检索结果-内蒙古大学图书馆

Journal of Network Intelligence 2025年第1期10卷 339-352页

作者： Cui, Xiu-Yan Hwang, David Hebei Software Institute Hebei Province University Intelligent Interconnection Equipment and Multimodal Big Data Application Technology Research and Development Center Baoding071000 China College of Engineering St. Paul University Philippines Tuguegarao3500 Philippines

Aiming at the issue that the jobs predicted by the existing job recommendation methods cannot be precisely matched with the job seekers, this paper designs a personalized intelligent job recommendation method based on deep learning in the Elas-ticsearch environment. Firstly, to deal with the data sparsity and cold start issue of traditional collaborative filtering algorithms, the similarity calculation formula of Pearson’s correlation in the algorithm is modified to enhance the accuracy of similarity calculation. Secondly, on the ground of the history of different job seekers, the keywords of job seekers are constructed in terms of various weights, and input into ElasticSearch to recall the set of jobs that are strongly related to the job seekers. Then adopting Convolutional Neural Network (CNN) to extract the text data features of job seekers and positions, and meanwhile, integrating the attention mechanism to get the auxiliary features of job seekers and positions, and finally, integrating the implicit feedback data with other at-tribute features of job seekers and positions as the input of the improved collaborative filtration algorithm, so that we can realize the intelligent recommendation of jobs for job seekers. Simulation outcome indicates that the Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), Root Mean Squared Error (RMSE) and Root Mean Square Percentage Error (RMSPE) of the suggested method are 0.0681, 0.0519, 0.0834 and 0.0628 respectively, which are lower than those of the comparison method, and the accuracy of the recommendation is effectively enhanced. © 2025, Taiwan Ubiquitous Information CO LTD. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

big data and AI in Financial Risk Assessment: The New Scorecard Approach 4

Big Data and AI in Financial Risk Assessment: The New Scorec...

引用

4th IEEE International Conference on Information Technology, big data and Artificial Intelligence, ICIBA 2024

作者： Li, Hualin Chen, Kai Yang, Suyi Zhang, Dequan Zhou, Chenchen Li, Kaidong Intelligent Application of Financial Big Data Chongqing Colleges Universities Engineering Research Center China Shu Yi Xin Credit Management Co Ltd China Chongqing Institute of Engineering School of Big Data and Artificial Intelligence China

ISBN: (纸本)9798350363586

This paper presents a framework for assessing financial risk across industries by integrating rule-based modeling, the Analytic Hierarchy Process (AHP), and artificial intelligence (AI) techniques. The framework utilizes diverse data sources, including financial, tax, and judicial records, as well as financial reports from listed companies, to improve enterprise credit *** process begins with data preparation, which involves collecting and preprocessing data to ensure its quality and consistency. A rule-based preprocessing algorithm is developed to standardize the data for scoring. In the second phase, scoring is done using rule-based modeling informed by expert advice and AHP, which prioritizes and weights factors impacting industrial risk. This generates a customized scorecard for each industry. The third phase focuses on training AI models on the dataset. These models automatically learn to assign weights to indicators and generate industry scores by identifying complex patterns between the data and industry performance. The framework concludes with cross-validation to confirm the accuracy and reliability of the results. This approach provides insights into industry-wide scoring, supports continuous monitoring of industry performance, and enhances financial risk management decision-making. The proposed framework offers a robust and reliable tool for assessing financial risk across various industries. © 2024 IEEE.

关键词： Decentralized finance

来源：评论

学校读者我要写书评

暂无评论

An accurate cell segmentation method for high-resolution complex brain image 9

An accurate cell segmentation method for high-resolution com...

引用

9th International Conference on Image, Vision and computing, ICIVC 2024

作者： Xu, Xiaofeng Li, Shuai Zheng, Wei Henan Engineering Research Center of Intelligent Processing for Big Data of Digital Image School of Computer Science and Technology Nanyang Normal University Nanyang China

