Association for Scientic Computing Electronics and Engineering (ASCEE): Open Journal Systems
Not a member yet
785 research outputs found
Sort by
Person and Activity Recognition Based on Joint Motion Features Using Deep Learning with Drone Camera
Full text linkThe increasing demand for drone-based surveillance systems has raised significant concerns about advancements in person and activity recognition based on joint motion features within visual monitoring frameworks. This study contributes to developing deep learning models that improve surveillance systems by using RGB video data recorded by drone cameras. In this study, a framework for person and activity recognition based on 120 datasets is proposed, from drone camera-recorded videos of 10 subjects, each performing six movements: walking, running, jogging, boxing, waving, and clapping. Joint motion features, including joint positions and joint angles, were extracted and processed as one-dimensional series data. The 1D-CNN, LeNet, AlexNet, and AlexNet-LSTM architectures were developed and evaluated for classification tasks. Evaluation results show that AlexNet-LSTM outperformed the other models in person recognition, achieving a classification accuracy of 0.8544, a precision of 0.9161, a recall of 0.8575, and an F1-score of 0.8332, while AlexNet delivered superior performance in activity recognition with an accuracy of 0.8571, a precision of 0.8442, a recall of 0.8599, and an F1-score of 0.8463. The relatively small dataset size used likely favors simpler architectures like AlexNet. These findings highlight the effectiveness of joint motion features for person identification and emphasize the suitability of simpler classifier architectures for activity classification when working with small datasets
Optimization of a Robust Sigmoid PID Controller for Automatic Voltage Regulation Using the Nonlinear Sine-Cosine Algorithm with Amplifier Feedback Dynamic Weighted (AFDW) System
Full text linkThe given paper presents a robust Sigmoid-based Proportional-Integral-Derivative (SPID) controller for Automatic Voltage Regulator (AVR) systems, optimized using the Nonlinear Sine Cosine Algorithm (NSCA) enhanced with the Amplifier Feedback Dynamic Weighted (AFDW) system. Conventional PID controllers are frequently struggling with parameter variations and external interruptions that lead to instability and reduced performances in AVR systems. The proposed SPID controller overcomes these limitations by incorporating nonlinear sigmoid functions, improving the AVR system's robustness and dynamic response. While the AFDW system improves stability and responsiveness by dynamically adjusting the feedback weight, the NSCA balances exploration and exploitation to optimize controller parameters. The primary contribution of the present research is an overview of the NSCA-SPID controller, which offers superior results in voltage regulation compared to traditional PID and other metaheuristic-tuned controllers, enhancement in settling time, elimination of overshoot, and improvement in steady-state error. Additionally, performance index and statistical performances are used to validate the proposed SPID controller. Simulation results demonstrate significant achievements that emphasize the effectiveness of the NSCA-SPID controller toward enhancing the AVR system stability and controller design’s performance under varying load conditions. Finally, the proposed NSCA-SPID controller provides a promising solution for Enhancing the regulation of voltage in power systems, providing Superior and efficient technique for practical applications
Comic-film-music of “pendekar cyborg”: a case study of transmedia storytelling in Indonesian contemporary independent comics
No full textThis study explores independently published comics in Indonesia after 2010, which show differences from independent comics in the late 1990s and early 2000s. Contemporary independent comics distinguish themselves by positioning readers as patrons and the application of transmedia storytelling across platforms, especially related to film and music, and not for industrial purposes. The research questions presented are: what are transmedia storytelling practices in contemporary independent comics in Indonesia, and how is the context of creative freedom and control that underlies the production of printed comics presented through cross-media platforms? Using qualitative methodology, this study applies descriptive discourse analysis based on the visual culture framework, following Gillian Rose's methodological approach. The descriptive analysis focuses on the case study of transmedia storytelling "Pendekar Cyborg", an independently published comic series, which intersects with other media such as motion comics, animated music videos, film, and music. The findings show that contemporary Indonesian independent comics engage in canonical transmedia storytelling, in dimensions of spreadability, continuity, and multiplicity, while still reflecting the socio-political context. The work “Pendekar Cyborg” affirms creative freedom within an independent artistic community and expands narrative experiences through innovative, creator-driven transmedia strategies with community support. This research contributes to understanding how independent visual storytelling in Indonesia embraces transmedia formats to negotiate cultural meaning and audience engagement
Differentiated Learning in IPAS Subject to Enhance Fourth-Grade Critical Thinking
