Publication Search

The increasing volume of online hotel reviews provides valuable insights into customer perceptions but poses challenges for manual analysis due to its unstructured nature. This study aims to compare the performance of Recurrent Neural Network (RNN) and Bidirectional Encoder Representations from Transformers (BERT) in hotel review sentiment analysis. A total of 20,491 TripAdvisor hotel reviews were classified into three sentiment categories: negative, neutral, and positive. The research methodology includes text preprocessing, stratified data splitting, class imbalance handling using Random Over-Sampling, tokenization, and supervised model training. Model performance was evaluated using a confusion matrix and classification metrics. The results indicate that BERT outperforms RNN, achieving an accuracy of 80.54%, while RNN reached 62.21%. BERT demonstrated superior capability in capturing contextual and semantic information in hotel reviews. These findings suggest that transformer-based models are more effective for sentiment analysis of complex textual data in the hospitality domain and can support data-driven service improvement strategies.    

This study conducts sentiment analysis of Indonesian user reviews of the CapCut application using IndoBERT and compares two evaluation schemes: a single 80/20 train–test split and stratified 5-fold cross-validation (k=5). A total of 1,048,575 reviews were collected from the Google Play Store through web scraping and labeled into three sentiment classes based on rating: negative (1–2), neutral (3), and positive (4–5). After preprocessing—cleaning, case folding, banned-word removal, normalization—and duplicate removal, 517,962 reviews were retained. IndoBERT Base P1 was fine-tuned using fixed hyperparameters (batch size 32, learning rate 2e-5, up to 4 epochs, early stopping patience 2), while undersampling was applied to the training set to address class imbalance. Performance was assessed using accuracy, precision, recall, F1-score, and ROC-AUC, supported by confusion matrix and ROC-curve visualizations. The single split achieved an accuracy of 0.756, whereas cross-validation produced a mean accuracy of 0.740. Across both schemes, the positive class achieved the best performance (F1-score 0.850; ROC-AUC 0.918–0.919), while the neutral class remained the most challenging (precision 0.198–0.206; F1-score 0.280–0.283). Overall, cross-validation is recommended for reporting because it reduces dependence on a single partition and provides a more representative estimate across multiple splits.

: The rapid expansion of cybersecurity standards and threat intelligence frameworks has led to significant semantic fragmentation among security terminologies, hindering effective information retrieval and interoperability across systems. Traditional keyword-based search approaches are inadequate for capturing the contextual meaning of security terms, particularly within formal frameworks such as NIST, MITRE ATT&CK, and CWE. This study addresses this challenge by proposing CyberBERT, a transformer-based semantic search framework designed to align cybersecurity terminologies through deep contextual representation and ontology-driven reasoning. Research Objectives: The primary objective of this research is to develop a semantic retrieval model capable of understanding conceptual relationships between security terms beyond lexical similarity. Methodology: The proposed methodology fine-tunes a BERT-based model on the NIST Glossary corpus using a combination of masked language modeling and triplet loss objectives to generate discriminative semantic embeddings. These embeddings are further aligned with cybersecurity ontologies, including MITRE ATT&CK and CWE, to enhance semantic consistency and explainability. Semantic retrieval is performed using cosine similarity within a 768-dimensional embedding space and evaluated using Mean Reciprocal Rank (MRR) and Precision@K metrics. Results: Experimental results demonstrate that CyberBERT achieves an MRR of 0.832, outperforming domain-adapted baselines such as SecureBERT and CyBERT. The integration of ontology alignment improves semantic accuracy by over 6%, while robustness evaluations confirm resilience against adversarial linguistic perturbations. Visualization using t-SNE reveals coherent semantic clustering aligned with the five core NIST Cybersecurity Framework functions. Conclusions: In conclusion, CyberBERT effectively bridges semantic gaps across cybersecurity terminologies by combining transformer-based contextual learning with ontological reasoning. The framework offers a robust, interpretable, and scalable solution for semantic search, supporting improved interoperability and knowledge discovery in cybersecurity operations and standards harmonization.

