检索结果-内蒙古大学图书馆

Integrated Circuits and Communication Systems (ICICACS), IEEE International Conference on

作者： Gaurav Kumar G. Devayani C Saraswathi R. Melba Kani Sandeep Dongre M. S. Mohamed Mallick School of Computer Application Lovely Professional University Phagwara India Department of Computer Science and Business Systems M.Kumarasamy College of Engineering Karur India School of Management Studies Bannari Amman Institute of Technology Erode India Master of Business Administration Mar Ephraem college of Engineering and Technology Kanyakumari India Symbiosis Institute of Business Management (SIBM) Constituent of Symbiosis International (Deemed University) Nagpur India Department of Computer Science Engineering Vel Tech Rangarajan Dr Sagunthala R&D Institute of Science and Technology (Deemed to be University) Chennai India

ISBN: (数字)9798331508456

ISBN: (纸本)9798331508463

Online retailers must monitor and respond to changing consumer trends to stay competitive. AI-driven customization's revolutionary impact on market trends is the focus of this study on online buying and customer behavior. As AI advances, e-commerce platforms will be able to customize user experiences. Preprocessing, feature extraction, and model training comprise the AI-driven personalization process. Customer data from online marketplaces is collected first. It manages missing values, balance the data, encode categorical variables, scale the features, and minimize the dimensions as part of our thorough data preprocessing to ensure fair and applicable results. To trained the algorithms with CNN and Convolutional LSTM Based on key criteria, the AI model beat LSTM and CNN. It provides personalized insights and recommendations with an average accuracy of 92.03%. Personalized experiences and product suggestions enabled by AI-powered personalization have transformed e-commerce. It's important to use smart algorithms to engage customers and examine large databases. This proposed approach to shows that AI can transform online shopping and improve customer experiences.

关键词： Consumer behavior Accuracy Data preprocessing Transforms Market research Electronic commerce Convolutional neural networks Integrated circuit modeling Artificial intelligence Long short term memory

来源：评论

学校读者我要写书评

暂无评论

Leveraging Adaptive Algorithms for Real-Time Data Analysis

Leveraging Adaptive Algorithms for Real-Time Data Analysis

引用

International Conference on Computing and Networking Technology (ICCNT)

作者： Girija Shankar Sahoo R Hannah Jessie Rani Manish Kumar Goyal Vazeer Ali Mohammed D Little Femilin Jana Namrata N. Wasatkar Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh India Department of Electrical and Electronics Engineering Faculty of Engineering and Technology Jain (Deemed to be University) Bangalore Karnataka India Department of Computer Science & Application Vivekananda Global University Jaipur India Department of Computer & Information System Lewis University Illinois USA Department of Science and Humanities Prince Shri Venkateshwara Padmavathy Engineering College Chennai Department of Computer Engineering Vishwakarma Institute of Information Technology Pune INDIA

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

This paper proposes the use of adaptive algorithms for real-time data analysis. Adaptive algorithms are a set of practical methods used for acting information-driven optimization and studying. They have a wide variety of applications and may be implemented to a selection of facts analysis obligations. This paper offers an overview of existing adaptive algorithms and descriptions of several new programs in the area of actual-time facts analysis. In particular, the paper discusses the notion of adaptive thresholding, which allows for practical real-time evaluation of large datasets. The paper also provides a novel technique for making use of these algorithms in an online learning environment. Results from simulations illustrate the ability of the proposed method in real-international packages. Sooner or later, the paper presents numerous key lessons discovered and affords recommendations for future research and packages in this area.

关键词： Adaptation models Data analysis Real-time systems Optimization

来源：评论

学校读者我要写书评

暂无评论

Segment Together: A Versatile Paradigm for Semi-Supervised Medical Image Segmentation

引用

IEEE Transactions on Medical Imaging 2025年 PP卷 PP页

作者： Zeng, Qingjie Xie, Yutong Lu, Zilin Lu, Mengkang Wu, Yicheng Xia, Yong Northwestern Polytechnical University National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Computer Science and Engineering Xi’an710072 China The University of Adelaide Australian Institute for Machine Learning AdelaideSA5000 Australia Monash University Faculty of Information Technology Department of Data Science and AI Australia

