检索结果-内蒙古大学图书馆

2023 IEEE International Conference on Memristive Computing and Applications, ICMCA 2023

作者： Huang, Lili Zang, Hongyan Lei, Tengfei Li, Na Fu, Haiyan Liu, Aidi Jinan China School of Intelligent Manufacturing and Control Engineering Qilu Institute of Technology Jinan China School of Computer and Information Engineering Qilu Institute of Technology Jinan China

ISBN: (纸本)9798350316230

In this paper, a novel heterogeneous neural network is proposed by coupling improved memristor 2D HR neuron and 1D HNN neuron with locally active memristor. The effect of coupling intensity on synchronization behavior is analyzed. The results show that the increase in coupling intensity will lead to phase synchronization of the system. The coexistence of the firing pattern caused by the initial enhancement of the memristor is quantitatively analyzed and numerically simulated by introducing a multistable auto memristor. The results show that the newly constructed heterogeneous neural network exhibits an attractor bias pattern that enhances the initial migration behavior of the memristor, and these patterns have extreme multi-stability. © 2023 IEEE.

关键词： Memristors

来源：评论

学校读者我要写书评

暂无评论

MMLN: Multi-directional and Multi-constraint Learning Network for Remote Sensing Imagery Semantic Segmentation

引用

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 2024年 1-16页

作者： Sun, Hang Xie, Yongchang Ren, Dong Wen, Fangqing Tong, Lyuyang Chang, Laibin Hubei Key Laboratory of Intelligent Vision Based Monitoring for Hydroelectric Engineering China Three Gorges University Yichang China Institute of Vehicle Information Control and Network Technology Hubei University of Automotive Technology Shiyan China School of Computer Science Wuhan University Wuhan China

Recent advances in satellite remote sensing technology and computer technology have significantly impacted practical applications in remote sensing image segmentation. However, the prevalent hybrid segmentation models that combine Convolutional Neural Networks (CNNs) and Transformers, often overlook the critical exploration of local and global feature correlations across various scales. This exploration is essential for learning more representative features and strengthening context modeling capabilities. Additionally, the decoding layers of these models do not effectively exploit the pixel-level semantic relationships within cross-layer feature maps, thereby limiting the models' ability to discern small object features. To address these challenges, this paper introduces a Multi-directional and Multi-constraint Learning Network (MMLN) designed for semantic segmentation of remote sensing imagery. This network features a Multi-directional Dynamic Complement Decoder (MDCD), which enhances the interaction between local and global features in the feature space, and subsequently improves the feature discrimination within the segmentation network. Moreover, a Multi-constraint Saliency Boundary-adaptive Module (MSBM) is implemented to reinforce the spatial constraints on saliency at the edge regions and ensure semantic consistency along the mask boundaries. This, in turn, augments the segmentation model's capability to detect small objects. The evaluation on four datasets reveals that the MMLN outperforms the existing state-of-the-art methods in remote sensing imagery segmentation. The code is available at https://***/zhongyas/MMLN. Authors

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Design and implementation of a small diving safety detection underwater robot 7

Design and implementation of a small diving safety detection...

引用

2022 7th International Conference on Information Science, computer technology and Transportation, ISCTT 2022

作者： Ma, Qingqing Cheng, Jinglong Mai, Kaijun Pan, Enting Feng, Xizhe Ye, Zongyuan Institute of computer control technology Guangzhou Huali College Guangzhou China

ISBN: (纸本)9783800760565

In order to test the safety of diving in shallow waters, this design uses a small submersible safety detection underwater robot based on STM32 microcontroller, which can be used as a small cable unmanned underwater robot (ROV, Remote Operated Vehicle) detected in shallow waters. The underwater robot can realize the self-balance of the underwater posture, detect the underwater environment, fuse the sensor data, and send the water detection results to the upper computer display through the wireless module. Brief introduction of hardware structure design, software framework construction, introduce the control algorithm, sensor data collection and diving water hazard judgment. The underwater robot has verified the feasibility and stability of this design. © VDE VERLAG GMBH ∙ Berlin ∙ Offenbach.

关键词： Machine design

来源：评论

学校读者我要写书评

暂无评论

SSD object detection algorithm based on knowledge map

引用

International Journal of Wireless and Mobile Computing 2024年第2期27卷 152-160页

作者： Huang, Li Wang, Xiaofeng Lu, Jianhua Hu, Wei Zhang, Changrong College of Computer Science and Technology Wuhan University of Science and Technology Hubei Wuhan China China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan University of Science and Technology Hubei Wuhan China Key Laboratory of Metallurgical Equipment and Control Technology of the Ministry of Education Wuhan University of Science and Technology Hubei Wuhan China Precision Manufacturing Research Institute Research Centre for Biomimetic Robot and Intelligent Measurement and Control Wuhan University of Science and Technology Hubei Wuhan China

