检索结果-内蒙古大学图书馆

Fast, Scalable and Robust Centralized Routing for data Center Networks

ieee-ACM TRANSACTIONS ON NETWORKING 2023年第6期31卷 2624-2639页

作者： Lin, Fusheng Wang, Hongyu Chen, Guo Zhou, Guihua Xu, Tingting Wei, Dehui Chen, Li Lu, Yuanwei Qu, Andrew Shao, Hua Jiang, Hongbo Hunan Univ Coll Comp Sci & Elect Engn Changsha 410012 Peoples R China Tencent Shenzhen 518054 Peoples R China Nanjing Univ Dept Comp Sci & Technol Nanjing 210093 Peoples R China Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing 100876 Peoples R China Zhongguancun Lab Beijing 100081 Peoples R China Pinduoduo Shanghai 200000 Peoples R China

This paper presents a fast and robust centralized data center network (DCN) routing solution, called Primus. For fast routing calculation, Primus uses centralized controllers to collect/disseminate the network's link-states (LS), and offload the actual routing calculation onto each switch. Observing that the routing changes can be classified into a few fixed patterns in DCNs which have regular topologies, we simplify each switch's routing calculation into a table-lookup manner, i.e., comparing LS changes with pre-installed base topology and updating routing paths according to predefined rules. As such, the routing calculation time at each switch only needs 10s of us even in a large network topology containing 10K+ switches. For efficient controller fault-tolerance, Primus purposely uses reporter switch to ensure the LS updates successfully delivered to all affected switches. As such, Primus can use multiple stateless controllers and little redundant traffic to tolerate failures, which incurs little overhead under normal case, and keeps 10s of ms fast routing reaction time even under complex data-/control-plane failures. We design, implement and evaluate Primus with extensive experiments on Linux-machine controllers and white-box switches. Primus provides similar to 1200x and similar to 100x shorter convergence time than current distributed protocol BGP and the state-of-the-art centralized routing solution, respectively. Furthermore, Primus maintains good routing controllability/manageability thanks to its centralized architecture, which enables us to build several advanced routing features in our testbed, including routing failure visualization and weighted-cost-multi-path routing.

关键词： data center networks centralized routing network protocols

来源：评论

学校读者我要写书评

暂无评论

Research on Frequency Control Technology of Complex Power Grid Based on Multi-objective Optimization Particle Swarm Optimization Algorithm 6

Research on Frequency Control Technology of Complex Power Gr...

引用

6th Asia Conference on Energy and Electrical Engineering, ACEEE 2023

作者： Luo, Weihua Quan, Qing Lan, Qiang Sun, Yongchao Cheng, Dachuang Zheng, Tao Liu, Yan Southwest Branch of State Grid Corporation of China Dispatching Control Center Chengdu China Beijing KeDong Electric Power Control System Co. Ltd Data Visualization Business Department Beijing China

ISBN: (纸本)9798350312690

The problem of complex power grid frequency control of multi-level and multi-DC is a complex high-dimensional nonlinear programming question. According to the traditional power control mode, it is difficult to meet the requirements of safe, low-carbon and economic operation of the power grid. In this paper, a particle swarm optimization method based on multi-objective optimization is proposed. Considering the coordinated control strategy of the units under the jurisdiction of multi-level dispatching organizations, the coordinated control strategy of multiple DC power sources and the coordinated control strategy of multiple power sources, the control effects of the units under the jurisdiction of different dispatching organizations are simulated and analyzed respectively. The results show that the method in this paper is more conducive to the rapid recovery of the system frequency after the grid fault. © 2023 ieee.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Causal Interventional Training for Image Recognition

引用

ieee TRANSACTIONS ON MULTIMEDIA 2023年 25卷 1033-1044页

作者： Qin, Wei Zhang, Hanwang Hong, Richang Lim, Ee-Peng Sun, Qianru Hefei Univ Technol Key Lab Knowledge Engn Big Data Minist Educ Hefei 230006 Peoples R China Hefei Comprehens Natl Sci Ctr Inst Artificial Intelligence Hefei 230088 Peoples R China Nanyang Technol Univ Sch Comp Sci Singapore 639798 Singapore Singapore Management Univ Sch Informat Syst Singapore 178902 Singapore

Deep learning models often fit undesired dataset bias in training. In this paper, we formulate the bias using causal inference, which helps us uncover the ever-elusive causalities among the key factors in training, and thus pursue the desired causal effect without the bias. We start from revisiting the process of building a visual recognition system, and then propose a structural causal model (SCM) for the key variables involved in dataset collection and recognition model: object, common sense, bias, context, and label prediction. Based on the SCM, one can observe that there are "good " and "bad " biases. Intuitively, in the image where a car is driving on a high way in a desert, the "good " bias denoting the common-sense context is the highway, and the "bad " bias accounting for the noisy context factor is the desert. We tackle this problem with a novel causal interventional training (CIT) approach, where we control the observed context in each object class. We offer theoretical justifications for CIT and validate it with extensive classification experiments on CIFAR-10, CIFAR-100 and ImageNet, e.g., surpassing the standard deep neural networks ResNet-34 and ResNet-50, respectively, by 0.95% and 0.70% accuracies on the ImageNet. Our code is open-sourced on the GitHub https://***/qinwei-hfut/CIT.

