检索结果-内蒙古大学图书馆

42nd Chinese Control Conference, CCC 2023

作者： Liu, Yuanxuan Li, Dequan School of Mathematics and Data Science Anhui University of Science and Technology Huainan232000 China School of Artificial Intelligence Anhui University of Science and Technology Huainan232000 China

ISBN: (纸本)9789887581543

Adaptive algorithms are widely used in deep learning because of their fast convergence. Among them, Adam is the most widely used algorithm. However, studies have shown that Adam's generalization ability is weak. AdaX is a variant of Adam, which modifies the second moment of Adam and has good generalization ability. We propose a new adaptive and momental bound algorithm, called AdaXod, which characterizes of exponentially averaging the learning rate and is particularly useful for training deep neural networks. By setting an adaptively limited learning rate in the AdaX algorithm, the resultant AdaXod can effectively eliminate the problem of excessive learning rate in the later stage of neural network model training and thus stabilize training. Simulation experiments verify that AdaXod eliminates large learning rates during neural network training and outperforms other optimizers, especially on the complex network structures such as DenseNet. © 2023 Technical Committee on Control Theory, Chinese Association of Automation.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Solving Vehicle Routing Problem With Time Windows Based on Chaotic Adaptive Discrete Particle Swarm Optimization Algorithm

Solving Vehicle Routing Problem With Time Windows Based on C...

引用

2024 IEEE International Conference on Big data, Bigdata 2024

作者： Wei, Wenhong Ma, Yu Dong, Ani Li, Qingxia Dongguan University of Technology School of Computer Science and Technology Dongguan523808 China Dongguan City University School of Artificial Intelligence Dongguan523419 China

ISBN: (纸本)9798350362480

To address the limitations of existing particle swarm optimization algorithms in solving discrete problems, this paper proposes a discrete particle swarm optimization algorithm for vehicle routing problem with time windows. This algorithm enhances the velocity and position updating mechanism using an set-based strategy, making it more efficient in the discrete search process. Additionally, to further balance the algorithm's global search and local development capabilities, this paper introduces a chaotic mapping algorithm and a nonlinear dynamic adjustment parameter strategy to enhance the algorithm's convergence speed. © 2024 IEEE.

关键词： Optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

A Novel Reinforcement Learning Multi-Objective Community Detection Algorithm with E-Gradient-Greedy Strategy

A Novel Reinforcement Learning Multi-Objective Community Det...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Wei, Wenhong Meng, Yi Li, Qingxia School of Computer Science and Technology Dongguan University of Technology Dongguan523808 China School of Artificial Intelligence Dongguan City University Dongguan523419 China

ISBN: (纸本)9781665410205

Accurately categorizing communities within a social network is a crucial aspect of community detection, carrying significant practical relevance. To achieve a higher quality of community division, we combine reinforcement learning methods to learn the distribution characteristics of community nodes during the iteration process of the algorithm, which guides the nodes to migrate to other communities and enhances the algorithm's global search capability. Through a new E -gradient-greedy strategy, which can obtain a node's gradient information relative to its neighbors and achieve higher performance in local search. To speed up the adaptability of the algorithm at the beginning of the iteration and to alleviate the resolution limitation imposed by modularity optimization, this paper employs a triangular subnetwork-based weight assignment method for balancing the weights of each edge in the network. Experimental results on real-world and synthetic network datasets demonstrate that our method's community identification precision outperforms recent community detection algorithms, exhibiting higher accuracy, higher resolution, and adaptability to various network characteristics and structural changes. © 2024 IEEE.

关键词： Optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

Autonomous exploration driven by dual target points through multi-agent deep reinforcement learning 4

Autonomous exploration driven by dual target points through ...

引用

4th International Conference on Image Processing and Intelligent Control, IPIC 2024

作者： Fu, Tianyu Yan, Jiang Qin, Wenyan School of Computer Science and Artificial Intelligence Wuhan University of Technology Hubei Wuhan China School of Automation Wuhan University of Technology Hubei Wuhan China

ISBN: (纸本)9781510682313

In this letter, we present an autonomous navigation system driven by dual target points, designed for goal-directed exploration of unknown environments through multi-agent deep reinforcement learning. The system identifies candidate target points from the environment that could serve as potential navigation directions and selects the best two waypoints based on available data. Guided by these waypoints, robots are directed towards global targets. Utilizing multi-agent reinforcement learning, a movement strategy is trained in a simulated environment using LiDAR sensor data and pose information, enabling two robots to move towards the currently selected target points. Experiments demonstrate that our method effectively conducts target point exploration, and the collaborative exploration by two mobile robots significantly enhances the efficiency of global target point discovery. © 2024 SPIE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Self-Attention Residual Connection and Graph Neural Hawkes Bilayer Model for Session-Based Recommendation

