An effective approach to manage the content entered in forms is the use of electronic forms. However, if you use a paper form, it takes time to generate electronic forms. This paper has implemented a tool for automatic entry fields detection and for labels allocation to reduce the time required to place entry fields. As a result, we have verified that the implemented tool is useful to reduce the time to place entry fields. (c) 2022 The Author. Published by The Society of Artificial Life and Robotics. This is an open access article distributed under the CC BY-NC 4.0 license (http://creativecommons.org/licenses/by-nc/4.0/).
The integration of Human-Device Interfaces (HDIs) is fundamentally transforming how humans interact with technology, moving from traditional inputs like keyboards toward seamless, effortless communication. This paper explores the concept of "Mirroring Humanity" through the creation of a Digital Twin, facilitated by advanced interfaces such as Brain-Computer Interfaces (BCIs), wearable sensors, and haptic feedback. By leveraging Artificial Intelligence (AI) and machine learning, these systems enable real-time decision-making and the personalization of technology to individual user needs. Drawing on case studies from ACRLAB at Universiti Malaya, this work highlights advancements in contactless navigation such as eye-driven wheelchairs and immersive virtual teaching environments. These technologies demonstrate a proof of concept for enhancing independence among disabled communities and improving efficiency across industries including healthcare and automation. However, the shift toward highly integrated digital twins introduces significant challenges regarding data security, reliability, and the ethical implications of augmenting human traits. The paper concludes that while HDIs offer immense potential for global betterment, robust regulations, ethics and inclusive design are essential to mitigate risks and ensure sustainable technological advancement. (c) 2022 The Author. Published by The Society of Artificial Life and Robotics. This is an open access article distributed under the CC BY-NC 4.0 license (http://creativecommons.org/licenses/by-nc/4.0/).
This research introduces a drone obstacle avoidance system built upon depth estimation derived from monocular RGB images, with the objective of minimizing reliance on high-cost sensors such as LiDAR and RGB-D cameras. The proposed system incorporates ZoeDepth, a deep learning model for monocular depth prediction, and is implemented within a simulated environment using ROS and Gazebo. Two autonomous configurations were tested: one equipped with an RGB-D camera, and the other utilizing depth information inferred from RGB inputs. Evaluation results revealed that, although the RGB-D-equipped setup achieved higher accuracy, the RGB-based system was able to avoid obstacles and reach the target destination, despite exhibiting some localization errors. Future efforts will focus on increasing the system's resilience in densely populated environments and conducting validation through real-world trials. (c) 2022 The Author. Published by The Society of Artificial Life and Robotics. This is an open access article distributed under the CC BY-NC 4.0 license (http://creativecommons.org/licenses/by-nc/4.0/).
Production processes such as high-mix, low-volume manufacturing, where product specifications and task conditions change frequently, require mechanisms that can flexibly switch functions and offer high adaptability. However, achieving multifunctionality by simply combining multiple actuators increases cost, control-system complexity, and mass. To address these issues, this study proposes a novel rotary actuator that achieves normal motion, rapid motion, and variable stiffness with direction-independent output characteristics, using only two motors in combination with mechanical elements such as cam mechanisms and a differential mechanism. This paper describes the structure and functions of the proposed mechanism, the design principles of the output cam that governs the output characteristics, and a mathematical model of its rapid motion. Furthermore, computer-aided engineering simulations using the designed output cam are conducted to evaluate the output characteristics in the variable-stiffness mode and to compare the simulated rapid motion with the mathematical model, thereby validating the theoretical model. (c) 2022 The Author. Published by The Society of Artificial Life and Robotics. This is an open access article distributed under the CC BY-NC 4.0 license (http://creativecommons.org/licenses/by-nc/4.0/).
Automated piano player systems enable highly precise keystrokes and pedal operations. However, a direct translation of score data into performance often results in a mechanical and inexpressive sound, failing to capture the nuanced dynamics of a human pianist's interpretation. This discrepancy arises because pianists uniquely determine various performance parameters, such as note loudness (Velo), the time between notes (Step), and individual note durations (Gate). While deep learning has been utilized in prior research to predict these parameters, the accuracy of Velo prediction, in particular, has remained a significant challenge. To address this limitation, this paper proposes a novel deep learning system specifically designed to enhance the accuracy of Velo prediction by integrating two distinct neural networks. Furthermore, experiments conducted with our system demonstrate improved prediction accuracy compared to previous studies.