关键词： Training Automobiles Task analysis visualization Road transportation Image recognition data models Causality causal intervention deep learning imagenet image recognition

来源：评论

学校读者我要写书评

暂无评论

Effective visualization and Trend Forecasting of Crime data Through Big data Analytics and Mining 3

Effective Visualization and Trend Forecasting of Crime Data ...

引用

3rd International Conference on Pervasive Computing and Social Networking, ICPCSN 2023

作者： Mahendhiran, Pd Apsara, S.K. Vasudevan, Harshitha Nithish, S. Sri Krishna College of Engineering and Technology Department of Computer Science and Business Systems Tamil Nadu Coimbatore India Sri Krishna College of Engineering and Technology Department of Computer Science and Engineering Tamil Nadu Coimbatore India

ISBN: (纸本)9798350322842

A crime is an act that merits public condemnation and penalties, which is usually in the form of a fine or jail. It is a widespread social issue that affects a country's life style, economic progress, and credibility. People are at a worrisome point in terms of reducing criminal activity at a greater rate, as criminality rates have risen dramatically. If people can evaluate and predict the crime pattern and implement preventive steps ahead of time, crime rates can be lowered. In this research, the author has present Crime Cast, a system that analyses crime reports and anticipates trends and crime statistics based on a specified data set using deep learning techniques such as LSTM and DNN at a faster rate and with greater accuracy. Within a huge percentage of crime data, Big data Analytics is utilized to analyze and detect different crime patterns, their relationships, and trends. The information contains cases of kidnapping, murder, rape, stealing, and other crimes. With the help of the LSTM model and DNN several operations performed on the data. The expected outcomes will aid police and law enforcement agencies in clearer grasp crime trends, allowing them to track incidences and improve their decision-making processes. These results will allow the law enforcement and regulatory agencies to further immediately spot inappropriate behavior issues and provide information that will allow them to monitor activities and predict the likelihood of limiting the number of events, transporting property securely, and improving the dynamic cycle. © 2023 ieee.

关键词： Crime

来源：评论

学校读者我要写书评

暂无评论

Automatic Depression Detection via Learning and Fusing Features From Visual Cues

引用

ieee TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS 2023年第5期10卷 2806-2813页

作者： Guo, Yanrong Zhu, Chenyang Hao, Shijie Hong, Richang Hefei Univ Technol HFUT Minist Educ Key Lab Knowledge Engn Big Data Hefei 230009 Peoples R China Hefei Univ Technol HFUT Sch Comp Sci & Informat Engn Hefei 230009 Peoples R China

Depression is one of the most prevalent mental disorders, which seriously affects one's life. Traditional depression diagnostics commonly depend on rating with scales, which can be labor-intensive and subjective. In this context, automatic depression detection (ADD), aiming to assist medical experts in their diagnosis and analysis, has been attracting more attention for its better objectivity and fewer laborious interventions. A typical ADD model detects depression via automatically extracting task-specific features from medical records, such as video sequences, and sending them into a classifier for assistive prediction. However, it remains challenging to effectively extract depression-specific information from long sequences, thereby hindering a satisfying accuracy. In this article, we propose a novel ADD method via learning and fusing features from visual cues. Specifically, we first construct temporal dilated convolutional network (TDCN), in which multiple dilated convolution blocks (DCBs) are designed and stacked, to learn the long-range temporal information from sequences. Then, the featurewise attention (FWA) module is adopted to fuse different features extracted from TDCNs. The module learns to assign weights for the feature channels, aiming to better incorporate different kinds of visual features and further enhance the detection accuracy. Our method achieves the state-of-the-art performance on the Distress Analysis Interview Corpus Wizard-of-Oz (DAIC_WOZ) dataset compared with other visual-feature-based methods, showing its effectiveness.

