检索结果-内蒙古大学图书馆

4th World Symposium on software engineering, WSSE 2022

作者： Wu, Zhuoyi Ma, Zhiqiang Bao, Caijilahu Li, Leixiao Zhang, Xiaoxu Zhu, Fangyuan College of Data Science and Application Inner Mongolia University of Technology China Inner Mongolia Autonomous Region Engineering Technology Research Centre of Big Data Based Software Service China

ISBN: (纸本)9781450396950

Vehicle behavior recognition is one of the most important research fields in intelligent transportation. In the field of traffic surveillance videos, target vehicles only occupy small proportion of the video frame,making it difficult for the network to extract key features of small target vehicles. To solve this problem, this paper constructed vehicle-3C, a video dataset for vehicle behavior recognition, and was combined with deep learning theory. As a result, it proposed a vehicle behavior recognition method based on the theory of Two-Stream with Attention Network (TSAN). For this method, the two-stream convolutional network is used as a basic framework and attention units are embedded in it to extract temporal (motion) features and spatial features of target vehicles in traffic surveillance videos, and then the temporal and spatial features are fused for category judgment. The results showed that TSAN could achieve 81.8% identification accuracy in vehicle-3C dataset, which was better than other behavior recognition methods based on deep learning. In addition, TSAN also achieves a recognition accuracy of 77.2% in dataset UCF-101, which verifies the generalization performance of the network. Experimental results showed that TSAN could accurately extract and effectively fuse the temporal and spatial features of the foreground target vehicle in the video and achieve high recognition accuracy in the vehicle behavior recognition task. © 2022 ACM.

关键词： Vehicles

来源：评论

学校读者我要写书评

暂无评论

Edge Learning-Based Efficient Data Imputation of Water Quality 7th

Edge Learning-Based Efficient Data Imputation of Water Quali...

引用

7th International Conference on Computing, Control and Industrial engineering, CCIE 2023

作者： Wang, Yongsheng Chen, Zhen Liu, Limin Gao, Jing Liu, Guangwen Xu, Zhiwei School of Data Science and Application Inner Mongolia University of Technology Hohhot010080 China Inner Mongolia Autonomous Region Engineering Technology Research Center of Big Data Based Software Service Hohhot010080 China Institute of Computing Technology Chinese Academy of Sciences Beijing100000 China

ISBN: (纸本)9789819927296

Water quality monitoring is critical for developing effective surface water management strategies, whereas data preprocessing is the foundation for monitoring water quality. Water quality monitoring usually suffers from abnormal and missing values in the collected data of surface water quality, and thus an efficient data imputation method for water quality data is highly desired. To handle these challenges, we propose an edge learning-based data imputation method. By using VAE as the generator of WGAN-LP, the performance of value imputation of water quality is generalized and improved. In addition, we demonstrate the performance of the proposed method on two real-world datasets, collected from Wuliangsu Lake and Taihu Lake in inner mongolia. Compared with state of the art, the enhanced imputation accuarcy of water quality is achieved. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Water quality

来源：评论

学校读者我要写书评

暂无评论

Task Scheduling in Server Farms with Reinforcement Learning

Task Scheduling in Server Farms with Reinforcement Learning

引用

Computer Information Science and Application technology (CISAT), International Conference on

作者： Chao Deng Jianxiong Wan Chuyi Liu Leixiao Li Inner Mongolia University of Technology Huhhot China Inner Mongolia Autonomous Region Engineering & Technology Research Center of Big Data Based Software Service Huhhot China

ISBN: (数字)9798350375107

ISBN: (纸本)9798350375114

Multi-task concurrent scheduling is crucial to improving system performance. Commonly used traditional scheduling algorithms (random, greedy, etc.) are usually difficult to cope with dynamic tasks and resource requirements, resulting in unsatisfactory results. This paper proposes a deep reinforcement learning (DRL) method to solve the scheduling problem by modeling it as a Markov decision process (MDP). The Deep Q Network (DQN) algorithm uses experience replay to enhance learning stability and performance through training strategies and value networks. The training reward results show that it is 40.1 7% higher than the random scheduling strategy, proving its effectiveness.

