Jurnal Politeknik Negeri Batam (PoliBatam)
Not a member yet
3001 research outputs found
Sort by
Aspect-Based Sentiment Analysis of Reviews for Pandawa Beach Using Naive Bayes and SVM Methods
Get PDFThe presence of digital technology, especially online platforms such as Google Maps, has changed the way people search for information about tourist destinations, including reviews and ratings from previous visitors. Aspect-based sentiment analysis becomes a very useful tool to understand people\u27s views and feelings towards a place or product based on the reviews given and identify aspects of interest to tourists visiting Pandawa Beach, by utilizing Naive Bayes and Support Vector Machine (SVM) methods. The main objective of this research is to identify sentiment patterns based on aspects such as attraction, accessibility, amenities, and ancillary. Data was collected and labeled according to sentiment and aspects, then processed using preprocessing techniques, extracted by bag-of-words method, and chi-square feature selection. The model evaluation results showed that SVM produced the highest F1-Score value of 79,625%, while the Naive Bayes method reached 73.29%.The presence of digital technology, especially online platforms such as Google Maps, has changed the way people search for information about tourist destinations, including reviews and ratings from previous visitors. Aspect-based sentiment analysis becomes a very useful tool to understand people\u27s views and feelings towards a place or product based on the reviews given and identify aspects of interest to tourists visiting Pandawa Beach, by utilizing Naive Bayes and Support Vector Machine (SVM) methods. The main objective of this research is to identify sentiment patterns based on aspects such as attraction, accessibility, amenities, and ancillary. Data was collected and labeled according to sentiment and aspects, then processed using preprocessing techniques, extracted by bag-of-words method, and chi-square feature selection. The model evaluation results showed that SVM produced the highest F1-Score value of 79,625%, while the Naive Bayes method reached 73.29%
Regional Tax, Retributions, and Own-Source Revenues Performance of Bekasi City
Get PDFTax reform in Indonesia is also addressing issues related to Regional Tax and Retributions (PDRD), which have become the major sources of regional own-source revenue (PAD). Therefore, this study aimed to analyze the effectiveness and contribution of regional tax to PAD in Bekasi City from 2017-2022 as well as project the potential tax and retributions between 2024-2028. The study procedures were carried out using rigorous techniques, such as descriptive analysis, ratio analysis, and forecasting. The results showed that there were fluctuations in the effectiveness of PDRD in Bekasi City for 6 years. The highest effectiveness of regional tax occurred in 2017 and decreased from 2018 to 2019, while retributions showed a significant difference. The results also showed that the contribution of the 2 variables to PAD of Bekasi City was in the low category. The most potential revenue projections for 2024-2028 were Acquisition Duty of Right on Land and Building (BPHTB) and Retributions for Fire Extinguisher Testing Services
Implementasi Pemetaan Robot Roda Mecanum Otonom Berbasis LIDAR dengan SLAM
No full textThis article reviews an autonomous mobile robot with mecanum wheels using localization and mapping with Lidar. The mecanum wheeled robot is capable of autonomously moving from point A to point B. This study aims to determine the level of accuracy and precision in mapping to ensure the robot can operate efficiently, as well as to develop the ability to perform real-time environmental mapping using data obtained from the Lidar A2M12 sensor. It also aims to implement the SLAM (Simultaneous Localization and Mapping) algorithm to simultaneously determine the robot\u27s position and orientation while mapping. For independent movement, the robot must be aware of its surroundings and its position within that environment. The method used is simultaneous localization and mapping using the RPLidar A2M12 sensor and ROS (Robot Operating System). Based on the testing results, the gmapping SLAM error rate is 3.34%, with a sensor distance and angle measurement error of 1.16%. Overall, this autonomous robot can be used even in open areas and with simple obstacles. Artikel ini mengulas tentang autonomous mobile robot roda mekanum menggunakan lokalisasi dan pemetaanmenggunakan lidar Robot beroda mekanik adalah robot yang dapat bergerak dari titik A ke titik B secara mandiri.Tujuan dari penelitian ini adalah untuk mengevaluasi ketepatan dan akurasi pemetaan dan ketepatan dalampemetaan untuk memastikan robot dapat beroperasi dengan efisien serta membangun kemampuan untukmelakukan pemetaan lingkungan sekitar secara real-time menggunakan data yang diperoleh dari sensor LidarA2M12 dan mengimplementasikan algoritma SLAM (Simultaneous Localization and Mapping) untukmenentukan posisi dan orientasi robot secara simultan saat melakukan pemetaan. Untuk bergerak secara mandiri,robot harus menyadari lingkungannya dan posisinya dalam lingkungan tersebut. Metode yang digunakan adalahlokalisasi dan pemetaan simultan dengan menggunakan sensor RPLidar A2M12 dan ROS (Robot OperatingSystem). Berdasarkan hasil pengujian gmapping SLAM sebesar 3,34%, error pengukuran jarak dan sudut sensorsebesar 1,16%, secara keseluruhan, robot otonom ini dapat digunakan bahkan di area terbuka dan rintangansederhana
