检索结果-内蒙古大学图书馆

HoLens:A visual analytics design for higher-order movement modeling and visualization

Computational Visual Media 2024年第6期10卷 1079-1100页

作者： Zezheng Feng Fang Zhu Hongjun Wang Jianing Hao Shuang-Hua Yang Wei Zeng Huamin Qu Department of Computer Science and Engineering The Hong Kong University of Science and TechnologyHong KongChina Department of Computer Science and Engineering Southern University of Science and TechnologyShenzhen 518055China Thrust of Computational Media and Arts(CMA) The Hong Kong University of Science and Technology(Guangzhou)Guangzhou 511458China Department of Computer Science University of ReadingBerkshire RG66AHUK Shenzhen Key Laboratory of Safety and Security for Next Generation of Industrial Internet Southern University of Science and TechnologyShenzhen 518055China

Higher-order patterns reveal sequential multistep state transitions,which are usually superior to origin-destination analyses that depict only first-order geospatial movement *** methods for higher-order movement modeling first construct a directed acyclic graph(DAG)of movements and then extract higher-order patterns from the ***,DAG-based methods rely heavily on identifying movement keypoints,which are challenging for sparse movements and fail to consider the temporal variants critical for movements in urban *** overcome these limitations,we propose HoLens,a novel approach for modeling and visualizing higher-order movement patterns in the context of an urban *** mainly makes twofold contributions:First,we designed an auto-adaptive movement aggregation algorithm that self-organizes movements hierarchically by considering spatial proximity,contextual information,and tem-poral ***,we developed an interactive visual analytics interface comprising well-established visualization techniques,including the H-Flow for visualizing the higher-order patterns on the map and the higher-order state sequence chart for representing the higher-order state *** real-world case studies demonstrate that the method can adaptively aggregate data and exhibit the process of exploring higher-order patterns using *** also demonstrate the feasibility,usability,and effectiveness of our approach through expert interviews with three domain experts.

关键词： data visualization movement modeling state sequence visualization movement visualization urban visual analytics

来源：评论

学校读者我要写书评

暂无评论

Advancements in Credit Scoring, Profit Scoring, and Portfolio Optimization for P2P Lending 3

Advancements in Credit Scoring, Profit Scoring, and Portfoli...

引用

3rd International Conference on Communication, Control, and Intelligent Systems, CCIS 2024

作者： Nayaka, Premkumar Hegde, Anusha Bhowmik, Biswajit National Institute of Technology Karnataka Ishwarchandra Vidyasagar Ait Lab Brics Laboratory Department of Computer Science and Engineering Surathkal India National Institute of Technology Karnataka Brics Laboratory Department of Computer Science and Engineering Surathkal India

ISBN: (纸本)9798331528201

The Peer-to-peer (P2P) lending platform allows borrowers to connect directly with lenders outside traditional banking systems. Therefore, for the sustainability of these platforms, they must accurately assess the credit risk and profitability of the loans. Various credit scoring techniques, including Logistic Regression, neural networks, and ensemble methods, can be used to estimate the likelihood of borrower default. It is imperative to analyze the profit the lenders generated and enhance the credit scoring so that the investors face minimum loss. Once the profit analysis is done, then it is crucial to advise the investors about the portfolio of loans. This paper presents recent credit scoring, profit scoring, and portfolio optimization trends for P2P lending. We highlight the significant issues in incorporating machine learning models into credit scoring systems. The analysis emphasizes the need for a data-driven approach to perfecting lending practices, thus benefiting both borrowers and investors in the rapidly changing P2P landscape. © 2024 IEEE.

