检索结果-内蒙古大学图书馆

4th IFIP TC 12 International Conference on Intelligence science, ICIS 2020

作者： Wang, Dong-Sheng Zhao, Cui-Ping Wang, Qi Ofori, Kwame Dwomoh Han, Bin Liu, Ga-Qiong Wang, Shi Wang, Hua-Yu Zhang, Jing School of Computer Science Jiangsu University of Science of Technology Zhenjiang Jiangsu212001 China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China School of Army Engineering University Nanjing Jiangsu210007 China

ISBN: (纸本)9783030748258

Sentence similarity calculation is one of several research topics in natural language processing. It has been widely used in information retrieval, intelligent question answering and other fields. Traditional machine learning methods generally extract sentence features through manually defined feature templates and then perform similarity calculations. This type of method usually requires more human intervention and constantly has to deal with domain migration problems. Automatically extracting sentence features using certain deep learning algorithms helps to solve domain migration problems. The training data is of the domain is required to complete the extraction process. However, the neural network structure design in the deep learning model usually requires experienced experts to carry out multiple rounds of the tuning design phase. Using an automatic neural architecture search (ANAS) technology deals with all the network structure design problems. This paper proposes a sentence similarity calculation method based on neural architecture search. This method uses a combination of grid search and random search. The method in this paper is tested on the Quora "Question-Pairs" data set and has an accuracy of 81.8%. The experimental results show that the method proposed in this paper can efficiently and automatically learn the network structure of the deep learning model to achieve high accuracy. © 2021, IFIP International Federation for Information Processing.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Privacy-Preserving Secure Shared Nearest Neighbor Clustering Scheme in Internet of Things

SSRN

引用

SSRN 2023年

作者： Hu, Qiqi Zhang, Hanlin Sun, Jiakang Lin, Jie Xu, Hansong Kong, Fanyu College of Computer Science and Technology Qingdao University Qingdao266071 China College of Computer Science and Technology University of Chinese Academy of Sciences 101408 China School of Electronic and Information Engineering Xi’an Jiaotong University Xian710049 China School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai200240 China School of Software Shandong University Jinan250100 China

Shared Nearest Neighbor (SNN) is a density-based clustering approach extensively employed in industrial Internet of Things applications, including pattern recognition, image analysis, and data mining. The efficiency of SNN clustering poses a significant concern for IoT devices with constrained computational abilities, particularly when dealing with large-scale data. An effective solution is to delegate the computationally complex aspects of clustering to a remote cloud server. However, some security challenge may appear since the cloud environment is often untrustworthy. In this article, we proposed a privacy-preserving cloud-aided scheme for resource-limited IoT devices to execute SNN clustering securely and efficiently. To protect the privacy, we introduced a novel matrix transformation technique for encoding original data before transmitting it to the cloud. The cloud server processes the encoded data and returns results to the devices. The results will be decoded by device side to obtain the actual results. Besides, we developed a robust verification method to detect the accuracy of cloud’s result with optimal probability 1. Furthermore, we conducted comprehensive theoretical analysis and experimental evaluation, which confirmed the correctness, efficiency, and security for our scheme. In the final post-outsourcing tests, SNN's most complex step's time cost dropped from 10.859s to 1.183s in client side. © 2023, The Authors. All rights reserved.

关键词： Cluster analysis

来源：评论

学校读者我要写书评

暂无评论

SpliceMix: A Cross-scale and Semantic Blending Augmentation Strategy for Multi-label Image Classification

arXiv

引用

arXiv 2023年

作者： Wang, Lei Zhan, Yibing Ma, Leilei Tao, Dapeng Ding, Liang Gong, Chen The Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information Ministry of Education Jiangsu Key Laboratory of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology Jiangsu Nanjing210094 China The JD Explore Academy Beijing100000 China The School of Computer Science and Technology Anhui University Anhui Heifei230601 China The FIST LAB School of Information Science and Engineering Yunnan University Yunnan Kunming650091 China