Abstract: The rapid diffusion of Generative Artificial Intelligence (AI) has intensified public debate regarding its benefits, risks, and societal implications. This study investigates public sentiment and thematic structures surrounding Generative AI by analyzing Twitter discourse as a representation of large-scale, real-time public perception. The research addresses two main problems: how public sentiment toward Generative AI is distributed and what dominant themes shape this perception. Accordingly, the objective is to map both emotional polarity and thematic narratives embedded in social media conversations. A computational mixed-methods approach was employed using a dataset of 12,470 tweets collected on 17 December 2024. Sentiment classification was conducted using a transformer-based DistilBERT model, while semantic representations were generated with Sentence-BERT. Topic modeling was performed using BERTopic, integrating HDBSCAN clustering and class-based TF-IDF to extract coherent and interpretable topics. Human-in-the-loop validation supported the interpretive robustness of topic labeling. The findings reveal that public sentiment toward Generative AI is predominantly positive (41.8%), particularly in relation to productivity enhancement, education, and creative applications. Neutral sentiment (31.4%) reflects informational discourse, while negative sentiment (26.8%) centers on ethical concerns, privacy risks, misinformation, and AI hallucinations. Seven dominant topics were identified, with clear topic–sentiment alignment showing optimism in utility-driven themes and skepticism in ethics- and risk-related discussions. In conclusion, public perception of Generative AI is dualistic—characterized by strong enthusiasm alongside persistent caution. These results provide empirical insights for AI governance, responsible innovation, and future research on socio-technical impacts of Generative AI. *    

Polusi udara partikulat halus (PM2,5) merupakan ancaman serius bagi kesehatan masyarakat di Kabupaten Brebes, Jawa Tengah. Faktor penyumbang utamanya adalah emisi kendaraan di jalur Pantura, aktivitas industri perikanan, serta konsentrasi tinggi selama musim kemarau (Juni–November). Tidak adanya model peramalan sub-jam yang akurat menghambat pengembangan sistem peringatan dini yang efektif. Penelitian ini mengembangkan dan mengevaluasi model deep learning berbasis Transformer untuk memprediksi konsentrasi PM2,5 dengan resolusi waktu 15 menit. Data yang digunakan berasal dari NASA GEOS-CF (band PM25_RH35_GCC) yang diakses melalui Google Earth Engine menggunakan API Python. Dataset mencakup periode 1 Januari hingga 22 November 2025, menghasilkan 7.813 observasi per jam, yang kemudian diinterpolasi linear menjadi 31.249 titik data dengan resolusi 15 menit. Arsitektur Transformer terdiri dari 3 lapis enkoder, 4 kepala perhatian multi-head, dimensi embedding 128, dimensi feed-forward 256, panjang sekuen 60 timestep, dan augmentasi fitur menggunakan rerata bergulir (*rolling mean*, jendela = 3) dan beda pertama (*first difference*). Pelatihan dilakukan dengan TensorFlow-Keras, pengoptimal Adam, penjadwal peluruhan kosinus (*cosine decay scheduler*), dan fungsi kerugian Huber. Pembagian data dilakukan secara kronologis: 70% pelatihan, 30% validasi. Evaluasi pada set uji independen (16 Agustus–21 November 2025, 9.357 observasi atau 97 hari 11 jam 15 menit) menghasilkan MAE 0,7691 µg/m³, RMSE 1,2052 µg/m³, R² 0,9945, dan *Explained Variance Score* 0,9948. Model ini mampu menggambarkan variasi diurnal dan anomali musiman secara akurat, jauh melampaui model LSTM dan GTWR konvensional. Penelitian ini memberikan kontribusi signifikan di bidang Teknologi Informasi melalui kerangka kerja pengolahan *big data* satelit untuk aplikasi lingkungan.