The scarcity of annotations has become a significant obstacle in training powerful deep-learning models for medical image segmentation, limiting their clinical application. To overcome this, semi-supervised learning that leverages abundant unlabeled data is highly desirable to enhance model training. However, most existing works still focus on specific medical tasks and underestimate the potential of learning across diverse tasks and datasets. In this paper, we propose a Versatile Semi-supervised framework (VerSemi) to present a new perspective that integrates various SSL tasks into a unified model with an extensive label space, exploiting more unlabeled data for semi-supervised medical image segmentation. Specifically, we introduce a dynamic task-prompted design to segment various targets from different datasets. Next, this unified model is used to identify the foreground regions from all labeled data, capturing cross-dataset semantics. Particularly, we create a synthetic task with a CutMix strategy to augment foreground targets within the expanded label space. To effectively utilize unlabeled data, we introduce a consistency constraint that aligns aggregated predictions from various tasks with those from the synthetic task, further guiding the model to accurately segment foreground regions during training. We evaluated our VerSemi framework against seven established SSL methods on four public benchmarking datasets. Our results suggest that VerSemi consistently outperforms all competing methods, beating the second-best method with a 2.69% average Dice gain on four datasets and setting a new state of the art for semi-supervised medical image segmentation. Code is available at https://***/maxwell0027/VerSemi. © 1982-2012 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Innovative Deep Learning Model-based Stock Price Prediction using a Hybrid Approach of CNN and Gradient Recurrent Unit

Innovative Deep Learning Model-based Stock Price Prediction ...

引用

International Conference on Communication and Electronics Systems (ICCES)

作者： B. Srinivasa Rao Rajib Bhattacharya Manoj Kumar Tiwari K. Aruna Kumari Mahavir A. Devmane Kamlesh Singh Department of Computer Science and Engineering Gokaraju Rangaraju Institute of Engineering and Technology Hyderabad Telangana India Department of PGDM Globsyn Business School Chandipur West Bengal India Department of Computer Application JECRC University Jaipur Rajasthan India Mathematics. GSS GITAM (Deemed to be) University Visakhapatnam India Department of Computer Engineering VPPCOE & VA Mumbai Maharashtra India Department of Computer Science and Engineering Graphic Era Hill University Dehradun India

The fluctuation in stock prices from industry to industry are a major source of concern in the market. As the market attracts more participants and stock prices play a larger role in more transactions, the ability to accurately predict stock price movements becomes more valuable. When making an investment, many people first look at the share price and then try to anticipate whether or not that price will go up or down in the future. The traditional problem of forecasting the stock market using Machine Learning tools and methodologies has been thoroughly studied. Time dependence, volatility, and similar complicated dependencies are interesting aspects that make this modeling non-trivial. To overcome this the proposed method in this work is a deep learning-based hybrid strategy for predicting stock prices. Preprocessing is performed after input is delivered to increase precision. Selecting MPSOA features is the next step. In the end, it's put to use in MC-GRU model training. The proposed method achieves better results than both the CNN and GRU models.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MP-DPCC: A Motion Proxy-Based Dynamic Point Cloud Compression Framework

MP-DPCC: A Motion Proxy-Based Dynamic Point Cloud Compressio...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： ZhaoYi Jiang Dong Han Cao Song FangZhe Nan Bailin Yang School of Computer Science and Technolgy Zhejiang Gongshang University School of Statistics and Mathematics Zhejiang Gongshang University Economic Forecasting and Policy Simulation Laboratory Zhejiang Gongshang University Collaborative Innovation Center of Statistical Data Engineering Technology & Application Zhejiang Gongshang University

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

The increasing data volume and the demand for real-time transmission highlight the necessity for efficient compression of dynamic point cloud data. Existing methods primarily focus on reducing inter-frame redundancy by calculating per-point motion information, overlooking the computational and storage costs involved. In this paper, we propose a novel motion proxy-based dynamic point cloud compression framework to enhance the efficiency and accuracy of motion information utilization. Specifically, we introduce a feature proxy module to adaptively locate proxy points, which represent the overall motion through the motion of proxy points. Additionally, a motion enhancement module is employed to refine motion details and prevent local information loss caused by dense motion trajectories. Extensive experiments demonstrate the superiority of our approach. Compared with baseline methods, it achieves an average BD-rate improvement of 12.07% (D1) and 11.90% (D2).

关键词： Point cloud compression Costs Accuracy Dynamics Termination of employment Signal processing Real-time systems Acoustics Trajectory Speech processing

来源：评论

学校读者我要写书评

暂无评论

Passive Detection for Multiple Underwater Targets with Linear Frequency Modulation Signals

Passive Detection for Multiple Underwater Targets with Linea...

