Jurnal Politeknik Negeri Batam (PoliBatam)
Not a member yet
3001 research outputs found
Sort by
The Impact of Work Stress on Employee Engagement at PT Pacific Rubber Works
No full textThe dynamics of the manufacturing sector in the industrial era 4.0 demand optimal management of employee engagement during complex production processes. This study analyzes the impact of work stress on employee engagement in employees of PT. Pacific Rubber Works. A quantitative explanatory method using purposive sampling involved 121 respondents, who were analyzed using simple linear regression. Results showed a very weak negative association (r = -0.106) that was not significant (t = -1.163; p = 0.247). The regression equation Y = 33.175 - 0.062X indicates that each 1-unit increase in stress decreases engagement by 0.062 units. Work stress accounted for only 1.1% of the variance in employee engagement. (R² = 0.011), while 98.9% was influenced by other factors such as job satisfaction, work-life balance, and social support. The study concluded that the impact of stress on engagement does not follow conventional linear patterns in standardized manufacturing. It is recommended that management adopt a holistic approach that emphasizes dominant contextual factors to optimize employee engagement
Workshop Pola Hidup Bersih dan Sehat Untuk Siswa MI Simpang Kabupaten Sukabumi
No full textThis community service activity aimed to increase awareness and understanding of clean and healthy living behavior among elementary school students. The workshop, held on August 7, 2025, at MI Simpang, involved interactive learning sessions and practical demonstrations, including proper handwashing techniques. Students actively participated in the activities and showed great enthusiasm. As a result, the workshop successfully improved students’ knowledge and personal hygiene awareness. This initiative is expected to contribute to the creation of a cleaner and healthier school environment.Kegiatan pengabdian kepada masyarakat ini bertujuan untuk meningkatkan kesadaran dan pemahaman siswa terhadap perilaku hidup bersih dan sehat. Workshop dilaksanakan pada tanggal 7 Agustus 2025 di MI Simpang dengan melibatkan sesi pembelajaran interaktif dan praktik langsung mencuci tangan dengan benar. Para siswa mengikuti kegiatan dengan antusias dan berpartisipasi aktif. Hasilnya, kegiatan ini berhasil meningkatkan pengetahuan serta kesadaran siswa terhadap pentingnya kebersihan pribadi. Kegiatan ini diharapkan dapat mendukung terciptanya lingkungan sekolah yang lebih bersih dan sehat
Pendampingan Optimalisasi Digital pada Social Enterprise di Batam
No full textThis community service activity aims to enhance the capacity of social enterprise actors in Batam City through training and mentoring on the use of digital applications. Social enterprise is a form of enterprise that is not only profit-oriented but also has a social mission to create a positive impact on the community. Prior to the training, the implementation team conducted interviews and data collection to identify the level of digital literacy, technology needs, and challenges faced by the social enterprise actors. The data collection results showed that most social enterprise actors have high motivation to develop but are still limited in their mastery of digital technology and online marketing. The digital application training activities, carried out by lecturers and students of the Batam State Polytechnic, were then focused on the use of Microsoft Excel and Canva digital applications. These two applications were chosen based on the priority needs of the Social Enterprises, which are expected to assist in financial management, promotion, and increasing the operational efficiency of their social businesses. Through this training, social enterprise actors are expected to be able to optimize digital technology to expand the social and economic impact of their businesses. This activity is a strategic step in driving digital transformation based on community empowerment.Kegiatan pengabdian kepada masyarakat ini bertujuan untuk meningkatkan kapasitas pelaku social enterprise di Kota Batam melalui pelatihan dan pendampingan penggunaan aplikasi digital. Social enterprise merupakan bentuk usaha yang tidak hanya berorientasi pada keuntungan ekonomi, tetapi juga memiliki misi sosial untuk memberikan dampak positif bagi masyarakat. Sebelum pelatihan dilakukan, tim pelaksana melakukan kegiatan wawancara dan pendataan untuk mengidentifikasi tingkat kemampuan digital, kebutuhan teknologi, serta tantangan yang dihadapi oleh pelaku usaha sosial. Hasil pendataan menunjukkan bahwa sebagian besar pelaku social enterprise memiliki motivasi tinggi untuk berkembang, namun masih terbatas dalam penguasaan teknologi digital dan pemasaran daring. Kegiatan pelatihan aplikasi digital yang dilaksanakan oleh dosen dan mahasiswa Politeknik Negeri Batam kemudian difokuskan pada penggunaan aplikasi digital Microsoft Excel dan Canva. Kedua aplikasi ini dipilih berdasarkan prioritas kebutuhan dari Social Enterprise yang diharapkan dapat membantu manajemen keuangan, promosi, dan peningkatan efisiensi operasional usaha sosialnya. Melalui pelatihan ini, pelaku usaha sosial diharapkan mampu mengoptimalkan teknologi digital untuk memperluas dampak sosial dan ekonomi usahanya. Kegiatan ini menjadi langkah strategis dalam mendorong transformasi digital berbasis pemberdayaan masyarakat
Effect of Premna pubescens Ethanol Extract on Erythrocyte Count and Kidney Histology in Rattus norvegicus L
Get PDFPremna pubescens (wild leaves) has a rich history of traditional medicinal use, including as an anti-inflammatory, antioxidant, and anticancer agent. This study aimed to investigate the potential therapeutic effects of the ethanol extract of Premna pubescens leaves on erythrocyte count and kidney histology in Rattus norvegicus L. Twenty-four male Wistar rats were divided into four groups: control, ethanol extract of wild leaves, Sheep Red Blood Cell (SRBC) antigen, and combined ethanol extract with SRBC. The experiment involved administering wild leaf ethanol extract at 250 mg/kg BW for 30 days, followed by SRBC injection on days 8 and 15. Erythrocyte counts were measured, and kidney histological changes were observed.The results showed a significant increase in erythrocyte count in the A1 (7.42 ± 0.35 million cells/μl) and A3 groups (7.77 ± 0.23 million cells/μl) compared to the control group (7.05 ± 1.07 million cells/μl) and SRBC-treated rats (6.61 ± 0.18 million cells/μl). Histological analysis of the kidneys revealed clearer glomeruli and tubules, with reduced signs of inflammation and bleeding compared to the SRBC-treated group. These findings suggest that Premna pubescens extract has potential therapeutic effects on erythrocyte count and renal tissue, likely due to its antioxidant and anti-inflammatory properties. In conclusion, the ethanol extract of Premna pubescens shows promise in positively affecting erythrocyte count and mitigating kidney damage, demonstrating its potential as a therapeutic agent. 