Recently, Mix-style data augmentation methods (e.g., Mixup and CutMix) have shown promising performance in various visual tasks. However, these methods are primarily designed for single-label images, ignoring the considerable discrepancies between single- and multi-label images, i.e., a multi-label image involves multiple co-occurred categories and fickle object scales. On the other hand, previous multi-label image classification (MLIC) methods tend to design elaborate models, bringing expensive computation. In this paper, we introduce a simple but effective augmentation strategy for multi-label image classification, namely SpliceMix. The "splice" in our method is two-fold: 1) Each mixed image is a splice of several downsampled images in the form of a grid, where the semantics of images attending to mixing are blended without object deficiencies for alleviating co-occurred bias;2) We splice mixed images and the original mini-batch to form a new SpliceMixed mini-batch, which allows an image with different scales to contribute to training together. Furthermore, such splice in our SpliceMixed mini-batch enables interactions between mixed images and original regular images. We also offer a simple and non-parametric extension based on consistency learning (SpliceMix-CL) to show the flexible extensibility of our SpliceMix. Extensive experiments on various tasks demonstrate that only using SpliceMix with a baseline model (e.g., ResNet) achieves better performance than state-of-the-art methods. Moreover, the generalizability of our SpliceMix is further validated by the improvements in current MLIC methods when married with our SpliceMix. The code is available at https://***/zuiran/SpliceMix. Copyright © 2023, The Authors. All rights reserved.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

FedABC: Targeting Fair Competition in Personalized Federated Learning

arXiv

引用

arXiv 2023年

作者： Wang, Dui Shen, Li Luo, Yong Hu, Han Su, Kehua Wen, Yonggang Tao, Dacheng National Engineering Research Center for Multimedia Software School of Computer Science Institute of Artificial Intelligence Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University China Hubei Luojia Laboratory Wuhan China JD Explore Academy China School of Information and Electronics Beijing Institute of Technology China School of Computer Science and Engineering Nanyang Technological University Singapore

Federated learning aims to collaboratively train models without accessing their client’s local private data. The data may be Non-IID for different clients and thus resulting in poor performance. Recently, personalized federated learning (PFL) has achieved great success in handling Non-IID data by enforcing regularization in local optimization or improving the model aggregation scheme on the server. However, most of the PFL approaches do not take into account the unfair competition issue caused by the imbalanced data distribution and lack of positive samples for some classes in each client. To address this issue, we propose a novel and generic PFL framework termed Federated Averaging via Binary Classification, dubbed FedABC. In particular, we adopt the "one-vs-all" training strategy in each client to alleviate the unfair competition between classes by constructing a personalized binary classification problem for each class. This may aggravate the class imbalance challenge and thus a novel personalized binary classification loss that incorporates both the under-sampling and hard sample mining strategies is designed. Extensive experiments are conducted on two popular datasets under different settings, and the results demonstrate that our FedABC can significantly outperform the existing counterparts. Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

MUCD: Unsupervised Point Cloud Change Detection via Masked Consistency 39

MUCD: Unsupervised Point Cloud Change Detection via Masked C...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Wu, Yue Wang, Zhipeng Yuan, Yongzhe Gong, Maoguo Li, Hao Zhang, Mingyang Ma, Wenping Miao, Qiguang MoE Key Lab of Collaborative Intelligence Systems Xidian University China School of Computer Science and Technology Xidian University China Academy of Artificial Intelligence College of Mathematics Science Inner Mongolia Normal University China School of Electronic Engineering Xidian University China School of Artificial Intelligence Xidian University China

ISBN: (纸本)157735897X

3D Change Detection (3DCD) has gradually become another research hotspot after image change detection. Recent works focus on using artificial labels for supervised or weakly-supervised training of siamese networks to segment changed points. However, labeling every points of multitemporal point clouds is very expensive and time-consuming. In addition, these works lack effective self-supervised signals, and existing self-supervised signals often fail to capture sufficiently rich change information. To solve this problem, we assume that the powerful representation of 3D objects should model the consistency information of unchanged regions and distinguish different objects. Based on this assumption, we propose a new unsupervised framework called MUCD to learn change information of multi-temporal point clouds through bidirectional optimization of change segmentor and feature extractor. The training of network is divided into two stages. We first design a foreknowledge point contrastive loss based on the characteristics of the 3DCD task to initialize the feature extractor, and then propose a masked consistency loss to further learn the shared geometric information of unchanged regions in the multi-temporal point clouds, utilizing it as a free and powerful supervised signal to train a change segmentor. In the inference stage, only the segmentor is used to take multi-temporal point clouds as input and produce change segmentation result. Extensive experiments are conducted on SLPCCD and Urb3DCD, two real-world datasets of streets and urban buildings, to verify that our proposed unsupervised method is highly competitive and even outperforms supervised methods in scenes where semantic information changes occur, exhibiting better performance in generalization ability and robustness. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Complementary multi-branch CNNs towards real-world 3D point classification

Complementary multi-branch CNNs towards real-world 3D point ...