引用

International Conference on Signal Processing Proceedings (ICSP)

作者： Junfeng Wang Yue Cui Mingzhang Zhou Haixin Sun Lanjun Liu Ailing Zhang School of Integrated Circuit Science and Engineering Tianjin University of Technology China Key Laboratory of Southeast Coast Marine Information Intelligent Perception and Application MNR China College of Computer and Information Engineering Tianjin Normal University China School of Information Science and Engineering Xiamen University Xiamen China College of Engineering Ocean University of China Qingdao China

ISBN: (数字)9798350387384

ISBN: (纸本)9798350387391

Detecting the status of autonomous underwater vehicle, referred to hereinafter as an underwater target, is fundamental for successfully fulfilling cognition tasks or improving communication quality. In this article, we present a thorough study over the passive detection issue for multiple underwater targets emitting the linear frequency modulation signals. Specifically, hypothesis testing model, which comprises the signals received at the underwater detection node including periodic emission signals from the targets and additive noise, is firstly proposed for the practical scenarios. Then, the detection scheme has been investigated. Among this scheme, the behavior of the signals emitted by the underwater targets has been analyzed; and the primary aiming of the detection procedure, i.e., decision rule and its performance, has also been discussed and derived for the aforementioned scenarios. Towards the end, to confirm the advantages of our proposed studies, numerical simulation examples are carried out to examine the performance under different conditions.

关键词： Additive noise Autonomous underwater vehicles Chirp modulation Frequency modulation Signal processing Numerical simulation Cognition Testing

来源：评论

学校读者我要写书评

暂无评论

ExpoNAS: Using Exposure-based Candidate Exclusion to Reduce NAS Space for Heterogeneous Pipeline of CNNs 29

ExpoNAS: Using Exposure-based Candidate Exclusion to Reduce ...

引用

29th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2023

作者： Duan, Huijuan Wang, Danghui Zhao, Xingting Mei, Kuizhi Wang, Jihe Polytechnical University School of Computer Science Northwestern Xi'an China Northwestern Polytechnical University Engineering Research Center of Embedded System Integration Ministry of Education Xi'an China Xi'An Jiaotong University Institute of Artificial Intelligence and Robotics Xi'an China Northwestern Polytechnical University Natl. Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Xi'an China

ISBN: (纸本)9798350330717

Efficiently deploying neural network models on heterogeneous edge systems faces unique challenges. Two major issues are underutilized pipelines caused by hardware heterogeneity and explosive growth of architecture search space. To address these challenges, we propose ExpoNAS, a framework enabling fast deployment-oriented neural architecture search on heterogeneous platforms. ExpoNAS evaluates model partitioning and deployability before search to meet accuracy and latency constraints. However, repeated partitioning leads to exponential growth in architecture search space. We first observe a strong correlation between operational exposure and accuracy improvement, and then we propose an exposure-based reduction technique that excludes the operations of low exposure. By removing these non-critical operations, the exposure-based pruning successfully reduces architecture search time. Our experiments on popular datasets show that the ExpoNAS pipelined design improves execution efficiency by a factor of 2 compared to traditional batch processing. Without compromising accuracy, ExpoNAS is able to reduce the architecture search time by 47.5% for discovering high-accuracy networks, compared to the SOTA NAS strategies. © 2023 IEEE.

关键词： heterogeneous systems NAS pipeline mapping search space reduction

来源：评论

学校读者我要写书评

暂无评论

STDEN: Towards Physics-Guided Neural Networks for Traffic Flow Prediction

arXiv

引用

arXiv 2022年

作者： Ji, Jiahao Wang, Jingyuan Jiang, Zhe Jiang, Jiawei Zhang, Hu State Key Laboratory of Software Development Environment School of Computer Science & Engineering Beihang University Beijing China Peng Cheng Laboratory Shenzhen China Department of Computer & Information Science & Engineering The University of Florida United States MOE Engineering Research Center of Advanced Computer Application Technology School of Computer Science & Engineering Beihang University Beijing China

