Publication Search

Concept drift, the phenomenon where the statistical properties of data streams change over time, poses a significant challenge in machine learning, particularly for long term data streams. Traditional machine learning models, including batch learning and non-adaptive approaches, struggle to detect and adapt to these changes, leading to degraded performance and inaccurate predictions. This study proposes an adaptive computational model designed to detect and respond to concept drift using incremental learning techniques and statistical drift detection mechanisms. The model integrates an Adaptive Drift Detector (ADD) and Incremental Learning System, enabling real-time adjustments to data distribution changes. The model is evaluated across synthetic and real-world datasets, demonstrating its superior ability to detect abrupt, gradual, and recurring drifts compared to traditional models. Experimental results indicate that the adaptive model maintains high prediction accuracy, minimizes false positive rates, and reduces detection delays. Furthermore, the model performs well in resource-constrained environments, making it suitable for real-time applications such as healthcare prediction, fault detection, and IoT systems. Despite its promising performance, the study identifies challenges related to computational complexity and the model’s performance with imbalanced datasets and noisy data. Future research should focus on optimizing the model’s scalability, computational efficiency, and adaptability to more complex data types to ensure broader applicability in dynamic environments. This work contributes to advancing the detection and adaptation of concept drift, offering a robust solution for dynamic and evolving data streams.

Cloud native architectures are essential for modern software systems due to their ability to handle dynamic environments, scalability, and high availability. However, ensuring resilience in these systems remains a significant challenge, particularly under varying operational conditions such as high-load periods and failure scenarios. This study aims to assess the resilience of cloud native architectures using quantitative metrics that objectively evaluate key attributes such as availability, fault tolerance, recovery time, and scalability. Through the application of these metrics, the study identifies the strengths and weaknesses of the architecture, providing insights into how the system performs under stress and recovers from failures. The results show that while the architecture demonstrates strong availability and scalability under typical conditions, recovery time and scalability under extreme load conditions reveal areas for improvement. Specifically, issues with resource allocation and self-healing capabilities were identified as key weaknesses affecting the overall resilience of the system. These findings highlight the importance of using data-driven metrics to gain detailed insights into system resilience and to guide architectural improvements. The study also emphasizes the need for continuous monitoring and adaptation of the architecture to optimize fault tolerance and recovery processes. The implications of this research extend to cloud application developers and architects, offering actionable recommendations for improving system resilience. Future research could focus on integrating real-time monitoring systems, developing more advanced resilience metrics, and incorporating AI-driven scaling techniques to further enhance the adaptability and robustness of cloud native systems. By addressing these challenges, cloud native architectures can be better equipped to maintain high performance and reliability in dynamic, real-world environments.

User experience (UX) evaluation plays a crucial role in understanding how users interact with digital platforms and in improving product design. Traditional UX evaluation methods, such as surveys and interaction logs, often rely on a single data source, which limits the depth of analysis. This study explores the integration of multimodal data processing techniques in UX research, aiming to enhance the accuracy and comprehensiveness of UX evaluations. By combining interaction logs, visual attention data, and physiological measurements, this approach provides a more holistic understanding of user behavior, emotional responses, and satisfaction. Interaction logs offer objective data on user actions, while eye-tracking and physiological data capture users' emotional states, providing richer insights into usability and user experience. This study highlights the effectiveness of multimodal integration in identifying patterns that traditional methods overlook, such as emotional responses to interface elements and real-time feedback from users. The findings reveal that multimodal data processing improves the precision of UX assessment by combining objective behaviors with subjective emotional responses, offering a more complete view of user interactions. The study also discusses the challenges of data synchronization and the potential ethical concerns related to the use of physiological data. The integration of these data sources shows great potential for enhancing the design process, allowing designers to make informed decisions based on comprehensive insights. Finally, this research underscores the future potential of multimodal analytics in UX research, suggesting further exploration of additional data modalities and real-time applications in various digital environments.