Limited access to electricity in rural areas of developing countries has driven innovation in gravity-assisted human-powered mechanical systems. This study presents the mathematical modeling and simulation of a newly designed hide tanning device that utilizes a simple pendulum mechanism powered by human muscle force. The equipment integrates a simple pendulum, cylindrical gear transmission, bearings, and hide straps into a dynamic system. Equations of motion were derived using the Lagrangian method, validated through numerical simulation over a ten-second period. The torque resistance of the hide strap was evaluated using finite element analysis (FEA) in a previous study, enabling the calculation of the strap's resistance coefficient. Simulation results demonstrated the damping effect caused by the hide straps on the pendulum's oscillation and quantified the required excitation force applied by hand. The device is capable of tanning up to six hide straps simultaneously. The findings confirm that the proposed equipment effectively reduces physical effort, improves labor efficiency, and offers a sustainable and user-friendly solution suitable for traditional hide processing in remote and off-grid communities. (c) 2022 The Author. Published by The Society of Artificial Life and Robotics. This is an open access article distributed under the CC BY-NC 4.0 license (http://creativecommons.org/licenses/by-nc/4.0/).
Agriculture is one of the most ancient and most important professions forming the base of any society. The development of any country depends on the agricultural produce and its related areas to ensure greater growth in the country. One of the major problems affecting the agricultural produce of farmers worldwide is the unrestricted growth of weeds in the farm and agricultural areas which results in reduced produce for the farmers. One of the most elementary steps in the process of weed removal involves the detection of weeds in a field filled with agricultural produce. This process has been made easy by implementing the YOLOv8 process, which has produced great results ensuring easy detection of weeds and crops, making it easier and efficient for the farmers to increase and enhance their produce. YOLOv8 offers improved weed and crop detection with a precise classification rate of 0.9895 which indicates a highly accurate and successful classification. This allows farmers to efficiently identify and eliminate weeds, leading to higher productivity and better crop yields, ultimately supporting the agricultural growth of the country. This model can ensure easier, more efficient, and enhanced detection to improve the process of identifying the weeds and thereby eliminating them. (c) 2022 The Author. Published by The Society of Artificial Life and Robotics. This is an open access article distributed under the CC BY-NC 4.0 license (http://creativecommons.org/licenses/by-nc/4.0/).
Monitoring the operational integrity of industrial control systems (ICS) is a fundamental concern in modern infrastructure environments. While previous studies have primarily relied on direct access to controllers' data for system observation, this study adopts a passive network-based approach to minimize potential disruptions. By analyzing communication traffic within a simulated dam control system, the research investigates how network-observable information exchanged between devices can reflect system-level operational behavior. Through detailed inspection of packet-level data, including protocol usage, register values that reveal PLC operational states, the study aims to enhance situational awareness without interfering with system operations. (c) 2022 The Author. Published by The Society of Artificial Life and Robotics. This is an open access article distributed under the CC BY-NC 4.0 license (http://creativecommons.org/licenses/by-nc/4.0/).
Image-based visual regression testing has the problem that it takes time required to find layout defects. Therefore, this paper develops MIXVRT (MIX Visual Regression Testing tool), which mixes image comparison and HTML code comparison. It highlights the layout defects. From evaluation experiments, we have confirmed that the time required to find layout defects can be reduced compared to the conventional methods of image-based visual regression testing, while detecting them accurately without omissions or false detections. (c) 2022 The Author. Published by The Society of Artificial Life and Robotics. This is an open access article distributed under the CC BY-NC 4.0 license (http://creativecommons.org/licenses/by-nc/4.0/).
Aquaculture continues to expand as a response to rising seafood demand, but feeding remains a critical challenge due to its high costs and environmental impact. This study introduces an underwater imaging system that integrates video enhancement, YOLOv8-based fish detection, and velocity estimation to provide a data-driven solution for optimizing feeding strategies. Unlike conventional farmer intuition, the proposed approach offers objective monitoring of fish behavior under real aquaculture conditions. The system enhances underwater video quality by correcting color distortion, reducing noise, and sharpening contours, which improved fish detection accuracy from 69.3% to 73.2%. YOLOv8 achieved an overall detection accuracy of 85%, while velocity tracking successfully distinguished between normal and hunger-driven behaviors. These results confirm that fish velocity is a reliable indicator of feeding demand. By linking motion dynamics with feeding decisions, the system can reduce feed waste, lower costs, and improve fish health while minimizing environmental impacts. This work demonstrates the potential of integrating artificial intelligence and imaging technologies to establish standardized, sustainable, and more profitable aquaculture feeding practices. Future studies will focus on larger datasets, adaptive enhancement techniques, and real-time feeding control. (c) 2022 The Author. Published by The Society of Artificial Life and Robotics. This is an open access article distributed under the CC BY-NC 4.0 license (http://creativecommons.org/licenses/by-nc/4.0/).