ISBN: (纸本)9798350385991

Cell segmentation is a key step in medical image analysis and cell biology research, and is important in areas such as understanding cell behaviour, cancer detection and cell cycle analysis. This task is challenging due to the presence of overlap between cells and image noise. With the development of imaging techniques, the amount and quality of acquired cellular image data have increased significantly and even contain diverse information such as neuronal structures and blood vessels, which puts higher demands on segmentation techniques. Real rat brain cell images obtained using micro-optical slice tomography (MOST) contain complex and diverse information such as neuronal structure, cell morphology, and the distribution of blood vessels, demonstrating the characteristics of real biological samples, for which segmentation of the target region is more difficult. In order to solve these challenges, this paper proposes a new cell image segmentation method that combines watershed order differential feature extraction and fuzzy entropy spatial theory. Due to the complexity of image information, we first use traditional image enhancement techniques. Then feature extraction is performed and fuzzy entropy processing is added to achieve accurate identification of cell boundaries. Then distance transform and curvature analysis are added to further segment the cell clusters into individual cells while avoiding over-segmentation and missed detection. Experiments demonstrate that the method not only shows high performance on our dataset, but also validates our method on several publicly available cellular datasets respectively, proving that the segmentation algorithm shows great potential for segmentation on different types of cells. Future research will further optimise the model to improve segmentation performance on complex and irregularly shaped cells and explore the application of these methods to other types of medical image segmentation tasks. © 2024 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Transparent Access to Heterogeneous IoT Based on Virtual Resources

引用

Computers, Materials & Continua 2023年第3期74卷 4983-4999页

作者： Wenquan Jin Sunhwan Lim Young-Ho Suh Chanwon Park Dohyeun Kim Big Data Research Center Jeju National UniversityJeju63243Korea Autonomous IoT Research Section Intelligent Convergence Research LaboratoryElectronics and Telecommunications Research InstituteDaejeon34129Korea Department of Computer Engineering Jeju National UniversityJeju63243Korea

The Internet of Things(IoT)inspires industries to deploy a massive number of connected devices to provide smart and ubiquitous services to influence our daily *** computing leverages sufficient computation and storage at the edge of the network to enable deploying complex functions closer to the environment using Internet-connected *** to the purpose of the environment including privacy level,domain functionality,network scale and service quality,various environment-specific services can be provided through heterogeneous applications with sensors and actuators based on edge ***,for providing user-friendly service scenarios based on the transparent access to heterogeneous devices in edge computing,a consistent interface shall be provided to deliver services from edge computing to *** this paper,we propose transparent computing based on virtual resources to access heterogeneous IoT devices without considering the underlying network configuration at the edge of the *** supporting transparent access to different edge computing environments through a consistent interface,the virtual resource of edge gateway is proposed to bridge the Internet and devices which are deployed on the edge of the *** proposed edge gateway exposes the services of the Internet of Things devices to the Internet using virtual resources that represent the resources of physical *** virtual resources provide a consistent interface to enable clients to access devices in edge computing without considering underlying *** virtual resource is generated by the resource directory in the edge gateway through the registration of a *** on the device registration,the device information is stored in the gateway to link virtual resources and devices for translating messages according to the destination protocols and identifying physical devices that are represented by virtual ***,through collaboration with the serv

关键词： Internet of things edge computing edge gateway transparent computing virtualization resource directory virtual resource

来源：评论

学校读者我要写书评

暂无评论

DDoS Detection and Defense Based on FLAD and SDN 20

DDoS Detection and Defense Based on FLAD and SDN

引用

20th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery, ICNC-FSKD 2024

作者： Dong, Jie Fang, Wenyu Zheng, Wanling Liu, Jinkun Liu, Yanhua College of Computer and Data Science Fuzhou University Fuzhou350108 China Fujian Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou350108 China Engineering Research Center of Big Data Intelligence Ministry of Education Fuzhou350108 China

ISBN: (纸本)9798350356328

In order to achieve more efficient and accurate DDoS detection while ensuring data privacy, this paper proposes a DDoS detection method based on FLAD. Firstly, this paper uses the FLAD algorithm to train a global DDoS detection model without leaving local traffic data, protecting the privacy and security of traffic data between different hosts, and improving aggregation efficiency by dynamically adjusting the aggregation weights to adapt to different sub-dataset increments. Secondly, a DDoS traffic detection method based on the integration of LSTM and CNN is proposed, which extracts and analyzes the temporal correlation of traffic data by calculating the statistical characteristics of traffic data within a time period, to achieve real-time detection of traffic feature data. Again, combined with the concept of SDN, real-time defense against DDoS based on ODL-API is implemented, and precise matching of DDoS detection results with network entity information is achieved, realizing the technology of real-time and precise issuance of multiple flow rules, effectively blocking DDoS malicious attack traffic, protecting important entities in the topology, and maintaining stable traffic in the topology. This paper focuses on solving the detection problem of DDoS traffic data increments and uneven data distribution through the FLAD algorithm. Experimental results show that the proposed method improves the accuracy of DDoS attack detection by more than 4% and the F1 Score by more than 7% compared to the FedAvg aggregation algorithm. © 2024 IEEE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Tensor Graph Convolutional Network for Dynamic Graph Representation Learning 7

Tensor Graph Convolutional Network for Dynamic Graph Represe...