关键词： Decentralized finance

来源：评论

学校读者我要写书评

暂无评论

The most tenuous group query

引用

Frontiers of computer Science 2023年第2期17卷 197-208页

作者： Na LI Huaijie ZHU Wenhao LU Ningning CUI Wei LIU Jian YIN Jianliang XU Wang-Chien LEE School of Computer Science and Engineering Sun Yat-Sen UniversityGuangzhou 510006China Laboratory of Big Data Analysis and Processing Guangzhou 510006China School of Artificial Intelligence Sun Yat-Sen UniversityGuangzhou 510006China Department of Computer Science Anhui UniversityHefei 230601China Department of Computer Science Hong Kong Baptist UniversityHong Kong 999077China Department of Computer Science The Pennsylvania State UniversityState College 19019USA

Rtecently a lot of works have been investigating to find the tenuous groups,i.e.,groups with few social interactions and weak relationships among members,for reviewer selection and psycho-educational group ***,the metrics(e.g.,k-triangle,k-line,and k-tenuity)used to measure the tenuity,require a suitable k value to be specified which is difficult for users without background ***,in this paper we formulate the most tenuous group(MTG)query in terms of the group distance and average group distance of a group measuring the tenuity to eliminate the influence of parameter k on the tenuity of the *** address the MTG problem,we first propose an exact algorithm,namely MTGVDIS,which takes priority to selecting those vertices whose vertex distance is large,to generate the result group,and also utilizes effective filtering and pruning *** MTGVDIS is not fast enough,we design an efficient exact algorithm,called MTG-VDGE,which exploits the degree metric to sort the vertexes and proposes a new combination order,namely degree and reverse based branch and bound(DRBB).MTG-VDGE gives priority to those vertices with small *** a large p,we further develop an approximation algorithm,namely MTG-VDLT,which discards candidate attendees with high degree to reduce the number of vertices to be *** experimental results on real datasets manifest that the proposed algorithms outperform existing approaches on both efficiency and group tenuity.

关键词： tenuous group pruning strategy social network group query

来源：评论

学校读者我要写书评

暂无评论

Enhancing Automated Short Answer Grading with Prompt-Driven Augmentation and Prompt Adaptive Oversampling 27th

Enhancing Automated Short Answer Grading with Prompt-Driven...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Afeefa, P.P. Hazari, Raju Das, Pranesh Machine Learning Laboratory Department of Computer Science and Engineering National Institute of Technology Calicut Kozhikode India

ISBN: (纸本)9783031781186

Automated Short Answer Grading (ASAG) comes under automatic answer script evaluation where the answer length is limited from one phrase to one paragraph. The main task in ASAG is generating a good sentence embedding for both the student and the reference answers. The existing works on the embedding creation perform better when using different deep-learning techniques and language models. However, the deep-learning techniques’ performance mainly depends on the training set size and quality. Most of the publicly available datasets typically have a limited number of reference and student answer pairs. To automate the dataset expansion, text augmentation techniques can be used. Conventional methods like back-translation, synonym replacement, and random deletion may replace some important technical words with other non-relevant terms, resulting in a loss of contextual meaning. We propose a new augmentation strategy for the ASAG datasets using LLM (Large Language Model) prompting. The effect of the proposed strategy is analysed on sentence transformer fine-tuning. We experimented with four different sizes of augmented training sets to determine the impact of the size of augmented training data on fine-tuning the sentence transformer model. Results indicate that sentence transformer fine-tuned using a 50% prompt-driven augmented dataset generates better embeddings. After having good embeddings, the traditional classifiers can be used to classify the student answers to different scores. We introduce "Prompt Adaptive Oversampling (PAO)" to address the class imbalance issue during grade classification. The effectiveness of the proposed strategy is analysed on two different public datasets: SPRAG, and Mohler-ASAG. The proposed method performs better while training highly imbalanced datasets. The source code of this work is available here. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Classification of Poikilocytosis Abnormality Using Ensemble Deep Learning Technique 3rd

Classification of Poikilocytosis Abnormality Using Ensemble...