No full textThis study employs a qualitative research method and was conducted at SD Muhammadiyah Karangkajen Yogyakarta, utilizing data sources that include the IPAS teacher for grade IV. Data collection techniques encompassed observation, interviews, and documentation. The validity of the data was ensured through source and technique triangulation. Data analysis followed the Miled and Huberman model, involving the stages of data collection, data reduction, data presentation, and conclusion drawing. The results of the study indicate that that the implementation of differentiated instruction to support critical thinking in fourth-grade students at SD Muhammadiyah Karangkajen Yogyakarta in the IPAS subject involves differentiated processes. The differentiation process encompasses a series of activities in learning, including thought- provoking questions, material delivery, active and enjoyable learning approaches, completion of Student Worksheets (LKPD), presentations, and evaluations. In this context, various aspects that support students' critical thinking abilities, such as interpretation, analysis, self-regulation, inference, explanation, and evaluation, can be observed in a conducive and enjoyable learning environment for the students
TikTok and the transformation of social interaction
Full text linkThis research aims to investigate how TikTok, as a dominant social media platform among Generation Z, influences the transformation of social interaction in a digital context. Utilizing a quantitative approach supported by simulated survey data, this study explores the extent to which TikTok affects communication patterns, perceived changes in social behavior, and levels of social satisfaction. A total of 100 simulated responses from individuals aged 18 to 26 were analyzed using a structured questionnaire designed to capture the frequency of TikTok interaction, behavioral shifts in social engagement, and emotional outcomes related to online connectivity. The findings indicate a generally high level of platform engagement, with moderate indications of behavioral transformation and perceived digital fulfillment. Although the correlation between variables was weak in the simulated data, the study offers a nuanced understanding of how short-form video platforms like TikTok shape interpersonal dynamics, self-expression, and community belonging among young users. The primary contribution of this research lies in its early attempt to quantify the psychosocial effects of TikTok on Gen Z’s digital interactions through a structured, data-informed lens. By mapping the intersection of media consumption, behavioral change, and emotional gratification in a simulated environment, this study lays the groundwork for future empirical investigations and theoretical refinements in the field of digital media studies. It also adds to the emerging discourse on the sociocultural implications of algorithmically curated content in reshaping contemporary modes of social connectivity
Formulation of a Lyapunov-Based PID Controller for Level Control of a Coupled-Tank System
Full text linkThis manuscript proposes a Proportional-Integral-Derivative (PID) control algorithm based on Lyapunov stability criteria. To verify the technique, the study is further extended to investigate its feasibility in controlling the liquid level of a coupled-tank system. A comparative study is conducted with the well-established Ziegler-Nichols tuning technique, known for its rapid and aggressive response. While Ziegler-Nichols often achieves quick tuning, it is prone to instability or degraded performance, particularly in systems with slow dynamics, such as the coupled-tank system. The results demonstrate the practical viability of the Lyapunov-based PID approach. The findings show that the Lyapunov-PID controller significantly outperforms the Ziegler-Nichols PID, achieving a 33.63% reduction in overshoot and a 45.14% improvement in settling time. These improvements highlight the advantage of incorporating Lyapunov-based criteria in PID design for systems where stability and performance are critical. However, the proposed approach has limitations such as increased computational complexity and the need for abstract tuning effort, along with difficulty in selecting appropriate Lyapunov functions
Evaluating the Effectiveness of Alzheimer’s Detection Using GANs and Deep Convolutional Neural Networks (DCNNs)
Full text linkAlzheimer’s is a gradually worsening condition that damages the brain, making timely and precise diagnosis essential for better patient care and outcomes. However, existing detection methods using DCNNs are often hampered by the problem of class imbalance in datasets, particularly OASIS and ADNI, where some classes are underrepresented. This study proposes a novel approach integrating GANs with DCNNs to tackle class imbalance by creating synthetic samples for underrepresented categories. The primary focus of this research is demonstrating that using GANs for data augmentation can significantly strengthen DCNNs performance in Alzheimer's detection by balancing the data distribution across all classes. The proposed method involves training DCNNs with both original and GAN-generated data, with data partitioning of 80:10:10 for training/ validation/ testing. GANs are applied to generate new samples for underrepresented classes within the OASIS and ADNI datasets, ensuring balanced datasets for model training. The experimental results show that using GANs improves classification performance significantly. In the case of the OASIS dataset, the mean accuracy and F1 Score rose from 99.64% and 95.07% (without GANs) to 99.98% and 99.96% (with GANs). For the ADNI dataset, the average accuracy and F1 Score improved from 96.21% and 93.01% to 99.51% and 99.03% after applying GANs. Compared to existing methods, the proposed GANs + DCNNs model achieves higher accuracy and robustness in detecting various stages of Alzheimer's disease, particularly for minority classes. These findings confirm the effectiveness of GANs in improving DCNNs' performance for Alzheimer's detection, providing a promising framework for future diagnostic implementations
