检索结果-内蒙古大学图书馆

Improved U-NET Semantic Segmentation Network

学校读者我要写书评

暂无评论

Improved U-NET Semantic Segmentation Network

第三十九届中国控制会议

作者： Xueyan Gao Lijin Fang College of Information Science and Engineering Northeastern University Faculty of Robot Science and Engineering Northeastern University

In order to enable neural networks to better process images, this paper proposed a network with residual network and attention mechanism（AM）. The residual network solves the shortcomings of insufficient depth of U-NET network to a certain extent. The attention mechanism can adaptively fuse processed context information and place different attentions for different objects and shapes, instead of simply aggregating all processed information. The method proposed in this paper is compared with the network using the residual network alone and the network using the attention mechanism alone. The experimental results show that the network proposed in this paper performs better.

关键词： U-NET Neural network Residual network Attention mechanism

Reduced Network Cumulative Constraint Violation for Distributed Bandit Convex Optimization under Slater’s Condition

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhang, Kunpeng Yi, Xinlei Ding, Jinliang Cao, Ming Johansson, Karl H. Yang, Tao State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang110819 China Department of Control Science and Engineering College of Electronics and Information Engineering Tongji University Shanghai201800 China Engineering and Technology Institute Groningen Faculty of Science and Engineering University of Groningen GroningenAG 9747 Netherlands Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Sweden Digital Futures Stockholm10044 Sweden

This paper studies the distributed bandit convex optimization problem with time-varying inequality constraints, where the goal is to minimize network regret and cumulative constraint violation. To calculate network cumulative constraint violation, existing distributed bandit online algorithms solving this problem directly use the clipped constraint function to replace its original constraint function. However, the use of the clipping operation renders Slater’s condition (i.e, there exists a point that strictly satisfies the inequality constraints at all iterations) ineffective to achieve reduced network cumulative constraint violation. To tackle this challenge, we propose a new distributed bandit online primal–dual algorithm. If local loss functions are convex, we show that the proposed algorithm establishes an O(T max{c,1−c})network regret bound and an O(T 1−c/2) network cumulative constraint violation bound, where T is the total number of iterations and c ∈ (0, 1) is a user-defined trade-off parameter. When Slater’s condition holds, the network cumulative constraint violation bound is reduced to O(T 1−c). In addition, if local loss functions are strongly convex, for the case where strongly convex parameters are unknown, the network regret bound is reduced to O(T1−c), and the network cumulative constraint violation bound is O(T1−c/2) and O(T1−c) without and with Slater’s condition, respectively. For the case where strongly convex parameters are known, the network regret bound is further reduced to O)(log(T)), and the network cumulative constraint violation bound is reduced to O(log(T)T) and O(log(T)) without and with Slater’s condition, respectively. To the best of our knowledge, this paper is among the first to establish reduced (network) cumulative constraint violation bounds for (distributed) bandit convex optimization with time-varying constraints under Slater’s condition. Finally, a numerical example is provided to verify the theoretical results. Copyright © 2

关键词： Convex optimization

Free-Form Composition Networks for Egocentric Action Recognition

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wang, Haoran Cheng, Qinghua Yu, Baosheng Zhan, Yibing Tao, Dapeng Ding, Liang Ling, Haibin College of Information Science and Engineering Northeastern University Shenyang110819 China School of Computer Science Faculty of Engineering The University of Sydney DarlingtonNSW2008 Australia JD Explore Academy Beijing100176 China School of Information Science and Engineering Yunnan University Yunnan Kunming650091 China Department of Computer Science Stony Brook University Stony Brook United States