With the pervasive integration of artificial intelligence into all aspects of human life, talent emerges as a primary resource. Upon analysing the current state of talent training in higher education institutions, issues such as dispersed knowledge points, overlapping content, a singular practice approach and ineffective evaluation have been identified. In response to these challenges, this paper proposes a multidisciplinary and comprehensive practical teaching methodology grounded in the knowledge graph framework. It delves into diverse paths for practical teaching and assessment, including aspects like teaching objectives, problem decomposition, resource integration, implementation methods and performance evaluation. The practical application of the SSD algorithm in researching service robot indoor object detection serves as an illustrative example. Employing the holistic practical teaching approach facilitated by the knowledge graph, this model guides students in acquiring object detection expertise, thereby enhancing their comprehensive development. Copyright © 2024 Inderscience Enterprises Ltd.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of a Smart Orchard Comprehensive Service Platform

Design and Implementation of a Smart Orchard Comprehensive S...

引用

2023 IEEE International Conference on Electrical, Automation and computer Engineering, ICEACE 2023

作者： Xie, Ling Luan, Di Liu, Hongying Wei, Wei Zijin Institute of Nanjing University of Science and Technology Intelligent Control Academy Nanjing China Zijin Institute of Nanjing University of Science and Technology Computer Academy Nanjing China

ISBN: (纸本)9798350309614

The intelligent orchard integrated service platform is an innovative solution integrating software and hardware technology, which aims to improve the efficiency and quality of traditional orchard management. Traditional orchard planting relies on artificial experience and subjective judgment, and faces difficulties in pest control, water and fertilizer management and picking scheduling. This platform includes four sub parts: intelligent orchard monitoring system, target recognition and positioning system, pest identification system and integrated information service platform. It combines information transmission, image processing, artificial intelligence, Internet of things and data science to achieve comprehensive orchard management services, which helps to improve orchard management and production efficiency and promote the sustainable development of orchards. © 2023 IEEE.

关键词： Disease and Pest Identification Fruit Location Recognition Sensor Detection Smart Orchard Web Development

来源：评论

学校读者我要写书评

暂无评论

Design and Realization of Unmanned Vehicle Autonomous Navigation System Based on Binocular Camera 3

Design and Realization of Unmanned Vehicle Autonomous Naviga...

引用

3rd International Conference on computer Science, Electronic Information Engineering and Intelligent control technology, CEI 2023

作者： Guo, Tianxing Lin, Lianlei Liu, Huanyu Li, Junbao School of Electronics and Information Engineering Harbin Institute of Technology Department of Automatic Test and Control Harbin China Information Countermeasure Technique Institute School of Computer Science and Technology Harbin Institute of Technology Harbin China

ISBN: (纸本)9798350372052

Aiming at the navigation problem of unmanned vehicles in extreme environments such as communication interference and limited GPS signals, this study proposes an autonomous navigation method based on binocular cameras. The method enables the unmanned vehicle to complete the task of localization and map building using only binocular images, without the need for other sensors or signal sources. Meanwhile, this study also proposes a local path planning obstacle avoidance method based on depth map, which, when combined with global localization information, can take into account both local obstacle avoidance and global path navigation, and can cope with random environmental changes. The system uses a single sensor for autonomous obstacle avoidance and navigation, which reduces the computational requirements and ensures the low cost of the navigation system. In order to verify the reliability and effectiveness of the system under signal-constrained conditions, the system is evaluated in a simulation environment and a real field scenario, respectively. The experimental results show that the system is able to achieve reliable localization and path planning under signal-constrained conditions. © 2023 IEEE.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

MAPF-GPT: Imitation Learning for Multi-Agent Pathfinding at Scale 39

MAPF-GPT: Imitation Learning for Multi-Agent Pathfinding at ...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Andreychuk, Anton Yakovlev, Konstantin Panov, Aleksandr Skrynnik, Alexey AIRI Moscow Russia Federal Research Center "Computer Science and Control" The Russian Academy of Sciences Moscow Russia Moscow Institute of Physics and Technology Dolgoprudny Russia

ISBN: (纸本)157735897X

Multi-agent pathfinding (MAPF) is a problem that generally requires finding collision-free paths for multiple agents in a shared environment. Solving MAPF optimally, even under restrictive assumptions, is NP-hard, yet efficient solutions for this problem are critical for numerous applications, such as automated warehouses and transportation systems. Recently, learning-based approaches to MAPF have gained attention, particularly those leveraging deep reinforcement learning. Typically, such learning-based MAPF solvers are augmented with additional components like single-agent planning or communication. Orthogonally, in this work we rely solely on imitation learning that leverages a large dataset of expert MAPF solutions and transformer-based neural network to create a foundation model for MAPF called MAPF-GPT. The latter is capable of generating actions without additional heuristics or communication. MAPF-GPT demonstrates zero-shot learning abilities when solving the MAPF problems that are not present in the training dataset. We show that MAPF-GPT is able to outperform the state-of-the-art learnable MAPF solvers on a diverse range of problem instances and is computationally efficient during inference. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Research on regional personnel monitoring technology based on channel state information 7

Research on regional personnel monitoring technology based o...

