Jurnal Politeknik Negeri Batam (PoliBatam)
Not a member yet
3001 research outputs found
Sort by
Classification of Cat Skin Diseases Using MobileNetV2 Architecture with Transfer Learning
No full textSkin diseases in cats often present similar visual symptoms across different conditions, making early and accurate diagnosis challenging for pet owners and veterinarians. This study develops a classification model for cat skin diseases: Fungal Infection, Flea Infestation, Scabies, and Healthy, using the MobileNetV2 architecture with a transfer learning approach. A total of 1,600 RGB images were collected from public datasets and divided into 1,280 training and 320 validation samples. The dataset underwent preprocessing, normalization, and data augmentation techniques such as rotation, shear, zoom, and flipping to enhance model generalization and reduce overfitting. Several experiments were conducted to analyze the impact of input size and learning rate adjustments on model performance. The optimal configuration was achieved using an input size of 224×224 pixels, a learning rate of 0.001, and augmentation applied to the training data. The resulting model achieved a validation accuracy of 91.8%, with an average precision, recall, and F1-score of 91%, demonstrating balanced performance across all classes. These results indicate that the MobileNetV2 architecture, combined with appropriate hyperparameter tuning and augmentation, provides a reliable and computationally efficient method for automatic identification of cat skin diseases. This approach can support early diagnosis, improve animal welfare, and serve as a foundation for the development of practical veterinary diagnostic applications.Skin diseases in cats often present similar visual symptoms across different conditions, making early and accurate diagnosis challenging for pet owners and veterinarians. This study develops a classification model for cat skin diseases: Fungal Infection, Flea Infestation, Scabies, and Healthy, using the MobileNetV2 architecture with a transfer learning approach. A total of 1,600 RGB images were collected from public datasets and divided into 1,280 training and 320 validation samples. The dataset underwent preprocessing, normalization, and data augmentation techniques such as rotation, shear, zoom, and flipping to enhance model generalization and reduce overfitting. Several experiments were conducted to analyze the impact of input size and learning rate adjustments on model performance. The optimal configuration was achieved using an input size of 224×224 pixels, a learning rate of 0.001, and augmentation applied to the training data. The resulting model achieved a validation accuracy of 91.8%, with an average precision, recall, and F1-score of 91%, demonstrating balanced performance across all classes. These results indicate that the MobileNetV2 architecture, combined with appropriate hyperparameter tuning and augmentation, provides a reliable and computationally efficient method for automatic identification of cat skin diseases. This approach can support early diagnosis, improve animal welfare, and serve as a foundation for the development of practical veterinary diagnostic applications
Sentiment Analysis of US-China Tariffs using IndoBERT and Economic Impact on Indonesia
No full textThe US-China trade war has influenced public perception due to its potential economic impact on developing countries like Indonesia. This study analyses Indonesian sentiment towards the tariff policies and their correlation with economic indicators. The dataset consisted of 38,739 social media comments collected through web scraping. The data were processed through data cleaning, case folding, stopword removal, normalization, and stemming. Each comment was labeled as positive, negative, and neutral. The dataset was split into 80% training and 20% testing sets, followed by an oversampling process to balance the class distribution. The data is fine-tuned using the IndoBERT model with the Python programming language. The model achieved its highest performance with an accuracy of 93.03%, precision of 93.42%, recall of 93.03%, and F1-score of 92.94%. Spearman correlation revealed a weak to moderate positive and significant correlation (ρ = 0.434, p-value < 0.05) between public sentiment and global soybean prices. These findings underscore the effectiveness of combining a deep learning model like IndoBERT with statistical analysis to link digital discourse to tangible economic indicators, highlighting the method\u27s potential as a data-driven tool for policy evaluation
Performance Analysis of YOLO, Faster R-CNN, and DETR for Automated Personal Protective Equipment Detection
No full textAutomated monitoring of Personal Protective Equipment (PPE) is crucial for enhancing safety in high-risk environments like construction sites, yet selecting the optimal detection model requires careful evaluation of accuracy versus efficiency trade-offs. This study presents a comparative performance analysis across distinct object detection paradigms represented by YOLO (YOLOv8, YOLOv11n), Faster R-CNN, and DETR to benchmark their suitability for real-time PPE detection. However, this study moves beyond a simple technical benchmark by also proposing a logical process to transform raw model detections (e.g., \u27person\u27, \u27hardhat\u27) into actionable compliance verification information (e.g., \u27Compliant\u27/\u27Non-Compliant\u27). Using a curated construction site safety dataset, models were evaluated based on standard accuracy metrics (including [email protected]:.95) and efficiency measures (inference latency). Results indicate that DETR and YOLOv11n achieved the highest overall accuracy with an identical [email protected]:.95 of 0.770, closely followed by YOLOv8 (0.763), while the YOLO family demonstrated significantly superior real-time efficiency (6-7 ms latency). Faster R-CNN recorded a lower mAP (0.703) and the highest latency. Conclusively, YOLOv11n offers the most compelling balance for the detection phase, and the proposed logical process provides a practical method for integrating this technical output into automated safety monitoring systems