This study conceptually examines a self-supervised multi-scale fusion framework designed to enhance accuracy and computational efficiency in medical image segmentation, a domain where data scarcity and annotation cost remain major challenges. Traditional supervised approaches are constrained by their reliance on extensive labeled datasets, limiting applicability in real-world clinical environments. Self-supervised learning (SSL) mitigates this issue by extracting supervisory signals directly from unlabeled data, enabling the model to learn rich feature representations without human annotation. Simultaneously, multi-scale fusion architectures integrate global contextual information with fine-grained local features, supporting robust segmentation across varying anatomical structures and image resolutions. Through a qualitative methodology involving library research and content analysis, this study synthesizes state-of-the-art SSL-driven segmentation techniques and highlights how adaptive multi-scale fusion mechanisms address limitations of existing convolutional and transformer-based architectures. The analysis indicates that combining SSL and multi-scale strategies leads to more generalizable, scalable, and computationally efficient segmentation pipelines suitable for diverse medical imaging modalities. The proposed framework represents a promising direction for developing next-generation diagnostic tools capable of handling sparse labels, complex textures, and real-time deployment constraints.

Power transformer theft, a pervasive issue disrupting critical infrastructure, necessitates the development of cost-effective and energy-autonomous security solutions. This paper presents the design and implementation of a detection-focused anti-theft framework that integrates a Raspberry Pi Zero W, camera module, and passive infrared (PIR) motion sensors powered by a solar system for continuous monitoring. The system is designed for remote, off-grid deployment, utilizing a headless Raspberry Pi powered by a 5V solar panel and power bank to ensure energy autonomy. Upon motion detection, captured images are processed on the edge device using OpenCV’s Haar Cascade classifier, optimized for upper-body detection to minimize false positives and verify human presence. Captured images are processed locally on the edge device using OpenCV’s Haar Cascade classifier to confirm human presence before an alert is sent to the mobile application, emphasizing real-time operation and low latency. Once an intrusion is confirmed, the images are saved locally and uploaded via the Secure File Transfer Protocol to a custom-developed Android application. The app provides a dedicated remote monitoring interface, enabling secure file transfer and system access, while providing users with immediate notifications and image management capabilities. The system emphasizes low power consumption, real-time operation, and low deployment cost. Tests over 200 triggered events under varied environmental conditions achieved 90% detection accuracy with an average latency of 4.5 s. Solar autonomy was maintained for approximately 24 h under normal operation. It is concluded that the integration of solar power, edge computing of images, and mobile monitoring provides a feasible, scalable, and financially viable framework for securing transformers, especially in resource-constrained environments.

Power transformers are crucial in the electrical distribution system, and their operational stability is significantly affected by load imbalance among phases. Load imbalance can lead to the flow of neutral current through the neutral conductor, causing additional power losses in the transformer. This study analyzes the impact of load imbalance on neutral current and power losses at Transformer 1 (30 MVA capacity, 70/20 kV) at the Bungaran Substation. Data such as phase current, neutral current, and power losses were measured at 12:00 and 21:00. At 12:00, the transformer’s full-load current was 839.17 A with a loading of 28.44% and a load imbalance of 0.74%, resulting in a neutral current of 4.36 A (1.83% of load current). The power loss due to neutral current was 12.64 W (4.36×10-5 %), and the loss due to neutral current flowing to the ground was 760 W (2.62×10-3 %). At 21:00, the full-load current decreased to 834.46 A, with a loading of 29.36% and a higher load imbalance of 1.36%. This caused a neutral current of 7.94 A (3.24%), with a power loss of 41.90 W (1.43×10-4 %) and a ground power loss of 2.52 W (8.60×10-3 %). The power losses were minimal compared to the transformer’s capacity, having little effect on system efficiency. However, maintaining load balance is essential for system efficiency and transformer longevity.

This study presents a Systematic Literature Review on Artificial Intelligence (AI) and Natural Language Processing (NLP) applications for customer support automation and digital service optimization. The review follows the PRISMA framework to ensure methodological rigor and transparency, focusing on literature published between 2020 and 2025 from the Scopus database. The findings reveal that AI-driven technologies, including Machine Learning, Deep Learning, and Large Language Models, have significantly improved efficiency, response time, and customer satisfaction in customer support and digital service. Common NLP applications include sentiment analysis, ticket classification, and automated response generation. Among these, hybrid and transformer-based models demonstrate superior accuracy and contextual understanding compared to traditional algorithms. However, several challenges persist, including data quality limitations, privacy and security concerns, algorithmic bias, and linguistic ambiguities such as sarcasm and negation. Moreover, issues related to trust and ethical adoption continue to influence user acceptance of AI systems. This review provides a comprehensive synthesis of current methodologies, trends, and research gaps, offering insights for future studies to develop explainable, secure, and human-centered AI systems that enhance the sustainability and transparency of digital customer support services.