关键词： Training Greedy algorithms Scheduling algorithms Heuristic algorithms System performance Multitasking Stability analysis Resource management Servers Optimization

来源：评论

学校读者我要写书评

暂无评论

Predicting Gasoline RON Loss by Machine Learning 6

Predicting Gasoline RON Loss by Machine Learning

引用

6th IEEE International Conference on Sensing, Diagnostics, Prognostics, and Control, SDPC 2022

作者： Liu, Limin Chen, Zhen Wang, Yongsheng Liu, Guangwen Inner Mongolia University of Technology Inner Mongolia Autonomous Region Engineering & Technology Research Center of Big Data Based Software Service College of Data Science and Application Hohhot China Inner Mongolia University of Technology College of Data Science and Application Hohhot China

ISBN: (数字)9781665469869

ISBN: (纸本)9781665469869

In order to improve gasoline quality and reduce the environmental pollution caused by gasoline combustion, we aim to study the nonlinear relationship between octane loss and various gasoline components in gasoline refining process, further optimize the gasoline refining process, and reduce the content of sulfur and olefin in gasoline products while minimizing the octane loss. Firstly, we used the nonlinear data reduction algorithm t-SNE to preprocess the data of each component in gasoline and clarify each characteristic parameter;then we constructed the Multiple Nonlinear Regression (MNR) model to analyze the correlation and influence of each characteristic data on octane value;finally, we selected NSGA-II multi-objective genetic algorithm. The NSGA-II multi-objective genetic algorithm was selected for in-depth optimization of the model. The multiple linear regression model was also constructed for comparison experiments, and the advantages and disadvantages of the predicted results of the two models were analyzed, as well as the feasibility of extension. In the experiments with industrial data samples published in Sinopec Gaoqiao Petrochemical real-time database (Honeywell PHD) and LIMS experimental database, it was found that the multivariate nonlinear regression model has more superiority in achieving the purpose of the study, the value of harmful content in gasoline was reduced by 32.7%, and the predicted data of each component of gasoline was more in line with environmental protection requirements. Therefore, the multivariate nonlinear model has the highest reasonableness in predicting the octane loss values. © 2022 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Optimal Sharding for Dynamic Throughput Optimization in Blockchain Systems with Deep Reinforcement Learning

Optimal Sharding for Dynamic Throughput Optimization in Bloc...

引用

2023 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2023

作者： Yao, Bingbing Wan, Jianxiong Jaffry, Shan Li, Leixiao Ma, Zhiqiang Liu, Chuyi Inner Mongolia University of Technology Hohhot China Inner Mongolia Autonomous Region Engineering & Technology Research Center of Big Data Based Software Service Hohhot China Research Center of Large-Scale Energy Storage Technologies Ministry of Education of the People's Republic of China China Syntronic Research and Development Canada Inc. Canada

ISBN: (纸本)9798350337020

The rapid advancement in blockchain technology has enabled its applications across wide spectrum of fields. The blockchain throughput, which is usually measured by Transactions Per Second (TPS), is one of the key metrics to reflect the performance of the blockchain systems. However, current blockchain systems have low TPS rates that makes them unsuitable for latency critical applications like Vehicle-to-vehicle (V2V) communication. To address the above issue, the sharding technology, which divides the network into multiple disjoint groups so that transactions can be processed in parallel, is applied to the blockchain systems as a promising solution to improve TPS. This paper considers the Optimal Blockchain Sharding (OBCS) problem which is formulated as a Markov Decision Process (MDP) where the decision variables are the number of shards, block size and block interval. Previous works solved the OBCS problem via Deep Reinforcement Learning (DRL) based methods where the action space has to be discretized such that it is not too large for tractability. However, the discretization degrades the solution quality since the optimal solution usually lies between discrete values. In this paper, we treat the block size and block interval as continuous decision variables and propose a sharding control algorithm based on Parametrized Deep Q-Networks (P-DQN) to efficiently handle the discrete-continuous hybrid action space without the scalability issue. Experimental results show that our Parametrized Deep Q-Networks Blockchain Sharding (P-DQNBS) method can effectively improve the TPS by up to 20%. © 2023 IEEE.