Perancangan dan Implementasi Sirkulasi Air Pada Rumah Kaca Hidroponik Menggunakan Parameter Sensor Multivariabel Berbasis Web
No full textBudidaya Pertanian hidroponik dalam rumah kaca menjadi solusi inovatif untuk meningkatkan efisiensi pertumbuhan tanaman, karena petani hidroponik dapat melakukan kontrol lingkungan dalam rumah kaca tersebut. Salah satu faktor penting dalam sistem ini adalah sirkulasi air, yang mempengaruhi ketersediaan nutrisi dan oksigen bagi tanaman menggunakan sensor multivariable, dan diolah dengan metode fuzzy Tsukamoto. Melalui adanya sensor DHT 11 untuk mengukur suhu dan kelembapan udara didalam rumah kaca, sensor DS18B20 untuk mengukur suhu pada air serta sensor pH untuk mengukur tingkat keasaman pada air, dilakukan pengujian sebanyak sepuluh kali yang menghasilkan sepuluh kondisi berbeda. Saat sistem otomasi sirkulasi air bekerja selama 5 menit, kelembapan meningkat sebesar 7% serta pH turun sekitar 0,5. Sedangkan suhu dapat turun sekitar 1,7°C setelah sistem otomasi kipas bekerja selama 5 menit.Pertanian hidroponik yang dibudidayakan didalam rumah kaca menjadi solusi inovatif untuk meningkatkan efisiensi pertumbuhan tanaman, dikarenakan dalam sebuah sistem rumah kaca petani hidroponik dapat melakukan kontrol lingkungan dalam rumah kaca tersebut. Salah satu faktor penting dalam sistem ini adalah sirkulasi air, yang mempengaruhi ketersediaan nutrisi dan oksigen bagi tanaman. Dengan menggunakan sensor multivariabel maka sistem sirkulasi air otomatis dapat dibuat dan di monitor dengan apikasi berbasis web. Sistem ini menggunakan berbagai sensor, termasuk sensor untuk mengukur suhu dan kelembapan udara, sensor untuk mengukur suhu air dan sensor pH untuk memantau kondisi air dan lingkungan secara real-time. Dengan adanya integrasi sensor multivariabel dan pemantauan berbasis web, sistem ini memberikan kemudahan dalam pengelolaan pertanian hidroponik secara otomatis dan efisien
Analisis High Vibration Demin Make Up Pump di PLTGU Tanjung Uncang
No full textMasalah yang terjadi di PLTGU Tanjung Uncang adalah terjadi indikasi vibrasi tinggi di Demin Make Up Pump B sehingga dilakukan penelitian yang berfokus pada analisis penyebab vibrasi yang terjadi dan solusi untuk menanganinya. Metode penelitian yang digunakan adalah pengambilan data dilapangan dan analisis vibrasi menggunakan analisis fishbone dengan data acuan berdasarkan ISO 2372. Dari hasil pengukuran yang telah dilakukan ditemukan nilai vibrasi tinggi pada sisi Axial DE sebesar 5.5 mm/s dan Axial NDE sebesar 4.8 mm/s. Penyebab nilai vibrasi menjadi tinggi yaitu misalignment dan kerusakan rubber coupling. Setelah perbaikan selesai dilakukan pengukuran ulang ditemukan nilai vibrasi tertinggi hanya pada sisi Horizontal DE 1.4 mm/s dan di sisi Radial NDE 1.4 mm/s. Hal itu mengindikasikan bahwa Demin Make Pump dalam kondisi yang baik dan siap untuk di operasikan kembali.Masalah yang terjadi di PLTGU Tanjung Uncang adalah terjadi indikasi vibrasi tinggi di Demin Make Up Pump B sehingga dilakukan penelitian yang berfokus pada analisis penyebab vibrasi yang terjadi dan solusi untuk menanganginya. Metode penelitian yang digunakan adalah pengambilan data dilapangan dan analisis vibrasi berdasarkan ISO 2372. Dari hasil pengukuran yang telah dilakukan ditemukan nilai vibrasi tinggi pada sisi Axial DE sebesar 5.5 mm/s dan Axial NDE sebesar 4.8 mm/s. Hal itu mengindikasikan bahwa Demin Make Pump dalam kondisi yang baik dan siap untuk di operasikan kembali
Quality Analysis of the Registration Information System Website using ISO/IEC 9126 Standard
No full textThe performance of registration information systems is a crucial factor in ensuring the efficiency and effectiveness of academic administrative services. This study evaluates the quality of a registration information system based on the ISO 9126 standard, focusing on key aspects such as functionality, reliability, usability, efficiency, maintainability, and portability. The data collection methods used in this study vary based on each quality aspect. For the usability and maintainability aspects, data was collected through a questionnaire distributed to 100 respondents, consisting of students, prospective students, and academic staff. For the efficiency aspect, the GTMetrix tool was used to evaluate website performance. The reliability aspect was tested using the WAPT application. The functionality aspect was assessed using black-box testing with a total of 10 participants consisting of 2 prospective students, 5 students, and 3 administrative staff members, while portability was evaluated by accessing the website on five different mobile devices with varying screen sizes, operating systems, and types. The evaluation results indicate that the system performs well in functionality, usability, portability, reliability and maintainability but requires significant improvements in efficiency, particularly in LCP optimization. Based on these findings, optimization strategies such as image compression, CSS and JavaScript minification, and server-side caching implementation are recommended