Turtle Dove Classification Using CNN Algorithm With MobileNetV2 Transfer Learning
Get PDFThis study aims to optimize the performance of a Convolutional Neural Network (CNN) model based on the MobileNetV2 architecture in classifying Java sparrow images by testing four main parameters: optimizer, learning rate, number of epochs, and batch size. The dataset consists of 800 images divided evenly into four classes. The results show that using the Adam optimizer yields the best accuracy with a training accuracy of 97.50%, validation accuracy of 98.75%, and testing accuracy of 98.13%. A learning rate of 0.001 produces the same results, indicating consistent performance with this configuration. Epoch testing shows that 35 epochs yield the highest performance with a training accuracy of 98.39%, validation accuracy of 100%, and testing accuracy of 98.75%. Meanwhile, batch size testing shows that a batch size of 32 yields the highest testing accuracy of 98.85%, a batch size of 64 yields the highest training accuracy of 98.63%, and a batch size of 128 yields the highest validation accuracy of 99.58%. These findings suggest that smaller batch sizes tend to yield better performance in terms of model generalization, while larger batch sizes provide higher stability in the training process but do not always reflect actual performance on the test data. The results of this study can serve as a reference for selecting parameter configurations to improve the accuracy and generalization of image classification models using MobileNetV2. These results emphasize the importance of proper parameter settings in improving the accuracy and stability of image classification models. They can be a reference in model development in object recognition
Human Vulnerabilities to Social Engineering Attacks: A Systematic Literature Review for Building a Human Firewall
Get PDFSocial engineering attacks exploit human psychology to deceive individuals into compromising information security, making the human element a critical vulnerability in cybersecurity systems. This study aims to identify and analyze patterns of human susceptibility in social engineering through a systematic literature review (SLR). Guided by the PRISMA 2020 protocol, a total of 865 articles were initially retrieved from databases such as Scopus, IEEE Xplore, ResearchGate, and Google Scholar. After applying strict inclusion and exclusion criteria, 39 peer-reviewed articles published between 2020 and 2024 were selected for thematic synthesis. The results reveal recurring human vulnerability factors including low security awareness, emotional manipulation (e.g., fear, urgency), overtrust in authority, and lack of behavioral control. These vulnerabilities manifest in predictable victim profiles and behavioral patterns, which are often exploited through phishing, pretexting, and other deception-based tactics. Furthermore, the review highlights the limitations of current mitigation strategies that focus solely on technical solutions without integrating human behavior models. The findings serve as a conceptual foundation for building a “human firewall,” emphasizing awareness, vigilance, and behavioral training as integral components of social engineering defense. This study also lays the groundwork for the development of a human-centric detection model in future research, particularly in the context of mobile banking
Stock Sentiment Prediction of LQ-45 Based on News Articles Using LSTM
Get PDFThe growth in the number of investors in the financial market indicates that the investment world is currently experiencing rapid development. One of the long-term investment instruments that has experienced significant growth in the financial market is the stock market. Growth data as of September 2024 sourced from the Indonesia Stock Exchange report reveals that the number of stock market investors has reached more than 6 million single investor identification (SID). The share price of a company can be influenced by two main factors, namely internal factors and external factors. Internal factors come from within the company itself, while external factors come from conditions outside the company. Model development uses the Long Short-Term Memory (LSTM) method to predict daily stock sentiment in realtime. Labeling is done based on the history of stock price changes taken from Yahoo Finance. Stock market news data is obtained automatically every day through Really Simple Syndication (RSS) with the help of cronjob. The results of the LSTM model showed good performance, with a macro F1-Score of 0.73, a macro precision of 0.72, and a macro recall of 0.75. When compared to baseline models such as Logistic Regression, Naive Bayes, and Random Forest which only achieve a macro F1-Score of 0.58, 0.54, and 0.65, respectively, it can be concluded that the developed LSTM model has superior performance. This research can provide new considerations to investors, so as to reduce the risk of loss due to errors in choosing companies to invest in
Implementation of Ant Colony Optimization (ACO) Algorithm for Route Optimization of Tourist Paths in Takengon
