检索结果-内蒙古大学图书馆

IEEE Workshop on Applications of computer Vision (WACV)

作者： Gregor Koehler Tassilo Wald Constantin Ulrich David Zimmerer Paul F. Jaeger Jörg K. H. Franke Simon Kohl Fabian Isensee Klaus H. Maier-Hein Division of Medical Image Computing German Cancer Research Center (DKFZ) Heidelberg Germany Helmholtz Information and Data Science School for Health Karlsruhe/Heidelberg Germany Helmholtz Imaging DKFZ National Center for Tumor Diseases (NCT) NCT Heidelberg a Partnership Between DKFZ University Medical Center Heidelberg Interactive Machine Learning Group DKFZ Machine Learning Lab University of Freiburg Freiburg Germany Latent Labs (***) London UK Applied Computer Vision Lab DKFZ Pattern Analysis and Learning Group Heidelberg University Hospital Heidelberg Germany

Despite the remarkable success of deep learning systems over the last decade, a key difference still remains between neural network and human decision-making: As humans, we can not only form a decision on the spot, but also ponder, revisiting an initial guess from different angles, distilling relevant information, arriving at a better decision. Here, we propose RecycleNet, a latent feature recycling method, instilling the pondering capability for neural networks to refine initial decisions over a number of recycling steps, where outputs are fed back into earlier network layers in an iterative fashion. This approach makes minimal assumptions about the neural network architecture and thus can be implemented in a wide variety of contexts. Using medical image segmentation as the evaluation environment, we show that latent feature recycling enables the network to iteratively refine initial predictions even beyond the iterations seen during training, converging towards an improved decision. We evaluate this across a variety of segmentation benchmarks and show consistent improvements even compared with top-performing segmentation methods. This allows trading increased computation time for improved performance, which can be beneficial, especially for safety-critical applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design and Comparison of Collaborative Filtering Technology for Product Suggestions in E-Commerce

Design and Comparison of Collaborative Filtering Technology ...

引用

Automation, computing and Renewable Systems (ICACRS), International Conference on

作者： P. Rajasekar B. Mohanraj S. N. Padhi N. Sivakumar Lavanya J Charles Prabu V Department of Data Science and Business Systems School of Computing SRM Institute of Science and Technology Chennai Tamil Nadu India Department of Information Technology Karpagam College of Engineering Coimbatore Tamil Nadu India Department of Mechanical Engineering Koneru Lakshmaiah Education Foundation Vaddeswaram Andhra Pradesh India Department of Computer Science and Engineering Panimalar Engineering College Chennai City Campus Chennai Tamil Nadu India Department of Fashion Designing SRM Institute of Science and Technology CSH Kattankulathur Campus Chennai Tamil Nadu India Department of Computer Science Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Tamil Nadu India

ISBN: (纸本)9781665460859

E-commerce websites and internet purchasing have never been more necessary. Product recommendations are a key tactic employed by online buying platforms. This study compares two different filtering algorithms that are used in product recommendationson websites like Amazon and Flipkart. Reviews of electrical devices, user data, and timestamps were all gathered from Kaggle and put into a dataset. These specifics then undergo several preprocessing steps. The steps are data visualization, duplicate value analysis, missing value analysis, and datatype analysis. The exhibited data is then used to train and test the machine learning models. For this purpose, two machine learning models are developed using two different algorithms. The algorithms K-Nearest Neighbor(KNN) and Support Vector Decomposition (SVD) are employed. The models are then trained to acquire used in the prediction procedure after that. The best models for the prediction process are then determined by scrutinizing the results of both models. The Root Mean Square Error (RMSE), Mean Square Error (MSE), and Mean Absolute Error (MAE) values are located and compared because the findings of the analysis weren't *** erroneous data are plotted into a graph and evaluated to further demonstrate the point. As the SVD method is discovered to be the best of the group, the algorithm's greatest and worst predictions are discovered and examined. Even the poorest model constructed for the study's predictions turned out to be superior to several other prediction algorithms used for product suggestions. This algorithm can be deployed into the backend of any e-commerce website making it more effective.