Evaluating the Acceptance and Success of Mobile Banking Systems Using a Combination of UTAUT2 and Delone & McLean Models
No full textMobile Banking is a digital banking innovation designed to facilitate financial transactions, payments, and account management. However, ensuring that the application meets user expectations remains a challenge. Based on Playstore reviews, 30% of users reported various obstacles, particularly difficulty accessing the app, leading to transaction failures. This study aims to see what factors affect user satisfaction. The research employed the SemPLS method, chosen due to its ability to handle complex models with multiple latent variables and assess intricate relationships between constructs. SemPLS is particularly useful for exploratory research and allows analysis without strict assumptions regarding data distribution. Data were collected from 382 respondents, determined using the Lemeshow formula. Validity was tested using factor loading (≥0.7), while reliability was confirmed through Cronbach’s Alpha and Composite Reliability (CR) ≥0.7.The findings indicate that human factors significantly impact user satisfaction, contributing 43.6% base R-Square value. Key influencing factors include Price Value, Performance Expectancy, Effort Expectancy, Social Influence, Hedonic Motivation, Facilitating Conditions, Habits, and Behavioral Intentions. Among these, Effort Expectancy, which represents ease of use, plays a crucial role in user satisfaction.To improve user experience, it is recommended to enhance access speed by optimizing server performance, reduce transaction failures through system stability improvements, and integrate AI-driven customer support for real-time troubleshooting. Future research could explore the role of trust and security perceptions in increasing user satisfaction and loyalty. These findings emphasize the importance of considering human aspects in digital service development to create a seamless and efficient banking experience
Multiclass Sentiment Analysis of Electric Vehicle Incentive Policies Using IndoBERT and DeBERTa Algorithms
No full textThe electric vehicle (EV) incentive policy in Indonesia has generated various public reactions, particularly on social media platforms. This study aims to classify public sentiment using the IndoBERT and DeBERTa transformer models. A total of 6,758 comments were collected from YouTube, filtered, preprocessed, and labeled into three sentiment categories: positive, negative, and neutral. From this, 1,711 clean data points were used and analyzed in two phases: before and after applying the Random Oversampling technique to address class imbalance. Model performance was evaluated using accuracy, precision, recall, F1-score, and training time. In the initial phase, IndoBERT achieved 96% accuracy with 603.71 seconds of training time, while DeBERTa reached 93% in 439.19 seconds. After balancing and applying 5-Fold Cross Validation, IndoBERT maintained 96% accuracy with balanced metric distribution, while DeBERTa recorded 93% accuracy. IndoBERT performed better in recognizing neutral sentiment, whereas DeBERTa was more time-efficient. These results highlight the effectiveness of local transformer models and data balancing techniques in improving sentiment classification performance on imbalanced datasets.The electric vehicle (EV) incentive policy in Indonesia has generated various public reactions, particularly on social media platforms. This study aims to classify public sentiment using the IndoBERT and DeBERTa transformer models. A total of 6,758 comments were collected from YouTube, filtered, preprocessed, and labeled into three sentiment categories: positive, negative, and neutral. From this, 1,711 clean data points were used and analyzed in two phases: before and after applying the Random Oversampling technique to address class imbalance. Model performance was evaluated using accuracy, precision, recall, F1-score, and training time. In the initial phase, IndoBERT achieved 96% accuracy with 603.71 seconds of training time, while DeBERTa reached 93% in 439.19 seconds. After balancing and applying 5-Fold Cross Validation, IndoBERT maintained 96% accuracy with balanced metric distribution, while DeBERTa recorded 93% accuracy. IndoBERT performed better in recognizing neutral sentiment, whereas DeBERTa was more time-efficient. These results highlight the effectiveness of local transformer models and data balancing techniques in improving sentiment classification performance on imbalanced datasets