Edge-Internet of Things (Edge IoT) systems are increasingly integral to applications that require real time signal processing, particularly where low latency and energy efficiency are critical. This paper explores the design and performance evaluation of a heterogeneous microprocessor architecture aimed at optimizing energy consumption and real time performance. The heterogeneous architecture integrates multiple types of cores, such as Central Processing Units (CPUs), Digital Signal Processors (DSPs), and Graphics Processing Units (GPUs), to allocate tasks based on computational demand. The proposed design significantly reduces energy consumption, particularly during high-performance tasks, while maintaining real time processing guarantees. Simulation-based performance evaluation was conducted to assess the energy efficiency, latency, and overall system performance under varying workloads, including real time Digital Signal Processing (DSP) benchmarks. The results showed that the heterogeneous architecture outperformed traditional homogeneous processors, demonstrating up to a 19-fold improvement in energy efficiency. Furthermore, the system reduced latency by up to 45% in real time applications, making it particularly suitable for Edge IoT environments such as industrial automation and smart healthcare, where both performance and energy efficiency are critical. Despite some trade-offs in task scheduling complexity, the heterogeneous design was able to balance power consumption and computational performance effectively. The findings suggest that this architecture can serve as a foundation for future Edge IoT systems, providing significant advantages in terms of energy efficiency, real time processing, and scalability. Future work will focus on further optimization of the architecture and exploring its application across various IoT environments.

The increasing demand for low latency and high-throughput multimedia applications has spurred significant advancements in hardware software co design. This study explores the integration of custom digital signal processing (DSP) hardware accelerators with optimized software frameworks to enhance deep learning accelerated DSP tasks. The proposed co design approach significantly reduces latency and improves throughput compared to traditional software-only DSP implementations. Through the development of custom hardware accelerators built with FPGA technology, the system achieves up to a 1.85x reduction in latency and a 1.5x improvement in throughput for real-time multimedia tasks such as image recognition, video decoding, and audio processing. The combination of hardware and software optimizations allows for better resource utilization, enabling the parallel processing of computationally intensive tasks while the software framework handles less demanding operations. Additionally, the co design system demonstrated improved energy efficiency, making it highly suitable for embedded systems. The results show that the hardware software co design approach offers substantial advantages in performance, latency reduction, and energy efficiency, positioning it as a viable solution for real-time multimedia applications. The findings have important implications for applications requiring fast data processing, such as autonomous driving, healthcare, and disaster management. Future research could explore alternative hardware accelerators, advanced software optimizations, and AI-based resource management to further improve the system’s efficiency and scalability for more complex multimedia tasks.

This study investigates the integration of high performance communication protocols with adaptive signal processing engines in multi-core systems, aiming to enhance scalability, throughput, and inter-core communication efficiency. The challenges inherent in traditional multi core architectures, such as communication overhead, latency, and scalability limitations, are addressed through the incorporation of Network-on-Chip (NoC) architectures and adaptive signal processing techniques. By using a multi-core digital signal processing (DSP) platform, the study evaluates the performance improvements achieved by this integration under varying workloads and core configurations. The experimental results show a 35% improvement in throughput and a 25% reduction in communication latency, highlighting the effectiveness of adaptive communication protocols in managing data traffic between cores and reducing bottlenecks. The integration of NoC architecture facilitates parallel data transfers, while adaptive signal processing engines ensure that data flows more efficiently across the cores, enhancing system responsiveness, especially under high data rate conditions. Furthermore, the study explores the scalability of the proposed system, demonstrating its ability to maintain high performance as core counts increase. The findings emphasize the potential of combining advanced communication protocols with adaptive signal processing for optimizing multi-core system performance. Practical implications of this research include the design of scalable, flexible, and efficient multi core architectures suitable for complex, data-intensive applications. Future research should focus on further refining communication protocols and exploring additional integration strategies to enhance the adaptability and scalability of multi-core systems in next-generation computing environments.

