Jurnal Politeknik Negeri Batam (PoliBatam)
Not a member yet
3001 research outputs found
Sort by
Pemasangan dan Instalasi Sistem Keamanan di Perumahan Rawan Pencuri Menggunakan CCTV Fanindo Tanjung Uncang Batam
No full textCriminal acts in the community such as theft of motorized vehicles, bicycles and hit-and-run victims are increasingly widespread, in the last 1 year in Fanindo housing there have been four thefts of children\u27s bicycles. Therefore, a security system is needed in the housing to prevent and monitor things that harm the community, namely in the form of CCTV. The methods carried out in the service include surveying the location to determine the strategic installation point with the local RT head, selecting the type of camera, determining the electrical path, determining the placement of the DVR (Digital Video Recorder), and software settings. This service activity received a very positive response from both the RT management and the local community and is expected to be able to reduce criminal acts such as theft and other criminal acts.Tindakan Kriminal di lingkungan Masyarakat seperti pencurian kendaraan bermotor, sepeda dan korban tabrak lari semakin marak, dalam 1 tahun terakhir di perumahan fanindo telah terjadi empat kali pencurian sepeda anak-anak. Oleh karena itu, dibutuhkan sistem keamanan di dalam perumahan tersebut guna mencegah dan mengawasi hal-hal yang merugikan Masyarakat.yaitu berupa CCTV Metode yang dilakukan dalam pengabdian meliputi dari survei lokasi untuk menentukan titik pemasangan yang strategis bersama ketua RT setempat, pemilihan jenis kamera, menentukan jalur kelistrikan, menentukan penempatan DVR (Digital Video Recorder), serta pengaturan perangkat lunak. Kegiatan pengabdian ini mendapat respon yang sangan positif baik oleh pengurus RT maupun Masyarakat setempat dan diharapkan mampu mengurangi tindakan kriminal seperti pencurian maupun tindakan kriminal lainnya
Sosialisasi dan Pelatihan Hidroponik Sederhana Untuk Pembelajaran Sains di SMA Negeri 1 Pemali
Get PDFHydroponics is a method of cultivation without soil, but instead utilizes nutrient-rich mineral solutions containing essential elements. This community service activity aims to improve students\u27 skills in creating and maintaining simple hydroponic systems at SMAN 1 Pemali, particularly within the Green Bee extracurricular group. A total of 30 students participated in this activity. The method used in this activity involved socialization and training on simple hydroponics, specifically the wick system. In this activity, in addition to direct practice, students actively engaged in discussions and asked questions, demonstrating their enthusiasm and curiosity about hydroponic plant cultivation. The results of this community service activity include increased knowledge among the students of SMAN 1 Pemali regarding the preparation of hydroponic tools and materials, the preparation of growing media, the planting process of hydroponic pakcoy vegetables, and the monitoring and evaluation of simple hydroponics. The pakcoy plants in the wick system hydroponic produced during practice were distributed to students of SMAN 1 Pemali as a form of appreciation. This activity also raised awareness about the importance of utilizing limited space and recycled materials for plant cultivation through hydroponics. This opportunity has the potential to serve as a foundation for future entrepreneurial ventures.
Hidroponik merupakan suatu metode bercocok tanam tanpa menggunakan media tanah, melainkan dengan menggunakan larutan mineral bernutrisi yang mengandung unsur hara. Kegiatan pengabdian ini bertujuan untuk meningkatkan keterampilan siswa dalam membuat dan merawat hidroponik sederhana di SMAN 1 Pemali khususnya pada Ekstrakurikuler Green Bee. Jumlah siswa yang mengikuti kegiatan ini adalah sebanyak 30 orang. Metode yang digunakan dalam kegiatan ini adalah dengan memberikan sosialisasi dan pelatihan mengenai hidroponik sederhana yaitu hidroponik sumbu yang dikenal sebagai hidroponik wick system. Dalam kegiatan ini, selain melakukan praktik secara langsung, siswa juga aktif berdiskusi dan memberikan pertanyaan menunjukkan antusias dan keingintahuan mereka terhadap budidaya tanaman hidroponik ini. Hasil dari kegiatan yang dilakukan dalam pengabdian masyarakat ini adalah meningkatkan pengetahuan siswa-siswi SMAN 1 Pemali mengenai penyiapan alat dan bahan hidroponik, persiapan media tanam, penanaman sayur pakcoy hidroponik, monitor dan evaluasi hidroponik sederhana. Tanaman pakcoy hasil dari praktik ini dibagikan kepada siswa SMAN 1 Pemali sebagai bentuk apresiasi. Kegiatan pengabdian ini juga memberikan kesadaran tentang pentingnya memanfaatkan lahan sempit serta barang-barang bekas, untuk budidaya tanaman melalui hidroponik. Peluang ini berpotensi menjadi bekal dalam wirausaha baru di masa depan