The implementation of industrial robots is a critical strategy for mitigating the severe labor shortages affecting all industries in Japan. A significant barrier to their widespread adoption is the substantial capital investment required for the hardware and system integration. This study addresses this challenge through the development of a mobile Augmented Reality (AR) application designed to facilitate the robot adoption process. We have engineered and validated a system that enables the visualization and verification of a robot's operational trajectory prior to its physical installation, confirming its efficacy. (c) 2022 The Author. Published by The Society of Artificial Life and Robotics. This is an open access article distributed under the CC BY-NC 4.0 license (http://creativecommons.org/licenses/by-nc/4.0/).
The Schneider Electric Twido PLCs are analyzed, focusing on the UMAS protocol vulnerabilities, which lack essential security features such as encryption, authentication, and replay attack protection. Key design flaws, including unencrypted communications and unrestricted memory access, are identified and real-world attacks are replicated using publicly disclosed CVEs. A Snort-based Intrusion Detection System (IDS) is developed to address these vulnerabilities, incorporating custom rules to detect abnormal traffic patterns and high-risk function codes within the UMAS protocol. Simulated attack scenarios confirm the IDS's ability to identify unauthorized operations. This solution is lightweight, scalable, and offers practical security improvements for industrial control systems relying on proprietary protocols like UMAS. (c) 2022 The Author. Published by The Society of Artificial Life and Robotics. This is an open access article distributed under the CC BY-NC 4.0 license (http://creativecommons.org/licenses/by-nc/4.0/).
Inrecent years, data-driven approaches have become increasingly important in sports analytics, particularly in the context of tactical analysis. Inthe domain of volleyball, the precise estimation of player positions is of paramount importance for the purpose of performance evaluation. Conventional methodologies are contingent on projective transformation employing fixed reference points; a process which restricts its applicability when considering variable viewpoints. This limitation assumes particular relevance in the context of broadcast footage. The present study proposes a robust system for estimating player positions from arbitrary camera angles, including legacy and zoomed-in footage. The proposed methodology utilizes the YOLOv9 model for player detection and employs manual identification of court lines and the net to define dynamic reference points for homography. The findings of Experiment 1 demonstrate that player positions can be estimated with an average error of 0.30 meters, which is sufficient for tactical use. Furthermore, experiment 2 introduces a dual-camera triangulation approach to address the challenge of estimating airborne players, where conventional ground-contact assumptions are inadequate. The synchronization of cameras and the utilization of calibration through the employment of chessboard patterns facilitate the computation of the three-dimensional position of jumping players, yielding an average error of 0.43 meters. This outcome underscores the method's aptitude for effectively managing real volleyball dynamics, incorporating in-air motion. Collectively, these methodologies furnish a versatile and precise instrument for volleyball analysis, thereby establishing a foundation for more extensive implementations within the domain of sports informatics. (c) 2022 The Author. Published by The Society of Artificial Life and Robotics. This is an open access article distributed under the CC BY-NC 4.0 license (http://creativecommons.org/licenses/by-nc/4.0/).
The preservation of construction heritage faces increasing challenges associated with aging infrastructure, environmental degradation, and limited conservation resources. This study proposes a structured Digital Guardian Framework integrating artificial intelligence (AI), robotics, and digital twin technologies for intelligent heritage conservation. Unlike conventional review-based discussions, this research introduces a methodological framework that combines AI-driven predictive analytics, robotic inspection and intervention systems, and digital monitoring environments to support decision-making in heritage preservation. The framework is validated through analytical evaluation and application to the Sultan Abdul Samad Building in Malaysia, demonstrating how automated inspection, risk prediction, and non-invasive restoration strategies can enhance conservation efficiency while maintaining architectural authenticity. Quantitative performance indicators suggest improvements in inspection accuracy, risk reduction, and lifecycle sustainability compared with traditional conservation approaches. The study contributes a scalable interdisciplinary model bridging robotics engineering and heritage conservation, supporting future smart preservation ecosystems. (c) 2022 The Author. Published by The Society of Artificial Life and Robotics. This is an open access article distributed under the CC BY-NC 4.0 license
The collaborative behavior of multiple systems provides valuable functions and services to users. However, it is actualized by large and complex implementations, which frequently include serious failures. In this study, we propose an automated random simulation (ARS) technique for checking the abstract collaborative behavior of multiple systems at the design level. The abstract collaborative behavior is expected to be designed using an extended place/transition net with attributed tokens (EPNAT), and the checking is performed dynamically based on the design called "EPNAT model". The ARS technique consists of (1) an algorithm for model execution using random search with the evaluation of constraints including feasibility, and (2) a stopping criterion for model execution focusing on glue transitions. The ARS technique requires tool support; therefore, we developed a prototype tool. We ran the prototype tool with a trial model and three faulty models, and found its effectiveness and future challenges. (c) 2022 The Author. Published by The Society of Artificial Life and Robotics. This is an open access article distributed under the CC BY-NC 4.0 license (http://creativecommons.org/licenses/by-nc/4.0/).