Egocentric action recognition is gaining significant attention in the field of human action recognition. In this paper, we address data scarcity issue in egocentric action recognition from a compositional generalization perspective. To tackle this problem, we propose a free-form composition network (FFCN) that can simultaneously learn disentangled verb, preposition, and noun representations, and then use them to compose new samples in the feature space for rare classes of action videos. First, we use a graph to capture the spatial-temporal relations among different hand/object instances in each action video. We thus decompose each action into a set of verb and preposition spatial-temporal representations using the edge features in the graph. The temporal decomposition extracts verb and preposition representations from different video frames, while the spatial decomposition adaptively learns verb and preposition representations from action-related instances in each frame. With these spatial-temporal representations of verbs and prepositions, we can compose new samples for those rare classes in a free-form manner, which is not restricted to a rigid form of a verb and a noun. The proposed FFCN can directly generate new training data samples for rare classes, hence significantly improve action recognition performance. We evaluated our method on three popular egocentric action recognition datasets, Something-Something V2, H2O, and EPIC-KITCHENS-100, and the experimental results demonstrate the effectiveness of the proposed method for handling data scarcity problems, including long-tailed and few-shot egocentric action recognition. Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning

A Blockchain-Based Distributed Collaborative Sensing and Spectrum Access Approach for Consumer Electronics

学校读者我要写书评

暂无评论

IEEE Transactions on Consumer Electronics 2025年

作者： Peng, Yuhuai Li, Yuan Guo, Yu Zhang, Dawei Khan, Fazlullah Alturki, Ryan Alshawi, Bandar Northeastern University College of Computer Science and Engineering Shenyang110819 China Zhiyuan Research Institute Xihu District Hangzhou China Zhengzhou University School of Computer and Artificial Intelligence Henan Zhengzhou450001 China University of Nottingham Ningbo China School of Computer Science Faculty of Science and Engineering Zhejiang Ningbo315104 China KKR and KSR Institute of Technology and Sciences Department of Computer Science and Engineering Andhra Pradesh Guntur India Division of Research and Development Lovely Professional University Phagwara India University Centre of Research and Development Chandigarh University Mohali India Umm Al-Qura University Department of Software Engineering College of Computing Makkah Saudi Arabia Umm Al-Qura University College of Computing Department of Computer and Network Engineering Makkah Saudi Arabia

Cognitive radio (CR) provides key technical support for the seamless communication of consumer electronic (CE) devices through distributed cooperative sensing and spectrum access. However, its openness and dynamic nature introduce potential security risks and challenges. Due to the openness of wireless communication, spectrum sensing and access are vulnerable to malicious attacks, and resource-constrained devices cannot effectively implement artificial intelligence (AI)-driven encryption and access control strategies. To address these limitations, this study proposes a blockchain-based distributed collaborative sensing method for CE devices. In the proposed method, after sensing, the smart contracts verify node legitimacy using the ring signature method. The malicious users are rejected by the outlier detection method, which improves the collaborative anti-interference ability. In addition, by using a centralized training and distributed execution architecture, a secure spectrum sensing strategy based on multi-agent reinforcement learning is designed. The proposed strategy ensures that each node makes independent decisions, which enhances the adaptability of the CE ecosystem. The proposed method is verified by extensive simulations, and the results show that it can maintain spectrum awareness of more than 95.72% and an access success rate of 91.19% under malicious attacks. Moreover, communication overhead is significantly reduced by approximately 93.53%. © 1975-2011 IEEE.

关键词： Blockchain

An Interactive Annotation Method Based on Incremental Learning

学校读者我要写书评

暂无评论

An Interactive Annotation Method Based on Incremental Learni...

Image Processing, Computer Vision and Machine Learning (ICICML), International Conference on

作者： Xiusheng Duan Guohua Sun Jingya Cao Yuyang Zhang Jingchao Yang Duyu Han Department of Artificial Intelligence and Big Data Hebei Polytechnic Institute Shijiazhuang China Intelligent Application Technology Research and Development Center Hebei Provincial University Road Traffic Perception Shijiazhuang China School of Mechanical Engineering Shijiazhuang Tiedao University Shijiazhuang China Faculty of Robot Science and Engineering Northeastern University Shenyang China Hebei Jiaotong Vocational and Technical College Shijiazhuang China

