检索结果-内蒙古大学图书馆

Joint CNN and Transformer Network via weakly supervised Learning for efficient crowd counting

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Wang, Fusen Liu, Kai Long, Fei Sang, Nong Xia, Xiaofeng Sang, Jun School of Big Data & Software Engineering Chongqing University Chongqing401331 China School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China

Currently, for crowd counting, the fully supervised methods via density map estimation are the mainstream research directions. However, such methods need location-level annotation of persons in an image, which is time-consuming and laborious. Therefore, the weakly supervised method just relying upon the count-level annotation is urgently needed. Since CNN is not suitable for modeling the global context and the interactions between image patches, crowd counting with weakly supervised learning via CNN generally can not show good performance. The weakly supervised model via Transformer was sequentially proposed to model the global context and learn contrast features. However, the transformer directly partitions the crowd images into a series of tokens, which may not be a good choice due to each pedestrian being an independent individual, and the parameter number of the network is very large. Hence, we propose a Joint CNN and Transformer Network (JCTNet) via weakly supervised learning for crowd counting in this paper. JCTNet consists of three parts: CNN feature extraction module (CFM), Transformer feature extraction module (TFM), and counting regression module (CRM). In particular, the CFM extracts crowd semantic information features, then sends their patch partitions to TRM for modeling global context, and CRM is used to predict the number of people. Extensive experiments and visualizations demonstrate that JCTNet can effectively focus on the crowd regions and obtain superior weakly supervised counting performance on five mainstream datasets. The number of parameters of the model can be reduced by about 67%∼73% compared with the pure Transformer works. We also tried to explain the phenomenon that a model constrained only by count-level annotations can still focus on the crowd regions. We believe our work can promote further research in this field. Copyright © 2022, The Authors. All rights reserved.

关键词： Feature extraction

DNGNN: Efficient Deep Noisy Graph Neural Network for Spatio-Temporal Series Forecasting

学校读者我要写书评

暂无评论

DNGNN: Efficient Deep Noisy Graph Neural Network for Spatio-...

2025 2nd International Conference on Algorithms, Software Engineering and Network Security (ASENS)

作者： Songbo Wang Yifan Chen Haizhi Xu Jianqiao Hu Peiyu Zeng Ziming Hu School of Computing and Data Science The University of Hong Kong Hong Kong China School of Microelectronics Science and Technology Sun Yat-sen University Zhuhai China School of Software Engineering South China University of Technology Guangzhou China School of Materials Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing China School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China

ISBN: (数字)9798331520298

ISBN: (纸本)9798331520304

Spatio-temporal series forecasting plays a vital role in the domain of multivariate time series prediction. By leveraging accurate and comprehensive spatio-temporal sequence prediction models, it becomes possible to extract higher-order spatio-temporal interactions between real-world connections, thereby contributing to smart city construction. Spatio-Temporal Graph Neural Networks (STGNNs) have emerged as a highly effective approach for addressing spatio-temporal series prediction challenges. Nevertheless, most existing methods predominantly rely on traditional graph convolutional networks (GCNs) and their variants for spatial feature extraction. Due to inherent limitations such as over-smoothing, these models often constrain spatial feature encoding to shallow architectures, typically limited to 2-3 layers. Additionally, the presence of noisy data in real-world scenarios significantly impacts the prediction accuracy of existing STGNN models. In this paper, building upon the classic STGNN framework, we propose a graph neural network framework based on deep residual connections and noise injection mechanism to address the aforementioned issues. Specifically, inspired by the principles of initial residual connection and identity mapping, we proposed a deep spatio-temporal graph neural network framework of 12 layers to capture the high-dimensional interactions, while using noise injection mechanism to mitigate the adverse effects of noisy data. Sufficient experimental results on typical time-series datasets demonstrate the effectiveness of our proposed framework.

关键词： Accuracy Noise Time series analysis Predictive models Feature extraction Transformers Graph neural networks Spatiotemporal phenomena Noise measurement Forecasting

Self-optimization in distributed manufacturing systems using Modular State-based Stackelberg Games

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Yuwono, Steve Hussain, Ahmar Kamal Schwung, Dorothea Schwung, Andreas Department of Automation Technology and Learning Systems South Westphalia University of Applied Sciences Lübecker Ring 2 Soest59494 Germany Data and Knowledge Engineering Group Otto von Guericke University Magdeburg Universitätsplatz 2 Magdeburg39106 Germany Department of Artificial Intelligence and Data Science in Automation Technology Hochschule Düsseldorf University of Applied Sciences Münsterstraße 156 Düsseldorf40476 Germany

In this study, we introduce Modular State-based Stackelberg Games (Mod-SbSG), a novel game structure developed for distributed self-learning in modular manufacturing systems. Mod-SbSG enhances cooperative decision-making among self-learning agents within production systems by integrating State-based Potential Games (SbPG) with Stackelberg games. This hierarchical structure assigns more important modules of the manufacturing system a first-mover advantage, while less important modules respond optimally to the leaders' decisions. This decision-making process differs from typical multi-agent learning algorithms in manufacturing systems, where decisions are made simultaneously. We provide convergence guarantees for the novel game structure and design learning algorithms to account for the hierarchical game structure. We further analyse the effects of single-leader/multiple-follower and multiple-leader/multiple-follower scenarios within a Mod-SbSG. To assess its effectiveness, we implement and test Mod-SbSG in an industrial control setting using two laboratory-scale testbeds featuring sequential and serial-parallel processes. The proposed approach delivers promising results compared to the vanilla SbPG, which reduces overflow by 97.1%, and in some cases, prevents overflow entirely. Additionally, it decreases power consumption by 5-13% while satisfying the production demand, which significantly improves potential (global objective) values. © 2024, CC BY-NC-ND.