Get PDFThis study aims to design and implement a system for determining the shortest route between tourist destinations in Takengon using the Ant Colony Optimization (ACO) algorithm. The system is developed to assist travelers in obtaining efficient visitation routes based on distance and travel time. Experiments were conducted on 20 tourist locations, resulting in an optimized route with a total travel distance of 40.40 km and an estimated travel time of 81 minutes. The computation process took only 0.024001 seconds with a memory usage of 20.23 KB. The ACO algorithm was executed using 10 ants with key parameters set to alpha (α) = 1, beta (β) = 2, and rho (ρ) = 0.5. ACO demonstrated high effectiveness in exploring route combinations and iteratively generating near-optimal solutions. The chosen parameters were determined through experimentation to balance solution quality and convergence speed. In addition to generating the optimal visitation sequence, the system also provides complete turn-by-turn navigation instructions, including major roads such as Jalan Lintas Tengah Sumatera and Jalan Lebe Kader. The actual estimated travel route based on the generated navigation covers a distance of 97.4 km with a travel duration of approximately 2 hours and 42 minutes. The results indicate that ACO is an effective and efficient approach for solving medium- to large-scale tourist route optimization problems. The developed system can serve as a practical tool in the tourism sector and has the potential to be adapted and implemented in other tourist regions with similar routing challenges
Dendritic ShuffleNetV2 Model for Alzheimer’s Disease Imaging Classification
Get PDFThis study investigates the integration of a dendritic neural model (DNM) into the ShuffleNetV2 architecture to enhance Alzheimer’s stage classification from MRI scans. The proposed “Dendritic ShuffleNetV2” retains the original network’s computational cost (0.31 GFLOPs) while incurring only a 1.6% increase in parameter count (from 2.48 M to 2.52 M) and achieves faster convergence (15 epochs versus 22 epochs). Experiments were conducted on a four‑class Alzheimer’s MRI dataset comprising Non‑Demented, Very Mild Demented, Mild Demented, and Moderate Demented categories. Compared to the baseline ShuffleNetV2, the Dendritic variant yielded an average accuracy improvement of 0.79%, with corresponding gains of approximately 0.8% in weighted precision, recall, and F1‑score. Confusion matrix analysis revealed persistent overlap between the Very Mild and Mild Demented classes, although overall discrimination—particularly for the majority and early‑stage classes—remained robust. Training stability was maintained without significant overfitting.This study investigates the integration of a dendritic neural model (DNM) into the ShuffleNetV2 architecture to enhance Alzheimer’s stage classification from MRI scans. The proposed “Dendritic ShuffleNetV2” retains the original network’s computational cost (0.31 GFLOPs) while incurring only a 1.6% increase in parameter count (from 2.48 M to 2.52 M) and achieves faster convergence (15 epochs versus 22 epochs). Experiments were conducted on a four‑class Alzheimer’s MRI dataset comprising Non‑Demented, Very Mild Demented, Mild Demented, and Moderate Demented categories. Compared to the baseline ShuffleNetV2, the Dendritic variant yielded an average accuracy improvement of 0.79%, with corresponding gains of approximately 0.8% in weighted precision, recall, and F1‑score. Confusion matrix analysis revealed persistent overlap between the Very Mild and Mild Demented classes, although overall discrimination—particularly for the majority and early‑stage classes—remained robust. Training stability was maintained without significant overfitting
News Recommendation System Using Content-Based Filtering through RSS Customization Service
Get PDFNews refers to stories or information about current events or incidents. Several news websites offer a service called RSS (Really Simple Syndication), which enables users to easily receive updates on the latest news. News RSS feeds are typically generated based on the order of publication time or general categories. The content of these news RSS feeds can be customized to align with user interests or preferences. A recommendation system can be utilized as an approach to customize RSS feeds. This study was conducted to design a system capable of generating RSS feeds based on news recommendations using the content-based TF-IDF method and cosine similarity. Data scraping and preprocessing of news articles from various RSS feeds of Indonesian news websites were automated using cron jobs. Content-based filtering modeling was carried out using TF-IDF and cosine similarity. The design and customization of RSS feeds were implemented in a Flask application and packaged within several endpoints. The recommendations generated based on user click interactions were reasonably relevant, as they successfully presented news titles similar to the clicked articles, with cosine similarity scores ranging from 0.2 to 1.0. The majority of respondents agreed that the recommended news articles were relevant to the articles they had clicked and aligned with their interests. The RSS feed evaluation yielded highly satisfactory results, with all aspects assessed in the user acceptance survey achieving an average score exceeding 80%, and the overall results of the customer satisfaction survey indicated scores starting from 90%