In recent years, military science and technology has been developed rapidly, and new equipments has been equipped in the army. Augmented Reality (AR) technology provides the possibility to solve the problem of equipments operation training. But in the training process, One of the essential technologies is how to location and identify the operation keys. Obviously, the sample set of equipments operation keys is the basis of key recognition, and a certain scale of sample set is an indispensable element to ensure the performance of the recognition model. On the basis of manually establishing a small sample set, this paper puts forward a mechanism based on interactive automatic sample labeling and sample set expanding, the target recognition model was updated by incremental learning method at the same time.

关键词：

High-Performance Inference Graph Convolutional Networks for Skeleton-Based Action Recognition

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wang, Junyi Li, Ziao Liu, Bangli Cai, Haibin Saada, Mohamad Meng, Qinggang Robot Science and Engineering Northeastern University Liaoning Shenyang110819 China School of Intelligent Systems Engineering Sun Yat-sen University Guangdong Shenzhen518107 China Foshan Graduate School of Innovation Northeastern University Guangdong Foshan528311 China Computer Science and Informatics De Montfort University LeicesterLE1 9BH United Kingdom Department of Computer Science Loughborough University LoughboroughLE11 3TU United Kingdom

Recently, the significant achievements have been made in skeleton-based human action recognition with the emergence of graph convolutional networks (GCNs). However, the state-of-the-art (SOTA) models used for this task focus on constructing more complex higher-order connections between joint nodes to describe skeleton information, which leads to complex inference processes and high computational costs. To address the slow inference speed caused by overly complex model structures, we introduce reparameterization and over-parameterization techniques to GCNs and propose two novel high-performance inference GCNs, namely HPI-GCN-RP and HPI-GCN-OP. After the completion of model training, model parameters are fixed. HPI-GCN-RP adopts re-parameterization technique to transform high-performance training model into fast inference model through linear transformations, which achieves a higher inference speed with competitive model performance. HPI-GCN-OP further utilizes over-parameterization technique to achieve higher performance improvement by introducing additional inference parameters, albeit with slightly decreased inference speed. The experimental results on the two skeleton-based action recognition datasets demonstrate the effectiveness of our approach. Our HPI-GCN-OP achieves performance comparable to the current state-of-the-art (SOTA) models, with inference speeds five times faster. Specifically, our HPI-GCN-OP achieves an accuracy of 93% on the cross-subject split of the NTU-RGB+D 60 dataset, and 90.1% on the cross-subject benchmark of the NTU-RGB+D 120 dataset. Code is available at ***/lizaowo/HPI-GCN. Copyright © 2023, The Authors. All rights reserved.

关键词： Musculoskeletal system

Manipulator Package Sorting and Placing System Based on Computer Vision

学校读者我要写书评

暂无评论

Manipulator Package Sorting and Placing System Based on Comp...

Chinese Control and Decision Conference, CCDC

作者： Zhangchao Pan Zixi Jia Kaiyuan Jing Yinguang Ding Qianmeng Liang Faculty of Robot Science and Engineering Northeastern University Liaoning

ISBN: (数字)9781728158556

ISBN: (纸本)9781728158563

Nowadays the logistics industry is developing rapidly. This paper proposes and designs a vision-based manipulator express sorting and delivery system for the problem of express stacking. This system combines computer vision, deep learning, manipulator control and motion planning technologies. This paper uses the YOLO algorithm and PCL to determine the position and normal vector of the pick-up point of the package, plans and controls the movement of the manipulator to the target position to suck the package, and uses vision to determine the size of the package and obtain customer information. Compared with RCNN and SDD algorithm, YOLO has a faster detection speed [1], and at the same time, it handles small stacked targets such as express boxes with higher accuracy. Therefore, this system uses the YOLOv3 algorithm to improve the system's extraction accuracy and speed. Finally, the success rate of the system was 75%, and the completion time was about 15s.