Boost Converter Control Using Proportional-Integral-Derivative Controller Optimized by Whale Optimization Algorithm
Full text linkThis work offers an improved control approach for a boost converter called WOA_PID by combining a Whale Optimization Algorithm (WOA) with a Proportional-Integral-Derivative (PID) controller. The main goal is to optimize the PID controller gains for better voltage control and improved system stability and performance. Although boost converters are employed for step-up DC-DC conversion, they have nonlinear dynamics and sudden load changes that create major problems in conventional controller tuning. This work guarantees improved transient response and lower steady-state error by using the WOA employed as an optimization tool to effectively optimize the PID gains by minimizing the Integral Square Error (ISE) performance index. Simulations are used to assess the suggested WOA_PID controller, which showed better performance than traditional PID tuning techniques. The key aspects are zero overshoot, quicker rise and settling time of 0.216 and 0.654 respectively as well as improved output voltage control under changing load situations. Findings verify the efficiency of the WOA-based tuning approach in optimizing the PID controller for boost converters, providing a robust solution for practical applications in power electronics
Performance optimization of a thermoelectric energy harvesting system utilizing waste heat from an internal combustion engine
Full text linkThis study presents the performance optimization of a Thermoelectric Energy Harvesting (TEH) system designed to recover waste heat from Internal Combustion Engines (ICEs). It includes optimizing the energy conversion efficiency of the thermoelectric module (TEM), optimizing the design of the Plate Heat Exhcanger (PHE), and simulation-based validation. The optimization process, conducted using Python optimization code developed for the study, yielded an energy conversion efficiency of 7.209%, marking a 56% improvement over the experimentally measured efficiency of 4.63%. The optimized PHE design, incorporate finless triangular-rectangular composite duct. The analysis showed a fully turbulent flow within the PHE, which significantly enhances convective heat transfer coefficients, improve the heat exchange between the exhaust gas and heat exchanger surfaces, and reduces the risk of fouling and clogging. The exhaust gas contained 1792W of waste heat, with 230W transferred to the hot side of the TEM. This corresponds to a heat exchanger effectiveness of 0.13, indicating that only 13% of the available waste heat in the exhaust gas is utilized by the TEM. The overall TEH system efficiency was determined to be 0.94%, which, despite being relatively modest, yields considerable energy savings in large-scale applications where waste heat is abundant. Computational simulations, using a CAD model in SOLIDWORKS, validated the TEH system’s optimized performance, by ensuring the desired temperature gradient is maintained across the TEM, given that the power output of the TEH is directly proportional to the temperature gradient across the thermoelectric couples in the TE
Comparative Analysis of Yolov-8 Segmentation for Gait Performance in Individuals with Lower Limb Disabilities
Full text linkThis research aims to develop an example of gait pattern segmentation between normal and disabled individuals. Walking is the movement of moving from one place to another, where individuals with physical limitations on the legs have different walking patterns compared to individuals without physical limitations. This study classifies gait into three categories, namely individuals with assistive devices (crutches), individuals without assistive devices, and normal individuals. The study involved 10 subjects, consisting of 2 individuals with assistive devices, 3 individuals without assistive devices, and 5 normal individuals. The research process was conducted through three main stages, namely: image database creation, data annotation, and model training and segmentation using YOLOv8. YOLOv8-seg is the platform used to segment the data. The test results showed that the YOLOv8L-seg model achieved convergence value at the 23rd epoch with the 4th scenario in recognizing the walking patterns of the three categories. However, research on walking patterns of people with disabilities faces several obstacles, such as the lack of confidence or emotion of the subject during the data collection process, which is conducted at the location of the subject's choice. In addition, YOLOv8-seg showed consistent performance across the five models used, obtaining a maximum mAP50 value of 0.995 for mAP50 box and mAP50 mask