The Influence of Customer Experience on Customer Loyalty Through Repurchase Intention in Shopee Jakarta Users
No full textThis research focuses on the Shopee platform to analyse the effect of customer experience on customer loyalty through repurchase intention as a mediating variable. A quantitative research design was employed, using purposive sampling to select respondents. A total of 131 participants took part in this study, comprising male and female residents of Jakarta aged 17 to 30 years who had made at least one purchase on Shopee within the past six months. Data were gathered through an online questionnaire distributed via Google Forms, utilising a four-point Likert scale ranging from strongly disagree to strongly agree. The collected data were analysed using the Partial Least Squares (PLS) technique through the SmartPLS software version 4.1.1.5. The results confirm that customer experience has a positive impact on both repurchase intention and customer loyalty, with repurchase intention also serving as a significant mediating factor between the two variables
Linking Green Accounting and CSR Practices to Financial and Sustainability Performance
No full textDuring the global pressure for environmental transparency, green accounting and CSR becomes a bridge between company’s profitability and sustainability. This research examines the influence of green accounting and CSR on financial performance and sustainability performance. PLS-SEM method with SmartPLS 4.1.2 would be used to analyze the data for this study. Samples used in this study consisted of 39 companies from mining and crude palm oil sectors listed on Indonesia Stock Exchange (IDX) between 2021-2023. Green accounting will be measured with PROPER awards. CSR will be measured based on environmental costs. Financial performance will be measured using ratio of Return of Assets (ROA), and sustainability performance will be measured with GRI 2021 index. Analysis results indicate that green accounting negatively impacts financial performance, but exerts a significant positive influence on sustainability performance. CSR positively enhances financial performance but has no significant effect on sustainability performance. Moreover, analysis confirms no mediating role of financial performance in the connections linking green accounting or CSR to sustainability performance
Enhancing Corporate Integrity: Profitability, Transfer Pricing, and Tax Avoidance with the Role of Bonus Mechanisms and Stewardship Theory
No full textThis study examines the effect of transfer pricing and bonus mechanisms on tax avoidance. It tests profitability as a moderating variable in multinational companies. Grounded in Stewardship Theory, the research explores whether managerial incentives and corporate profitability influence firms’ tax behavior. It emphasizes the balance between financial performance and ethical tax practices. A quantitative approach was used with secondary data from the financial reports of industrial sector companies listed on the Indonesia Stock Exchange (IDX) during 2020–2022. The sample was selected through purposive sampling, consisting of 21 companies. Panel data regression analysis was conducted using the Ordinary Least Squares (OLS) method, supported by Chow, Hausman, and Lagrange Multiplier (LM) tests to determine the most appropriate model. The results show that both transfer pricing and bonus mechanisms have a significant positive effect on tax avoidance. This indicates that multinational firms use intra-group transactions and performance-based incentives to minimize tax burdens. However, profitability does not significantly moderate these relationships. This suggests that firm performance alone does not weaken or strengthen the impact of transfer pricing and bonus mechanisms on tax avoidance. These findings contribute to the literature on corporate governance and tax planning by providing empirical evidence on the interplay between managerial incentives, profitability, and ethical financial behavior. The research offers valuable implications for policymakers and companies in developing responsible compensation systems and regulatory frameworks to curb aggressive tax practices
From Transparency and Governance to Compliance: How Tax Digitalization Shapes Business Sustainability
No full textThis study investigates the effects of tax transparency and corporate governance on tax compliance, with tax digitalization as a moderating variable, among companies operating in the Cikarang–Cibitung industrial area. Grounded in legitimacy theory, the research posits that transparent tax practices, strong governance structures, and digital integration enhance organizational legitimacy and compliance. A quantitative research design was employed using survey data from 300 respondents involved in tax-related functions across manufacturing, trade, and service sectors. Data were analyzed using Partial Least Squares Structural Equation Modeling (PLS-SEM). Results reveal that tax transparency significantly and positively affects tax compliance (β = 0.187, p < 0.001), supporting the notion that openness fosters trust and mitigates noncompliance risks. Similarly, corporate governance positively affects compliance (β = 0.169, p < 0.01), underscoring the importance of accountability and ethical oversight. The moderating analysis shows that tax digitalization strengthens the effects of both transparency (β = 0.221, p < 0.05) and governance (β = 0.198, p < 0.05) on compliance, indicating that digital platforms enhance efficiency and monitoring in tax administration. The model explains 65% of the variance in tax compliance (R² = 0.65), demonstrating robust explanatory power. These findings affirm legitimacy theory’s proposition that organizations maintain societal trust by adopting transparent, responsible, and digitally adaptive tax practices. The study contributes theoretically by integrating digital transformation into legitimacy-based frameworks and offers practical implications for policymakers and corporate leaders aiming to strengthen sustainable tax compliance