关键词： Manipulators Cameras Path planning Sorting Volume measurement Computer vision

Social Bots: Detection and Challenges

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Yang, Kai-Cheng Varol, Onur Nwala, Alexander C. Sayyadiharikandeh, Mohsen Ferrara, Emilio Flammini, Alessandro Menczer, Filippo Luddy School of Informatics Computing and Engineering Indiana University Bloomington United States Network Science Institute Northeastern University United States Faculty of Engineering and Natural Sciences Sabanci University Turkey Department of Applied Science William & Mary United States Thomas Lord Department of Computer Science University of Southern California United States

While social media are a key source of data for computational social science, their ease of manipulation by malicious actors threatens the integrity of online information exchanges and their analysis. In this Chapter, we focus on malicious social bots, a prominent vehicle for such manipulation. We start by discussing recent studies about the presence and actions of social bots in various online discussions to show their real-world implications and the need for detection methods. Then we discuss the challenges of bot detection methods and use Botometer, a publicly available bot detection tool, as a case study to describe recent developments in this area. We close with a practical guide on how to handle social bots in social media research. © 2023, CC BY.

关键词： Botnet

Introducing Shape Prior Module in Diffusion Model for Medical Image Segmentation

学校读者我要写书评

暂无评论

Introducing Shape Prior Module in Diffusion Model for Medica...

IEEE International Conference on Mechatronics, robotics and Automation (ICMRA)

作者： Zhiqing Zhang Guojia Fan Tianyong Liu Nan Li Yuyang Liu Ziyu Liu Canwei Dong Shoujun Zhou Shenzhen Institute of Advanced Technology University of Chinese Academy of Sciences Shenzhen China College Of Information Science and Engineering Northeastern University (Of Affiliation) Shenzhen China College Of Geosciences Northeast Petroleum University Shenzhen China Department of Computer Science City University of Hong Kong Shenzhen China Shenyang Institute of Automation University of Chinese Academy of Sciences Shenzhen China Faculty of Science and Engineering Chinese Academy of Sciences University of Nottingham Ningbo China Ningbo China College Of Information Science And Engineering Northeastern University (Of Affiliation) Shenzhen China

ISBN: (数字)9798350307535

ISBN: (纸本)9798350307542

Medical image segmentation is critical for diagnosing and treating spinal disorders. However, the presence of high noise, ambiguity, and uncertainty makes this task highly challenging. Factors such as unclear anatomical boundaries, inter-class similarities, and irrational annotations contribute to this challenge. Achieving both accurate and diverse segmentation templates is essential to support radiologists in clinical practice. In recent years, denoising diffusion probabilistic modeling (DDPM) has emerged as a prominent research topic in computer vision. It has demonstrated effectiveness in various vision tasks, including image deblurring, super-resolution, anomaly detection, and even semantic representation generation at the pixel level. Despite the robustness of existing diffusion models in visual generation tasks, they still struggle with discrete masks and their various effects. To address the need for accurate and diverse spine medical image segmentation templates, we propose an end-to-end framework called VerseDiff-UNet, which leverages the denoising diffusion probabilistic model (DDPM). Our approach integrates the diffusion model into a standard U-shaped architecture. At each step, we combine the noise-added image with the labeled mask to guide the diffusion direction accurately towards the target region. Furthermore, to capture specific anatomical a priori information in medical images, we incorporate a shape a priori module. This module efficiently extracts structural semantic information from the input spine images. We evaluate our method on a single dataset of spine images acquired through X-ray imaging. Our results demonstrate that VerseDiff-UNet significantly outperforms other state-of-the-art methods in terms of accuracy while preserving the natural features and variations of anatomy. The generality and validity of our proposed model are confirmed through extensive experiments. By enabling more precise segmentation of anatomical structures, our framew

关键词： Image segmentation Visualization Accuracy Shape Semantics Noise reduction Anatomical structure Diffusion models Probabilistic logic X-ray imaging