This community service program was carried out with the aim of enhancing teachers’ competencies in utilizing Artificial Intelligence technology, particularly the Generative Pre-trained Transformer (GPT), as a tool for developing digital teaching materials. The background of this activity stems from the limited understanding of teachers in applying AI technology to support 21 st-century learning. The implementation method involved intensive training that included an introduction to GPT concepts, hands-on practice in creating digital modules, designing evaluation questions, and simulating the use of teaching materials in the classroom. The activity was attended by several teachers from SMP Zawiyyah Darussalami, who demonstrated high enthusiasm throughout the sessions. Evaluation through pre-test and post-test results showed a significant improvement in teachers’ understanding and skills in using GPT. Thus, this community service activity successfully provided a positive impact by improving teachers’ competencies and opening opportunities for GPT utilization as an innovation in digital learning within schools.

Kreo Village, located in Larangan District, Tangerang Regency, still relies heavily on very traditional communication methods in daily life. While this approach reflects local wisdom and strong cultural values, the changing times demand a digital transformation, especially in the field of communication. With the rapid advancement of digital technology and the growing quality of human resources in the village, the need for a more modern communication system is becoming increasingly important. One potential solution is the use of artificial intelligence technology such as ChatGPT. ChatGPT (Generative Pre-trained Transformer) is a language model based on AI developed by OpenAI. This technology can understand and generate natural language interactively, similar to human conversation. By integrating ChatGPT into community communication activities, Kreo Village can speed up access to information, facilitate the exchange of ideas and opinions, and bridge the existing digital gap. In addition, ChatGPT can also be used as an educational tool to help residents understand digital technology, support learning activities, and strengthen community participation in village development. Through this initiative, Kreo Village can move toward becoming a more inclusive, adaptive, and competitive digital village in the modern era.

Amyotrophic Lateral Sclerosis (ALS) is a progressive neurodegenerative disorder that presents significant diagnostic challenges due to its heterogeneous clinical manifestations and symptom overlap with other neurological conditions. Early and accurate diagnosis is critical for initiating timely interventions and improving patient outcomes. Traditional diagnostic approaches rely heavily on clinical expertise and manual interpretation of neuroimaging data, such as structural MRI, Diffusion Tensor Imaging (DTI), and functional MRI (fMRI), which are inherently time-consuming and prone to interobserver variability. Recent advances in Artificial Intelligence (AI) and Deep Learning (DL) have demonstrated potential for automating neuroimaging analysis, yet existing models often suffer from limited generalizability across modalities and datasets. To address these limitations, we propose a Transformer-augmented deep learning ensemble framework for automated ALS diagnosis using multi-modal neuroimaging data. The proposed architecture integrates Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and Vision Transformers (ViTs) to leverage the complementary strengths of spatial, temporal, and global contextual feature representations. An adaptive weighting-based fusion mechanism dynamically integrates modality-specific outputs, enhancing the robustness and reliability of the final diagnosis. Comprehensive preprocessing steps, including intensity normalization, motion correction, and modality-specific data augmentation, are employed to ensure cross-modality consistency. Evaluation using 5-fold cross-validation on a curated multi-modal ALS neuroimaging dataset demon-strates the superior performance of the proposed model, achieving a mean classification accuracy of 94.5% ± 0.7%, precision of 93.9% ± 0.8%, recall of 92.9% ± 0.9%, F1-score of 93.4% ± 0.7%, spec-ificity of 97.4% ± 0.6%, and AUC-ROC of 0.968 ± 0.004. These results significantly outperform baseline CNN models and highlight the potential of transformer-augmented ensembles in complex neurodiagnostic applications. This framework offers a promising tool for clinicians, supporting early and precise ALS detection and enabling more personalized and effective patient management strategies.