STUDI KOMPARATIF PENGGUNAAN YOKE AC DAN DC UNTUK DETEKSI CACAT SUBSURFACE PADA MATERIAL BERLAPIS CAT
Get PDFPenelitian ini bertujuan untuk mengevaluasi perbandingan efektivitas yoke AC dan yoke DC dalam mendeteksi cacat bawah permukaan (subsurface defect) pada pelat baja karbon A36 yang dilapisi cat dengan ketebalan bervariasi menggunakan metode Magnetic Particle Inspection (MPI). Lima spesimen baja dengan ketebalan lapisan cat 100, 200, 300, 400, dan 500 mikron diuji. Metode visible wet particle diterapkan setelah kalibrasi yoke AC dan DC sesuai standar BS 6072. Hasil penelitian menunjukkan bahwa pada ketebalan cat 100 mikron, yoke AC mendeteksi 93% cacat, sedangkan yoke DC mendeteksi 98%. Seiring dengan meningkatnya ketebalan cat, performa yoke AC menurun drastis, terutama pada ketebalan 500 mikron, di mana yoke AC hanya mampu mendeteksi 38% cacat, sementara yoke DC masih mampu mendeteksi 43%. Dengan demikian, yoke DC lebih efektif dalam mendeteksi cacat bawah permukaan pada spesimen dengan lapisan cat yang lebih tebal dibandingkan yoke AC.Penelitian ini bertujuan untuk mengevaluasi perbandingan efektivitas yoke AC dan yoke DC dalam mendeteksi cacat bawah permukaan (subsurface defect) pada pelat baja karbon A36 yang dilapisi cat dengan ketebalan bervariasi menggunakan metode Magnetic Particle Inspection (MPI). Lima spesimen baja dengan ketebalan lapisan cat 100, 200, 300, 400, dan 500 mikron diuji. Metode visible wet particle diterapkan setelah kalibrasi yoke AC dan DC sesuai standar BS 6072. Hasil penelitian menunjukkan bahwa pada ketebalan cat 100 mikron, yoke AC mendeteksi 93% cacat, sedangkan yoke DC mendeteksi 98%. Seiring dengan meningkatnya ketebalan cat, performa yoke AC menurun drastis, terutama pada ketebalan 500 mikron, di mana yoke AC hanya mampu mendeteksi 38% cacat, sementara yoke DC masih mampu mendeteksi 43%. Dengan demikian, yoke DC lebih efektif dalam mendeteksi cacat bawah permukaan pada spesimen dengan lapisan cat yang lebih tebal dibandingkan yoke AC
STUDI PERBANDINGAN CUT QUALITY PADA VARIASI CUTTING SPEED DALAM PLASMA CUTTING
No full textDalam fabrikasi logam, plasma cutting sangat penting karena menawarkan hasil potongan yang presisi, efisien dan fleksibel. Salah satu parameter kritis dalam plasma cutting yaitu cutting speed. Tujuan penelitian ini yaitu membandingkan kualitas hasil potong (cut quality) pada material mild steel dengan ketebalan 8 mm. Variasi cutting speed yang diteliti meliputi 3000 mm/min, 4000 mm/min, 5000 mm/min, dan 6000 mm/min. Pengamatan cut quality dilakukan secara visual dan pengukuran kedalaman hasil potongan menggunakan vernier caliper. Hasil pengamatan menunjukkan bahwa pada parameter cutting speed 3000 mm/min menghasilkan cut quality terbaik. Pada variasi cutting speed yang rendah menghasilkan cut quality yang baik karena plasma memiliki waktu yang cukup untuk penetrasi dan memotong material dengan bersih.
Dalam fabrikasi logam, plasma cutting sangat penting karena menawarkan hasil potongan yang presisi, efisien dan fleksibel. Salah satu parameter kritis dalam plasma cutting yaitu cutting speed. Tujuan penelitian ini yaitu membandingkan kualitas hasil potong (cut quality) pada material mild steel dengan ketebalan 8 mm. Variasi cutting speed yang diteliti yaitu 3000 mm/min, 4000 mm/min, 5000 mm/min, dan 6000 mm/min. Pengamatan cut quality dilakukan secara visual dan pengukuran kedalaman hasil potongan menggunakan vernier caliper. Hasil pengamatan menunjukkan bahwa pada parameter cutting speed 3000 mm/min menghasilkan cut quality terbaik. Pada variasi cutting speed yang rendah menghasilkan cut quality yang baik karena plasma memiliki waktu yang cukup untuk penetrasi dan memotong material dengan bersih.
