Originally presented in previous work to capture the set of fundamental elements of the UML state machine specification, Common Declarative Language (CDL) provides a model that can aid in the validation and verificati...
详细信息
With the rapid development of intelligent systems, Multi-Agent Systems (MAS) have shown unique advantages in solving complex decision-making problems. Particularly in the field of Multi-Agent Reinforcement Learning (M...
详细信息
This paper addresses the limitations of the Contrastive Language-Image Pre-training (CLIP) model's image encoder and proposes a segmentation model WSSS-ECFE with enhanced CLIP feature extraction, aiming to improve...
详细信息
Human Action Recognition (HAR) has widespread applications in areas such as human-computer interaction, elderly care, and home healthcare. However, current sensor-based HAR faces challenges of low fine-grained recogni...
详细信息
Coalbed methane (CBM) is a vital unconventional energy resource, and predicting its spatiotemporal pressure dynamics is crucial for efficient development strategies. This paper proposes a novel deep learning–based da...
详细信息
Retinal vessel image segmentation is crucial for the early diagnosis and treatment of ophthalmic diseases. However, accurate segmentation remains challenging due to the complexity and diversity of retinal images, as w...
详细信息
Transformer-based methods have improved the quality of hyperspectral images (HSIs) reconstructed from RGB by effectively capturing their remote relationships. The self-attention mechanisms in existing Transformer mode...
详细信息
Graph Convolutional Networks (GCNs) have attracted considerable attention in the realm of human action recognition. However, conventional GCNs-based methods typically struggle to construct adjacency matrices that capt...
详细信息
Force feedback devices offer realistic and intuitive feedback to operators, and achieving higher accuracy and transparency has been a prominent research focus in this field. However, errors in real-time force or posit...
详细信息
Force feedback devices offer realistic and intuitive feedback to operators, and achieving higher accuracy and transparency has been a prominent research focus in this field. However, errors in real-time force or position calculations are inevitable, which can have adverse effects on the accuracy of the equipment. This article presents the design of a parallel mechanism that incorporates a constant force and velocity mapping relationship based on the type synthesis of the constant Jacobian matrix. Specifically, the mechanism maintains a fixed direction of force applied to the operating platform by the drive pair, which is mounted on the fixed platform in each limb, irrespective of position changes. This unique feature enables the mechanism to achieve a complete net weight balance. The implementation method is detailed in this article, which involves adding appropriate counterweights to achieve a balance between the weight of the connecting rod and the overall gravity of the operating platform. Furthermore, the optimization of structural parameters helps to improve the performance of the developed prototype. The proposed design scheme not only addresses the fundamental reduction of errors caused by real-time force and position mapping solving but also enhances operational transparency. Finally, simulation and experimental tests are conducted to validate the proposed theory.
Dynamic interval multi-objective optimization problems are a class of optimization problems whose interval parameters change with the environment. However, the existing algorithms fail to fully consider the characteri...
详细信息
Dynamic interval multi-objective optimization problems are a class of optimization problems whose interval parameters change with the environment. However, the existing algorithms fail to fully consider the characteristics of interval parameters and can not accurately assess the severity of environmental changes, resulting in a decline in the effectiveness of the detection mechanism. Therefore, effectively dealing with the inherent uncertainty of interval values becomes an important challenge. To address these problems, this paper proposes a dynamic interval multi- objective optimization algorithm based on environment change detection (IO-ECD). Firstly, a change severity detection operator is designed by using the average overlap degree of individual objective interval to classify different severity of environmental changes. Secondly, this paper uses the local search and the interval prediction mechanism based on feed-forward centroid and special points set to cope with various levels of environmental changes. Finally, inspired by hypervolume contribution and objective value inaccuracy, an interval crowding distance operator is constructed to guide population evolution. The algorithm is compared with six cutting-edge algorithms in eight test cases and a combinatorial optimization scenario. The experimental results show that the algorithm performs exceptionally well in most aspects and has strong competitiveness.
暂无评论