An electrostimulator is a medical device designed to deliver controlled electrical stimulation to nerves and muscles, supporting rehabilitation and therapy for patients with neuromuscular disorders. This study focuses on designing and developing a portable electrostimulator that offers three distinct waveform modes: continuous wave, discontinuous wave, and dense-disperse wave, providing versatility for different therapeutic needs. The device is powered and controlled by an Arduino Mega 2560 microcontroller, coupled with a Nextion touchscreen LCD interface that allows users to adjust waveform type, frequency, and stimulation intensity with ease. Waveforms are generated through an NE555 IC circuit, with amplitude adjusted via a potentiometer and subsequently amplified using a step-up transformer to achieve therapeutic voltage levels. Functionality and performance tests were conducted using an oscilloscope, and the device was benchmarked against a commercial KWD-808 electrostimulator. Results demonstrate that the developed electrostimulator reliably produces the intended waveforms, achieving peak voltages up to 32V and frequencies ranging from 33.3 Hz to 66.6 Hz, confirming its effectiveness and feasibility for non-clinical nerve and muscle therapy applications.

This study aims to analyze the operational condition of the distribution transformer at substation PY094, PLN ULP Pringgabaya, with a primary focus on identifying and calculating the level of load imbalance on the consumer side. Data were collected through direct measurements of electrical parameters, including voltage and current in each phase, followed by a detailed analysis of energy losses. The measurement results indicated a significant load imbalance. In Feeder B, the average phase currents were recorded at 103.8 A for phase R, 130.2 A for phase S, and 90.4 A for phase T. Meanwhile, in Feeder D, the average phase currents were 47.4 A for phase R, 18 A for phase S, and 20.4 A for phase T. This imbalance caused notable power losses in the distribution system, with an estimated daily energy loss of 28.94 kWh, assuming the system operates 12 hours per day. To address this issue, load balancing simulations were carried out using ETAP software. The simulation involved redistributing load values across each phase in the two main feeders. Feeder B was simulated at 46.82% of the transformer’s full capacity, while Feeder D was simulated at 12.38% of the total 160 kVA capacity. The simulation results demonstrated that redistributing the load significantly reduced the current imbalance, thereby minimizing power losses and improving the operational efficiency of the distribution substation. Therefore, load balancing strategies are essential for enhancing energy efficiency and ensuring the reliability of electricity supply in distribution networks.

This study aims to analyze the effect of transformer oil purification on oil breakdown voltage and evaluate its benefits in maintaining transformer performance and reliability. Oil purification is a crucial preventive maintenance step to preserve insulation quality and prevent operational failures caused by reduced dielectric properties. The study was conducted through several stages, including data collection, oil purification, measurement of breakdown voltage before and after purification, and evaluation of results. Data collection involved measuring the oil’s electrical properties according to SPLN 49-1:1982 and observing results using a Break Down Voltage (BDV) test. Purification of a Trafindo 400 kVA transformer was performed through visual inspection, connecting the inlet and outlet hoses to the purification machine, and circulating the oil until the breakdown voltage met the required standards. Results indicated that the oil breakdown voltage before purification was below standard due to reduced insulation quality caused by water contamination, charcoal particles, thermal degradation, and dissolved gases that weakened dielectric properties. Additional factors such as electrical stress, mechanical stress, and excessive loading also contributed to insulation deterioration. After purification, the oil breakdown voltage increased significantly to meet the standard of >30 kV/2.5 mm, demonstrating that purification effectively restores the oil’s insulating capacity and supports optimal transformer performance. Analysis confirms that the transformer oil remains suitable for use, and routine annual purification is recommended to maintain reliability, efficiency, and operational performance. This study highlights oil purification as an effective preventive measure for transformer stability, extending operational life, and reducing the risk of insulation failure. The findings provide valuable guidance for transformer maintenance in the electricity industry, ensuring safe and optimal long-term operation.