Self-Attention Residual Connection and Graph Neural Hawkes B...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Li, Huan Chen, Senpeng Wei, Wenhong Dong, Ani Li, Qingxia School of Computer Science and Technology Dongguan University of Technology Dongguan523808 China School of Artificial Intelligence Dongguan City University Dongguan523419 China

ISBN: (纸本)9781665410205

Session-based recommendation aims to make recommendations for anonymous users based on limited session data. However, traditional session-based recommendation methods fail to capture complex item transitions and simply represent the user's last clicked item as a short-term preference, neglecting the global sequential information of the session. This approach struggles to consider transitions between contexts and cannot accurately capture the user's true intentions. To address these issues, this paper proposes a session recommendation method based on self-attention residual connections and graph neural Hawkes (SRGNH). This method introduces a duallayer network structure consisting of graph neural self-attention residual connection layers and graph neural Hawkes layers, designed to learn users' long-term and short-term preferences, respectively. SRGNH employs a Gated Graph Neural Network (GGNN) to capture complex interactions between nodes, obtaining latent vectors for each item. It incorporates self-attention networks and residual connections to effectively utilize low-level inspired information for capturing users' long-term preferences. The graph neural Hawkes layer combines the Hawkes process with GGNN to capture the relationship between user item clicks over continuous time, accurately representing users' short-term preferences. To better represent user intent, we linearly combine users' long-term and short-term preferences in the end. Experimental results demonstrate that the proposed SRGNH outperforms other recommendation models on the Diginetica, Yoochoose1/64, and Yoochoose1/4 datasets. © 2024 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

AF-NET: Urban Road Vehicle Ground Penetrating Radar Image Denoising via Attention U-Net 2

AF-NET: Urban Road Vehicle Ground Penetrating Radar Image De...

引用

2nd IEEE International Conference on Sensors, Electronics and computer Engineering, ICSECE 2024

作者： Huang, Yingjie Li, Ce Li, Quanzhi Computer Science and Technology School of Artificial Intelligence China University of Mining & Technology Xueyuan Rd Beijing Haidian100089 China

ISBN: (纸本)9798350373646

In urban environment, vehicle-mounted GPR images of urban roads may be disturbed by various noises, which will affect the correct recognition of underground structures. Therefore, de-noising radar images can improve data quality, ensure accurate detection of underground structures, and optimize urban planning and infrastructure management. However, there are few data sets of vehiclemounted GPR images on urban roads, and there is a lack of corresponding models for noise recognition. To solve these problems, an innovative radar image denoising framework, namely AF-NET, is proposed. This framework is based on convolutional neural network, uses Attention U-Net as the core framework, and adds LayerNorm, SCA and Simple Gate to improve computing efficiency. Experiments show that the collected radar image data set exceeds the previous SOTA0.25 dB. In the experiment, we successfully de-noise the radar image by designing the training image codec and using the features extracted by AF-NET. The PSNR of this method on the acquired radar image dataset is 43.34 dB, which verifies the effectiveness of AF-NET in the radar image denoising task. © 2024 IEEE.

关键词： Radar imaging

来源：评论

学校读者我要写书评

暂无评论

Ship Detection in SAR Images Based on Oriented Bounding Box and Supervised Contrastive Learning 24

Ship Detection in SAR Images Based on Oriented Bounding Box ...

引用

7th International Conference on Image and Graphics Processing, ICIGP 2024

作者： Zhang, Sizheng Pei, Mingtao Liu, Xueyan Zhao, Xijun School of Computer Science & Technology Beijing Institute of Technology China China North Artificial Intelligence & Innovation Research Institute China

ISBN: (纸本)9798400716720

Ship detection in SAR images is a challenging task due to the small target size, background noise, near-coastline noise, etc. In this paper, we propose to employ existing SAR dataset as a transitive dataset to improve the performance of detection model pre-trained on natural images. Specifically, we propose to use the oriented bounding box (OBB) and the contrastive learning method to fully utilize the transitive dataset. We employ a supervised contrastive learning method based on MoCo v2 and trained the model on the transitive dataset which is modified by using the oriented bounding box annotations generated from the existing horizontal bounding box annotations. We evaluate our method on different detection models and the experimental results show that using OBB and supervised contrastive learning can improve the performance of detection models, especially on inshore ship detection task. © 2024 ACM.

关键词： Synthetic aperture radar

来源：评论

学校读者我要写书评

暂无评论

Kathakali Mudras: An AI-Enhanced Predictive Approach 11

Kathakali Mudras: An AI-Enhanced Predictive Approach

引用

11th International Conference on Soft Computing and Machine intelligence, ISCMI 2024

作者： Mulerikkal, Jaison Paul Janani, K. Sreelakshmi, P.S. James, Divya Lakshmi, K.S. Sajanraj, T.D. Binu, A. Department of Information Technology India Rajagiri School of Engineering & Technology Kochi India Department of Computer Science and Engineering India Department of Computer Science and Business Systems India Department of Artificial Intelligence and Data Science India Department of Computer Science Loughborough University Leicester United Kingdom

