ComEngApp-Journal
Not a member yet
102 research outputs found
Sort by
Deep Learning for ECG-Based Arrhythmia Classification Based on Time-Domain Features
Full text linkArrhythmia is a disturbance in the electrical activity of the heart that can affect the rhythm and duration of the heartbeat. Early detection of arrhythmia is crucial to prevent more serious complications. Electrocardiogram (ECG) is an effective non-invasive diagnostic tool in detecting arrhythmia, but manual detection by experts takes time. To overcome this limitation, this research develops an arrhythmia classification system by utilizing deep learning. This study involves a series of stages, starting from pre-processing, feature extraction, and arrhythmia classification models using convolutional neural networks (CNN) and long short-term memory (LSTM). The results showed that feature extraction successfully improved model efficiency and accuracy. Evaluation of model performance using accuracy, recall, precision, specificity, and F1-score metrics showed that the LSTM model achieved 95% accuracy, 96% recall, 96% precision, 99% specificity, and 96% F1-score, outperforming the CNN model which achieved 91% accuracy, 90% recall, 89% precision, 98% specificity, and 89% F1-score. Thus, these results indicate that the LSTM model is superior in arrhythmia classification
Implementation of Weightless Neural Network in Embedded Face Recognition for Eye and Nose Pattern Mobile Identification
Full text linkThe pattern of the human face is a form of self-identity and also a form of originality for each individual. The development of facial recognition technology impacts its application in various computing devices, both in computer vision and on single-chip processors. One of the continuously developed implementations is in the form of robot vision by identifying facial features. This research aims to develop a facial recognition system focusing on the identification of the eye and nose areas. This research utilizes the Weightless Neural Network (WNN) method with the Immediate Scan technique. The combination of methods allows for rapid and accurate pattern recognition, even when the face changes position. The detection process is carried out using the Haar Cascade Classifier algorithm, which functions to recognize faces and divides the area into nine different zones to ensure accurate identification. The hardware implementation was carried out on a Raspberry Pi for face detection and facial pattern recognition, as well as the data processor for the robot vision sensor and actuator on the microcontroller. The results of the robot\u27s movement testing have worked well according to the calculation of GPS data values to determine the robot\u27s last position. Then, in the face pattern recognition process, it shows that the proposed method can achieve a maximum accuracy level of up to 98.87% in testing with the internal data set, while testing under different conditions experiences a slight decrease in accuracy to 91.38%. The highest similarity percentage to the faces of other individuals reached 75.69%, indicating that this method is quite adaptive to various facial variations. The execution time of the identification process ranges from 11 ms to 17 ms, depending on the amount of data compared during the scanning. This research is expected to serve as a foundation for further development in robotics systems and embedded system-based facial recognition
LinkedIn User Interface Optimization with Design Thinking Methods: Improve user experience and engagement
Full text linkLinkedIn is one of the world\u27s biggest social networking platforms, used to build connections, exploring career opportunities, and sharing professional insights. Users are increasingly prioritizing simple, effective, and user-friendly design, so improving LinkedIn\u27s user interface is exceptionally imperative. LinkedIn is often perceived as confusing by its users, with many stating that features within the application are difficult to find and navigation is inefficient. This problem can hinder LinkedIn\u27s effectiveness in meeting the professional needs of its users. This research aims to optimize the LinkedIn interface using a design thinking approach. The method involves five stages: empathize, define, ideate, prototype, and test. Design thinking prioritizes user needs, wants, and challenges. The advantage of the design thinking approach is that it becomes a solution, so what is produced is more relevant and effective in solving the real problems of the users. Data was collected through questionnaires to identify the key issues with navigation and ease of use of features on LinkedIn. The results show that the design thinking approach allows the creation of a simpler user interface with more effective navigation and features that are easy to find. The conclusion of this research is that the design thinking method is able to solve interface design problems in the LinkedIn application
TeleOTIVA: Advanced AI-Powered Automated Screening System for Early Detection of Precancerous Lesions