Chat Generative Pretrained Transformer (ChatGPT) has rapidly gained popularity and is increasingly utilized across various fields, including education, where it plays a significant role as a supporting tool for academic tasks. In the educational context, ChatGPT can assist students in preparing and completing a wide range of assignments, providing quick access to structured information and alternative perspectives. This study was designed to explore the views of both students and lecturers on the integration of ChatGPT in academic activities, specifically as a support system for handling student assignments. Employing a descriptive qualitative approach, data were collected through interviews with 5 students and 6 lecturers from the Business Education Study Program at the State University of Surabaya. The findings reveal contrasting yet complementary perspectives. From the students’ point of view, ChatGPT offers considerable benefits, particularly in enhancing independence, efficiency, and time management when working on lecture assignments. However, these advantages are accompanied by drawbacks, such as decreased creativity, reduced critical thinking, and diminished interest in consulting traditional learning resources like books. On the other hand, lecturers acknowledge the usefulness of ChatGPT in simplifying student work and accelerating the completion of assignments but express concerns regarding the overreliance on artificial intelligence, which could potentially hinder the development of essential academic skills. Overall, the research suggests that while ChatGPT presents valuable opportunities to enhance learning processes, it must be applied thoughtfully, with careful guidance from educators to balance efficiency with the cultivation of creativity, critical thinking, and academic integrity.

Understanding electric motors and transformers is crucial in the field of electrical power engineering education. To enhance practical learning, a trainer was designed for single-phase AC motors, incorporating an Earth Leakage Circuit Breaker (ELCB) safety system to prevent electric current leakage, which could pose a risk during experiments. The aim of this research is to design and develop a trainer module that serves as both an interactive and safe learning tool for laboratory practicums. The trainer is equipped with a safety circuit, along with controllers such as a voltmeter, ammeter, selector switch, pushbutton, relay, and potentiometer, allowing students to understand and control various electrical parameters. The tool underwent voltage measurements and functional tests at three distinct measurement points to evaluate its performance and safety features. The results demonstrated that the trainer performed effectively, significantly enhancing students' practical understanding of electric power systems and contributing to better hands-on learning experiences in electrical engineering.

Information technology refers to any technology that assists human needs. Advances in computing and information technology significantly impact education through the use of computer networks and the internet. Artificial Intelligence (AI) is one of the most beneficial applications across various fields, including healthcare, industry, governance, and particularly in education, as exemplified by ChatGPT (Chat Generative Pre-Trained Transformer). This study focuses on the accuracy of ChatGPT in analyzing learning materials for Buddhist Religious Education. It not only examines the technological accuracy but also explores its potential as an effective learning tool in formal educational settings. The method employed is a literature review, aiming to investigate the accuracy of ChatGPT in educational contexts. This research seeks to evaluate ChatGPT's capability to analyze materials and provide precise answers. However, as ChatGPT continues to evolve, there is a risk of increasing student dependency on its use. Despite its advantages, ChatGPT also has limitations, such as its reliance on available data.  

The Sundanese language, once spoken by 48 million individuals, has experienced a significant decline in speakers, losing 2 million in the past decade. This decline is attributed to weakened intergenerational transmission and the dominance of more widely used languages. The challenges in developing Natural Language Processing (NLP) tools for Sundanese stem from the lack of annotated corpora, trained language models, and adequate processing tools, complicating efforts to preserve and enhance the language's usability. This research aims to address these challenges by implementing emotion classification in Sundanese text using Long Short-Term Memory (LSTM) and Bidirectional Encoder Representations from Transformers (BERT) models. The study utilizes a dataset of annotated Sundanese tweets, applying preprocessing techniques such as cleansing, stopword removal, stemming, and tokenization to prepare the data for analysis. The results indicate that the BERT model significantly outperforms the LSTM model, achieving an accuracy of approximately 80% compared to LSTM's 70%. These findings highlight the potential of advanced NLP techniques in enhancing the understanding of emotional nuances in Sundanese communication and contribute to the revitalization of the language in the digital age.