关键词： blockchain deep reinforcement learning hybrid action space sharding

来源：评论

学校读者我要写书评

暂无评论

Dual Consistent Constraint via Disentangled Consistency and Complementarity for Multi-view Clustering

arXiv

引用

arXiv 2025年

作者： Li, Bo Yun, Jing College of Data Science and Application Inner Mongolia University of Technology Inner Mongolia Huhhot010080 China Inner Mongolia Autonomous Region Engineering and Technology Research Center of Big Data-Based Software Service Inner Mongolia Huhhot010080 China Inner Mongolia Key Laboratory of Beijiang Cyberspace Security Inner Mongolia Huhhot010080 China

Multi-view clustering can explore common semantics from multiple views and has received increasing attention in recent years. However, current methods focus on learning consistency in representation, neglecting the contribution of each view’s complementarity aspect in representation learning. This limit poses a significant challenge in multi-view representation learning. This paper proposes a novel multi-view clustering framework that introduces a disentangled variational autoencoder that separates multi-view into shared and private information, i.e., consistency and complementarity information. We first learn informative and consistent representations by maximizing mutual information across different views through contrastive learning. This process will ignore complementary information. Then, we employ consistency inference constraints to explicitly utilize complementary information when attempting to seek the consistency of shared information across all views. Specifically, we perform a within-reconstruction using the private and shared information of each view and a cross-reconstruction using the shared information of all views. The dual consistency constraints are not only effective in improving the representation quality of data but also easy to extend to other scenarios, especially in complex multi-view scenes. This could be the first attempt to employ dual consistent constraint in a unified MVC theoretical framework. During the training procedure, the consistency and complementarity features are jointly optimized. Extensive experiments show that our method outperforms baseline methods. © 2025, CC BY.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Multi-Task Computation Offloading based on Vehicular Blockchain

Multi-Task Computation Offloading based on Vehicular Blockch...

引用

Frontiers technology of Information and Computer (ICFTIC), IEEE International Conference on

作者： Zhen Meng Chuyi Liu Guanyu Ren Jianxiong Wan Leixiao Li Inner Mongolia University of Technology Hohhot China Inner Mongolia Autonomous Region Engineering & Technology Research Center of Big Data Based Software Service Hohhot China

With the increase of vehicular applications, which aimed at improving traffic safety and driving experience, the limited computing resources of vehicles face the challenge of the real-time task requirements. Vehicular Edge Computing is an efficient way to augment the computational capabilities of vehicles. However, there are few researches have simultaneously considered the vehicle reliability, task prioritization, and timely scheduling of tasks. To bridge this gap and motivate vehicles to share computing resources, this paper proposed a multi-task offloading method. We formulated a revenue maximization problem and designed a control algorithm for this problem based on deep reinforcement learning. Meanwhile, we employed blockchain technology to ensure vehicle reliability. Simulation results validate the effectiveness of the proposed method, demonstrating a profits improvement of 67.98%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

EA-YOLO: An Endangered Animal Detection Algorithm Incorporating Attention Mechanisms

EA-YOLO: An Endangered Animal Detection Algorithm Incorporat...

引用

International Conference on Computer engineering and Applications (ICCEA)

作者： Kai Yan Junping Qin Lei Wang Hao Sun Shulan Sun Xiaole Shi College of Data Science and Application Inner Mongolia University of Technology Hohhot China Inner Mongolia Autonomous Region Engineering Technology Research Center of Big Data Based Software Service College of Data Science and Application Inner Mongolia University of Technology Hohhot China

ISBN: (数字)9798350386776

ISBN: (纸本)9798350386783

Endangered animal resources are crucial for biodiversity conservation and research. The detection and identification of endangered animals is a significant means to achieve this. However, the recognition accuracy of endangered animals is often affected by complex environmental conditions in the field. This paper proposes an improved algorithm named Endangered Animals-You Only Look Once (EA-YOLO) to address the issues of low target recognition accuracy and lack of feature extraction caused by complex environmental conditions and small target proportions in the picture. The algorithm is based on YOLOv8. This paper proposes two improvements to YOLOv8. Firstly, a multi-scale object detection head is introduced to fuse more image feature information, enhancing the network's ability to perceive and localize small targets. Secondly, a Global Attention Mechanism (GAM) module is added to learn richer feature information. The network can focus on important features and ignore irrelevant ones, leading to improved performance. The EA-YOLO model was evaluated on the LoTE-Animal dataset through extensive experiments. Results indicate that the improved model achieved an average accuracy of 95%, which is a 9% improvement over the original algorithm while maintaining competitive detection accuracy.