引用

3rd International Conference on Emerging Electronics and Automation, E2A 2023

作者： Dhar, Prasenjit Singh, Mohit Kumar Ahmed, Tanveer Suganya, Devi K. Medical Imaging Laboratory Computer Science and Engineering Department National Institute of Technology Silchar Assam India

ISBN: (纸本)9789819768011

Red blood cells (RBCs) also known as erythrocytes are an essential component of the human body that play several important roles. RBCs transport oxygen (O2) from the lungs to the body’s tissues, remove carbon dioxide (CO2), regulate pH balance, support the immune system, and provide diagnostic information. The abnormal shapes of RBCs (signified as poikilocytosis) are unable to carry O2 and CO2, leading to decreased O2 delivery to the tissues and an increased workload on the heart and lungs. Anemia, thalassemia, and other blood-related illnesses affect the body for insufficient replenishment (oxygen, protein, nutrients). Hematologists take more time to examine RBC shapes manually using a microscope. In this study ensemble deep learning technique was introduced to examine poikilocytosis abnormality accurately and efficiently. The proposed ensemble model outperforms state-of-the-art approaches with an excellent accuracy and F1-score of 98.77%. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Multi-Scale Time Series Segmentation Network Based on Eddy Current Testing for Detecting Surface Metal Defects

引用

IEEE/CAA Journal of Automatica Sinica 2025年第3期12卷 528-538页

作者： Xiaorui Li Xiaojuan Ban Haoran Qiao Zhaolin Yuan Hong-Ning Dai Chao Yao Yu Guo Mohammad S.Obaidat George Q.Huang the School of Intelligence Science and Technology University of Science and Technology Beijing the Beijing Advanced Innovation Center for Materials Genome Engineering the Key Laboratory of Intelligent Bionic Unmanned Systems and the Institute of Materials Intelligent Technology Liaoning Academy of Materials IEEE the Department of Computer Science Hong Kong Baptist University the School of Computer and Communication Engineering Key Laboratory of Advanced Materials and Devices for Post-Moore Chips Ministry of Education University of Science and Technology Beijing the Beijing Advanced Innovation Center for Materials Genome Engineering University of Science and Technology Beijing the School of Computer and Communication Engineering University of Science and Technology Beijing the King Abdullah Ⅱ School of Information Technology The University of Jordan the Department of Computational Intelligence the School of Computing SRM University the School of Engineering The Amity University The Hong Kong Polytechnic University

In high-risk industrial environments like nuclear power plants, precise defect identification and localization are essential for maintaining production stability and safety. However, the complexity of such a harsh environment leads to significant variations in the shape and size of the defects. To address this challenge, we propose the multivariate time series segmentation network(MSSN), which adopts a multiscale convolutional network with multi-stage and depth-separable convolutions for efficient feature extraction through variable-length templates. To tackle the classification difficulty caused by structural signal variance, MSSN employs logarithmic normalization to adjust instance distributions. Furthermore, it integrates classification with smoothing loss functions to accurately identify defect segments amid similar structural and defect signal subsequences. Our algorithm evaluated on both the Mackey-Glass dataset and industrial dataset achieves over 95% localization and demonstrates the capture capability on the synthetic dataset. In a nuclear plant's heat transfer tube dataset, it captures 90% of defect instances with75% middle localization F1 score.

关键词： Eddy current testing nondestructive testing semantic segmentation time series analysis

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Approach to SMS Spam Filtering Integrating Embedded and Statistical Features 13

A Comprehensive Approach to SMS Spam Filtering Integrating E...

引用

13th International Conference on computer and Knowledge engineering, ICCKE 2023

作者： Hosseinpour, Shaghayegh Keyvanpour, Mohammad Reza Alzahra University Faculty of Engineering Data Mining Laboratory Department of Computer Engineering Tehran Iran Alzahra University Faculty of Engineering Department of Computer Engineering Tehran Iran

ISBN: (纸本)9798350330151

Modern society relies heavily on mobile phones to communicate. One of the most valuable mobile phone services is SMS (Short Message Service), which simplifies communication greatly. There have been spammers who have misused this platform by sending inappropriate messages to users, provoking them and costing them money. Due to imbalanced data, unclear semantics, and the inability to extract sufficient features from short messages, SMS spam can be difficult to filter. While spam messages have been filtered so far using various methods, their accuracy is still a work in progress. This study uses embeddings and TF-IDF to provide more information from short text messages while improving SMS spam filtering accuracy. The proposed approach was tested on a real dataset. Experiments analyzing evaluation parameters demonstrate that this model is effective. © 2023 IEEE.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Low 3D-HEVC Depth Map Intra Modes Selection Complexity Based on Clustering Algorithm and an Efficient Edge Detection 1st

Low 3D-HEVC Depth Map Intra Modes Selection Complexity Based...