引用

7th International Conference on Intelligent Computing and Signal Processing, ICSP 2022

作者： Mai, Kaijun Lu, Xinghua Luo, Guohua Cheng, Jinglong Guangzhou Huali College Institute of Computer Control Technology Guangzhou China

ISBN: (纸本)9781665478571

In view of the shortcomings of traditional camera and sensor type monitoring, such as blind spots, limited recognition distance and sensitive scene limitations, this paper proposes a human activity detection and monitoring method based on channel-state-information (CSI). The CSI information of the WiFi signal in the monitored area. Next, use the Butterworth low-pass filter to detect and remove abnormal data. And then use the principal component analysis (PCA) to extract the features of the human body posture, gait information, and number of people model;Learn to build a number recognition model for CSI data;because everyone is different, gait information can be used as an ID for human identification to identify different identities, and the human gait information based on Dynamic Time Warping (DTW) can be Effective identification, so as to play the effect of regional environmental monitoring. In the experiment, this method can achieve 92% capture performance for human gesture recognition, more than 93% error in indoor area recognition is less than 1, and the correct rate of gait recognition is up to 95.2%. © 2022 IEEE.

关键词： Personnel

来源：评论

学校读者我要写书评

暂无评论

Integrated access control monitoring system based on face video detection 2

Integrated access control monitoring system based on face vi...

引用

2nd International Conference on Consumer Electronics and computer Engineering, ICCECE 2022

作者： Zhai, Qian Institute of Computer Control Technology Guangzhou Huali College Guangzhou China

ISBN: (纸本)9781665408868

In order to realize the integrated entrance guard detection in the scene of random flow of *** with face recognition algorithm, the design method of integrated entrance guard monitoring system is proposed based on face video detection. A face video feature detection model in the scene of random flow of people is established, block matching on the face video features in the scene of random flow of people is performed, a living feature analysis model of face video monitoring in the scene of random flow of people is established by adopting the method of block feature information fusion, the face feature recognition and information fusion is realized by adopting the method of biological directional recognition, and the statistical features and edge detail parameters of face video in the scene of random flow of people are extracted, Combined with the face anti-deception algorithm, the authenticity of the face in the process of integrated entrance guard monitoring is judged. On the basis of dynamic biometric detection, the feature recognition of facial expressions under different expressions such as nature, smile and mouth opening are realized, and the integrated entrance guard monitoring is realized according to the feature recognition results. In the embedded and cloud technology environment, the alarm controller of integrated access control is built to realize access control, information privacy protection, image recognition and information playback, and the system hardware design is realized. The simulation results show that the designed integrated entrance guard monitoring system has high detection and recognition ability of face features and good recognition accuracy. © 2022 IEEE.

关键词： Monitoring

来源：评论

学校读者我要写书评

暂无评论

Adaptive dynamic surface control for quadrotor-slung load transportation system with uncertainties

引用

Science China(Technological Sciences) 2023年第10期66卷 2917-2929页

作者： DING Feng HUANG Jian SUN Chong AI Yong XU WenXia YANG ChenGuang School of Computer Science South-Central Minzu UniversityWuhan 430074China Key Laboratory of Ministryof EducationforImage Processing and Intelligent ControlHubei Key Laboratoryof Brain-inspired Intelligent Systems School of Artificial Intelligence and Automation Huazhong University of Science and TechnologyWuhan 430074China School of Computer Science and Engineering Wuhan Institute of TechnologyWuhan 430205China Key Laboratory of Ministry of Education for Autonomous Systems and Networked Control Guangdong Engineering Technology Research Center of Control of Intelligent SystemsCollege of Automation Science and EngineeringSouth China University of TechnologyGuangzhou 510640China

Quadrotors play a significant role in our lives and are transforming our *** cable-suspended loads is an unavoidable quadrotor application trend and a hot research topic in the control ***,the load swing and unpredictability pose significant challenges to the quadrotor's *** this paper,an anti-swing controller with an inner-outer control strategy for the quadrotor-slung load transportation system is *** facilitate the controller design,the outer position dynamics are restructured in the form of ***,a virtual controller is created to force the underactuated states to the dynamic surface to ensure the position subsystem's *** improve robustness,an adaptive law is used to eliminate the effects of uncertain cable ***,a dynamic surface controller for the inner attitude subsystem is presented to drive the actual force to the virtual *** is demonstrated that the control strategy can stabilize the quadrotor despite mass and cable length *** results are provided to demonstrate the efficacy and durability of the proposed method.

关键词： quadrotor-slung load transportation system dynamic surface control adaptive law cascade system model uncertainties

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：