Publication Search

The increasing adoption of collaborative robots in modern manufacturing environments requires reliable perception systems that can ensure both safety and operational efficiency during human–robot collaboration. This study proposes a CNN-based real-time computer vision system for object and human detection in shared robotic workspaces. The research focuses on developing and evaluating a single-stage deep learning detection model optimized for real-time performance while maintaining high detection accuracy. The proposed methodology includes dataset preparation, model training using transfer learning, real-time system implementation, and comprehensive performance evaluation. Experimental results demonstrate that the developed system achieves high detection accuracy, as reflected by strong precision, recall, and mean Average Precision (mAP) values, while maintaining low inference latency suitable for real-time operation. The system consistently operates above real-time frame-rate thresholds, ensuring timely perception updates required for safety-related decision-making in collaborative robotic environments. Graphical and quantitative analyses further confirm the stability of inference performance under dynamic interaction scenarios involving human movement and multiple objects. Compared with existing approaches, the proposed system provides a balanced trade-off between accuracy and computational efficiency, making it practical for deployment in safety-aware human–robot collaboration scenarios. Overall, the findings indicate that CNN-based real-time object detection systems can effectively support perception and situational awareness in collaborative robotics, contributing to safer and more efficient industrial automation.

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.

Real time decision making applications, such as those used in autonomous vehicles, smart cities, and industrial IoT, require fast, scalable, and accurate analytics to ensure timely responses and optimized operations. Traditional cloud-based systems face significant challenges in meeting these requirements due to high latency, limited scalability, and bottlenecks in data processing. This study explores the use of a hybrid Edge Cloud architecture to optimize End to end machine learning (ML) pipelines for real time applications. The proposed system offloads time-sensitive tasks to edge devices, while computationally intensive processes are handled by the cloud, ensuring efficient use of resources and reduced latency. Experimental results demonstrate that the hybrid model reduces inference latency by up to 70% compared to cloud-only systems, while maintaining model accuracy and increasing throughput. Additionally, the scalability of the hybrid architecture is highlighted, as it can handle large-scale data streams and adapt to varying workloads. The findings show that hybrid Edge Cloud architectures are well-suited for applications where fast decision making is critical, such as autonomous systems and real time analytics in smart cities. However, challenges remain in managing resources across edge and cloud systems, particularly in balancing computational loads and ensuring system reliability. Future research should focus on optimizing task partitioning, integrating advanced edge AI models, and exploring the use of 5G networks to enhance performance further. Overall, the study demonstrates the potential of hybrid Edge Cloud systems in overcoming the limitations of traditional cloud-based ML pipelines and provides insights into the future of real time data processing.

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 food and beverage (FnB) industry is one of the main supporting sectors of tourism in Indonesia and has experienced rapid growth along with the increasing number of tourist activities and consumer demand. However, previous studies indicate that Service Quality in the FnB industry remains suboptimal, particularly in aspects related to human resources (HR). Issues such as inconsistent service performance, low responsiveness, and limited employee competence and work attitude are commonly identified. This study aims to systematically examine the role of human resources in Service Quality within the FnB industry and to identify key factors, management strategies, and existing research gaps. This research employed a Systematic Literature Review (SLR) method using the PICOC framework, analyzing 20 national and international journal articles published between 2015 - 2025 and retrieved from Google Scholar. The findings reveal that the most influential HR factors affecting Service Quality include competence, communication skills, work attitude, experience, and employee training. Furthermore, effective human resource management practices demonstrate a positive relationship with improved Service Quality. Nevertheless, the review identifies a lack of comprehensive studies integrating HR management and Service Quality within the specific Context of the Indonesian FnB industry, indicating opportunities for future research.

The increasing demand for real time parallel processing in cloud computing environments necessitates the development of more efficient and fault-tolerant scheduling algorithms. Traditional scheduling methods, such as static algorithms, often fall short when handling dynamic workloads and system failures, leading to increased task latency and reduced system performance. In contrast, adaptive scheduling algorithms dynamically adjust to changes in system conditions and workloads, ensuring timely task completion and optimized resource utilization. This study evaluates the performance of adaptive scheduling algorithms in real time cloud environments, focusing on key factors such as task latency, system resilience, and fault tolerance. Simulation experiments were conducted using cloud computing models that incorporate fault injection scenarios, including network failures and virtual machine crashes. The results show that adaptive algorithms significantly outperform traditional static schedulers in terms of task latency reduction and improved system resilience. These algorithms demonstrated better fault recovery times and ensured consistent real time performance, even under failure conditions. The findings highlight the advantages of adaptive scheduling in cloud environments, particularly for applications requiring rapid data processing and high system reliability. Despite the promising results, challenges remain regarding the scalability and complexity of these algorithms in large-scale cloud systems. Further research is needed to optimize adaptive scheduling algorithms for efficiency, scalability, and comprehensive performance evaluation, taking into account factors such as energy consumption, cost, and reliability. This research contributes to advancing cloud computing infrastructures that can dynamically handle real time tasks and maintain high performance under varying workloads and failures.

