Object detection,a major challenge in computer vision and pattern recognition,plays a significant part in many applications,crossing artificial intelligence,face recognition,and autonomous driving.It involves focusing...Object detection,a major challenge in computer vision and pattern recognition,plays a significant part in many applications,crossing artificial intelligence,face recognition,and autonomous driving.It involves focusing on identifying the detection,localization,and categorization of targets in images.A particularly important emerging task is distinguishing real animals from toy replicas in real-time,mostly for smart camera systems in both urban and natural environments.However,that difficult task is affected by factors such as showing angle,occlusion,light intensity,variations,and texture differences.To tackle these challenges,this paper recommends Group Sparse YOLOv8(You Only Look Once version 8),an improved real-time object detection algorithm that improves YOLOv8 by integrating group sparsity regularization.This adjustment improves efficiency and accuracy while utilizing the computational costs and power consumption,including a frame selection approach.And a hybrid parallel processing method that merges pipelining with dataflow strategies to improve the performance.Established using a custom dataset of toy and real animal images along with well-known datasets,namely ImageNet,MSCOCO,and CIFAR-10/100.The combination of Group Sparsity with YOLOv8 shows high detection accuracy with lower latency.Here provides a real and resource-efficient solution for intelligent camera systems and improves real-time object detection and classification in environments,differentiating between real and toy animals.展开更多
Autonomous connected vehicles(ACV)involve advanced control strategies to effectively balance safety,efficiency,energy consumption,and passenger comfort.This research introduces a deep reinforcement learning(DRL)-based...Autonomous connected vehicles(ACV)involve advanced control strategies to effectively balance safety,efficiency,energy consumption,and passenger comfort.This research introduces a deep reinforcement learning(DRL)-based car-following(CF)framework employing the Deep Deterministic Policy Gradient(DDPG)algorithm,which integrates a multi-objective reward function that balances the four goals while maintaining safe policy learning.Utilizing real-world driving data from the highD dataset,the proposed model learns adaptive speed control policies suitable for dynamic traffic scenarios.The performance of the DRL-based model is evaluated against a traditional model predictive control-adaptive cruise control(MPC-ACC)controller.Results show that theDRLmodel significantly enhances safety,achieving zero collisions and a higher average time-to-collision(TTC)of 8.45 s,compared to 5.67 s for MPC and 6.12 s for human drivers.For efficiency,the model demonstrates 89.2% headway compliance and maintains speed tracking errors below 1.2 m/s in 90% of cases.In terms of energy optimization,the proposed approach reduces fuel consumption by 5.4% relative to MPC.Additionally,it enhances passenger comfort by lowering jerk values by 65%,achieving 0.12 m/s3 vs.0.34 m/s3 for human drivers.A multi-objective reward function is integrated to ensure stable policy convergence while simultaneously balancing the four key performance metrics.Moreover,the findings underscore the potential of DRL in advancing autonomous vehicle control,offering a robust and sustainable solution for safer,more efficient,and more comfortable transportation systems.展开更多
The goal of this paper is to analyze and propose a reconstruction of functional possibilities and database requirements of a Web based Educational Information system. For the research the Information system of the Tec...The goal of this paper is to analyze and propose a reconstruction of functional possibilities and database requirements of a Web based Educational Information system. For the research the Information system of the Technology School ＂electronic Systems＂ （TUES） associated with the Technical University of Sofia is on focus. The modules for admission of students, specialty classification, and graduation of students, management of the student＇s work in computer classrooms and lecturers＇ data management have been analyzed, developed and implemented. The additionally developed modules concern mainly the management of educational process and do not affect the e-learning or the official part modules. That led to the idea that the functionality for managing educational process has to be organized in a separate module defined as module for administrative services of educational process. Such restructuring of the system will bring flexibility in further growth of the system--for example students＇ admission or selection for different purposes.展开更多
The Taiping-Huangshan composite intrusion is a unique complex with characteristics changing from calc-alkaline (Taiping intrusion) to alkaline (Huangshan intrusion). Huangshan intrusion samples show a spectacular tetr...The Taiping-Huangshan composite intrusion is a unique complex with characteristics changing from calc-alkaline (Taiping intrusion) to alkaline (Huangshan intrusion). Huangshan intrusion samples show a spectacular tetrad effect in their REE distribution patterns as well as non-CHARAC (charge-and radius-controlled) trace element behavior, indicating a highly evolved late-stage magma component. This composite intrusion provides a rare opportunity to investigate the variance of tectonic setting and lithospheric thinning of the southeastern Yangtze Craton in late Mesozoic era. Zircon SHRIMP U-Pb analyses yield an emplacement age of 140.6±1.2 Ma for the Taiping intrusion, and ages of 127.7±1.3, 125.7±1.4, 125.1±1.5, and 125.2±5.5 Ma for four samples from the Huangshan intrusion respectively. The ages for four different phases of the Huangshan intrusion agree within their small analytical errors, indicating that the emplacement was in a short time. The Taiping and Huangshan intrusions are intimately associated, but there is about 15 Ma interval between their intrusion, and the magma characters change from calc-alkaline to alkaline without transition. This probably corresponds to lithospheric thinning of the southeastern Yangtze Craton. This event possibly happened from about 141 Ma (the emplacement age of the Taiping intrusion), to 128 Ma (start of emplacement of the Huangshan intrusion). The thinning mechanism is dominantly delamination.展开更多
文摘Object detection,a major challenge in computer vision and pattern recognition,plays a significant part in many applications,crossing artificial intelligence,face recognition,and autonomous driving.It involves focusing on identifying the detection,localization,and categorization of targets in images.A particularly important emerging task is distinguishing real animals from toy replicas in real-time,mostly for smart camera systems in both urban and natural environments.However,that difficult task is affected by factors such as showing angle,occlusion,light intensity,variations,and texture differences.To tackle these challenges,this paper recommends Group Sparse YOLOv8(You Only Look Once version 8),an improved real-time object detection algorithm that improves YOLOv8 by integrating group sparsity regularization.This adjustment improves efficiency and accuracy while utilizing the computational costs and power consumption,including a frame selection approach.And a hybrid parallel processing method that merges pipelining with dataflow strategies to improve the performance.Established using a custom dataset of toy and real animal images along with well-known datasets,namely ImageNet,MSCOCO,and CIFAR-10/100.The combination of Group Sparsity with YOLOv8 shows high detection accuracy with lower latency.Here provides a real and resource-efficient solution for intelligent camera systems and improves real-time object detection and classification in environments,differentiating between real and toy animals.