引用

2021 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2021

作者： Tang, Zifeng Hao, Fusheng Zhang, Qieshi Cheng, Jun Zhang, Jin Yuan, Shuai Shenzhen Institute of Advanced Technology Chinese Academy of Science CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems China Chinese University of Hong Kong Hong Kong Shenzhen University College of Computer Science and Software Engineering China Guangdong University of Technology College of Mechanical and Electrical Engineering China

ISBN: (纸本)9781665436786

Autonomous driving requires precise and efficient point clouds processing techniques, where deep learning has shown great potential. Nonetheless, most of the existing works achieve high accuracy in synthetic data while performing unsatisfactorily in real-world datasets. On the other hand, though existing multi-view-based, volumetric-based, and point-based methods have achieved promising results, they still suffer from high computational complexity or low memory utilization efficiency. For example, the computational time and memory consumption of multi-view-based and volumetric-based methods increase at most cubically with the increasing of the input resolution, while half of the point-based methods's runtime is wasted due to their irregular memory access. To address these issues, we propose a novel method to fuse complementary CNNs, dubbed as Multi-Branch Convolutional Neural Networks (MBCNN), which achieves the current state-of-the-art performance while maintaining high efficiency. The underlying design of MBCNN is to utilize the point-based convolution as a local-feature branch and spherical convolution as a global-feature branch, to capture patterns in space and exploit the merit of the pointwise MLP, which is robust to the perturbation. Besides, we design an efficient voxel-based indexing technique to prevent the feature-extracting phase from being blocked, thus significantly accelerating the procedure of finding a point's neighbor. Experimental results show that MBCNN achieves state-of-the-art performance on the real-world 3D point clouds dataset while reducing 30% of runtime in neighbor indexing. © 2021 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Convolution Neural Networks for Clinical Image Segmentation with Evolutionary Compression

Convolution Neural Networks for Clinical Image Segmentation ...

引用

Advance Computing and Innovative Technologies in engineering (ICACITE), International Conference on

作者： Ashiq V. M E. J. Thomson Fredrik Sonali Vyas N. Shilpa Kapil Joshi Sakshi Gupta Department of Computer Science Karpagam Academy of Higher Education Coimbatore Department of Computer Applications Karpagam Academy of Higher Education Coimbatore (Selection Grade) School of Computer Science University of Petroleum and Energy Studies Dehradun Uttarakhand Department of Electronics and Communication Engineering SR University Warangal Telangana India Uttaranchal Institute of Technology Uttaranchal University Department of Professional Communication Graphic Era Deemed to be University Dehradun Uttarakhand India

Convolutional Neural Networks (CNN) have been very useful for image-related applications as a result of their high level of accuracy and their ability to analyze data in real time. Neural networks have a variety of potential applications, some of which include the classification of pictures, the fragmentation of images, and the identification of objects in photographs. Images are often used in the medical industry for the purposes of diagnosis as well as surgery. In this article, a study on the use of convolutional neural networks (CNNs) for clinical picture segmentation is presented, coupled with an approach for evolutionary model compression. On a collection of clinical pictures, four distinct models—UNet, ENet, ECO-UNet, and ECO-ENet—were assessed. The accuracy of their segmentation was gauged using the Dice coefficient, sensitivity, and specificity. The findings indicate that although the UNet and ENet models had high segmentation accuracy, the ECO-UNet and ECO-ENet models had even greater accuracy. The model size was subsequently decreased using the evolutionary compression technique, and even at high compression ratios, the compressed models' performance was comparable to that of the original models. These findings show how successful the evolutionary compression approach is in reducing model size as well as the potential of CNNs for clinical picture segmentation tasks. In environments with limited resources, this strategy may be very helpful. Overall, the research demonstrates that evolutionary compression and CNNs provide a potential method for clinical picture segmentation..

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Novel Optimized AI Based Model for Traffic Prediction in VANET

A Novel Optimized AI Based Model for Traffic Prediction in V...

引用

International Conference on Inventive Research in Computing Applications (ICIRCA)

作者： Pradeep R Revathi K Aby K Thomas Srikanth R Department of Electrical and Electronics Engineering SNS College of Engineering Coimbatore India Department of Information Technology SNS College of Engineering Coimbatore India Department of Electronics and Communication Engineering Alliance College of Engineering and Design Alliance University Bangalore India Department of Computer Science and Engineering Karpagam Academy of Higher Education Coimbatore India

Research into a novel type of wireless network, the vehicle ad hoc network (VANET), has gained an increasing research interest in recent years. By exchanging data about things like vehicle velocity, location, and direction, VANET facilitates interaction between moving vehicles and fixed infrastructure. It's best to take an alternate route, if possible, when there's a high probability that a large number of cars will use the same one to get from point A to point B. If vehicles could precisely foresee traffic congestion, they could potentially evade it. Hence, suggested using DRL in VANET to improve traffic congestion forecasting. In addition, this deep reinforcement learning model examines and compares various neural networks, such as the CNN, MLP, and LSTM, to determine which is best with the results. The proposed strategy is evaluated based on the ATTD and the AWTD of vehicles, which serve as metrics to assess its effectiveness. Through simulation analysis, it is evident that the suggested approach enhances the average travel time delay and average waiting time delay across multiple iterations, considering the environmental factors as inputs. The simulation results demonstrate that compared to existing algorithms used for network traffic prediction, the deep reinforcement learning model provides superior performance in terms of both execution time and prediction errors.