The integration of Digital Signal Processing (DSP) algorithms in low power microcontroller based embedded systems has emerged as a promising solution to optimize energy efficiency without compromising signal accuracy and performance. This study focuses on the design and optimization of DSP algorithms specifically for microcontrollers, aimed at achieving real-time, reliable monitoring for applications such as healthcare, environmental sensing, and IoT devices. The research highlights the system's ability to handle complex signal processing tasks while maintaining low power consumption, ensuring long-term, continuous operation in remote or battery-powered environments. The system employs various techniques, including advanced power management strategies such as dynamic voltage scaling (DVS) and adaptive voltage scaling (AVS), along with lightweight AI algorithms and model pruning, to minimize energy use. The results show significant reductions in power consumption compared to traditional systems, particularly during continuous monitoring tasks. Despite this, the optimized DSP algorithms maintain or even enhance signal accuracy, ensuring that critical monitoring data remains reliable. Furthermore, the system demonstrates robust performance and reliability over extended periods, making it suitable for long-term deployment in critical applications such as wearable medical devices and industrial sensors. This research provides a foundation for the development of future low power embedded systems, emphasizing the importance of DSP-aware optimization in achieving energy-efficient and high-performance monitoring. Future improvements may include advanced AI-driven power optimization techniques, enhanced scalability, and cross-domain interoperability, ensuring that these systems can be effectively deployed across diverse applications, from healthcare to environmental monitoring.

This research explores the impact of Cache Aware optimizations on signal processing pipelines in High Throughput computing systems. The growing demand for efficient memory management in modern computing systems, especially for data-intensive applications such as artificial intelligence (AI) and multimedia processing, necessitates the development of optimized memory hierarchies. Traditional memory systems often suffer from memory bottlenecks, significantly reducing the performance of these systems. This study investigates how memory hierarchy optimizations, particularly cache line aware optimization, dependency-aware caching, and adaptive cache replacement algorithms, can mitigate these challenges and improve system performance. Through analytical modeling and experimental benchmarking, this work evaluates various memory hierarchy configurations, including processing-in-memory (PIM) and three-dimensional integrated circuits (3D ICs), comparing them to conventional systems. The results demonstrate that Cache Aware optimizations lead to a reduction in memory access latency by up to 30%, while throughput improved by up to 40%. Additionally, cache hit rates increased by 25%, and energy consumption was reduced by up to 20%, highlighting the effectiveness of optimized memory management. The research contributes to the field by providing valuable insights into the design and implementation of efficient signal processing pipelines. It also identifies key challenges, including the need for dynamic occupancy mechanisms and DAG-aware scheduling algorithms, and suggests potential areas for future research, such as the exploration of collaborative caching approaches and further optimization of cache-adaptive algorithms. This work lays the foundation for more efficient, high-performance computing systems that can handle large datasets and complex tasks in real-time applications.

Continuous chemical control of rat pests (Rattus spp.) can sometimes lead to resistance and resurgence problems, and even some cases of inaccurate targeting ultimately killing livestock. The idea of ​​​​repelling rats in rice fields using vibrations of crickets and other natural animals transmitted via radio has been done and the results are quite optimal for rat control, but it has not been done in corn cultivation. The purpose of this study was to determine the effect of cat sound audio on the intensity of rat pest attacks (Rattus spp.) in corn (Zea mays L.) plantations. The research location was in a farmer's land owned by a farmer in Dagan Village, Solokuro District, Lamongan Regency. Determination of sampling points using the diagonal method, each into 5 sub-observation plots. In each sub-plot, markers were placed as sampling points. Audio with cat and bird sounds was played continuously from 05.00 pm - 07.00 am. Observations were conducted at 7:00 a.m. at all sampling points at 30 and 60 days after planting. Observations were conducted for three days using audio and three days without audio. Damage symptoms were observed directly at each sampling point. Corn plants showing symptoms were then recorded and analyzed using the Damage Intensity formula. Observations showed that the use of cat sound audio was able to reduce the level of rat infestation. At 30 days after planting, the damage percentage was reduced by 8.33%. Meanwhile, at 60 days after planting, the damage percentage was reduced by 18.33%.

This study aims to improve the quality of gallon water products and strengthen the competitiveness of CV. Anugerah Gemilang through the implementation of Quality Function Deployment (QFD) using the House of Quality (HoQ). The QFD approach is employed to translate the Voice of Customer (VoC) into technical product characteristics as well as service quality attributes that influence customer satisfaction. The research method applied is quantitative-descriptive with the support of qualitative data. Quantitative data were collected through questionnaires distributed to customers to measure the importance and satisfaction levels regarding product and service attributes, while qualitative data were obtained through in-depth interviews to reinforce and validate the questionnaire results. Subsequently, the VoC data were analyzed using the HoQ matrix to determine quality improvement priorities based on customer importance weights. This study is expected to produce strategic recommendations in the form of prioritized product and service quality enhancements focused on customer satisfaction, thereby supporting the sustainable improvement of the company’s competitiveness.