 
Opinion Classification on IMDb Reviews Using Naïve Bayes Algorithm
No full textThis study aims to classify user opinions on IMDb movie reviews using the Multinomial Naïve Bayes algorithm. The dataset consists of 50,000 reviews, evenly distributed between 25,000 positive and 25,000 negative reviews. The preprocessing stage includes cleaning, case folding, stopword removal, tokenization, and lemmatization using the NLTK library. Text features are represented through the TF-IDF method to capture the significance of each word in the documents. The Multinomial Naïve Bayes model was trained using the hold-out validation technique with an 80:20 split for training and testing data. Hyperparameter tuning of α (Laplace smoothing) was conducted to enhance model stability and accuracy. The model’s performance was evaluated using accuracy, precision, recall, and F1-score metrics, supported by a confusion matrix visualization. The results show that the model achieved an accuracy of 87%, with precision of 87.9%, recall of 85.4%, and an F1-score of 86.6%. In comparison, Logistic Regression as a baseline algorithm achieved an accuracy of 91%. Nevertheless, the Naïve Bayes algorithm remains competitive and computationally efficient for large-scale text data, making it highly relevant for sentiment analysis of movie reviews.This study aims to classify user opinions on IMDb movie reviews using the Multinomial Naïve Bayes algorithm. The dataset consists of 50,000 reviews, evenly distributed between 25,000 positive and 25,000 negative reviews. The preprocessing stage includes cleaning, case folding, stopword removal, tokenization, and lemmatization using the NLTK library. Text features are represented through the TF-IDF method to capture the significance of each word in the documents. The Multinomial Naïve Bayes model was trained using the hold-out validation technique with an 80:20 split for training and testing data. Hyperparameter tuning of α (Laplace smoothing) was conducted to enhance model stability and accuracy. The model’s performance was evaluated using accuracy, precision, recall, and F1-score metrics, supported by a confusion matrix visualization. The results show that the model achieved an accuracy of 87%, with precision of 87.9%, recall of 85.4%, and an F1-score of 86.6%. In comparison, Logistic Regression as a baseline algorithm achieved an accuracy of 91%. Nevertheless, the Naïve Bayes algorithm remains competitive and computationally efficient for large-scale text data, making it highly relevant for sentiment analysis of movie reviews
Adaptive File Integrity Monitoring for Container Virtualization Environments using OSSEC with Real-Time Alerting
No full textIn this ever-evolving digital age, container technology has become one of the main solutions in cloud computing due to its efficiency and flexibility. However, the dynamic and ephemeral nature of containers poses new challenges in terms of security, especially regarding data integrity. The implementation of OSSEC in container environments requires a tailored approach, as it lacks native support for automatically detecting new containers. Agents must be embedded within container images or installed at the host level. These agents activate each time a container runs and send monitoring data to the OSSEC server. With orchestration and automated configuration, monitoring results are stored externally, and real-time email alerts can be triggered upon detecting suspicious file changes. Container environments are increasingly targeted by cyber threats such as malware and ransomware, which pose risks of unauthorized data access or encryption. Limited file integrity monitoring within containers creates a security gap that can be exploited undetected. This research addresses the issue by implementing a File Integrity Monitoring (FIM) mechanism using OSSEC, an open-source Host Intrusion Detection System (HIDS) capable of real-time file and log monitoring, malware detection, and automated threat response. OSSEC is deployed within a Docker-based setup and integrated with a Web User Interface for visualizing logs and monitoring activity. The system includes real-time email notifications for immediate alerts. Testing through file modification scenarios confirmed OSSEC’s accuracy in detecting changes and notifying administrators. This implementation effectively strengthens data security and provides timely threat detection in containerized environments
A Predictive Model for Crop Irrigation Schedulling Using Machine Learning and IoT-Generated Environmental Data
No full textThis study develops and evaluates a machine learning model for predicting optimal irrigation schedules using real-time environmental data collected from an Internet of Things (IoT) system. Building upon a previously validated smart farming monitoring system that provided real-time data on temperature, humidity, and soil moisture, this research addresses the next step: moving from monitoring to predictive analytics. Data collected over a six-day period from DHT11 temperature and humidity sensors, as well as soil moisture sensors, were used to train a predictive model. The model is designed to forecast future soil moisture levels, thereby providing farmers with proactive recommendations for irrigation. A Long Short-Term Memory (LSTM) neural network was employed to capture the temporal dependencies between atmospheric conditions and soil moisture. The model was trained on a portion of the collected data and then validated on a separate, unseen dataset. The evaluation yielded a Mean Absolute Error (MAE) of 2.5%, a Root Mean Square Error (RMSE) of 3.1%, and an R-squared (R2) value of 0.92, demonstrating high predictive accuracy. This approach aims to enhance water resource management, reduce manual intervention, and improve crop health by ensuring water is supplied only when necessary. The results indicate that the machine learning model can accurately predict irrigation needs, offering a significant improvement over traditional, reactive monitoring systems and marking a substantial step towards data-driven, precision agriculture