关键词： Training Support vector machines Analytical models Machine learning algorithms data visualization Machine learning Predictive models

来源：评论

学校读者我要写书评

暂无评论

OSAF_e: One-Stage Anchor Free Object Detection Method Considering Effective Area 9th

OSAF_e: One-Stage Anchor Free Object Detection Method Consid...

引用

9th International Conference on Artificial Intelligence and Mobile Services, AIMS 2020, held as part of the Services Conference Federation, SCF 2020

作者： Zhang, Yong Zhang, Lizong Rao, Zhihong Duan, Guiduo Wang, Chunyu School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu611731 China China Electronic Technology Cyber Security Co. Ltd. Chengdu610000 China Trusted Cloud Computing and Big Data Key Laboratory of Sichuan Province Chengdu611731 China School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu610054 China

ISBN: (纸本)9783030596040

The task of object detection is to identify the bounding box of the object and its corresponding category in images. In this paper, we propose a new one-stage anchor free object detection algorithm OSAF_e, with the consideration of effective mapping area. A feature extraction network is used to obtain high level feature, and the true bounding box of the object in the original image is mapped to the grid of feature map, in order to perform category prediction and bounding box regression. The proposed algorithm is evaluated with the Pascal Voc dataset, and the experiments indicate that it has a better result. © 2020, Springer Nature Switzerland AG.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Higher-Order Attribute-Enhancing Heterogeneous Graph Neural Networks

arXiv

引用

arXiv 2021年

作者： Li, Jianxin Peng, Hao Cao, Yuwei Dou, Yingtong Zhang, Hekai Yu, Philip S. He, Lifang Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100083 China the Department of Computer Science University of Illinois at Chicago ChicagoIL60607 United States School of Information Science and Engineering Yanshan University Qinhuangdao066004 China the Department of Computer Science and Engineering Lehigh University BethlehemPA18015 United States

Graph neural networks (GNNs) have been widely used in deep learning on graphs. They can learn effective node representations that achieve superior performances in graph analysis tasks such as node classification and node clustering. However, most methods ignore the heterogeneity in real-world graphs. Methods designed for heterogeneous graphs, on the other hand, fail to learn complex semantic representations because they only use meta-paths instead of meta-graphs. Furthermore, they cannot fully capture the content-based correlations between nodes, as they either do not use the self-attention mechanism or only use it to consider the immediate neighbors of each node, ignoring the higher-order neighbors. We propose a novel Higher-order Attribute-Enhancing (HAE) framework that enhances node embedding in a layer-by-layer manner. Under the HAE framework, we propose a Higher-order Attribute-Enhancing Graph Neural Network (HAEGNN) for heterogeneous network representation learning. HAEGNN simultaneously incorporates meta-paths and meta-graphs for rich, heterogeneous semantics, and leverages the self-attention mechanism to explore content-based nodes’ interactions. The unique higher-order architecture of HAEGNN allows examining the first-order as well as higher-order neighborhoods. Moreover, HAEGNN shows good explainability as it learns the importances of different meta-paths and meta-graphs. HAEGNN is also memory-efficient, for it avoids per meta-path based matrix calculation. Experimental results not only show HAEGNN’s superior performance against the state-of-the-art methods in node classification, node clustering, and visualization, but also demonstrate its superiorities in terms of memory efficiency and explainability. © 2021, CC BY.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

ConTIG: Continuous representation learning on temporal interaction graphs

arXiv

引用

arXiv 2021年

作者： Yan, Xu Fan, Xiaoliang Yang, Peizhen Wu, Zonghan Pan, Shirui Chen, Longbiao Zang, Yu Wang, Cheng Fujian Key Laboratory of Sensing and Computing for Smart Cities School of Informatics Computer Science & Technology Department Xiamen University Xiamen China Centre for Artificial Intelligence FEIT University of Technology Sydney Australia Department of Data Science and AI Faculty of Information Technology Monash University Australia

—Representation learning on temporal interaction graphs (TIG) is to model complex networks with the dynamic evolution of interactions arising in a broad spectrum of problems. Existing dynamic embedding methods on TIG discretely update node embeddings merely when an interaction occurs. They fail to capture the continuous dynamic evolution of embedding trajectories of nodes. In this paper, we propose a two-module framework named ConTIG, a continuous representation method that captures the continuous dynamic evolution of node embedding trajectories. With two essential modules, our model exploit three-fold factors in dynamic networks which include latest interaction, neighbor features and inherent characteristics. In the first update module, we employ a continuous inference block to learn the nodes’ state trajectories by learning from time-adjacent interaction patterns between node pairs using ordinary differential equations. In the second transform module, we introduce a self-attention mechanism to predict future node embeddings by aggregating historical temporal interaction information. Experiments results demonstrate the superiority of ConTIG on temporal link prediction, temporal node recommendation and dynamic node classification tasks compared with a range of state-of-the-art baselines, especially for long-interval interactions prediction. © 2021, CC BY.