Full text linkIn 2023, the Indonesian Ministry of Health launched the Rencana Aksi Nasional (RAN) to enhance the detection and management of cervical cancer in Indonesia. One of the main pillars in this movement is the implementation of early screening for precancerous lesions aimed at identifying and treating these lesions before they develop into cervical cancer. This effort includes improving public access to healthcare services, providing education and awareness about the importance of early detection, and utilizing the latest technology in screening procedures. It is hoped that, through these targeted and effective interventions, the incidence of cervical cancer can be significantly reduced. This research aims to facilitate the early detection screening process for cervical precancerous lesions, particularly in difficult areas for medical experts to reach. This study also seeks to assist obstetricians and gynecologists in detecting precancerous lesions automatically, quickly, and accurately. By developing an advanced technology-based screening system, it is hoped that early detection of precancerous lesions can be carried out more efficiently, thereby increasing the chances of timely treatment and reducing the incidence of cervical cancer across various regions in Indonesia. This system is designed to provide reliable and user-friendly diagnostic support as it is developed on a mobile platform that can be accessed anytime and anywhere. This research developed a system for early screening called TeleOTIVA. The TeleOTIVA application system is an advanced platform that uses artificial intelligence (AI) based approaches to provide optimal services in early detection of precancerous lesions. This application is designed for mobile, allowing users to access and use its advanced features anytime and anywhere. With the integration of AI technology, TeleOTIVA can detect and analyze cervical precancerous lesions accurately and quickly to provide accurate and efficient screening results. The TeleOTIVA application system is capable of providing satisfactory detection results. The performance of the proposed model achieves accuracy, sensitivity, and specificity levels above 90%. With this high performance, TeleOTIVA ensures that the detection of precancerous lesions is carried out with high reliability and precision, instilling greater confidence in healthcare professionals and users during the screening and diagnosis process. The implementation of our application model offers numerous advantages over traditional methods. It significantly enhances efficiency by automating processes, reduces human error through rigorous error-checking mechanisms, and accelerates the processing of large datasets. These improvements streamline operations and ensure more reliable and rapid data analysis
Development of a Littering Behavior Detection Using 3D Convolutional Neural Networks (3D CNN)
Full text linkLittering has become a significant problem that negatively impacts public health and environmental cleanliness. This research introduces an innovative solution using 3D Convolutional Neural Networks (3D CNN) technology to automatically detect littering behavior through real-time CCTV recordings. Two models were developed and tested. Model 1, which employs Conv3D, Batch Normalization, and Dropout, showed high training accuracy but exhibited fluctuations in validation accuracy, indicating potential overfitting. In contrast, Model 2, designed with a simpler structure without Batch Normalization and Dropout, achieved higher classification accuracy and efficiency. Both models significantly contribute to addressing littering in public areas, increasing awareness, and supporting environmental law enforcement. The integration of 3D CNN technology in detecting littering behavior demonstrates its potential to reduce pollution and promote environmentally responsible behavior
IoT-Enabled Real-Time Monitoring and Loss-of-Life Estimation of Distribution Transformers
Full text linkA distribution transformer is required in power distribution networks to step down the voltage relevant and usable for consumers. Its failure not only disrupts electricity supply but also incurs high replacement costs, with broader economic implications. Ensuring reliable operation, therefore, requires accurate and continuous monitoring of its performance. This paper presents IoT-Enabled Real-Time Monitoring and Loss-of-Life Estimation of Distribution Transformers developed and tested on a 10 kVA, 0.415 kV prototype distribution transformer, connected to three residential loads. A dedicated data acquisition system was developed, which monitors key parameters: load current, phase voltage, transformer oil level, ambient temperature, and oil temperature in real time over 14 days. An algorithm was implemented to analyze daily load profiles and hotspot temperature data, which were then used to estimate transformer loss of life. The results show that transformer ageing is highly sensitive to load variation. During weekdays, the cumulative equivalent ageing reached 2.22 hours per day, corresponding to a daily loss of life of 0.00296%. On weekends, higher residential loads increased cumulative ageing to 4.79 hours, with a corresponding life loss of 0.0063%. A simulated one-hour peak load of 1.43 pu resulted in 25.75 hours of ageing, translating to a life loss of 0.034%, demonstrating the severe impact of overloads. These findings emphasize that peak load periods dominate insulation ageing and can substantially reduce service life if unchecked
Enhanced Short-Term Residential Load Forecasting Using K- means Clustering and Iterative Residual LSTM Networks
