In this study, we propose a telerehabilitation system designed to remotely monitor patients and analyze data collected from wearable devices throughout a 12-week physical exercise program. The system, developed under ...
详细信息
ISBN:
(数字)9798331521165
ISBN:
(纸本)9798331521172
In this study, we propose a telerehabilitation system designed to remotely monitor patients and analyze data collected from wearable devices throughout a 12-week physical exercise program. The system, developed under the RAPIDO project, utilizes a multiple linear regression federated learning (MLRFL) approach to predict patients' rehabilitation outcomes while preserving data privacy. In particular, federated learning allows decentralized data analysis, ensuring that sensitive patient data remains on local devices while only model updates are shared. Preliminary results of the MLRFL compared to a centralized learning architecture show similar prediction performance while adding all the federated learning advantages, thus making it a promising approach.
This study aims to develop an algorithm that contributes to participation evaluation by analyzing the activeness and consistency of user responses in an interactive conversation chatbot system. DST analysisbased AI pr...
详细信息
ISBN:
(数字)9798331520403
ISBN:
(纸本)9798331520410
This study aims to develop an algorithm that contributes to participation evaluation by analyzing the activeness and consistency of user responses in an interactive conversation chatbot system. DST analysisbased AI prompt engineering was proposed to evaluate the activeness of responses through the user's response speed and length of response, and to determine whether it is consistent with past utterances. By integrating these factors, the system increases the reliability of the response and strengthens the interaction with the user by creating personalized chatbot utterances. This approach has applicability in psychological counseling and is expected to improve user participation in various industries, including education and healthcare.
In this paper, we introduce a novel Direct Yaw Moment Control (DYC) system designed to bolster the stability of four-wheel independent drive (4WID) electric vehicles in diverse extreme driving conditions. Our proposed...
详细信息
ISBN:
(数字)9798331533892
ISBN:
(纸本)9798331533908
In this paper, we introduce a novel Direct Yaw Moment Control (DYC) system designed to bolster the stability of four-wheel independent drive (4WID) electric vehicles in diverse extreme driving conditions. Our proposed system is developed based on the design of Non-singular Fast Terminal Sliding Mode Control (NFTSMC) methods to calculate two optimal additional yaw moments, each targeting specific control objectives: the desired yaw rate and the desired sideslip angle. These calculated values are then intelligently weighted in real time using a Fuzzy Logic system to determine the final additional yaw moment applied to the vehicle. The stability of the NFTSMC methods is rigorously ensured through the Lyapunov theory. Simulation results underscore the efficacy of our proposed DYC system, particularly in navigating through extreme driving scenarios. Comparisons with no control and fixed weight-based SMC strategies demonstrated significant improvements in both yaw rate and sideslip angle tracking performance. The proposed method not only amplifies control effectiveness, ensuring swift convergence and high precision, but also substantially mitigates chattering phenomena, as evidenced by yaw moment and torque observations.
This paper presents the design and implementation of an Internet of Thing (IOT)-based long-distance fire-extinguishment system named “Stationary 3-Axis Fire-Emergency Response Base” (STAFERB). The system aims to pro...
详细信息
ISBN:
(数字)9798331520762
ISBN:
(纸本)9798331520779
This paper presents the design and implementation of an Internet of Thing (IOT)-based long-distance fire-extinguishment system named “Stationary 3-Axis Fire-Emergency Response Base” (STAFERB). The system aims to provide immediate response to fire hazards in various environments, including residential areas, building complexes, commercial areas, small-scale industries, large factories, dense slum areas, and remotely located forest regions. The proposed STAFERB is designed to receive fire location coordinates, fire intensity, and probable cause information. It then calculates the path of a projectile based on considering obstacles and self-detection of a clear line of sight to reach the t1arget location. The system uses this information to select the appropriate speed and type of fire retardant. The designed STAFERB features robust communication, self-path detection, auto-orientation, and reduced response time, making it a significant advancement in fire-fighting technology. Experimental results demonstrate the effectiveness of the proposed STAFERB in mitigating fire hazards and hence can be well suited for real-time disaster management.
To address the issue of data scarcity in entity relationship extraction tasks within the domain of ancient texts and meet the needs of researchers in digital humanities, this paper proposes an automated data annotatio...