关键词： Reinforcement learning

Research and application of artificial intelligence based webshell detection model: A literature review

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Ma, Mingrui Han, Lansheng Zhou, Chunjie Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan430074 China The Key Laboratory of Ministry of Education for Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Hubei Wuhan430074 China

Webshell, as the"culprit" behind numerous network attacks, is one of the research hotspots in the field of cybersecurity. However, the complexity, stealthiness, and confusing nature of webshells pose significant challenges to the corresponding detection schemes. With the rise of artificial intelligence (AI) technology, researchers have started to apply different intelligent algorithms and neural network architectures to the task of webshell detection. However, the related research still lacks a systematic and standardized methodological process, which is confusing and redundant. Therefore, following the development timeline, we carefully summarize the progress of relevant research in this field, dividing it into three stages: Start Stage, Initial Development Stage, and In-depth Development Stage. We further elaborate on the main characteristics and core algorithms of each stage. In addition, we analyze the pain points and challenges that still exist in this field and predict the future development trend of this field from our point of view. To the best of our knowledge, this is the first review that details the research related to AI-based webshell detection. It is also hoped that this paper can provide detailed technical information for more researchers interested in AI-based webshell detection tasks. Copyright © 2024, The Authors. All rights reserved.

关键词： Machine learning

Classification of Ship Navigation Behavior in Inland Crossing Channels

学校读者我要写书评

暂无评论

Classification of Ship Navigation Behavior in Inland Crossin...

2021 International Conference on Security, Pattern Analysis, and Cybernetics, SPAC 2021

作者： Huang, Ziyi Zuo, Yi Li, Tieshan Wang, Haocheng Navigation College Dalian Maritime University Dalian China Collaborative Innovation Center of Maritime Big Data and Shipping Artificial General Intelligence Dalian China School of Automation Engineering University of Electronic Science and Technology of China Chengdu China

ISBN: (纸本)9781665443227

With the development of inland river transportation in China and the popularization of automatic identification systems (AIS), it has become more and more important to collect ship movement information and use it for maritime monitoring and management. However, ship movement information is complicated, and AIS data is often missing. It is very difficult to classify ship navigation behavior. This paper proposes an improved SRC model to solve it. In order to verify the performance of the model, the preprocessed data set of Huai'an section of Beijing-Hangzhou Canal is applied to the model. After comparing with other traditional classification models, the results show that the SRC model can effectively classify the navigation behavior of ships, and in most cases is better than other traditional classification models. © 2021 IEEE.

关键词： Ships

Implementing Genetic Algorithms for Optimization in Neuro-Cognitive Rehabilitation Robotics 1

学校读者我要写书评

暂无评论

Implementing Genetic Algorithms for Optimization in Neuro-Co...

1st IEEE International Conference on Cognitive Robotics and Intelligent Systems, ICC - ROBINS 2024

作者： Abhang, L.B. Changala, Ravindra Ghosh, Anudeb Manage, Prabhakar S Rao, Vuda Sreenivasa Kiran Bala, B. Loni Under. SPPU University Pravara Rural Engineering College Automation and Robotics Dept Pune India Guru Nanak Institutions Technical Campus Department of Information Technology Hyderabad India Siksha - Bhavana Department of Environmental Studies Visva-Bharati Santiniketan India Kle Technological University's Msscet Belagavi Campus Department of Electronics and Communication Karnataka Belagavi India Education Foundation Department of Computer Science and Engineering Koneru Lakshmaiah A.P Vaddeswaram522302 India K.Ramakrishnan College of Engineering The Department Department of Artificial Intelligence and Data Science Trichy India

ISBN: (纸本)9798350372748

The study explores the intersection of robotics and neuro-cognitive rehabilitation to offer personalized assistance for individuals with neurological disorders, emphasizing autism spectrum disorder (ASD). The proposed methodology integrates Genetic Algorithms (GAs) to optimize the performance of robotic interventions. The data collection phase involves compiling a comprehensive image dataset capturing facial expressions, gestures, and relevant visual cues associated with ASD. Leveraging robotic platforms designed for therapeutic interventions, feature extraction techniques identify intricate patterns within the data. Advanced algorithms, including GAs, classify the dataset into positive (ASD) and negative (non-ASD) categories. The framework introduces a Diagnosis Matrix for enhanced diagnostic precision, correlating observed robotic interactions with clinical assessments. An Ontology Knowledge base adapts responses based on evolving patient needs. The proposed method surpasses all others, achieving an accuracy of 95.08% and demonstrating superior precision, recall, and F1-score metrics. This indicates the efficacy of the proposed approach in achieving a well-balanced performance with high accuracy and robustness in correctly identifying positive instances. The results underscore the potential of the proposed method for classification tasks, showcasing its superiority in comparison to traditional SVM, CNN, and even a well-established deep learning architecture like VGG-16. The Receiver Operating Characteristic curve validates the model's discriminatory power. © 2024 IEEE.