关键词：

来源：评论

学校读者我要写书评

暂无评论

AI-Based Prediction of Respiratory Complications

AI-Based Prediction of Respiratory Complications

引用

Communication, Computing and Energy Efficient Technologies (I3CEET), International Conference on

作者： Zaid Alsalami Bhupchand Kumhar Neeraj Varshney M.B Marasulov Deeksha Verma B. Arun Kumar Department of Computers Techniques Engineering College of Technical Engineering The Islamic University Najaf Iraq Department of Computers Techniques Engineering College of Technical Engineering The Islamic University of Al Diwaniyah Al Diwaniyah Iraq Department of Computer Science & Engineering IES Institute of Technology and Management IES University Bhopal M.P. India Department of Computer Engineering and Applications GLA University Mathura India Department of Physics and Chemistry Tashkent Institute of Irrigation and Agricultural Mechanization Engineers" National Research University Tashkent Uzbekistan Institute of Polymer Chemistry and Physics Tashkent Uzbekistan Western Caspian University Scientific Researcher Baku Azerbaijan Department of Computer Science Engineering Chandigarh Engineering College Chandigarh Group of Colleges Jhanjeri Mohali Punjab India Department of Computer Science Engineering Karpagam Academy of Higher Education Coimbatore

ISBN: (数字)9798331541583

ISBN: (纸本)9798331541590

Aviation route infection may be a serious health problem that results in at least 3 million deaths annually. By 2030, it is also anticipated to be among the leading causes of death worldwide. A number of studies have been conducted to demonstrate the latest developments in fake intelligence computations to aid in the identification and categorization of various illnesses. This thorough review aims to describe the most advanced machine learning and deep learning frameworks for detecting aircraft route deviations, conceptualize the trends of further research in this area, and assess the difficulties and possible solutions going forward. This effective writing survey includes a review of 135 articles on transport route infections, including tuberculosis, emphysema, bronchitis, lung cancer, a condition called me covid-19, a condition known as asthma, aspiratory edema, and pneumonic embolism. It also emphasizes the use of computerized learning techniques to prevent these infections. The exercise of thought is concluded with an analysis of the issues around improving the proficiency and applicability of robotic and profound learning-assisted air channel identification of viruses.

关键词： Deep learning COVID-19 Surveys Pneumonia Reviews Tuberculosis Predictive models Telecommunication computing Robots Optimization

来源：评论

学校读者我要写书评

暂无评论

Advancing Wireless Communication: A Comprehensive Study On Multi-User Mimo-Ofdm Techniques

Advancing Wireless Communication: A Comprehensive Study On M...

引用

International Conference on Contemporary Computing and Informatics (IC3I)

作者： Praveen Singh Rahul Vishnoi Suraj Malik M. Vigenesh S. Arul Antran Vijay Monali Ravindra Borade Department of Management Studies Graphic Era Deemed to be University Dehradun Urttarakhand India Department of ECE Teerthankar Mahaveer University Moradabad Uttar Pradesh India School of Engineering and Technology IIMT University Meerut Uttar Pradesh India Department of Computer Science Engineering Karpagam Academy of Higher Education Coimbatore Tamilnadu India Department of Computer Science Engineering Karpagam College of Engineering Coimbatore Tamilnadu India AI&Ds Vishwakarma Institute of Information Technology Pune Maharashtra India

A actually massive settings is created when horizontal frequency division packet switching, a common technique for high-rate wireless data transport, is integrated with transceivers at the transmitting and receiving ends to increase spectral efficiency and/or to boost system power on time-variant and intensity touchpoints. The multiple access future research directions in design process are investigated in this article, which would include measured data and simulation, input signal spectrum sensing methods employing intuitive arrays, space-time methods, error - correcting computer programming methods, protocol and datagram style, or signal computation for frequency and time standardization, spectrum sensing, and channel locating in frameworks. The article also takes into account an open-source hardware solution.

关键词：

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：