compare the performance of several Machine Learning (ML) and Deep Learning (DL) algorithms in heart disease classification using the Heart Disease dataset with 918 samples. The methods tested included Naïve Bayes, Decision Tree, Random Forest, Support Vector Machine (SVM), Logistic Regression, K-Nearest Neighbor (KNN), and Deep Neural Network (DNN). Preprocessing included feature normalization, data splitting (80:20), and simple hyperparameter tuning for parameter-sensitive models. Evaluations were conducted using accuracy, precision, recall, F1-score, AUC, and confusion matrix analysis to identify error patterns. The results showed that SVM and DNN achieved the highest accuracies of 91.3% and 92.1%, respectively. However, DNN has higher computational costs and risks of overfitting on small datasets. These findings confirm that traditional ML models such as SVM remain highly competitive on tabular medical data
Forest and Land Fire Disaster Risk Assessment Using Geographic Information Systems in Arut Selatan District, West Kotawaringin Regency, Central Kalimantan Province
No full textKotawaringin Barat Regency, Central Kalimantan Province, has six sub-districts, namely Kumai District, Arut Selatan District, Arut Utara District, Pangkalan Lada District, Pangkalan Banteng District, and Kotawaringin Lama District, all of which are areas prone to natural disasters. One of them is forest and land fires. In recent years, there have been many forest and land fires in the Kotawaringin Barat Regency area. Starting in 2022, there were around 75 forest and land fires; in 2023, there were around 201 incidents; and in 2024, there were around 36 incidents, all of which were in the Arut Selatan District and Kumai District. With the occurrence of forest and land fires, most of them in the two sub-districts, namely Kumai and Arut Selatan Districts, this study took the location of Arut Selatan District. The assessment of forest and land fire disaster risks uses spatial analysis methods. To find the weight of hazard, vulnerability, and capacity using secondary data processed with the formula according to the Regulation of the Head of BNPB Number 2 of 2012 concerning disaster risk assessment using the Excel application. The results of the assessment of the risk of forest and land fires in the South are dominated by high classifications of 9 villages/sub-districts with a percentage of 83.8% of the total area. While for the moderate classification of 5 villages/sub-districts with a percentage of 2.7% of the total area and moderate classification of 6 villages/sub-districts with a percentage of 13.5% of the total area. With the high risk of forest and land fires because the percentage of hazards and vulnerabilities is still high and the percentage of capacity is still classified as moderate. For this reason, it is necessary to increase capacity in dealing with forest and land fires to reduce the risk of forest and land fires that occur
Implementasi Metode Pose to Pose pada Perancangan Animasi "Ali & Umar"
No full textAnimation, as a rapidly evolving art form, requires effective techniques to produce realistic and engaging movements. The pose-to-pose method, which focuses on creating key poses, is utilized in the design of the animation "Ali & Umar." This article explores the application of this method using Blender to enhance animation quality. Through this method, animators can better control each movement and add additional poses to increase dynamism. The pose-to-pose technique involves planning the animation by setting key poses at various stages of movement, allowing animators to achieve smooth and realistic motion and easily correct errors. The production process of this animation is divided into three main stages: preparation, creation, and refinement. In the preparation stage, the story and characters are designed with the help of artificial intelligence (AI) to facilitate initial visualization. The creation stage includes 3D modeling, texturing, rigging, and animating the characters and other visual elements, with the pose-to-pose method ensuring accurate character movements. Finally, the refinement stage involves editing and optimizing video quality and adding sound. The results of this study indicate that the pose-to-pose method is effective in producing educational 3D animations, aiming to convey an Islamic message about the dangers of shirk through an engaging medium. These findings open opportunities for the development of more innovative Islamic educational media in the future
ANALISIS PERFORMA COOLING TOWER JENIS INDUCED DRAFT COUNTER FLOW DI POWER PLANT PT. X
No full textThe cooling tower is a crucial component in the water cooling system of a power plant. During its operation, the cooling process occurs when the water entering the cooling tower undergoes heat transfer through direct contact with cool air, resulting in evaporation. This process leads to water losses in the form of evaporation loss and blowdown, which affect the cooling capacity of production equipment. This study aims to analyze the performance of an induced draft counter-flow cooling tower at PT. X by examining parameters such as range, approach, cooling effectiveness, evaporation loss, and cooling capacity. The results indicate that the cooling tower operates with a range of 6.03°C, an approach of 4.4°C, a cooling effectiveness of 58.75%, a make-up water rate of 43.07 m³/h, and a cooling capacity of 29,419.58 kW. A strong correlation (0.958) between inlet and outlet water temperatures demonstrates consistent heat transfer performance. The system shows improved performance, with ΔT increasing from 2.78°C in 2015 to 6.44°C in 2024. Based on the analysis, it can be concluded that the cooling tower remains feasible for operation but requires regular maintenance to optimize performance.Cooling tower merupakan komponen penting dalam sistem pendinginan air di power plant. Penelitian bertujuan menganalisis performa cooling tower jenis Induced draft counter flow di PT. X. Hasil penelitian menunjukkan cooling tower beroperasi dengan range 6,03°C, approach 4,4°C, efektivitas 58,75%, make-up water 43,07 m³/jam, dan kapasitas pendinginan 29.419,58 kW. Korelasi kuat antara temperatur air masuk dan keluar (0,958) menunjukkan performa perpindahan panas yang konsisten. Sistem menunjukkan peningkatan performa dengan ΔT meningkat dari 2,78°C (2015) menjadi 6,44°C (2024). Cooling tower masih layak digunakan namun memerlukan perawatan rutin untuk optimasi performa
Kajian Penggunaan ESP32-CAM dengan Platform Edge Impulse Untuk Sistem Buka Tutup Kandang Kucing
No full textSalah satu kajian penting dalam proses sistem buka tutup kendang kucing yaitu pengenalan objek. Pengenalan objek bertujuan untuk mengidentifikasi dan menentukan lokasi objek dalam citra atau video. Penelitian telah berhasil mengimplementasikan pengenalan kucing dengan ESP32-CAM dan platform Edge Impulse. ESP32-CAM merupakan modul kamera yang terintegrasi dengan mikrokontroler, sementara Edge Impulse merupakan platform yang memungkinkan pengembangan model pembelajaran mesin pada perangkat edge. Tingkat akurasi sistem yang dibuat pada penelitian ini telah mencapai 93,33% sehingga sistem ini dapat diandalkan untuk membuka pintu kandang secara otomatis ketika kucing yang telah dikenali berada di depan kamera. Dengan keberhasilan dari penelitian yang dilakukan, pemelihara kucing dapat melakukan pengontrolan dan perawatan yang lebih baik terhadap kucing peliharaannya