关键词： Feature extraction Depression visualization Task analysis Convolution Medical diagnostic imaging data mining Depression detection dilated convolution fusion visual cue

来源：评论

学校读者我要写书评

暂无评论

An Efficient RGB-D Hand Gesture Detection Framework for Dexterous Robot Hand-Arm Teleoperation System

引用

ieee TRANSACTIONS ON HUMAN-MACHINE SYSTEMS 2023年第1期53卷 13-23页

作者： Gao, Qing Ju, Zhaojie Chen, Yongquan Wang, Qiwen Chi, Chuliang Chinese Univ Hong Kong Shenzhen Inst Artificial Intelligence & Robot Soc Shenzhen 518172 Peoples R China Chinese Univ Hong Kong Inst Robot & Intelligent Mfg Shenzhen 518172 Peoples R China Univ Portsmouth Sch Comp Portsmouth PO1 3HE Hants England

Aiming at the problems of accurate and fast hand gesture detection and teleoperation mapping in the hand-based visual teleoperation of dexterous robots, an efficient hand gesture detection framework based on deep learning is proposed in this article. It can achieve an accurate and fast hand gesture detection and teleoperation of dexterous robots based on an anchor-free network architecture by using an RGB-D camera. First, an RGB-D early-fusion method based on the HSV space is proposed, effectively reducing background interference and enhancing hand information. Second, a hand gesture classification network (HandClasNet) is proposed to realize hand detection and localization by detecting the center and corner points of hands, and a HandClasNet is proposed to realize gesture recognition by using a parallel EfficientNet structure. Then, a dexterous robot hand-arm teleoperation system based on the hand gesture detection framework is designed to realize the hand-based teleoperation of a dexterous robot. Our method achieves high accuracy with fast speed on public and custom hand datasets and outperforms some state-of-the-art methods. In addition, the application of the proposed method in the hand-based teleoperation system can control the grasping of various objects by a dexterous hand-arm system in real time and accurately, which verifies the efficiency of our method.

关键词： Robots Location awareness visualization Robot kinematics Interference Robot vision systems data integration Dexterous robot hand gesture detection RGB-D teleoperation

来源：评论

学校读者我要写书评

暂无评论

Detection of Commodities Based on Multi-Feature Fusion and Attention Screening by Entropy Function Guidance

引用

ieee ACCESS 2023年 11卷 90595-90612页

作者： Xie, An Xie, Kai Dong, Hao-Nan He, Jian-Biao Yangtze Univ Sch Elect & Informat Jingzhou 434023 Peoples R China Yangtze Univ Western Res Inst Karamay 834000 Peoples R China Cent South Univ Sch Comp Sci & Engn Changsha 410083 Peoples R China

Although traditional convolutional neural networks (CNN) have been significantly improved for target detection, they cannot be completely applied to objects with occlusions in commodity detection. Therefore, we propose a target detection method based on an improved YOLOv5 model and an improved attention mechanism algorithm is proposed to solve the commodity occlusion problem. This method improves the traditional YOLO deep convolution network, features a more detailed BiFPN layer, and performs lightweight two-way feature fusion, where the multidimensional features of the commodities are convolved and fused, thus improving the overall detection speed and accuracy of the YOLO-R algorithm. Feature entropy is introduced to the attention channel to restrict the threshold value and obtain the global information of the occlusion target. The global information obtained is fused with a bidirectional feature pyramid layer to enhance the robustness of the features. This method could accurately and quickly detect the occluded commodities and the detection accuracy has been greatly improved. Experiments show that the improved YOLO-R model can improve the accuracy and speed of commodity detection, and can achieve good results in objective evaluation. The average accuracy of commodity detection on the self-made product dataset is up to 97.80%, and the detection rate is 22.72F/s. Therefore, the method in this paper has high detection accuracy and fast detection speed.

关键词： Feature extraction Entropy Object detection data mining visualization Robustness Prediction algorithms Bidirectional control Lightweight feature fusion attention channel feature entropy bidirectional feature

来源：评论

学校读者我要写书评

暂无评论

MTANet: Multitask-Aware Network With Hierarchical Multimodal Fusion for RGB-T Urban Scene Understanding

IEEE TRANSACTIONS ON INTELLIGENT VEHICLES

引用

ieee TRANSACTIONS ON INTELLIGENT VEHICLES 2023年第1期8卷 48-58页

作者： Zhou, Wujie Dong, Shaohua Lei, Jingsheng Yu, Lu Zhejiang Univ Sci & Technol Sch Informat & Elect Engn Hangzhou 310023 Peoples R China Zhejiang Univ Inst Informat & Commun Engn Hangzhou 310027 Peoples R China

Understanding urban scenes is a fundamental ability requirement for assisted driving and autonomous vehicles. Most of the available urban scene understanding methods use red-green-blue (RGB) images;however, their segmentation performances are prone to degradation under adverse lighting conditions. Recently, many effective artificial neural networks have been presented for urban scene understanding and have shown that incorporating RGB and thermal (RGB-T) images can improve segmentation accuracy even under unsatisfactory lighting conditions. However, the potential of multimodal feature fusion has not been fully exploited because operations such as simply concatenating the RGB and thermal features or averaging their maps have been adopted. To improve the fusion of multimodal features and the segmentation accuracy, we propose a multitask-aware network (MTANet) with hierarchical multimodal fusion (multiscale fusion strategy) for RGB-T urban scene understanding. We developed a hierarchical multimodal fusion module to enhance feature fusion and built a high-level semantic module to extract semantic information for merging with coarse features at various abstraction levels. Using the multilevel fusion module, we exploited low-, mid-, and high-level fusion to improve segmentation accuracy. The multitask module uses boundary, binary, and semantic supervision to optimize the MTANet parameters. Extensive experiments were performed on two benchmark RGB-T datasets to verify the improved performance of the proposed MTANet compared with state-of-the-art methods.(1)

