ComEngApp-Journal
Not a member yet
102 research outputs found
Sort by
Application of Additive Manufacturing Technology in Custom Surgery and Orthopedic Implants through 3D Bioprinting: Rapid Review
Full text linkMusculoskeletal disorders, which are the leading cause of global disability, require better implant reconstruction solutions, given the limitations of conventional implants in terms of anatomical fit, stability, and stress shielding risk. The objective of this rapid review is to summarize the latest evidence on the application of Additive Manufacturing (AM), 3D Printing, and 3D Bioprinting technologies in the manufacture of custom orthopedic implants. The method used was a Rapid Review with the PRISMA framework, which involved searching 3,291 articles in the PubMed and ScienceDirect databases and filtering them down to 14 selected articles. The results show that the integration of 3D imaging, 3D printing, and Artificial Intelligence (AI) significantly improves visual-spatial understanding in orthopedic education, as well as improves implant placement accuracy (e.g., in THA), reduces operating time, blood loss, and radiation exposure through the use of AI-based 3D preoperative planning, custom models, and 3D-printed surgical guides. However, challenges remain in terms of cost, preoperative production time, and lack of long-term follow-up data. In conclusion, 3D and AI technologies have revolutionized orthopedic practice by improving accuracy, efficiency, and personalization of therapy, requiring large-scale research and long-term evaluation for sustainable clinical implementation
Detection of Ventricular Septal Defect in Pediatric Cardiac Ultrasound Videos Using Parasternal View and Faster R-CNN
Full text linkCongenital heart disease (CHD), particularly ventricular septal defect (VSD), remains a major contributor to pediatric morbidity, while echocardiographic diagnosis is highly dependent on operator expertise and image quality. This study examines the feasibility of an object-detection-based intelligent imaging framework for localizing VSD in pediatric cardiac ultrasound videos acquired from the parasternal long-axis view. Rather than proposing a novel detection algorithm, this work adopts a system-oriented approach by evaluating the Faster R-CNN framework under practical clinical constraints, including limited annotated data and heterogeneous ultrasound characteristics. Three convolutional neural network backbones such as ResNet50, ResNet101, and Inception-ResNet V2 are comparatively analyzed within a unified detection pipeline. Experimental results indicate that the ResNet101-based model achieves the highest localization performance at an intersection-over-union threshold of 0.5, while ResNet50 provides more consistent precision across stricter localization thresholds. Although false-positive detections are observed in acoustically challenging frames, the proposed framework maintains real-time feasibility at approximately 7–8 frames per second. The findings offer practical insights into accuracy–efficiency trade-offs and backbone selection for the development of clinically aware intelligent echocardiography systems, supporting the application of information and communication technology in pediatric cardiac imaging
Drift-Resilient IoT Energy Monitoring for Low-Cost Voltage and Current Sensors
Full text linkLow-cost voltage and current sensors such as the ZMPT101B and ACS712 are widely used in IoT-based energy monitoring due to their affordability and ease of integration. However, their outputs suffer from drift caused by thermal variation, material degradation, and electromagnetic interference, leading to cumulative errors that compromise load monitoring, forecasting, and anomaly detection. This work presents a drift-resilient framework that integrates lightweight filtering and regression-based calibration into a unified pipeline deployable on ESP32-class devices. Moving average and adaptive Kalman filters suppress noise and track drift trends, regression models align sensor outputs with reference standards, and spectrogram-based analysis detects transient drift events for adaptive correction. Experiments under realistic conditions show substantial improvements: voltage RMSE decreased by over 90% (3.45V to 0.30V), current RMSE by 92% (0.065A to 0.005A), and MAPE to below 0.5%. Signal-to-noise ratio improved by approximately 21dB, confirming significant restoration of measurement fidelity. Compared with data-intensive deep learning or AutoML frameworks, the proposed method offers a scalable, interpretable, and resource-efficient solution for long-term IoT energy monitoring. By bridging drift mitigation strategies with the practical constraints of low-cost sensors, this framework enhances the reliability of smart grid and IoT-based infrastructures
Air Quality Monitoring System based on the TI MSP430 Microcontroller Family
Full text linkAir quality monitoring devices are generally sensor circuits coupled with signal processing devices, where the output signal provides intelligible information to users. In this project report, a low-cost portable air quality monitoring device based on the TI MSP430G2553 microcontroller is described and designed. The device can monitor the air quality in one’s immediate environment and hence it gives individuals an idea of how clean or polluted the air in their surroundings is. A design is presented which applies basic gas sensing techniques and analog-to-digital conversion (ADC) principles to achieve the needed functionality. The device is built with off-the-shelf components, which are easy to comprehend and assemble. The device can detect the presence of ammonia (NH3), nitrogen oxides (NOx), benzene (C6H6), Carbon dioxide (CO2), smoke, and other hazardous gases and it is powered by a dc supply voltage ranging between +7V and +12V
Implementation of Color Matching in Ball Image Processing Using OpenCV
Full text linkThis research focuses on object detection through color matching, enabling machines to detect objects based on specific colors using OpenCV, a Python library widely used in computer vision projects. As a form of Machine Learning and Artificial Intelligence, this method allows machines to automatically learn and classify objects by simulating the human visual system. The study aims to enable a machine to detect and locate a ball through digital image processing using a webcam. The research method includes digital image processing, implementation on a Raspberry Pi, and testing on a robot, where logic is applied to guide the robot toward the ball by detecting its color. The outcome is an object detection system that identifies the ball’s position in two dimensions based on its specific color. In this case, the RGB code (164, 122, 0) and a minimum ball size of 10 radians were successfully implemented on the robot. However, the system has limitations under certain conditions. Future improvements will involve integrating TensorFlow for dataset processing and OpenCV for real-time object detection to achieve more accurate results.