ISBN: (纸本)9798331518127

The goal of this research is to integrate an artificial intelligence framework for predicting Kathakali mudras, a crucial component of the traditional Indian dance style that is renowned for its complex hand and facial motions. Our goal is to protect and improve the accessibility of this traditional art form by utilising deep learning technology. To be more precise, we used the object identification model YOLOv8 together with convolutional neural networks (CNNs) like VGG 19, Inception V3, and ResNet 152 to predict and analyse Kathakali mudras. Furthermore, Few-shot learning (FSL) and support vector machines (SVMs) were used to offer a comparative viewpoint on the efficacy of machine learning method in this situation. The study entailed a thorough analysis of how well-performing different deep learning techniques performed. The predictive accuracy of VGG 19, Inception V3, and ResNet 152 for intricate mudras of Kathakali was subjected to a thorough evaluation process. In addition, an evaluation of YOLOv8's real-time object identification capabilities was conducted in order to investigate its potential in live performance circumstances. The results of the experiment showed that VGG 19 performed better than the other models and had the highest accuracy in mudra prediction. As a result, VGG 19 was chosen as the best algorithm for this particular application. The results of this study demonstrate how artificial intelligence (AI) technologies may support and preserve traditional artistic forms. This AI-integrated framework is a useful tool for scholars, educators, and dancers, promoting a deeper knowledge and enjoyment of this cultural legacy through its accurate analysis and prediction of Kathakali mudras. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Say No to the Poisonous Fungi: An Effective Strategy for Reducing 0-1 Cost in FungiCLEF2024 25

Say No to the Poisonous Fungi: An Effective Strategy for Red...

引用

25th Working Notes of the Conference and Labs of the Evaluation Forum, CLEF 2024

作者： Tan, Bao-Feng Li, Yang-Yang Wang, Peng Zhao, Lin Wei, Xiu-Shen School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China School of Computer Science and Engineering Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications Southeast University Nanjing China

The FungiCLEF2024 competition endeavors to precisely identify fungi species leveraging both metadata and image analysis. Pivotal to the success of this competition are two crucial evaluation metrics: minimizing the error rate and the 0-1 cost loss resulting from misclassification. To reduce the identification error rate, we introduce a Dynamic MLP framework, drawing inspiration from [1]. This approach effectively integrates image and metadata embeddings through recursive blocks, utilizing matrix multiplication for deep fusion of information. To further address the issue of 0-1 cost, we devise a novel probability-based screening strategy, which initially consolidates poisonous fungi categories into a single class, then employs marginal expected loss and a threshold parameter α to optimize the recall rate for poisonous species. These approaches significantly reduce the error rate and 0-1 cost associated with misclassification and achieve a score of 0.5548 on the private leaderboard, securing the third-place ranking. The code is available at https://***/bftan1949/FungiCLEF2024. © 2024 Copyright for this paper by its authors.

关键词： 0-1 cost loss Fine-grained image recognition Fungi Species Identification Open-Set

来源：评论

学校读者我要写书评

暂无评论

The most tenuous group query

引用

Frontiers of computer science 2023年第2期17卷 197-208页

作者： Na LI Huaijie ZHU Wenhao LU Ningning CUI Wei LIU Jian YIN Jianliang XU Wang-Chien LEE School of Computer Science and Engineering Sun Yat-Sen UniversityGuangzhou 510006China Laboratory of Big Data Analysis and Processing Guangzhou 510006China School of Artificial Intelligence Sun Yat-Sen UniversityGuangzhou 510006China Department of Computer Science Anhui UniversityHefei 230601China Department of Computer Science Hong Kong Baptist UniversityHong Kong 999077China Department of Computer Science The Pennsylvania State UniversityState College 19019USA

Rtecently a lot of works have been investigating to find the tenuous groups,i.e.,groups with few social interactions and weak relationships among members,for reviewer selection and psycho-educational group ***,the metrics(e.g.,k-triangle,k-line,and k-tenuity)used to measure the tenuity,require a suitable k value to be specified which is difficult for users without background ***,in this paper we formulate the most tenuous group(MTG)query in terms of the group distance and average group distance of a group measuring the tenuity to eliminate the influence of parameter k on the tenuity of the *** address the MTG problem,we first propose an exact algorithm,namely MTGVDIS,which takes priority to selecting those vertices whose vertex distance is large,to generate the result group,and also utilizes effective filtering and pruning *** MTGVDIS is not fast enough,we design an efficient exact algorithm,called MTG-VDGE,which exploits the degree metric to sort the vertexes and proposes a new combination order,namely degree and reverse based branch and bound(DRBB).MTG-VDGE gives priority to those vertices with small *** a large p,we further develop an approximation algorithm,namely MTG-VDLT,which discards candidate attendees with high degree to reduce the number of vertices to be *** experimental results on real datasets manifest that the proposed algorithms outperform existing approaches on both efficiency and group tenuity.

关键词： tenuous group pruning strategy social network group query

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：