引用

7th International Symposium on Autonomous Systems, ISAS 2024

作者： Wang, Ling Yuan, Ye The School of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing400065 China The Chongqing Key Laboratory of Big Data and Intelligent Computing Chongqing Engineering Research Center of Big Data Application For Smart Cities Chongqing Institute of Green and Intelligent Technology Chinese Academy of Sciences Chongqing400714 China College of Computer and Information Science Southwest University Chongqing400715 China

ISBN: (纸本)9798350363173

Dynamic graphs (DG) represent evolving interactions between entities in various real-world scenarios. Many existing DG representation learning models employ a combination of graph convolutional networks and sequence neural networks to capture spatial-temporal dependencies. However, this hybrid approach often fails to effectively capture the spatial-temporal continuity inherent in DGs. In this paper, we propose a novel approach called the Tensor Graph Convolutional Network (TGCN) to learn DG representations within a unified convolution framework based on tensor products. Our approach is founded on two key principles: (a) representing DG information in tensor form, and (b) leveraging tensor product operations to design a graph convolutional network that simultaneously models spatial and temporal features. Experimental results on three real-world DG datasets demonstrate that our proposed model achieves state-of-the-art performance. © 2024 IEEE.

关键词： Tensors

来源：评论

学校读者我要写书评

暂无评论

GIG-CAM+M: A Class Activation Mapping Method Incorporating Guided Integrated Gradients and Multi-scale Strategy

引用

KSII Transactions on Internet and Information Systems 2025年第4期19卷 1122-1139页

作者： Gao, Yanfei Miao, Xiongwei Zhang, Guoye Shanxi Finance & Taxation College Shanxi Taiyuan030024 China Shanxi Intelligent Big Data Industry Technology Innovation Research Institute Shanxi Taiyuan030024 China Shanxi Provincial Digital Government Service Center Shanxi Taiyuan030024 China

The interpretability of convolutional neural networks has garnered widespread attention, with class activation mapping (CAM)-based methods emerging as a prominent research direction. Integrated Grad-CAM is a widely used backpropagation-based CAM method, but its use of a linear path introduces noise during the integration process. To address this issue, we propose GIG-CAM, which replaces the linear path with an adaptive path. Unlike previous methods that require path specification, GIG-CAM dynamically determines the next input in the path based on saliency maps. Additionally, to enhance the resolution of saliency maps, we introduce a novel multi-scale fusion method, which recursively optimizes saliency maps at smaller scales using saliency maps at larger scales. This preserves the localization capability of the original-scale saliency maps while enhancing their resolution. Experimental results on the VOC2012 and ILSVRC2012 datasets demonstrate that GIG-CAM with fusion (GIG-CAM(F)) outperforms existing methods, achieving the highest scores in the Pointing Game (82.80% and 85.90% on ResNet50 for VOC2012 and ILSVRC2012, respectively) and Energy-Based Pointing Game (62.41% and 59.69%, respectively). Furthermore, GIG-CAM(F) achieves the lowest Drop% (22.59% and 17.04%) and highest Increase% (31.00% and 21.95%), validating its superior interpretability. Our results highlight the effectiveness of GIG-CAM in improving the quality and reliability of saliency maps, making it a robust solution for enhancing deep model transparency. Copyright © 2025 KSII.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

TIGA: Towards Efficient Near data Processing in SmartNICs-based Disaggregated Memory Systems 24

TIGA: Towards Efficient Near Data Processing in SmartNICs-ba...