High-performance traffic flow prediction model designing, a core technology of Intelligent Transportation System, is a long-standing but still challenging task for industrial and academic communities. The lack of integration between physical principles and data-driven models is an important reason for limiting the development of this field. In the literature, physics-based methods can usually provide a clear interpretation of the dynamic process of traffic flow systems but are with limited accuracy, while data-driven methods, especially deep learning with black-box structures, can achieve improved performance but can not be fully trusted due to lack of a reasonable physical basis. To bridge the gap between purely data-driven and physics-driven approaches, we propose a physics-guided deep learning model named Spatio- Temporal Differential Equation Network (STDEN), which casts the physical mechanism of traffic flow dynamics into a deep neural network framework. Specifically, we assume the traffic flow on road networks is driven by a latent potential energy field (like water flows are driven by the gravity field), and model the spatio-temporal dynamic process of the potential energy field as a differential equation network. STDEN absorbs both the performance advantage of data-driven models and the interpretability of physics-based models, so is named a physics-guided prediction model. Experiments on three real-world traffic datasets in Beijing show that our model outperforms state-of-the-art baselines by a significant margin. A case study further verifies that STDEN can capture the mechanism of urban traffic and generate accurate predictions with physical meaning. The proposed framework of differential equation network modeling may also cast light on other similar applications. Copyright © 2022, The Authors. All rights reserved.

关键词： Differential equations

来源：评论

学校读者我要写书评

暂无评论

Deep Fusion: A CNN-LSTM Image Caption Generator for Enhanced Visual Understanding

Deep Fusion: A CNN-LSTM Image Caption Generator for Enhanced...

引用

International Conference on Innovative Sustainable Computational Technologies (CISCT)

作者： Chandradeep Bhatt Sumit Rai Rahul Chauhan Deepika Dua Mukesh Kumar Sanjay Sharma CSE Department Graphic Era Hill University Dehradun India Computer Science and Engineering Graphic Era Hill University Dehradun India Department of School of Computing Uttranchal University Dehradun India Computer Application Department SGRRITS Dehradun India

Photo caption generators had gained huge recognition recently from the areas of NLP and computer vision. These generators produce captions that explain an image's content using deep learning algorithms. A sizable collection of image-caption pairs is used to train the algorithm. The photos are fed into a pre-trained CNN after the dataset has undergone preprocessing to extract its visual properties. Along with the picture features, the necessary captions are tokenized and supplied to the LSTM decoder. In order to accelerate the caption generation process, the LSTM decoder is trained to utilize beam search and maximum likelihood estimation methods. To assess the effectiveness of the suggested model, several metrics such as BLEU and METEOR are employed. The suggested CNN-LSTM image caption generator has a lot of promise for use in a variety of contexts, such as picture comprehension, information retrieval, and assistive technology for the blind. Combining CNN and LSTM models takes advantage of each architecture's capabilities, allowing the model to produce insightful and contextually appropriate captions for a variety of images. We also explore present difficulties and potential directions for additional investigation in this area. This research study concludes by presenting an innovative method for creating image captions that combines the strength of CNN and LSTM. The experimental outcomes demonstrate the efficacy and reliability of the suggested model, highlighting its potential to advance the field of image captioning and contribute to the creation of intelligent systems that can comprehend visual content and produce precise and insightful textual descriptions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Zebra: A cluster-aware blockchain consensus algorithm

引用

Journal of Network and computer applications 2024年 232卷

作者： Wan, Ji Hu, Kai Li, Jie Guo, Yichen Su, Hao Li, Shenzhang Ye, Yafei School of Computer Science and Engineering Beihang University Beijing China Yunnan Power Grid Co Ltd China Southern Power Grid Co Ltd Kunming China Beihang Yunnan Innovation Institute Yunnan Key Laboratory of Blockchain Application Technology China

The Consensus algorithm is the core of the permissioned blockchain, it directly affects the performance and scalability of the system. Performance is limited by the computing power and network bandwidth of a single leader node. Most existing blockchain systems adopt mesh or star topology. Blockchain performance decreases rapidly as the number of nodes increases. To solve this problem, we first design the n-k cluster tree and corresponding generation algorithm, which supports rapid reconfiguration of nodes. Then we propose the Zebra consensus algorithm, which is a cluster tree-based consensus algorithm. Compared to the PBFT, it has higher throughput and supports more nodes under the same hardware conditions. However, the tree network topology enhances scalability while also increasing latency among nodes. To reduce transaction latency, we designed the Pipeline-Zebra consensus algorithm that further improves the performance of blockchain systems in a tree network topology through parallel message propagation and block validation. The message complexity of the algorithm is O(n). Experimental results show that the performance of the algorithm proposed in this paper can reach 2.25 times that of the PBFT algorithm, and it supports four times the number of nodes under the same hardware. © 2024 Elsevier Ltd

关键词： Consensus algorithm

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：