关键词： Ordinary differential equations

来源：评论

学校读者我要写书评

暂无评论

Graph-Based Terminal Ranking for Sparsification of Interference Coordination Parameters in Ultra-Dense Networks 10th

Graph-Based Terminal Ranking for Sparsification of Interfere...

引用

10th EAI International Conference on Mobile Networks and Management, MONAMI 2020

作者： Gou, Junxiang Wang, Lusheng Lin, Hai Peng, Min Ministry of Education School of Computer Science and Information Engineering Key Laboratory of Knowledge Engineering with Big Data Hefei University of Technology Hefei230601 China Ministry of Education School of Cyber Science and Engineering Key Laboratory of Aerospace Information Security and Trusted Computing Wuhan University Wuhan430072 China Anhui Province Key Laboratory of Industry Safety and Emergency Technology Hefei230601 China

ISBN: (纸本)9783030640019

In the future mobile communication system, inter-cell interference becomes a serious problem due to the intensive deployment of cells and terminals. Traditional interference coordination schemes take long time for optimization in ultra-dense networks. Meanwhile, due to the increase of factors affecting communication and in order to better meet the communication needs of each terminal, an interference coordination scheme needs to fully consider multiple characteristic parameters of the terminal, which will further increase the scheme’s computational time. Therefore, we should compress all the data through sparsification of parameters before optimization. There are many terminal parameters, and the essence of sparsification of parameters is to rank terminals. In this paper, a graph-based terminal ranking scheme is designed. First, each terminal can be represented by its multiple parameters. Then, all terminals are used as the vertexes in the graph to form a complete weighted graph, and edge weights represent the degree of dissimilarity between terminals. A ranking of terminals is obtained by finding a minimum Hamiltonian path in the graph. Finally, the ranking of all parameter sequences is obtained according to terminals ranking, which makes the sparsity of all parameter sequences better. Simulation results show that the proposed scheme can accomplish sparsification of parameter sequences effectively, especially when the number of sequences increases. In addition, compared with the optimal coordination of traditional scheme, this scheme improves the fairness of the system while ensuring high system capacity, and dramatically reduces the computational time of interference coordination. © ICST Institute for computer sciences, Social Informatics and Telecommunications Engineering 2020.

关键词： Approximation algorithms

来源：评论

学校读者我要写书评

暂无评论

Practical Iterative Quantum Consensus Protocol with Sharding Construction

引用

IEEE Journal on Selected Areas in Communications 2025年

作者： Ying, Chenhao Du, Yuxuan Zhang, Weiting Jiang, Xikun Wang, Gang Jin, Haiming Li, Jie Luo, Yuan Tao, Dacheng Shanghai Jiao Tong University Department of Computer Science Shanghai China Zhejiang University Shanghai Jiao Tong University State Key Laboratory of Blockchain and Data Security Blockchain Advanced Research Center Jiangsu Wuxi214101 China Nanyang Technological University College of Computing&Data Science Singapore Beijing Jiaotong University School of Electronic and Information Engineering Beijing China University of Copenhagen Department of Computer Science Denmark Northeastern University School of Computer Science and Engineering Shenyang China Shanghai Key Laboratory of Trusted Data Circulation and Governance Web3 China