Pneumonia remains a leading cause of morbidity and mortality worldwide, particularly in resource-limited settings and among elderly populations, where timely diagnosis and continuous monitoring are often constrained by limited clinical infrastructure. This study presents an edge–cloud–integrated framework for early pneumonia risk monitoring, leveraging multimodal wearable sensors and deep learning to support continuous short-duration monitoring. The proposed system is designed to operate in near real time under simulated deployment conditions, continuously acquiring and analyzing physiological signals (respiratory rate, heart rate, SpO₂, and body temperature) alongside event-driven acoustic biomarkers (cough sounds) within a distributed architecture. A lightweight edge module performs local signal preprocessing and anomaly triage, selectively transmitting salient information to a cloud-based multimodal deep learning model for refined risk estimation and interpretability analysis. The framework was evaluated using a multi-source dataset comprising public repositories (MIMIC-III and Coswara) and a clinically supervised wearable study conducted in two Nigerian hospitals, resulting in 718  hours of quality-controlled multimodal monitoring data. In a pooled multi-source evaluation, the system achieved an AUC of 0.95, while in a clinically realistic local-only evaluation, the AUC was 0.86, reflecting a consistent but preliminary diagnostic signal. These results highlight the importance of local data adaptation for real-world applicability and suggest that multimodal AI can provide meaningful early risk indicators under resource constraints. Beyond predictive performance, this work demonstrates the feasibility of integrating multimodal learning, edge–cloud computation, and explainable analytics into a deployment-aware, privacy-preserving monitoring framework for low-resource healthcare environments.

Derivatives of substituted oxazol-5-one (1–3) and substituted oxazolo-isoxazole (4–6) were successfully synthesized through a multi-step reaction process. Initially, glycine was reacted with acetic anhydride to produce acetyl glycine as a key intermediate. This intermediate subsequently underwent a condensation reaction with various substituted benzaldehydes, leading to the formation of oxazol-5-one derivatives (1–3). In the final synthetic step, these oxazol-5-one derivatives were reacted with hydroxylamine hydrochloride to yield the corresponding oxazolo-isoxazole compounds (4–6). The chemical structures of all synthesized compounds were characterized and confirmed using Fourier Transform Infrared (FT-IR) spectroscopy and proton nuclear magnetic resonance (¹H NMR) spectroscopy. Furthermore, molecular docking studies were carried out to evaluate the potential biological interactions of the prepared compounds. Docking simulations were performed using PyRx software, while visualization and interaction analysis were conducted employing PyMOL and Discovery Studio. The combined experimental and computational approaches provide valuable insights into the structural properties and potential biological relevance of the synthesized compounds.

Technology-based learning media have now become a primary choice in supporting the learning process in elementary schools, in line with the development of the digital era and the growing demand for more innovative learning approaches. The utilization of technology in education is expected to enhance the quality of teaching and learning processes and encourage active student engagement. One technology-based learning medium considered effective and engaging is BrainPOP, a digital learning platform that presents educational content through interactive animated videos, quizzes, simulations, and various supporting activities designed to suit the characteristics of elementary school students. The selection of BrainPOP is based on its advantages in increasing students’ learning interest, facilitating the understanding of abstract concepts by making them more concrete, and enhancing students’ motivation and retention of learning materials. The visual, communicative, and interactive presentation of content enables students to learn in a more enjoyable and less monotonous manner. This medium is capable of creating an engaging, effective, and student-centered learning atmosphere, thereby fostering an active, creative, and enjoyable learning environment. Therefore, the use of BrainPOP in the learning process is expected not only to improve students’ learning outcomes but also to optimally and sustainably develop their interest, motivation, and engagement in learning.