People with disabilities continue to experience barriers in accessing education, employment, and social participation, requiring active government involvement through inclusive programs. One such initiative is the International Disability Day event organized by the South Tangerang City Social Service in collaboration with Rumah I’m Star. This study aims to analyze the public relations activities of the South Tangerang City Social Service by examining problem identification, planning, implementation, and interpretation in organizing the event. The research is based on the public relations model of Cutlip, Center, and Broom, which includes four stages: defining the problem, planning and programming, taking action and communicating, and evaluating the program. A qualitative approach with a descriptive method was employed. Data were collected through interviews, observations, and documentation, involving purposively selected informants from the Public Relations Division of the Social Service, the founder of Rumah I’m Star, beneficiaries, and public relations experts. The findings show that the Social Service identified low public awareness of disability issues as the main problem and responded by developing a collaborative communication strategy with Rumah I’m Star. The activities implemented included art performances, talk shows, and a bazaar showcasing the works of persons with disabilities, which were disseminated digitally. Program evaluation was conducted internally without standardized measurement instruments, limiting interpretation to event outcomes and participant involvement. Overall, the study concludes that these public relations efforts enhanced government communication and promoted inclusion awareness, although broader public engagement is needed for sustainable impact.

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 analysis methods used in this study include a case study on the use of closed-loop recycling and an evaluation of biopolymer performance across various industries, both of which are important components in the transformation of the manufacturing industry toward a circular economy. The research findings indicate that recycled materials can reduce carbon emissions by thirty to fifty percent and save production costs by fifteen to twenty-five percent. Artificial intelligence-based sorting technology improves sorting efficiency to 95 percent, and closed-loop recycling maintains the mechanical properties of materials up to 90 percent after four cycles. The degradation rate of biopolymers like PLA and PHA reaches 60-80% within six months, although production costs are still 2-3 times higher. The integrated approach increases resource efficiency by 45% and reduces waste by 60%. To achieve successful implementation, Extended Producer Responsibility (EPR) policies, strategic infrastructure investments, and collaboration from various parties thru the triple helix model must work together.

This study explores the integration of deep learning based approaches in real time video content analysis for intelligent human computer interaction (HCI) in multimedia systems. Traditional video analysis techniques, such as rule-based methods and offline processing, struggle with real time performance and adaptability to complex video data. In contrast, the deep learning model used in this research, particularly Convolutional Neural Networks (CNNs), provides high accuracy in object detection, feature extraction, and real time processing. The integration of CNNs with interactive visualization modules enables dynamic adjustments to video content based on user interactions, ensuring a seamless and engaging user experience. The system was benchmarked in terms of its processing speed, accuracy, and responsiveness, showing significant improvements over traditional approaches in real time video analysis. Moreover, the study demonstrates that combining deep learning with real time visualization enhances the efficiency of interactive multimedia applications, making it suitable for dynamic environments such as surveillance, security monitoring, and interactive media. Despite the system's strong performance, challenges such as computational demands in high-resolution video processing were identified, highlighting the need for further optimization. Future work will focus on optimizing the system for different hardware platforms, incorporating multimodal inputs, and refining deep learning models to address computational bottlenecks. This research contributes to advancing HCI by providing insights into the integration of deep learning for real time video content analysis, which is pivotal for enhancing the interactivity and adaptability of intelligent multimedia systems.

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.

Employee performance is a key factor in determining organizational success in achieving its strategic objectives. Various management studies indicate that employee performance is not solely influenced by individual factors, but is also significantly affected by organizational factors, particularly organizational planning and organizational structure. Effective organizational planning provides a clear direction and strategic framework that guides employees in performing their tasks, while an appropriate organizational structure facilitates coordination, clarifies authority, and supports the efficient execution of work. This study aims to analyze the influence of organizational planning and organizational structure on employee performance through a systematic literature review approach. The research method employed is a systematic literature review by examining relevant national and international journal articles published within the last ten years. Data were collected from reputable academic databases to ensure the credibility and relevance of the sources. The selected studies were analyzed qualitatively to identify patterns, relationships, and key findings related to the research variables. The results of the literature review indicate that systematic and well-formulated organizational planning contributes positively to improving goal clarity, work coordination, and employee motivation. Furthermore, an organizational structure that is aligned with organizational strategies plays an important role in clarifying task distribution, authority lines, and overall work effectiveness. The findings also reveal that organizational planning and organizational structure are interrelated and mutually reinforcing in shaping employee performance. This study concludes that the integration of organizational planning and organizational structure is a crucial factor in enhancing sustainable employee performance. The results of this study are expected to provide both theoretical contributions to organizational management studies and practical references for organizations in designing effective management systems.  