Business Sustainability through Halal Supply Chain, Green Finance, and Digital Literacy: Second-Order SEM Approach
No full textBusiness sustainability is crucial for every business. Understanding the factors that drive and sustain sustainability helps business actors develop effective strategies. This study examines the effects of Halal Supply Chain, Green Finance, and Digital Literacy on Business Sustainability. The population was culinary sector SMEs in Pekanbaru City that had halal certification and at least 2 years of operation. Slovin\u27s formula determined the sample size. Data were collected via questionnaires, yielding 170 valid responses. The analysis used the Second-Order SEM approach. Results show that Halal Supply Chain and Digital Literacy positively affect sustainability in culinary SMEs, while Green Finance does not. Integrating Halal Supply Chain and Digital Literacy practices helps culinary SMEs sustain their business
Spatial Variability of Tidal Characteristics in Bintan Coastal Waters: A Case Study of Moco Port, Bakau Bay, and Tanjung Uban Port
No full textTidal dynamics play a crucial role in coastal processes, port operations, and coastal management, particularly in regions characterized by complex oceanographic interactions such as Bintan Island, Riau Islands Province, Indonesia. This study analyzes the spatial variability of tidal characteristics in the coastal waters of Bintan Island at three observation sites, namely Bakau Bay, Tanjung Uban Port, and Moco Port, using global tidal prediction data generated by MIKE Powered by DHI and harmonic analysis based on the Admiralty method. Eight principal tidal constituents (M₂, S₂, K₁, O₁, N₂, P₁, K₂, and Q₁) were examined, and tidal types were classified using the Formzahl number. The results reveal clear spatial variability in tidal harmonic characteristics despite the close geographic proximity of the sites, with the M₂ constituent dominating tidal behavior at all locations, indicating strong lunar control. Significant contributions from diurnal constituents (K₁ and O₁) result in mixed tidal regimes, with Formzahl values of 1.10 at Bakau Bay, 0.66 at Tanjung Uban, and 1.29 at Moco, classifying all sites as mixed tides with a predominance of semidiurnal components. Variations in tidal amplitudes are closely related to local coastal morphology and exposure to open waters, with Tanjung Uban exhibiting the strongest tidal influence. This multi-location analysis provides a comprehensive understanding of spatial tidal variability in Bintan coastal waters and supports coastal planning, port management, and hydrodynamic modeling in the region
Logistical And Operational Challenges In Cold Chain Systems For Fishery Products In Developing Countries: A Literature Review: English
No full textThe delivery of fishery products must consistently maintain product quality and integrity to prevent deterioration during the post-harvest period. In developing countries, the distribution of fishery products faces challenges in the post-harvest cold chain system, ranging from infrastructure, technology, and transportation to human resources. This study aimed to identify the logistical and operational challenges in implementing cold chain systems for fishery products in developing countries. The method used in this research is a literature review, with data obtained from accredited journals focused on the topic of cold chain systems. Based on the literature review, it was found that cold chain system challenges in developing countries include road infrastructure that does not connect regions, technology that cannot be applied to the cold chain system because of high financial requirements, transportation units that do not meet cold chain shipping standards, and human resources that lack understanding of the importance of maintaining the quality and integrity of fishery products during the post-harvest period. The implications and recommendations include the need for improved infrastructure development, investment in technology, implementation of transportation units that meet cold chain standards, and enhancement of human resource quality.Pengiriman produk perikanan harus terus menjaga agar kualitas dan mutu produk agar tidak mengalami penurunan selama pascapanen, Distribusi produk perikanan di negara berkembang dihadapkan dengan tantangan dalam sistem rantai dingin pascapanen mulai dari infrastruktur, teknologi, transportasi, hingga sumberdaya manusia. Penelitian ini bertujuan untuk mengetahui tantangan logistik dan operasional dalam penerapan sistem rantai dingin pada produk perikanan di negara berkembang. Metode yang digunakan dalam penelitian ini ialah Kajian Literatur (Literature Review), data yang diperoleh dari jurnal yang terakreditasi dengan topik tertentu yaitu sistem rantai dingin. Berdasarkan kajian literatur ditemukan bahwa tantangan sistem rantai dingin di negara berkembang itu meliputi infrastruktur jalan yang belum menghubungkan antar wilayah, teknologi yang tidak mampu diterapkan pada sistem rantai dingin disebabkan kebutuhkan dana yang cukup besar, unit transportasi yang tidak sesuai standar pengiriman dengan rantai dingin, hingga kualitas sumberdaya manusia yang tidak memahami pentingkan menjaga mutu dan kualitas produk perikanan selama pascapanen. Implikasi dan rekomendasi dalam meningkatkan pembangunan infrastruktur diperlukan, investasi terhadap teknologi perlu dikembangkan, penggunaan unit transportasi yang sesuai standar pengiriman rantai dingin perlu diterapkan, serta peningkatan kualitas sumberdaya manusia perlu ditingkatkan