With the development of quantum blockchain, the quantum consensus protocols have garnered increasing attention, which play a crucial role in driving the implementation of quantum blockchains. However, existing protocols, derived from the classical consensus algorithms, face practical application challenges due to current quantum technology limitations. The first challenge is the bottleneck in generating large-scale entangled quantum states. The second challenge arises from the generation of malicious quantum states. The final challenge involves privacy concerns. To address these challenges, we propose a practical iterative QUantum consensus protocol with sharding construction, namely, Q-Union. In fact, Q-Union employs an iterative consensus algorithm where participating nodes are divided into multiple smaller shards, with the consensus process occurring within the current shard, and new shards are involved only if consensus is not achieved. Leveraging Greenberger-Horne- Zeilinge states and Aharonov states, Q-Union harnesses the advantages of quantum mechanics to achieve anonymous consensus, protecting the private information of participating nodes. Additionally, by integrating state verification, Q-Union ensures the correctness of the consensus procedure in the presence of malicious nodes generating adversarial quantum states. Finally, it is proven that Q-Union can also defend against Byzantine attacks from adversarial nodes, maintaining the same security level as traditional non-sharded consensus protocols. Specifically, it consistently outputs the correct consensus when the fraction of adversaries among participating nodes is less than 1/2 with synchronous communication. Both the theoretical analysis and performance illustration demonstrate the superior performance of the proposed Q-Union compared to state-of-the-art protocols. © 1983-2012 IEEE.

关键词： Quantum entanglement

来源：评论

学校读者我要写书评

暂无评论

The joint effects of physical activity and sleep duration on risk of osteoporosis in Taiwanese adult population: The Taiwan Biobank Study

引用

Osteoporosis International 2024年第3期35卷 523-531页

作者： Chen, Kun-Hui Su, Chen-Ming Liu, Wei-Ju Tzeng, Huey-En Lee, Chia-Lin Tsai, Chun-Hao Department of Orthopedic Surgery Taichung Veterans General Hospital Taichung 407219 Taiwan Department of Post-Baccalaureate Medicine College of Medicine National Chung Hsing University Taichung 402204 Taiwan Department of Computer Science & Information Engineering College of Computing and Informatics Providence University Taichung City 43301 Taiwan Department of Sports Medicine China Medical University Taichung 406040 Taiwan Department of Medical Research Taichung Veterans General Hospital Taichung 407219 Taiwan Intelligent Data Mining Laboratory Department of Medical Research Taichung Veterans General Hospital Taichung 407219 Taiwan School of Medicine Taipei Medical University Taipei 11031 Taiwan Division of Transfusion Medicine /Hematology - Oncology Taichung Veterans General Hospital Taichung 40705 Taiwan Department of Public Health College of Public Health China Medical University Taichung 406040 Taiwan Department of Medicine School of Medicine National Yang Ming Chiao Tung University Taipei 112304 Taiwan Department of Orthopedics China Medical University Hospital Taichung 406040 Taiwan College of Biomedical Engineering China Medical University Taichung 406040 Taiwan

Summary: Most studies investigating the association between physical activity and osteoporosis prevention only focused on specific types of physical activity. This study’s evidence regarding the combined effects or interaction of sleep duration and physical activity. The findings emphasize the role of sleep duration and physical activity in association with osteoporosis. Purpose: The associations between physical activity, sleep duration, and prevalent osteoporosis in Taiwanese adults were studied in this cross-sectional study. Methods: The Taiwan Biobank enrolled a community-based cohort of ~ 120,000 volunteers (as of April 30, 2020) between 30 and 76 years of age with no history of cancer. Amongst, bone mineral density (BMD) measures by dual-energy X-ray absorptiometry (DXA) were available in 22,402 participants. After excluding individuals who had no complete data of BMI (n = 23), MET score (n = 207), T-score (n = 8,826), and sleep duration (n = 16), 13,330 subjects were included as the primary cohort. Univariate and multivariable regression analyses were performed to determine the associations between the presence of osteoporosis, physical activity level, sleep duration, and other variables. Results: The results showed that after adjustment, subjects with physical activity < 20 METs/week and ≥ 20 METs/week (aOR = 1.017 and 0.767, respectively) were associated with risk of osteoporosis than those with zero MET. The odds of osteoporosis were not significantly lower in subjects who slept for ≥ 8 h/day (aOR = 0.934,p=0.266). In addition, compared to short sleepers with no physical activity, adults with increased physical activity ≥ 20 METs/week and sleep ≥ 8 h/day had a significantly lowest likelihood of osteoporosis (aOR = 0.702). Those with medium physical activity (< 20 METs/week) plus average sleep duration (6.5–8 h/day) did not have significant higher odds of osteoporosis (aOR = 1.129,p=0.151). Conclusion: The findings emphasize the joint role of sleep duration

关键词： Bone mineral density (BMD) Exercise habit Osteoporosis Sleep duration Taiwan biobank

来源：评论

学校读者我要写书评

暂无评论

Deep Sentiment Learning Network for Temporal-aware Recommendation Based on User Reviews

Deep Sentiment Learning Network for Temporal-aware Recommend...