关键词： Genetic algorithms

Research and application of Transformer based anomaly detection model: A literature review

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Ma, Mingrui Han, Lansheng Zhou, Chunjie Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Hubei Wuhan430074 China The Key Laboratory of Ministry of Education for Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Hubei Wuhan430074 China

Transformer, as one of the most advanced neural network models in Natural Language Processing (NLP), exhibits diverse applications in the field of anomaly detection. To inspire research on Transformer-based anomaly detection, this review offers a fresh perspective on the concept of anomaly detection. We explore the current challenges of anomaly detection and provide detailed insights into the operating principles of Transformer and its variants in anomaly detection tasks. Additionally, we delineate various application scenarios for Transformer-based anomaly detection models and discuss the datasets and evaluation metrics employed. Furthermore, this review highlights the key challenges in Transformer-based anomaly detection research and conducts a comprehensive analysis of future research trends in this domain. The review includes an extensive compilation of over 100 core references related to Transformer-based anomaly detection. To the best of our knowledge, this is the first comprehensive review that focuses on the research related to Transformer in the context of anomaly detection. We hope that this paper can provide detailed technical information to researchers interested in Transformer-based anomaly detection tasks. Copyright © 2024, The Authors. All rights reserved.

关键词： Anomaly detection

Federated Learning for Predictive Maintenance and Quality Inspection in Industrial Applications

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Pruckovskaja, Viktorija Weissenfeld, Axel Heistracher, Clemens Graser, Anita Kafka, Julia Leputsch, Peter Schall, Daniel Kemnitz, Jana Technische Universität Wien Vienna Austria Data Science & Artificial Intelligence AIT Austrian Institute of Technology Vienna Austria Innovation Software Stiwa Automation Attnang-Puchheim Austria Distributed AI Systems Research Siemens Technology Vienna Austria

data-driven machine learning is playing a crucial role in the advancements of Industry 4.0, specifically in enhancing predictive maintenance and quality inspection. Federated learning (FL) enables multiple participants to develop a machine learning model without compromising the privacy and confidentiality of their data. In this paper, we evaluate the performance of different FL aggregation methods and compare them to central and local training approaches. Our study is based on four datasets with varying data distributions. The results indicate that the performance of FL is highly dependent on the data and its distribution among clients. In some scenarios, FL can be an effective alternative to traditional central or local training methods. Additionally, we introduce a new federated learning dataset from a real-world quality inspection setting. Copyright © 2023, The Authors. All rights reserved.

关键词： Maintenance

Analysis of Visual Expression of Light and Color in Movies based on Wavelet Neural Network 2

学校读者我要写书评

暂无评论

Analysis of Visual Expression of Light and Color in Movies b...

2nd IEEE International Conference on Communication, Security and artificial intelligence, ICCSAI 2023

作者： Murugan, K. Mothi, R. George, Retty Priya, R. Esther Nagarathinam, S. Krishnakumar, S. Kpr Institute of Engineering and Technology Department of Electronics and Communication and Engineering Coimbatore India Dr. N.G.P. Institute of Technology Department of Biomedical Engineering Coimbatore India Scms School of Engineering and Technology Department of Ece Kerala Ernakulam India Jansons Institute of Technology Department of Artificial Intelligence and Data Science Coimbatore India Kumaraguru College of Technology Department of Ece Coimbatore India Sri Ramakrishna Engineering College Department of Robotics and Automation Coimbatore India

ISBN: (纸本)9798350369960

Movies are in the era of 'black, white and gray' ruling the screen, people have a strong desire for movies to truly reproduce colors, because the main rhythm of the 'black, white and gray' film visual music is not clear enough, the momentum is not strong enough, the meaning is not rich enough, and the color is not enough. Visual aesthetics cannot be attractive... Aiming at the dual challenges of colorization quality and timing stability in film colorization, a generative adversarial network with a recurrent structure is proposed, which can be used for automatic colorization of films without any reference frames and artificial intervention. The network generates a confrontation network based on classical conditions: the generator is used to generate color images and complete the task of colorization;The discriminator is used to identify the authenticity and improve the performance of the generator. Cycle structure and timing consistency loss are introduced to integrate timing information and solve the stability problem of coloring. Experimental results show that this method can effectively reduce flicker in the generated movie sequence while ensuring the coloring of a single frame image. This paper studies and analyzes the visual expression of light and color in movies based on wavelet neural network. © 2023 IEEE.

关键词： Color vision film Neural network