This study aims to analyze the effect of price as a component of the marketing mix of NutriSari products on consumers’ purchase intention at the STIE YPBI Campus Canteen. Price is a crucial element of the marketing mix that directly influences consumer perceptions and purchasing decisions. Therefore, understanding consumers’ price perceptions is essential for companies in developing effective marketing strategies and maintaining competitiveness. This research employed a quantitative descriptive approach, with data collected through questionnaires distributed to consumers at the STIE YPBI Campus Canteen. The population of this study consisted of 40 active consumers within the campus canteen environment. Data were analyzed using validity and reliability tests, normality testing, simple linear regression analysis, t-test, and F-test with the assistance of SPSS software. The results indicate that price has a significant effect on purchase intention, as evidenced by an F-test value of 5.440 and a coefficient of determination of 54.40%. This finding implies that 54.40% of consumers’ purchase intention is influenced by price, while the remaining percentage is affected by other factors not examined in this study. Furthermore, the t-test results show that the calculated t-value (2.332) is greater than the critical t-value (2.024), indicating a positive and significant effect of price on purchase intention. The indicators of price affordability, price-quality suitability, price competitiveness, and price-benefit suitability collectively contribute to increasing consumers’ purchase intention at the STIE YPBI Campus Canteen.

This study aims to determine the effect of price and service quality on customer satisfaction of members of the Merah Putih Candiroto Village Cooperative, Kendal District, Kendal Regency. This study uses a quantitative approach, associative research type, with a sample of members of the Merah Putih Candiroto Village Cooperative, Kendal. The sampling method was carried out using a saturated sampling technique. The total sample in this study was 137 respondents. The variables in this study were independent variables: price and service quality, and the dependent variable: customer satisfaction of members of the Merah Putih Candiroto Village Cooperative, Kendal. Testing in this study used instrument testing, classical assumption testing, and hypothesis testing with multiple regression tests using SPSS Version 25. The results of this study indicate that partially the price has a positive and significant effect on customer satisfaction of members of the Merah Putih Village Cooperative, Candiroto, Kendal with a t-count of 3.418 greater than the t-table of 0.1678 and a significant value of 0.001 smaller than the significance level of 0.05. And the quality of service partially has a positive and significant effect on customer satisfaction of members of the Merah Putih  Village Cooperative, Candiroto, Kendal with a t-count of 3.643 greater than the t-table of 0.1678 and a significant value of 0.000 smaller than the significance level of 0.05. Price and service quality simultaneously have a positive and significant effect on customer satisfaction of members of the Merah Putih Village Cooperative, Candiroto, Kendal, with F count of 715.041 greater than F table of 0.1678 with a significance of 0.000 smaller than the significance level of 0.05. The Adjusted R square result of 0.913 indicates that 91.3% of customer satisfaction of members of the Merah Putih Village Cooperative, Candiroto, Kendal, is influenced by price and service quality whose influence was tested in this study, while the remaining 8.7% is influenced by other variables not examined in this study.

The influence of self-efficacy, work engagement, and financial compensation is crucial to determine the extent of their impact on employee performance at PT Sinergi Gula Nusantara PG Meritjan. By understanding these relationships, company management can assess how these factors affect employee performance and thereby formulate more targeted human resource planning and development strategies in the future. This study employed a saturated sampling technique, in which the sample consisted of all permanent employees of PT Sinergi Gula Nusantara PG Meritjan, totaling 77 respondents. Data were collected through questionnaires, observations, and interviews. The results of the analysis indicate that self-efficacy, work engagement, and financial compensation have a significant effect on employee performance, both partially and simultaneously. This is evidenced by the multiple linear regression analysis, which shows significance values below 0.05 and a coefficient of determination of 0.677 or 67.7%, indicating that self-efficacy, work engagement, and financial compensation explain 67.7% of the variance in employee performance.

Limited legal literacy among village officials may contribute to disorderly village administration, inconsistent document formats, weak record-keeping, and poor archive traceability, ultimately affecting public service quality. This Community Service Program (Pengabdian kepada Masyarakat/PKM) aimed to strengthen the legal literacy of village officials in Larangan Luar Village, Pamekasan Regency, to improve orderly and accountable village administrative governance. The program applied a hands-on training model combined with mentoring/document clinics and a pretest–posttest evaluation involving village officials (n = 18). Implementation consisted of three core training sessions and two mentoring sessions over four weeks, focusing on document legality, official correspondence standards, numbering and registers, and basic archive management. Results showed an increase in the average legal literacy score from 54.1 (pretest) to 74.6 (posttest), an improvement of 20.5 points. Beyond knowledge gains, document quality and administrative order improved through the adoption of practical administrative tools developed during the program. Key outputs included a concise module (±22 pages), 10 village administrative document templates, one village administrative SOP, and a simple filing system based on document classification and folder numbering. In conclusion, strengthening village officials’ legal literacy through practice-based training and mentoring effectively supports improvements in village administrative governance and is potentially replicable in other villages in Pamekasan with context-specific adjustments.

