作者：
Yumei WangChuancong TangHai-Tao ZhangSchool of Artificial Intelligence and Automation
the Engineering Research Center of Autonomous Intelligent Unmanned Systemsthe Key Laboratory of Image Processing and Intelligent Controland the State Key Laboratory of Digital Manufacturing Equipment and TechnologyHuazhong University of Science and Technology
There are always some "key" nodes in a big complex network,which can joint the most connected *** to identify these nodes,finding a minimum set of nodes to attack for reducing the size of residual network...
There are always some "key" nodes in a big complex network,which can joint the most connected *** to identify these nodes,finding a minimum set of nodes to attack for reducing the size of residual network's Largest Connected Component(LCC) to break up the original network,has become a research ***,a method for determining the"key" nodes based on reinforcement learning framework and supervised learning model is *** algorithm can not only utilize the dynamic exploration ability of reinforcement learning to collect a rich training dataset,but also take advantage of the characteristics that supervised learning is adaptive and has strong generalization ability to possess high efficiency and strong *** order to further improve the algorithm's performance,-greedy mechanism is used to explore more network *** experiment results show that given the same fraction of removed nodes,our algorithm can make the residual LCC smaller in various networks which is superior to the state-of-the-art algorithms in terms of effectiveness and generalization.
This article investigates the multistability and stabilization of fractional-order competitive neural networks (FOCNNs) with unbounded time-varying delays. By utilizing the monotone operator, several sufficient condit...
详细信息
This article investigates the multistability and stabilization of fractional-order competitive neural networks (FOCNNs) with unbounded time-varying delays. By utilizing the monotone operator, several sufficient conditions of the coexistence of equilibrium points (EPs) are obtained for FOCNNs with concave-convex activation functions. And then, the multiple mu-stability of delayed FOCNNs is derived by the analytical method. Meanwhile, several comparisons with existing work are shown, which implies that the derived results cover the inverse-power stability and Mittag-Leffler stability as special cases. Moreover, the criteria on the stabilization of FOCNNs with uncertainty are established by designing a controller. Compared with the results of fractional-order neural networks, the obtained results in this article enrich and improve the previous results. Finally, three numerical examples are provided to show the effectiveness of the presented results.
Most proposed memristor-based circuits of associative memory consider various mechanisms in only one associative memory. Few works on circuit design of sequential associative memory have been reported. In this paper, ...
详细信息
Tactile object recognition is vital for robotic handling systems;however, existing technologies that concentrate on tactile sensors with high modulus are not suitable for soft grippers to classify deformable objects. ...
详细信息
Tactile object recognition is vital for robotic handling systems;however, existing technologies that concentrate on tactile sensors with high modulus are not suitable for soft grippers to classify deformable objects. In this letter, we integrated an indenter layer into the traditional microfluidic tactile sensor to increase its sensitivity based on the lensing effect of human skin. For the application of the developed sensor, we built HustGripper, a tendon-driven soft gripper, where the sensor was bonded on the fingertip. Experiments on the tactile classification of the deformable objects were conducted to validate the performance of the sensor, where different indenters, exploratory procedures, and data processing approaches were considered to explore the key factor to determine the classification accuracy.
作者：
Zou, An-MinLiu, YangyangHou, Zeng-GuangHu, ZhipeiShantou Univ
Coll Engn Dept Elect & Informat Engn Guangdong Prov Key Lab Digital Signal & Image Pro Shantou 515063 Peoples R China Shantou Univ
Minist Educ Key Lab Intelligent Mfg Technol Shantou 515063 Peoples R China Chinese Acad Sci
Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Shantou Univ
Coll Engn Guangdong Prov Key Lab Digital Signal & Image Pro Shantou 515063 Peoples R China Shantou Univ
Coll Engn Dept Elect & Informat Engn Shantou 515063 Peoples R China Univ Chinese Acad Sci
Sch Artificial Intelligence Beijing 100049 Peoples R China Macau Univ Sci & Technol
Inst Syst Engn CASIA MUST Joint Lab Intelligence Sci & Technol Macau Peoples R China
This article addresses the issue of output-feedback consensus control of multiagent systems under the directed topology and subject to bounded external disturbances. By employing a smooth time-varying function, a dist...
详细信息
This article addresses the issue of output-feedback consensus control of multiagent systems under the directed topology and subject to bounded external disturbances. By employing a smooth time-varying function, a distributed practical predefined-time (PPT) observer is developed to estimate the reference trajectory for the entire team (i.e., the leader's state) and a practical preset-time extended-state observer is also proposed to estimate bounded disturbances and unmeasurable system states. Next, a novel continuous and nonsingular PPT consensus control law is designed on the basis of the observers. Furthermore, the designed control protocol can achieve PPT stability, that is, consensus tracking errors are enforced to a neighborhood around zero within a predetermined time, which can be specified a priori, independent of initial states of agents and/or any other design parameters. Finally, illustrative numerical examples, including a comparative one, are provided to demonstrate the performance of the present predefined-time control approach.
NOMA (Non-Orthogonal Multiple Access), as one of the candidate technologies of 5G, can improve the spectrum efficiency and system capacity, and has attracted wide attention. The essence of NOMA is multi-user overlay t...
详细信息
Point-supervised Temporal Action Localization (PSTAL) is an emerging research direction for label-efficient learning. However, current methods mainly focus on optimizing the network either at the snippet-level or the ...
详细信息
Transferring vision-language knowledge from pretrained multimodal foundation models to various downstream tasks is a promising direction. However, most current few-shot action recognition methods are still limited to ...
详细信息
Deep perception of the unmanned surface vehicle's surroundings is an inaccessible part of its fully autonomous navigation mission. The existing methods, whether based on traditional stereo matching or deep learnin...
Deep perception of the unmanned surface vehicle's surroundings is an inaccessible part of its fully autonomous navigation mission. The existing methods, whether based on traditional stereo matching or deep learning, do not fully consider the characteristics of water environment, resulting in severe error depths in weak textures(sky, calm lake) and water reflections regions, that increases the risk of running aground or collision. What is worse that there is not a public dataset for depth estimation in the water environment. Therefore, this work proposes a self-supervised model for depth estimation named Water Depth Perception Network(WDNet) to address these problems. The decoder of this network has a wider receptive field and can effectively handle the depth error in the weak texture region. Besides, the WDNet is trained with a novel and effective loss function which assist the network to reduce errors in sky and water region, and some indexes are proposed to evaluate the model's performances in sky and water region. Finally, our proposed WDNet achieves a 0.1056 absolute relative error in ranging, the average number of error pixels in the sky area drops from 15803.87 to 580.91, which only accounted for 0.29% of the image,and the error in water region drops from 51.04 to 6.75, all of them are superior to the performance of baseline model.
Partially annotated images are easy to obtain in multi-label classification. However, unknown labels in partially annotated images exacerbate the positive-negative imbalance inherent in multi-label classification, whi...
Partially annotated images are easy to obtain in multi-label classification. However, unknown labels in partially annotated images exacerbate the positive-negative imbalance inherent in multi-label classification, which affects supervised learning of known labels. Most current methods require sufficient image annotations, and do not focus on the imbalance of the labels in the supervised training phase. In this paper, we propose saliency regularization (SR) for a novel self-training framework. In particular, we model saliency on the class-specific maps, and strengthen the saliency of object regions corresponding to the present labels. Besides, we introduce consistency regularization to mine unlabeled information to complement unknown labels with the help of SR. It is verified to alleviate the negative dominance caused by the imbalance, and achieve state-of-the-art performance on Pascal VOC 2007, MS-COCO, VG-200, and Openimages V3.
暂无评论