引用

1st edition of the International Conference on Artificial Intelligence and Green Computing, ICAIGC 2023

作者： Hamout, Hamza Elyousfi, Abderrahmane Computer Systems and Vision Laboratory Faculty of Sciences Ibn-Zohr University Agadir80000 Morocco Department of Computer Science National Engineering School of Applied Sciences Ibn-Zohr University Agadir80000 Morocco

ISBN: (纸本)9783031465833

In 2016, ITU-T Video Coding Experts Group (VCEG) and ISO/IEC MPEG finalize the recent 3-dimensional video coding standard founded on Multi-view texture Videos plus Depth maps (MVD) format called, the 3D extension of High-Efficiency Video Coding (3D-HEVC). In the current design of 3D-HEVC, the conventional intra-prediction modes and Depth Modeling Modes are exploited sophistically to improve the depth map coding performance. However, the coding efficiency improvement is achieved at the cost of computational complexity load, which obstructs 3D-High Efficiency Video Coding standards from practical world applications. In the 3D-HEVC, the depth maps are described by enormous homogeneous regions, and it is observed that for most of the cases, the DMMs and all or the majority of angular intra modes could be skipped for the homogenous area. Thus, we propose an efficient intra-coding model decision for a depth map founded on the clustering algorithm and edge detection to resolve the above-mentioned complexity increase. Experimental results demonstrate that the proposed intra-coding model decision for depth map can decrease the encoding time up to 41.35%, with insignificant loss of rate-distortion performance. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Edge detection

来源：评论

学校读者我要写书评

暂无评论

Enhancing QSAR Modeling: A Fusion of Sequential Feature Selection and Support Vector Machine 14

Enhancing QSAR Modeling: A Fusion of Sequential Feature Sele...

引用

14th International Conference on Information and Knowledge Technology, IKT 2023

作者： Khajehgili-Mirabadi, Farzaneh Keyvanpour, Mohammad Reza Alzahra University Data Mining Laboratory Department of Computer Engineering Faculty of Engineering Tehran Iran Alzahra University Faculty of Engineering Department of Computer Engineering Tehran Iran

ISBN: (纸本)9798350349412

Quantitative Structure-Activity Relationship (QSAR) modeling is an approach employed to predict the biological response of chemical compounds by considering their structural attributes. Classification machine learning algorithms can learn patterns and relationships between chemical structure (descriptors) and biological activity from datasets and then use this knowledge to predict active or inactive compounds. This study introduces a new approach that combines Sequential Feature Selection (SFS) with the Support Vector Machine (SVM) algorithm to select the most relevant molecular descriptors for QSAR modeling. SFS and SVM work collaboratively to identify the best subset of descriptors, resulting in improved predictive accuracy. The key steps include selecting an appropriate subset of descriptors using SFS from a larger set, SVM models are built using different subsets of descriptors, and the most accurate model is chosen for final use. As shown by measuring Accuracy and precision, In our study, the SFS-SVM model demonstrated superior performance in QSAR modeling on both DKPES and PubChem datasets. It achieved the highest accuracy and precision among the compared models, with 92.87% accuracy and 86.66% precision on DKPES, and 98.18% accuracy and 98.00% precision on PubChem. This outperformed other models like SFS-LR, Cluster-GA, RF, DT, and SVM, highlighting its efficiency in feature selection and predictive accuracy. © 2023 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Introduction to the Special Issue on Formal Methods and Models for System Design

引用

ACM Transactions on Embedded Computing Systems 2025年第3期24卷 1-3页

作者： Brandt, Jens Saha, Indranil Zhang, Lijun Hochschule Niederrhein Krefeld Germany Department of Computer Science and Engineering Indian Institute of Technology Kanpur Kanpur India State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences Beijing China

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：