引用

IEEE International Conference on Big data Analysis (ICBDA)

作者： Xinxin Li Tianqi Shang Dezhong Peng Xiaoyu Shi School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu China College of Computer Science Sichuan University Chengdu China Chongqing Key Laboratory of Big Data and Intelligent Computing Chongqing Institute of Green and Intelligent Technology Chinese Academy of Sciences Chongqing China

Recently, many websites encourage users to fill in reviews on items and services to improve the quality of personalized recommendation, because of the rich sentiment information hidden in user reviews. However, most existing recommendation methods based on reviews heavily emphasize extracting the rich sentiment information from reviews by using deep learning technologies as far as possible and always ignore the effects of temporal dynamical of user preferences. To address the above issues, we propose DSL- TR, a deep sentiment learning framework for the temporal-aware recommendation, using an intricate combination of bidirectional long short-term memory (BLSTM) and Convolution Neural Network (CNN). It consists of four layers: embedding layer, BLSTM layer, CNN layer and feature fusion layer. In the embedding layer, we explicitly combine the time information in the review embedding layer by regarding the review time as an independent factor. Then, we utilize the BLSTM and CNN networks to extract the long and short-terms of latent features of user and item in parallel. Finally, the factorization machine technique, as a rating predictor, is introduced on the last layer to estimate the rating based on the learned user and item latent features. We conduct extensive experiments on Amazon's four data sets. The results demonstrate that our proposed method outperforms several state-of-art methods consistently.

关键词： Deep learning Convolution Conferences Neural networks Big data Feature extraction data mining

来源：评论

学校读者我要写书评

暂无评论

Toward a Secure Wireless Sensor Network in Intrusion Detection System Utilizing Central-Smoothing Hypergraph Neural Network Optimized With Clouded Leopard Optimization Algorithm

引用

International Journal of Communication Systems 2025年第11期38卷

作者： Geerthik S Ramachandran A Jegan J Ishwarya M. V Associate Professor Department of Information Technology Agni College of Technology Chennai India Associate Professor Department of Artificial Intelligence & Data Science Saveetha Engineering College Thandalam Chennai India Assistant Professor Department of Computer Science and Engineering School of Computing SRM Institute Of Science And Technology Tiruchirappalli (Deemed To Be University) Trichy Tamilnadu India Associate Professor Department of Artificial Intelligence & Data Science Agni College of Technology Chennai India

Wireless sensor networks (WSNs) is the essential component of wireless technology that provides effective solutions for various monitoring applications. WSN is vulnerable to several security risks as intrusions, attacks, and suspicious activities. Therefore, this paper proposes a Secure WSN in intrusion detection system using Central-Smoothing Hypergraph Neural Network Optimized with Clouded Leopard Optimization Algorithm (WSN-IDS-CSHGNN-CLOA). Here, the input data is taken from WSN-DS database. The gathered data is pre-processed by regularized bias-aware ensemble Kalman filter (RBAEKF) for data cleaning and normalization. The pre-processed data is given into feature selection using Memetic Salp Swarm Optimization Algorithm (MSSOA) to select optimal features. The selected features are given into CSHGNN for classifying the IDS as denial of service (DoS), black hole, gray hole, flooding, and scheduling attacks in WSN. The CLOA is implemented to optimize the hyperparameters of CSHGNN. The performance of the proposed WSN-IDS-CSHGNN-CLOA approach attains 24.39%, 35.71%, and 25.55% higher accuracy; 24.44%, 34.28%, and 14.44% higher precision when compared to the existing techniques.

关键词： Central-Smoothing Hypergraph Neural Network Clouded Leopard Optimization Algorithm Memetic Salp Swarm Optimization Algorithm regularized bias-aware ensemble Kalman filter wireless sensor network

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：