详细信息
ISBN:
(数字)9798331529482
ISBN:
(纸本)9798331529499
To address the issue of data scarcity in entity relationship extraction tasks within the domain of ancient texts and meet the needs of researchers in digital humanities, this paper proposes an automated data annotation method based on the large language model ChatGPT and prompt engineering. By treating the large language model as a “data annotator,” we developed an entity relationship extraction dataset tailored to ritual scenarios in ancient texts for the natural language processing field. This dataset includes five entity types and ten relationship types, characterized by precise labeling. To verify the robustness and versatility of the dataset, comprehensive experiments were conducted on three pre-trained language models. The results demonstrate that pre-trained models based on prompt learning achieve the best performance in entity relationship extraction tasks. This study shows that the data annotation method leveraging large language models provides a feasible solution for automated data annotation, and the corpus of etiquette entity relationship extraction lays an important foundation for the construction of etiquette question answering system and knowledge graph of ancient books.
Security of software systems has become increasingly important due to the advancement in technology that occurs on a daily basis and due to the interconnectivity that the Internet network system provides. The manual t...
详细信息
ISBN:
(数字)9798331534677
ISBN:
(纸本)9798331534684
Security of software systems has become increasingly important due to the advancement in technology that occurs on a daily basis and due to the interconnectivity that the Internet network system provides. The manual testing process is time-consuming process and inefficient, especially for very large and complex systems. Reinforcement learning has shown promising results in different test generation approaches due to its ability to optimize the test generation process towards relevant parts of the system. A considerable body of work has been developed in recent years to exploit reinforcement learning for security test generation. This study provides a list of approaches and tools for security test generation using Reinforcement Learning (RL). By searching popular research publication databases, a list of 47 relevant studies has been identified and classified according to the type of approach, RL algorithm, application domain and publication metadata.
In recent years, point cloud streaming has attracted attention. Point cloud provides with higher reality and immersiveness. To reduce the file size of point cloud, some data compression methods such as video-based poi...
详细信息
ISBN:
(数字)9798331521165
ISBN:
(纸本)9798331521172
In recent years, point cloud streaming has attracted attention. Point cloud provides with higher reality and immersiveness. To reduce the file size of point cloud, some data compression methods such as video-based point cloud compression (V-PCC) are presented. However, most of methods are not suitable for point cloud live streaming due to the processing time of data compression. In this paper, we propose a point cloud live streaming system using scalable point cloud partitioning. The proposed method reduces file size by partitioning point cloud data into multiple layers and streams them sequentially, aiming to improve the number of rendered points and reduce playback interruptions (stalling). We implement the proposed system on actual devices and conduct performance evaluations.
Microelectromechanical system (MEMS) based pressure sensors have been utilized for decades; however, new trends in pressure sensors have recently emerged, such as increased sensitivity, a broader range and reduced chi...
详细信息
ISBN:
(数字)9798331508890
ISBN:
(纸本)9798331508906
Microelectromechanical system (MEMS) based pressure sensors have been utilized for decades; however, new trends in pressure sensors have recently emerged, such as increased sensitivity, a broader range and reduced chip size. This paper presents a tiny 0.6mm×0.8mm piezoresistive pressure sensor that offers exceptional sensitivity (0.27mV/kPa/3.3V) at a wide range of pressures (0-1MPa). The innovative composite pressure-sensitive film of the sensor is composed of a 10μm "*"-shaped single-crystalline silicon structure and a remarkably thin thickness of only 2.5μm poly-silicon film. It is developed utilizing the thin-film under bulk-silicon technique. And simultaneous improvement of detection sensitivity and linearity is achieved by etching out the nonlinear deformation region of the film.
In this work, we proposed a Rectangular Dielectric Resonator Antenna (RDRA) based Global Positioning system (GPS) antenna with energy harvesting capabilities to replace and eradicate traffic jams at the toll plaza due...
详细信息
ISBN:
(数字)9798331529833
ISBN:
(纸本)9798331529840
In this work, we proposed a Rectangular Dielectric Resonator Antenna (RDRA) based Global Positioning system (GPS) antenna with energy harvesting capabilities to replace and eradicate traffic jams at the toll plaza due to existing RFID technology. The GPS-based Electronic Toll with an efficient system is envisioned to streamline toll operations, reduce congestion, and improve the overall user experience with localization capabilities. The L1 band GPS antenna is connected to two channels, one with energy harvesting and another with an onboard unit (OBU) of the electronic system. In this paper, the GPS L1 antenna is designed at 1575.42 MHz. The GPS L1 antenna is designed with a matching circuit and RF to DC voltage devices, such as speed sensors, that can be powered by radio frequency energy harvesting systems used at GPS-based toll plazas.
Smart wheelchairs are designed to increase mobility, safety, and independence for the elderly and disabled persons. They are self-powered, reducing reliance on external power sources by incorporating solar panels that...
详细信息
暂无评论