The rapid development of digital technology has brought significant changes to the business landscape, transforming how products are marketed, services are delivered, and business relationships are built. In this context, students, as future members of the workforce and potential entrepreneurs, are required to possess strong digital literacy skills in order to effectively face challenges and seize emerging business opportunities. This study aims to analyze the importance of digital literacy in supporting students’ readiness to respond to future business trends. The research employed a descriptive approach using a literature review and observations of the entrepreneurship learning process in vocational schools. The findings indicate that digital literacy plays a crucial role in enhancing students’ creativity, adaptability, and ability to utilize digital platforms for online marketing, branding, and business communication. Furthermore, digital literacy helps students understand market dynamics, analyze consumer behavior, and adopt innovative business models that align with technological developments. Students with adequate digital literacy are better prepared to face rapid changes in the business environment and demonstrate higher confidence in applying technology to entrepreneurial activities. In conclusion, the integration of digital literacy into entrepreneurship education is essential to produce competitive, innovative, and adaptable graduates who are capable of thriving in the digital era and contributing to sustainable economic development.

This community service programme was implemented in the coastal community of Padelegan Village, Pademawu Subdistrict, Pamekasan Regency, with a focus on strengthening health literacy and behaviour-based disease prevention at the household level. The background of the activity is based on the vulnerability of coastal communities to health problems related to hygiene, household drinking water management, and environmental cleanliness, as well as the need for an approach that not only increases knowledge but also encourages consistent preventive practices. The programme aims to improve residents' ability to understand and use health information in an applicable manner, while strengthening key disease prevention behaviours through education and mentoring. The activity will be carried out from February to April 2025 with a behaviour-based education design combined with practice demonstrations and community mentoring, involving 48 participants (40 residents/households and 8 posyandu/PKK cadres). The stages included initial assessment, development of KIE media (brief modules and leaflets/posters), two education-demonstration sessions, two home mentoring sessions, and final evaluation. The evaluation was conducted using pre-post knowledge, attitude, and practice (KAP) assessments and practice observation through a checklist. The results showed an increase in health literacy and improved consistency in preventive behaviour; knowledge increased from 5.4 to 7.8, and compliance with hand washing at critical times increased from 41.7% to 72.9%. Programme outputs included an information, education and communication (IEC) package, a household monitoring checklist, and capacity building for cadres as local facilitators. It was concluded that the integration of participatory education, practical demonstrations and cadre mentoring has the potential to be effective in encouraging preventive behavioural change in coastal communities, with recommendations for integrating monitoring into the routine agenda of integrated health service posts (posyandu) and community empowerment groups (PKK) and for follow-up monitoring for 3–6 months to maintain the sustainability of practices.

Student organizations in schools play an important role as social institutions that support character building and the development of students’ social and leadership skills. However, in practice, many students still perceive school organizations merely as formal or administrative activities, resulting in low participation and limited understanding of their educational value. This condition highlights the need for socialization activities that emphasize meaningful organizational learning. This community service activity aims to strengthen students’ understanding of the role of school organizations as social learning spaces. A descriptive qualitative approach was employed involving 30 eleventh-grade students at SMK Muhammadiyah 04 Boyolali. Data were collected through observation, discussion notes, and students’ responses during interactive sessions.The activity was conducted through teacher coordination, material preparation, material presentation, and discussion and question-and-answer sessions. The results indicate an improvement in students’ understanding of the functions and benefits of student organizations as social institutions. Students showed increased awareness of the importance of cooperation, discipline, responsibility, and communication, as well as greater motivation to actively participate in school organizations. These findings suggest that participatory and dialogical socialization is effective in promoting meaningful organizational learning and supporting students’ character development.