关键词： Accuracy Attention mechanisms Head Animals Target recognition Fuses Computational modeling

来源：评论

学校读者我要写书评

暂无评论

Kinematic Modeling and Experimental Verification of Underdriven Rigid-Flex Integrated Manipulator*

Kinematic Modeling and Experimental Verification of Underdri...

引用

International Conference on Advanced Robotics and Mechatronics (ICARM)

作者： Shu F. Tang Tian T. Li Qi. Wang Peng F. Zhou Jing F. Jing School of Mechanical Engineering Inner Mongolia University of Technology Hohhot China Inner Mongolia Autonomous Region Key Laboratory of Special Service Intelligent Robot Hohhot China

ISBN: (数字)9798350385724

ISBN: (纸本)9798350385731

This paper presents an underactuated rigid-flexible integrated manipulator, which is equipped with three identical rigid-flexible coupled mechanical fingers. The first joint of the fingers is divided into two parts, the front end and the rear end, connected by a spring steel strip. The effective length of the spring steel strip is adjusted using shape memory alloy wires, resulting in variable stiffness characteristics of the fingers as the effective length of the spring steel strip changes. Kinematic analysis is conducted for different grasping modes to simulate and solve its motion space. Dynamic simulation of the manipulator is carried out to test the grasping stability under different grasping modes. An experimental platform for the underactuated rigid-flex coupled manipulator grasping is established, and through experiments, it is verified that the designed manipulator possesses good grasping capability and grasping stability.

关键词： Strips Shape memory alloys Fingers Wires Grasping Kinematics Stability analysis Steel Springs Manipulator dynamics

来源：评论

学校读者我要写书评

暂无评论

3D-MTR: 3D Reconstruction Algorithms for Deep Understanding of Images 2

3D-MTR: 3D Reconstruction Algorithms for Deep Understanding ...

引用

2nd International Conference on Computer Science, Electronic Information engineering and Intelligent Control technology, CEI 2022

作者： Gao, Tong Qin, Junping Xue, Hongcheng Xue, Liming Wang, Chao College of Data Science and Application Inner Mongolia Univer-sity of Technology Hohhot010080 China Inner Mongolia Autonomous Reg. Eng. Technology Research Center of Big Data Based Software Service Huhhot010080 China Agricultural Animal Husbandry Technology Generalization Center of Inner Mongolia Autonomous Region Education and Training Division Hohhot010010 China

ISBN: (数字)9781665476164

ISBN: (纸本)9781665476164

Three-dimensional data can improve the performance of computer vision downstream tasks. In this paper, computer vision is introduced from the two-dimensional world to the three-dimensional world through the three-dimensional reconstruction algorithm. A 3D reconstruction algorithm, 3D Masked autoencoder Transformer Reconstruction (3D-MTR), is proposed for deep understanding of series view to restore 3D model. 3D-MTR can reconstruct 3D models with high-level semantic information in the series of views. Among them, in order to accurately extract and fuse the feature vectors with spatial information in the series of views, the MAE self-supervised learning pre-training is performed on the two-dimensional encoder;in order to make the reconstructed model more realistic, the Transformer-based two-dimensional encoder is compared with adversarial training. Combined, the model is updated through advanced semantic information;in order to make up for the uncontrollable defect of adversarial training, a repair network is added at the end of the model. In order to verify the validity of the model, a comparison experiment was conducted with three classic 3D reconstruction models on the ShapeNet dataset, using the Chamfer distance and the intersection-over-union ratio as the model evaluation indicators, and the experiments were conducted. Perform qualitative and quantitative analysis. © 2022 IEEE.

关键词： Computer vision

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：