关键词： Semantics Thermal sensors Feature extraction Decoding Image segmentation Lighting visualization RGB-T data urban scene understanding hierarchical multimodal fusion high-level semantic information multilevel fusion multiple supervision

来源：评论

学校读者我要写书评

暂无评论

Beyond Word Embeddings: Heterogeneous Prior Knowledge Driven Multi-Label Image Classification

引用

ieee TRANSACTIONS ON MULTIMEDIA 2023年 25卷 4013-4025页

作者： Deng, Xiang Feng, Songhe Lyu, Gengyu Wang, Tao Lang, Congyan Beijing Jiaotong Univ Beijing Key Lab Traff Data Anal & Min Beijing 100044 Peoples R China Beijing Jiaotong Univ Sch Comp & Informat Technol Beijing 100044 Peoples R China

Multi-Label Image Classification (MLIC) is a fundamental yet challenging task which aims to recognize multiple labels from given images. The key to solve MLIC lies in how to accurately model the correlation between labels. Recent studies often adopt Graph Convolutional Network (GCN) to model label dependencies with word embeddings as prior knowledge. However, classical word embeddings typically contain redundant information due to the imperfect distributional hypothesis it relies on, which may degrade model generalizability. To tackle this problem, we propose a novel deep learning framework termed Visual-Semantic based Graph Convolutional Network (VSGCN), which alleviates the negative impact of redundant information by utilizing heterogeneous sources of prior knowledge. Specifically, we construct both visual prototype and semantic prototype for each label as heterogeneous prior label representations, which are further mapped to multi-label classifiers via two Multi-Head GCNs separately. The Multi-Head GCN mechanism proposed in this paper aims to guide the information propagation between prototypes for each label, which constructs multiple correlation graphs to simultaneously model the label correlation in different subspaces. Notably, we alleviate the negative influence of needless information by decreasing the inconsistency of predictions that come from visual space and semantic space. Extensive experiments conducted on various multi-label image datasets demonstrate the superiority of our proposed method.

关键词： Correlation Semantics Prototypes visualization Transformers Knowledge engineering Image classification Multi-label image classification heterogeneous prior knowledge graph convolutional network multi-head attention

来源：评论

学校读者我要写书评

暂无评论

Predictive Modeling for Autism Prediction: Deep Learning Insights from Facial Image data

Predictive Modeling for Autism Prediction: Deep Learning Ins...

引用

2023 International Conference on data science, Agents and Artificial Intelligence, ICDSAAI 2023

作者： Priyanka, S.A. Pandimeena, R. Ananya, H. Reshma, K. Chennai Institute of Technology Department of Biomedical Engineering Chennai69 India Chennai Institute of Technology Department of Electronics and Communication Engineering Chennai69 India

ISBN: (纸本)9798350348910

Autism, commonly known as autism spectrum disorder (ASD), encompasses a variety of symptoms and behaviors that might differ in intensity and manifestation among individuals. People with autism spectrum disorder (ASD) might exhibit varying degrees of difficulty with social communication, interaction, and behavior. Timely identification of autism spectrum disorder (ASD) is essential for delivering efficient intervention and assistance to children and their families. The researchers used convolutional neural networks (CNNs) and the VGG16 pre-trained model to categories the photos as either ASD-positive or negative. In addition, the research employs t-Distributed Stochastic Neighbor Embedding (t-SNE) to represent the complex characteristics of the images in a two-dimensional space. Following exploratory data analysis, the facial picture dataset undergoes preprocessing through techniques such as scaling, normalization, and augmentation. Next, we divide the dataset into separate training and validation sets. We train the CNN and VGG16 models using transfer learning and select the model with the highest performance for subsequent analysis. The chosen model is utilised to forecast the ASD and the outcomes are presented in terms of accuracy, precision, recall, and F1score. Ultimately, t-SNE visualisation is employed to represent the complex characteristics of the images in a two-dimensional framework. This aids in comprehending the arrangement of the images and detecting any discernible patterns or clusters that may suggest the presence of ASD. The results showcase the capacity of employing deep learning methods for predicting ASD using face photos, and t-SNE visualisation offers valuable insight into the fundamental characteristics of the images. © 2023 ieee.

关键词： visualization

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：