Mapping Influence Clusters: A Network Analysis of TikTok Influencer Co-Followership Among University Students
No full textThis study examines TikTok influencer co-followership patterns among university students through social network analysis to understand how shared influence functions within digital ecosystems. Using survey data from Indonesian university students who identified their top three most-followed TikTok influencers, we built a co-followership network comprising 266 unique influencers connected by 333 relationships. The research employed quantitative network analysis methods, such as centrality measures, community detection algorithms, and content categorisation, to map influence clusters and explore the network’s structural properties. Results reveal a fragmented network with a low density (0.0094) consisting of 49 connected components, indicating that student followership patterns form distinct thematic communities rather than a single, unified influence network. Centrality analysis identified key bridging influencers, with Tasya Farasya emerging as the most central figure, demonstrating broad appeal across multiple interest categories. Community detection uncovered clear clusters organised around lifestyle and entertainment content, comedy, food, educational material, and motivational themes. Content analysis revealed that travel and lifestyle influencers dominated the network (23.7%), followed by comedy and entertainment creators (16.9%), reflecting TikTok\u27s dual role as both an entertainment platform and a lifestyle guide for university students. The findings show how algorithmic personalisation creates confined influence communities while some central figures act as bridges across different content domains. This research advances methodological approaches by pioneering network analysis methods for influencer co-followership, thereby enhancing the understanding of digital influence as a networked rather than individual phenomenon. The results provide valuable insights for marketing professionals aiming to understand network influence, educational institutions developing media literacy programmes, and platform designers creating algorithmic recommendation systems
Comparison of Text Vectorization Methods for IMDB Movie Review Sentiment Analysis Using SVM
No full textSentiment Analysis is a scientific study in the field of Machine Learning that focuses on classifying opinions expressed in text. IMDb is a platform widely used to provide information and share viewpoints among moviegoers worldwide, where audience reactions often serve as a benchmark for a movie’s success. This research aims to classify positive and negative sentiments by applying and evaluating the effectiveness of Support Vector Machine (SVM) with four different feature representation methods: (a) Bag of Words (BoW), (b) TF-IDF, (c) Word2Vec, and (d) Doc2Vec. After preprocessing the textual data, each method was employed to extract features for model training. The experimental results demonstrate that the combination of SVM with Word2Vec achieved the best overall performance with an F1-Score of 0.8607 and an Accuracy of 0.8607, while also being the fastest in training time (75.0s). In comparison, BoW reached an F1-Score of 0.8219, TF-IDF achieved 0.8520, and Doc2Vec obtained 0.8440. These findings highlight that Word2Vec provides the most effective feature representation for sentiment classification using SVM in this study
Classification of Rice Leaf Diseases Using Support Vector Machine with HSV and GLCM-Based Feature Extraction
No full textThis study aims to classify rice leaf diseases using the Support Vector Machine (SVM) algorithm based on image processing and feature extraction. A total of 600 rice leaf images were collected, each representing one of five disease types: bacterial blight, leaf smut, leaf blast, brown spot, and hispa. The images underwent preprocessing, including resizing, background removal, and feature extraction using HSV and GLCM methods. Extracted features were then used to train and test an SVM classification model. The evaluation using confusion matrix showed an overall accuracy of 83%, with class-specific F1-scores ranging from 0.72 to 0.90. These results indicate that SVM is effective in classifying rice leaf diseases and can potentially assist farmers in early disease detection to reduce crop loss.This study aims to classify rice leaf diseases using the Support Vector Machine (SVM) algorithm based on image processing and feature extraction. A total of 600 rice leaf images were collected, each representing one of five disease types: bacterial blight, leaf smut, leaf blast, brown spot, and hispa. The images underwent preprocessing, including resizing, background removal, and feature extraction using HSV and GLCM methods. Extracted features were then used to train and test an SVM classification model. The evaluation using confusion matrix showed an overall accuracy of 83%, with class-specific F1-scores ranging from 0.72 to 0.90. These results indicate that SVM is effective in classifying rice leaf diseases and can potentially assist farmers in early disease detection to reduce crop loss