This study explores the role of visual analytics in enhancing decision-making processes within creative industries, focusing on its application to large-scale multimedia datasets. Visual analytics integrates interactive visualization techniques with computational algorithms, enabling users to explore complex datasets intuitively and derive actionable insights. The research centers on the design and implementation of interactive dashboards tailored to the creative sector, particularly film, music, and advertising industries, to facilitate real-time data exploration. The study also investigates the usability of these tools through expert-based evaluations, aiming to assess their effectiveness in supporting informed and timely decision-making. The findings reveal that interactive visualizations significantly improve insight discovery and pattern recognition, enabling decision-makers to uncover hidden trends in large multimedia datasets. However, challenges related to scalability, user acceptance, and real-time processing were encountered during the implementation phase. The research highlights the practical benefits of integrating visual analytics into industry workflows, which include enhanced content creation, audience engagement, and strategic planning. Furthermore, the study identifies key visual analytics techniques such as dynamic dashboards, pattern recognition, data mining, and clustering, which are essential for analyzing multimedia data. The study concludes by emphasizing the potential for wider applications of visual analytics in other sectors, suggesting future research directions to improve tool performance, scalability, and user accessibility, as well as exploring the integration of emerging technologies like artificial intelligence and virtual reality.

Smart cities are increasingly leveraging advanced technologies such as the Internet of Things (IoT), Artificial Intelligence (AI), and Big Data Analytics to optimize urban management and improve the quality of life for citizens. However, managing vast and diverse datasets from numerous sources in real-time presents several challenges. This research proposes a modular framework that integrates distributed data processing engines with container-based workflow orchestration to address scalability, latency, adaptability, and fault tolerance in smart city data analytics. The framework utilizes cloud native technologies, including Apache Spark and Kubernetes, to efficiently manage resources and ensure high availability. The experimental setup tested the framework’s ability to handle dynamic data loads, demonstrating scalability through real-time resource allocation and low-latency processing. The adaptability of the framework was evident in its seamless integration with various data sources, such as environmental sensors and traffic management systems, which require different processing methods. Additionally, the framework’s modularity provided fault tolerance, enabling continued operation even if individual components failed, a crucial feature for mission-critical applications in smart cities. Compared to traditional monolithic systems, the proposed framework outperformed in flexibility, scalability, and performance, offering significant improvements in handling real-time data streams. Despite these advantages, challenges remain, particularly in integrating heterogeneous data formats and optimizing real-time processing for high-priority applications. The research highlights the importance of scalable data analytics and efficient workflow orchestration for the future of smart city platforms, offering a foundation for the development of more resilient, adaptable, and efficient cloud native infrastructures.

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.

The rapid development of globalization and the acceleration of digital transformation have encouraged organizations to adopt more adaptive and collaborative work practices. In this context, collaborative culture has become a strategic element that plays a crucial role in enhancing organizational effectiveness and competitiveness. This study aims to comprehensively examine the concept, characteristics, forming factors, and theoretical foundations of collaborative culture in modern organizations. The research employs a qualitative approach through a literature review, analyzing reputable national and international journal articles, textbooks, and relevant institutional reports. Data analysis is conducted using a descriptive-analytical technique by synthesizing findings from previous studies. The results indicate that collaborative culture significantly contributes to improved communication quality, work coordination, adaptability, and both individual and organizational performance. Collaborative culture is shaped through the integration of shared vision, open communication, trust, willingness to share resources, collaborative leadership, flexible organizational structures, and the support of collaborative technologies. This study also highlights that the success of digital transformation largely depends on the strength of an effectively internalized collaborative culture. The findings are expected to provide a theoretical reference for organizations and researchers in developing sustainable collaborative culture strategies.