This study focuses on Google Maps as the platform to investigate the relationship between review counts and review ratings. Specifically, we conducted a questionnaire-based survey in which participants were asked to choose between two options, each presenting a different combination of review count and rating. Based on the questionnaire survey responses, we performed a correlation analysis, a random forest analysis, and an analysis of the impact of differences in review counts to explore the relationship between review quantity and quality. The results revealed that review ratings (qualitative information) tend to have a stronger influence on users' choices than review counts (quantitative information) when selecting tourist destinations. Furthermore, it was found that as the difference in review ratings increases, the ability of a higher review count to compensate for a lower rating diminishes. (c) 2022 The Author. Published by The Society of Artificial Life and Robotics. This is an open access article distributed under the CC BY-NC 4.0 license
Driver fatigue, feelings of emotional distress and impairment as a result of stressful events can pose significant risks of road safety. This research paper proposes a deep learning-based pose estimation system, which aims to identify unsafe driver states, by quantifying the driver's posture, head orientation, and their gesture movements. The developed model is trained in a diverse range of driving situations and identifies physiological and behavioural markers associated with fatigue driving. Unlike existing methods, it integrates pose estimation in conjunction with emotional and motion cues, allowing it to function reliably even during low-lighting or partially obscured conditions. (c) 2022 The Author. Published by The Society of Artificial Life and Robotics. This is an open access article distributed under the CC BY-NC 4.0 license (http://creativecommons.org/licenses/by-nc/4.0/).
In professional tennis, ranking systems such as the ATP rankings often exhibit inconsistencies between player rankings and actual match outcomes. These discrepancies, referred to in this study as violations, are exacerbated by non-uniform tournament participation and the selective inclusion of results in official rankings. This study proposes a novel ranking method that aggregates match outcomes from all tournaments used in each player's ATP ranking calculation. The method employs a directed graph representation and an optimization model to minimize violations while accounting for asymmetries in data inclusion. An empirical evaluation using the top 10 ATP players as of December 2023 demonstrates that the proposed method improves overall consistency with match outcomes, while causing some shifts in individual rankings. The method offers a fairer framework for evaluating player performance under conditions of selective and asymmetric tournament participation. (c) 2022 The Author. Published by The Society of Artificial Life and Robotics. This is an open access article distributed under the CC BY-NC 4.0 license(http://creativecommons.org/licenses/by-nc/4.0/).
Because of non-integrable constraints, we cannot regulate the nonholonomic systems towards arbitrary directions in the state space. The stabilization and tracking control laws developed for nonholonomic systems are generally mutual, i.e., the stabilization law is inapplicable for tracking uses and vice versa. The current work investigates the control problem of differentially-driven wheeled mobile robots and demonstrates an initial idea of a novel control design approach, named practical linearization control, for nonholonomic systems. We define an external dynamic oscillator and fuse it with robot states, followed by converting the nonholonomic robot model into a fully-actuated and linearizable one. Such fusion and conversion introduce a new control input without increasing the number of states to be regulated. Finally, we propose a continuous control law that can be used for both tracking and stabilization control tasks. It is, in Lyapunov's sense, proven that the tracking errors can be driven into an arbitrarily small ball enclosing the origin. Simulation results are carried out to validate the proposed control law. (c) 2022 The Author. Published by The Society of Artificial Life and Robotics. This is an open access article distributed under the CC BY-NC 4.0 license (http://creativecommons.org/licenses/by-nc/4.0/).
This study presents an in-depth evaluation and comparison of three mainstream object detection architectures - YOLOv5, YOLOv7, and YOLOv8 - in the context of intelligent music score recognition. Utilizing a labeled musical note dataset from Roboflow, all models were trained and tested under a consistent experimental workflow using Google Colab. Experimental results demonstrate that YOLOv8 outperforms the other models in key metrics such as mAP@0.5, precision, recall, and convergence stability, indicating its superior capability for small object detection and generalization. While YOLOv5 exhibited stable training behavior, its performance in precision and recall remained limited. YOLOv7, despite its theoretical advantages in inference speed, failed to deliver consistent detection results in this task. The findings validate YOLOv8's robustness in musical note detection under complex conditions and offer technical insights for selecting optimal models for intelligent score recognition systems. This work also extends the authors' previous research on an automatic soprano recorder-playing system, enhancing its perceptual module through improved note recognition accuracy. (c) 2022 The Author. Published by The Society of Artificial Life and Robotics. This is an open access article distributed under the CC BY-NC 4.0 license (http://creativecommons.org/licenses/by-nc/4.0/).