LSTM-Based Hand Gesture Recognition for Indonesian Sign Language System (SIBI) on Affix, Alphabet, Number, and Word
No full textSign language plays a critical role in enabling communication for the Deaf and hard-of-hearing community in Indonesia, yet there remains a significant gap in technological support for recognizing the official Indonesian sign language, Sistem Isyarat Bahasa Indonesia (SIBI). This study presents a deep learning-based hand gesture recognition system for SIBI, focusing on four primary gesture categories: affix, alphabet, number, and word. A large and diverse dataset of 21,351 videos was collected, covering 18 affix, 26 alphabet, 35 number, and 29 word classes. Hand keypoints were extracted using MediaPipe Holistic, and a bidirectional long short-term memory (BiLSTM) model was trained using 5-fold stratified cross-validation. The model achieved high recognition performance in the alphabet, number, and word categories, with mean test accuracies of 93.94%, 91.48%, and 92.41%, respectively, and slightly lower performance in the affix category at 68.17%. The affix category posed particular challenges due to subtle hand shape differences and high variability between signers, while the alphabet category consistently showed the highest accuracy due to its distinct and static handshapes. Evaluation metrics, including precision, recall, F1-score, and confusion matrix analysis, provided further insights into model strengths and limitations. Overall, the study demonstrates the effectiveness of LSTM models for sequential hand gesture recognition in SIBI and highlights areas for future improvement, such as handling non-manual features and improving generalization across signers.Sign language plays a critical role in enabling communication for the Deaf and hard-of-hearing community in Indonesia, yet there remains a significant gap in technological support for recognizing the official Indonesian sign language, Sistem Isyarat Bahasa Indonesia (SIBI). This study presents a deep learning-based hand gesture recognition system for SIBI, focusing on four primary gesture categories: affix, alphabet, number, and word. A large and diverse dataset of 21,351 videos was collected, covering 18 affix, 26 alphabet, 35 number, and 29 word classes. Hand keypoints were extracted using MediaPipe Holistic, and a bidirectional long short-term memory (BiLSTM) model was trained using 5-fold stratified cross-validation. The model achieved high recognition performance in the alphabet, number, and word categories, with mean test accuracies of 93.94%, 91.48%, and 92.41%, respectively, and slightly lower performance in the affix category at 68.17%. The affix category posed particular challenges due to subtle hand shape differences and high variability between signers, while the alphabet category consistently showed the highest accuracy due to its distinct and static handshapes. Evaluation metrics, including precision, recall, F1-score, and confusion matrix analysis, provided further insights into model strengths and limitations. Overall, the study demonstrates the effectiveness of LSTM models for sequential hand gesture recognition in SIBI and highlights areas for future improvement, such as handling non-manual features and improving generalization across signers
PENGARUH PROFITABILITAS DAN UKURAN PERUSAHAAN PADA NILAI PERUSAHAAN DENGAN KEPEMILIKAN MANAJERIAL SEBAGAI VARIABEL PEMODERASI
No full textThis research aims to obtain empirical evidence regarding the influence of profitability and company size on firm value and the role of managerial ownership in moderating this influence. The population of this research is property and real estate companies listed on the Indonesia Stock Exchange for the 2021-2023 period. The sampling technique used was purposive sampling technique and a sample of 102 observations was obtained. The data analysis technique used is Moderated Regression Analysis. The results of the analysis provide evidence that, 1) profitability has a positive effect on firm value, 2) company size has a negative effect on firm value, 3) managerial ownership does not moderate the effect of profitability on firm value, and 4) managerial ownership does not moderate the effect of company size on firm value.Penelitian ini bertujuan untuk memperoleh bukti empiris mengenai pengaruh profitabilitas dan ukuran perusahaan pada nilai perusahaan serta peran kepemilikan manajerial dalam memoderasi pengaruh tersebut. Populasi dari penelitian ini adalah perusahaan property dan real estate yang terdaftar di Bursa Efek Indonesia periode 2021-2023. Teknik pengambilan sampel yang digunakan adalah teknik purposive sampling dan diperoleh sampel sebanyak 102 amatan. Teknik analisis data yang digunakan adalah Moderated Regression Analysis. Hasil analisis memberikan bukti bahwa, 1) profitabilitas berpengaruh positif pada nilai perusahaan, 2) ukuran perusahaan berpengaruh negatif pada nilai perusahaan, 3) kepemilikan manajerial tidak memoderasi pengaruh profitabilitas pada nilai perusahaan, dan 4) kepemilikan manajerial tidak memoderasi pengaruh ukuran perusahaan pada nilai perusahaan