In high-performance computing (HPC) environments, the need to balance memory efficiency and query performance is crucial for ensuring optimal system performance. Traditional data structures, such as B-trees and hash tables, often prioritize either memory usage or query speed, leading to suboptimal performance in memory-constrained systems. This paper proposes a hybrid data structure that combines the strengths of multiple traditional data structures to optimize both memory usage and query processing speed. The proposed hybrid structure integrates cache-conscious algorithms, dynamic memory allocation, and compression techniques for intermediate query results. The approach is evaluated through extensive benchmarking tests comparing it to standard data structures like B-trees and hash tables under various workloads. Results show that the hybrid data structure reduces memory overhead by up to 30% while maintaining query processing speeds up to 1.5 times faster than conventional methods. Furthermore, the hybrid structure demonstrates robust performance across different types of queries, including both point and range queries, ensuring versatility and efficiency. The findings indicate that this hybrid approach provides a promising solution for HPC systems, where both memory efficiency and query speed are essential. Future research can explore extending the hybrid structure to distributed systems and emerging technologies, further improving its scalability and adaptability to new computational paradigms.

The increasing adoption of cloud native microservices has brought about significant improvements in scalability, flexibility, and resilience. However, these advancements also introduce substantial security challenges, particularly in distributed environments where traditional perimeter-based security models prove inadequate. This paper proposes a secure architecture for cloud native microservices that integrates Zero trust Network Access (ZTNA) and multi layered encryption techniques to address these security concerns. The architecture operates on the principle of "never trust, always verify," ensuring that access to resources is strictly controlled and continuously monitored. By incorporating multi layered encryption methods such as RSA and AES, the architecture ensures data protection both in transit and at rest, significantly reducing the risk of data breaches and unauthorized access. Through experimental evaluations, the proposed architecture demonstrated its effectiveness in preventing lateral movement, mitigating data leakage, and resisting common attack vectors such as man-in-the-middle (MITM) attacks and privilege escalation. Additionally, the performance of the system remained optimal, with minimal overhead despite the additional security layers. The architecture's scalability and robust security mechanisms make it a viable solution for real-world microservices environments, where both security and performance are crucial. This paper discusses the potential impact of this secure architecture on the broader field of distributed system security and offers recommendations for future work, including the integration of advanced machine learning techniques for real-time threat detection and automated responses, as well as the adaptation of the architecture for emerging technologies like edge computing and 6G networks.

This study aims to analyze the effect of workload on employee loyalty at the Class I TPI Immigration Office in Jambi, with performance allowance policies acting as a mediating variable. The research employed a quantitative approach involving 88 respondents selected from the total employee population. Data were collected through structured questionnaires and analyzed using statistical methods to examine both direct and indirect relationships among variables. The results indicate that employees generally perceive their workload as being at a moderate level; however, workload has a significant negative effect on employee loyalty. In contrast, performance allowance policies demonstrate a significant positive influence on loyalty. Furthermore, the findings reveal that performance allowance policies partially mediate the relationship between workload and employee loyalty, indicating their role in mitigating the negative impact of workload. These results suggest that effective performance allowance policies can enhance employee loyalty despite increasing workload demands. Therefore, organizations should balance workload management with fair and performance-based compensation policies to maintain employee loyalty.

The rapid proliferation of Internet of Things (IoT) devices across diverse industries has significantly increased the vulnerability of IoT edge networks to sophisticated cyber threats. Traditional intrusion detection systems (IDS), such as signature-based and anomaly-based approaches, are often insufficient in addressing the dynamic and evolving nature of these threats. This study proposes a hybrid intrusion detection system (IDS) framework that combines supervised machine learning (ML) techniques with deep reinforcement learning (DRL) to enhance detection performance in real-time, resource-constrained IoT environments. The proposed framework utilizes supervised learning for initial traffic classification and DRL for adaptive decision-making, enabling the system to continuously learn and optimize its detection policies based on new attack patterns. The hybrid approach significantly improves detection accuracy and reduces false positives when compared to conventional signature-based and single-model ML systems. In addition to improved detection capabilities, the framework's computational efficiency allows it to operate effectively within the constraints of IoT devices, ensuring that it is suitable for large-scale deployments. Benchmark evaluations using publicly available datasets, such as NSL-KDD, IoT-23, and BoT-IoT, show that the hybrid IDS framework outperforms traditional methods, providing a more robust and adaptive solution to cybersecurity challenges in IoT edge networks. The findings of this study suggest that combining machine learning with deep reinforcement learning offers a promising approach to secure IoT environments and address the limitations of existing IDS techniques. Future work will explore enhancing real-time adaptability, scalability, and the detection of zero-day attacks in evolving IoT ecosystems.