Keywords: Artificial Intelligence, Color Matching, Computer Vision, OpenCV, Digital Image Processing. 
Emotion Classification in Indonesian Text Using IndoBERT
Full text linkMental health issues have become a challenge that affects many individuals around the world. A 2018 WHO report noted an increase in deaths by suicide, with a frequency of one case every 40 seconds. The Ipsos Global 2023 survey showed that 44% of respondents in 31 countries are concerned about mental health, while 30% identified stress as a major issue. In Indonesia, the mental health situation is also a serious concern. The 2022 I-NAMHS survey found that 34.9% of adolescents face mental health problems, but only 2.6% of them utilize counseling services. Emotion detection in text is challenging due to the absence of facial expressions or voice modulation. This study aims to classify emotions in Indonesian text using the IndoBERT model. The dataset used consists of 5079 tweets with five emotion labels: Angry, Fear, Joy, Love, and Sad. Parameter variations include the composition of training, validation, and test data split (80:10:10, 75:15:15, and 60:20:20), as well as the combination of learning rate (1e-2 to 1e-7) and batch size (8, 16, and 32). The model was trained for 25 epochs with the application of early stop and patience for 5 epochs. The experimental results showed that the composition of data split 80:10:10, learning rate 1e-6, and batch size 8 resulted in optimal classification. Although some experiments showed indications of overfitting, this research has important implications in the early detection of emotions and can help in mental health treatment efforts
Deep Neural Networks for Intelligent Voice Authentication Systems in Large-Scale Electronic Voting
Full text linkThe authentication of eligible voters is an area of concern that needs further exploration of the prospects of electronic voting systems. The integration of voice authentication in electronic voting systems for varying numbers of disabled and prospective voters should be secure, scalable and suitable in both federal and state elections. Machine learning (ML) is an evolving field of computing that presents prospects in electronic voting. Applying ML algorithms to electronic voting provides optimal solutions to a wide range of biometric authentication challenges. This paper presents the design of an effective voice classification algorithm from a narrower perspective that can be used in developing prototype electronic voting systems in large-scale voting scenarios, particularly for disabled voters. Applying the knowledge of deep neural networks, a three hidden layer network using a feed-forward architecture is designed for classifying voice data acquired from prospective voters. The proposed design is tested on two different datasets and is adapted to handle small and vast amounts of voters’ voice information. Results indicated average training and average validation accuracies of 92% and 97% respectively for both deep learning models for inclusivity and accountability of disabled voters in secure electronic voting systems
A Low-cost Antenna Tracking System Integrated with GPS for UAVs
Full text linkIn today’s world, unmanned aerial vehicles (UAVs) are increasingly incorporated into different sectors to perform different functions for both military and commercial applications. Depending on the pace of use, the environment affects the signal quality, transmission and reception ability between the UAV and its ground control station (GCS). To mitigate the poor communication and avoid the disruption of communication between the GCS and UAV, an antenna tracking system (ATS) can be used. This work aims to design a good performance ATS using a helical antenna, integrated with GPS. The helical antenna is controlled by proportional-integral-derivative (PID) controller. To improve accuracy and provide redundancy in case of system failure, GPS is integrated to the ATS. The PID controller provides stability of the system in varying system operational stages against internal and external disturbances.
 
Improving Low-Cost Single-Phase Inverter Performance using DRL-Based Control System: Experimental Validation
Full text linkThis paper presents the improvement of a low-cost, single-phase pure sine wave inverter controlled by a deep reinforcement learning (DRL) agent. The study addresses the challenge of lacking performance of low-cost inverter, which is primarily due to the stability requirements of conventional control strategies. A DRL- based control approach is proposed to enhance voltage and frequency stability while reducing the need for extensive manual tuning. The system is validated through both simulation and experimental verification in a microgrid islanded configuration. The results demonstrate that the DRL-based inverter effectively maintains 220 VRMS at 50 Hz, achieving a stable root mean square voltage of 219.8 V, and a total harmonic distortion (THD) below 8%. The use of DRL making it an attractive solution for renewable energy systems, off-grid applications, and rural electrification. This study highlights the feasibility of DRL in power electronics and suggests that further optimization of training generalization and computational efficiency could enhance real-time and grid-tied deployment. The findings contribute to the advancement of intelligent inverter control, offering an alternative for next-generation microgrid and distributed energy systems
Implementation Of The Eco Cycle Classifier Deep Neural Network (EECDN-Net) Model For Image-Based Waste Classification
Full text linkWaste management is a global challenge that demands effective solutions, especially in classification and recycling processes. This study presents the development of an Eco Cycle Classifier Deep Neural Network (ECCDN-Net) model based on deep learning for image-based waste classification. The model integrates the DenseNet201 and ResNet18 architectures to improve visual feature extraction and reduce the vanishing gradient problem. The dataset used is TrashNet, which contains 2,527 images across six waste categories. Training was conducted over 50 epochs, utilizing data augmentation and class balancing to address the imbalanced data. Results show that ECCDN-Net achieved a validation accuracy of 87.75% and an average F1-score of 0.88. The confusion matrix reveals that the model performs well in recognizing most classes, although it faces difficulty distinguishing categories with high visual similarity, such as plastic and glass. This research demonstrates that ECCDN-Net effectively provides accurate waste classification and could serve as a promising solution for more adaptive and sustainable automatic waste sorting