Full text linkAccurate short-term load forecasting (STLF) is essential for optimizing energy management systems, ensuring operational efficiency, and balancing supply and demand in power grids. This study introduces a hybrid model, K-RNLSTM, which integrates K-means clustering with iterative Residual Long Short-Term Memory (LSTM) networks to improve prediction accuracy. The K-means clustering algorithm categorizes similar load patterns, allowing the model to handle seasonal and hourly variations more effectively. Iterative ResBlocks are incorporated within the LSTM framework to capture complex non-linear dependencies and improve the learning process without suffering from degradation. The model was evaluated using real- world residential electricity consumption data across four seasons: winter, spring, summer, and autumn. The K-RNLSTM model consistently outperformed traditional methods such as Extreme Learning Machines (ELM), Seasonal-Trend Loess (STL), Gated Recurrent Units (GRU), and standard LSTM in terms of Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and Mean Absolute Percentage Error (MAPE). The results demonstrated that K-RNLSTM achieved an average RMSE of 0.71, MAE of 0.43, and MAPE of 1.31%, surpassing benchmark models across all seasonal variations. Furthermore, the integration of ResBlocks significantly improved the model\u27s ability to minimize large forecasting errors, particularly during peak demand periods. This research demonstrates the effectiveness of combining clustering techniques with deep learning models for short-term load forecasting, offering a robust solution for power system operators to optimize energy distribution and reduce operational costs
Efficient Hierarchical Temporal Audio-Video Cross-Attention Fusion Network For Audio-Enhanced Text-To-Video Retrieval
Full text linkWith video and audio being integral to modern multimedia content, accurately retrieving relevant segments based on textual queries is crucial for enhancing user experience and information accessibility. However, contextual misalignment across video segments presents significant challenges, particularly when different segments exhibit varying degrees of relevance to specific portions of a text query. To address this issue, a novel Hierarchical Temporal Audio-Video Cross-Attention Fusion Network has been developed. This model utilizes a Video Swim Feature Pyramid video encoder to enhance the extraction of multi-scale spatial features and capture intricate details within videos. Additionally, a Temporal RoBERTa Graph Network serves as the text encoder, enabling a deep understanding of relationships within the text and allowing for minute interpretations of queries that encompass multiple themes. To effectively align video and audio representations with textual queries, the model employs a Hierarchical multiscale spatial-temporal attention mechanism. Furthermore, an Audio Spectrogram Short-Term Memory Transformer is utilized to capture the temporal dynamics of complex audio streams. To refine audio-text alignment, the model incorporates a Threshold-Based audio-text Dynamic Time cross-attention block, which selectively filters irrelevant audio components and dynamically adjusts for temporal misalignments. The experimental results demonstrate that the proposed model significantly enhances retrieval accuracy by effectively aligning video and audio representations with textual queries, resolving multi-scene transitions, and isolating relevant audio cues among complex soundscapes.
 
Development of Finite State Machine Computational Model for Dynamic Difficulty in an Educational Platformer Video Game
Full text linkThis research aims to address the issue of static and unengaging educational history games for players with diverse skill levels. To this end, a 2D platformer game titled "Parahyangan" was developed, implementing a Dynamic Difficulty Adjustment (DDA) system based on a Finite State Machine (FSM), which allows the difficulty level to adapt to the player\u27s performance. Using the Game Development Life Cycle (GDLC) methodology, the game was designed and quantitatively tested through a User Acceptance Test (UAT) with 85 respondents. The analysis shows that the game was well-received, falling into the "Good" category with a total satisfaction score of 77.55%. The core DDA feature was proven to be functional and well-accepted by the players. The user interface was identified as a major strength, while level progression was noted as an area for improvement. It is concluded that the implementation of DDA using an FSM is an effective solution for creating a more personalized, engaging, and sustainable learning medium for history that maintains player involvement
Implementation of Feature Selection for Optimizing Voice Detection Based on Gender using Random Forest
Full text linkGender-based voice detection is one of the machine learning applications that has various benefits in technology and services, such as virtual assistants, human-machine interaction systems, and voice data analysis. However, the use of too many features, including irrelevant features, can cause a decrease in accuracy and model performance. This research aims to optimize voice-based gender detection by applying a feature selection method to select significant features based on their correlation value to the target. Experimental results show that by using only the significant features selected through correlation analysis, the accuracy of the model is significantly improved compared to using all available features. This research confirms the importance of feature optimization to support the development of more efficient and accurate gender-based speech detection models