基金the Hebei Province Science and Technology Plan Project(19221909D)rincess Nourah bint Abdulrahman University Researchers Supporting Project number(PNURSP2025R308),Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.
文摘Autonomous connected vehicles(ACV)involve advanced control strategies to effectively balance safety,efficiency,energy consumption,and passenger comfort.This research introduces a deep reinforcement learning(DRL)-based car-following(CF)framework employing the Deep Deterministic Policy Gradient(DDPG)algorithm,which integrates a multi-objective reward function that balances the four goals while maintaining safe policy learning.Utilizing real-world driving data from the highD dataset,the proposed model learns adaptive speed control policies suitable for dynamic traffic scenarios.The performance of the DRL-based model is evaluated against a traditional model predictive control-adaptive cruise control(MPC-ACC)controller.Results show that theDRLmodel significantly enhances safety,achieving zero collisions and a higher average time-to-collision(TTC)of 8.45 s,compared to 5.67 s for MPC and 6.12 s for human drivers.For efficiency,the model demonstrates 89.2% headway compliance and maintains speed tracking errors below 1.2 m/s in 90% of cases.In terms of energy optimization,the proposed approach reduces fuel consumption by 5.4% relative to MPC.Additionally,it enhances passenger comfort by lowering jerk values by 65%,achieving 0.12 m/s3 vs.0.34 m/s3 for human drivers.A multi-objective reward function is integrated to ensure stable policy convergence while simultaneously balancing the four key performance metrics.Moreover,the findings underscore the potential of DRL in advancing autonomous vehicle control,offering a robust and sustainable solution for safer,more efficient,and more comfortable transportation systems.
文摘The goal of this paper is to analyze and propose a reconstruction of functional possibilities and database requirements of a Web based Educational Information system. For the research the Information system of the Technology School ＂electronic Systems＂ （TUES） associated with the Technical University of Sofia is on focus. The modules for admission of students, specialty classification, and graduation of students, management of the student＇s work in computer classrooms and lecturers＇ data management have been analyzed, developed and implemented. The additionally developed modules concern mainly the management of educational process and do not affect the e-learning or the official part modules. That led to the idea that the functionality for managing educational process has to be organized in a separate module defined as module for administrative services of educational process. Such restructuring of the system will bring flexibility in further growth of the system--for example students＇ admission or selection for different purposes.
基金Supported by National Natural Science Foundation of China (Grant Nos. 40772048, 40503006 and 40472035)China Geological Survey (Grant No. 1212010711814)
文摘The Taiping-Huangshan composite intrusion is a unique complex with characteristics changing from calc-alkaline (Taiping intrusion) to alkaline (Huangshan intrusion). Huangshan intrusion samples show a spectacular tetrad effect in their REE distribution patterns as well as non-CHARAC (charge-and radius-controlled) trace element behavior, indicating a highly evolved late-stage magma component. This composite intrusion provides a rare opportunity to investigate the variance of tectonic setting and lithospheric thinning of the southeastern Yangtze Craton in late Mesozoic era. Zircon SHRIMP U-Pb analyses yield an emplacement age of 140.6±1.2 Ma for the Taiping intrusion, and ages of 127.7±1.3, 125.7±1.4, 125.1±1.5, and 125.2±5.5 Ma for four samples from the Huangshan intrusion respectively. The ages for four different phases of the Huangshan intrusion agree within their small analytical errors, indicating that the emplacement was in a short time. The Taiping and Huangshan intrusions are intimately associated, but there is about 15 Ma interval between their intrusion, and the magma characters change from calc-alkaline to alkaline without transition. This probably corresponds to lithospheric thinning of the southeastern Yangtze Craton. This event possibly happened from about 141 Ma (the emplacement age of the Taiping intrusion), to 128 Ma (start of emplacement of the Huangshan intrusion). The thinning mechanism is dominantly delamination.