引用

61st ACM/IEEE Design Automation Conference, DAC 2024

作者： Duan, Zhuohui Yu, Zelin Liu, Haikun Liao, Xiaofei Jin, Hai Zheng, Shijie Wu, Sihan National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab Huazhong University of Science and Technology Wuhan430074 China

ISBN: (纸本)9798400706011

Memory disaggregation, facilitated by Smart Network Interface Cards (SmartNICs), has emerged as a cost-effective approach for sharing memory resources in data centers. However, current SoC-based SmartNICs face several challenges for supporting near-data processing (NDP) in disaggregated memory (DM) systems effectively, such as inefficient resource allocation for SmartNICs employed in NDP, and the lack of collaboration between SmartNICs on data nodes and CPUs on compute nodes. To address these issues, we propose TIGA, an efficient NDP framework for SmartNICs-based disaggregated memory systems. We propose an adaptive resource allocator to fully utilize the SoC cores among NDP engines automatically, and a SmartNIC-CPU cooperative computing mechanism to schedule NDP tasks among CPUs and SmartNICs. We prototype TIGA with FPGAs and evaluate it with several typical workloads. Experimental results show that TIGA significantly improves the efficiency of NDP tasks in DM systems compared with state-of-the-art SmartNIC-based co-processing schemes. © 2024 Copyright is held by the owner/author(s). Publication rights licensed to ACM.

关键词： Storage allocation (computer)

来源：评论

学校读者我要写书评

暂无评论

Evaluating RISC-V Vector Instruction Set Architecture Extension with Computer Vision Workloads

引用

Journal of Computer Science & Technology 2023年第4期38卷 807-820页

作者：李若时彭平邵志远金海郑然 National Engineering Research Center for Big Data Technology and System Huazhong University of Science and Technology Wuhan 430074China Services Computing Technology and System Laboratory Huazhong University of Science and TechnologyWuhan 430074 China Cluster and Grid Computing Lab Huazhong University of Science and TechnologyWuhan 430074China

Computer vision(CV)algorithms have been extensively used for a myriad of applications *** the multimedia data are generally well-formatted and regular,it is beneficial to leverage the massive parallel processing power of the underlying platform to improve the performances of CV *** Instruction Multiple data(SIMD)instructions,capable of conducting the same operation on multiple data items in a single instruction,are extensively employed to improve the efficiency of CV *** this paper,we evaluate the power and effectiveness of RISC-V vector extension(RV-V)on typical CV algorithms,such as Gray Scale,Mean Filter,and Edge *** our examinations,we show that compared with the baseline OpenCV implementation using scalar instructions,the equivalent implementations using the RV-V(version 0.8)can reduce the instruction count of the same CV algorithm up to 24x,when processing the same input ***,the actual performances improvement measured by the cycle counts is highly related with the specific implementation of the underlying RV-V *** our evaluation,by using the vector co-processor(with eight execution lanes)of Xuantie C906,vector-version CV algorithms averagely exhibit up to 2.98x performances speedups compared with their scalar counterparts.

关键词： RISC-V vector extension single instruction multiple data(SIMD) computer vision OpenCV

来源：评论

学校读者我要写书评

暂无评论

AegonKV: A High Bandwidth, Low Tail Latency, and Low Storage Cost KV-Separated LSM Store with SmartSSD-based GC Offloading 23

AegonKV: A High Bandwidth, Low Tail Latency, and Low Storage...

引用

23rd USENIX Conference on File and Storage Technologies, FAST 2025

作者： Duan, Zhuohui Feng, Hao Liu, Haikun Liao, Xiaofei Jin, Hai Li, Bangyu National Engineering Research Center for Big Data Technology and System Service Computing Technology and System Lab/Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology China

ISBN: (纸本)9781939133458

The key-value separation is renowned for its significant mitigation of the write amplification inherent in traditional LSM trees. However, KV separation potentially increases performance overhead in the management of Value region, especially for garbage collection (GC) operation that is used to reduce the redundant space occupation. In response, many efforts have been made to optimize the GC mechanism for KV separation. However, our analysis indicates that such solution based on trade-offs between CPU and I/O overheads cannot simultaneously satisfy the three requirements of KV separated systems in terms of throughput, tail latency, and space usage. This limitation hinders their real-world application. In this paper, we introduce AegonKV, a "three-birds-one-stone" solution that comprehensively enhances the throughput, tail latency, and space usage of KV separated systems. AegonKV first proposes a SmartSSD-based GC offloading mechanism to enable asynchronous GC operations without competing with LSM read/write for bandwidth or CPU. AegonKV leverages offload-friendly data structures and hardware/software execution logic to address the challenges of GC offloading. Experiments demonstrate that AegonKV achieves the largest throughput improvement of 1.28-3.3 times, a significant reduction of 37%-66% in tail latency, and 15%-85% in space overhead compared to existing KV separated systems. © 2025 FAST. All Rights Reserved.

关键词： Digital storage

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：