检索结果-内蒙古大学图书馆

2nd International Conference for Advancement in technology, ICONAT 2023

作者： Pattankar, Veena V Priyanga, P. Computer Science and Engineering Global Academy of Technology Bangalore India Artificial Intelligence and Machine Learning Global Academy of Technology Bangalore India

ISBN: (纸本)9781665475174

The scientific literature contains essential information connected to proteins, drugs, and symptoms. Researchers are extracting organized, brief, and understandable information from unstructured texts to keep up with the growing number of publications. Within the context of the biomedical area, this study investigates event extraction and natural language comprehension. We will build a flexible description of an event by first outlining several terminological methods. Second, we demonstrate event extraction, its challenges, and annotated corpora. Third, we investigate representative methodologies and provide an up-to-date analysis with performance discussion. We provide a taxonomy to assist academics in navigating the deluge of event extraction works. Fourth, we compare biomedical solutions to those in other domains to uncover fresh research opportunities and approaches. Finally, we discuss potential applications, explainability, and knowledge injection. © 2023 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

ReE3D: Boosting Novel View Synthesis for Monocular Images using Residual Encoders

引用

IEEE Transactions on Multimedia 2023年 1-11页

作者： Guo, KeHua Chen, Tianyu Ren, Sheng Hu, Bin Wu, Zheng Guo, Shaojun Fang, Hui School of Computer Science and Engineering Central South University Changsha China School of Computer and Electrical Engineering Hunan University of Arts and Science Changde China National Innovation of Defense Technology Academy of Military Sciences PLA China Beijing China Computer Science Department Loughborough University Loughborough U.K

In recent years, novel view synthesis from a monocular image has become a research hot-spot that attracts significant attention. Some recent work identifies latent vectors for high-quality view generation via iterative optimisation, which is a time-consuming process. In contrast, some others utilise an encoder learning a mapping function to approximately estimate optimal latent codes, which significantly reduces its processing time but sacrifices reconstruction quality. Consequently, how to balance synthesis quality and its generation efficiency still remains challenging. In this paper, we propose a residual-based encoder to incorporate with a 3D Generative Adversarial Networks (GAN), named ReE3D, for novel view synthesis. It applies an iterative prediction of latent codes to ensure much higher quality of novel view synthesis with an insignificant increase of processing time when compared to existing encoder-based 3D GAN inversion methods. Additionally, we enforce a novel geometric loss constraint on the encoder to predict view-invariant latent codes, thus effectively mitigating the trade-off between geometric and texture quality in 3D GAN inversion. Extensive experimental results demonstrate that our extended encoder-based method has achieved best trade-off performance in terms of novel view synthesis quality and its execution time. Our method has gained comparable synthesis quality with exponentially decreased processing time when compared to iterative optimisation methods, while improved synthesis performance of encoder-based methods significantly. IEEE

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Collaborative Service Provisioning for UAV-Assisted Mobile Edge Computing

引用

Chinese Journal of Electronics 2024年第6期33卷 1504-1514页

作者： Yuben QU Zhenhua WEI Zhen QIN Tao WU Jinghao MA Haipeng DAI Chao DONG The Key Laboratory of Dynamic Cognitive System of Electromagnetic Spectrum Space Ministry of Industry and Information Technology Colllege of Electronic and Information Engineering Nanjing University of Aeronautics and Astronautics Xi'an Research Institute of High Technology Department of Information and Communication Noncommissioned Officer Academy of PAP National University of Defense Technology Department of Computer Science and Technology Nanjing University

Unmanned aerial vehicle(UAV)-assisted mobile edge computing(MEC), as a way of coping with delaysensitive and computing-intensive tasks, is considered to be a key technology to solving the challenges of terrestrial MEC networks. In this work, we study the problem of collaborative service provisioning(CSP) for UAV-assisted MEC. Specifically, taking into account the task latency and other resource constraints, this paper investigates how to minimize the total energy consumption of all terrestrial user equipments, by jointly optimizing computing resource allocation, task offloading, UAV trajectory, and service placement. The CSP problem is a non-convex mixed integer nonlinear programming problem, owing to the complex coupling of mixed integral variables and non-convexity of CSP. To address the CSP problem, this paper proposes an alternating optimization-based solution with the convergence guarantee as follows. We iteratively deal with the joint service placement and task offloading subproblem, and UAV movement trajectory subproblem, by branch and bound and successive convex approximation, respectively,while the closed form of the optimal computation resource allocation can be efficiently obtained. Extensive simulations validate the effectiveness of the proposed algorithm compared to three baselines.

关键词： Energy consumption Multi-access edge computing Collaboration Programming Autonomous aerial vehicles Minimization Trajectory Resource management Optimization Convergence

来源：评论

学校读者我要写书评

暂无评论

A New Benchmark and Algorithm for Clothes-Changing Video Person Re-Identification

引用

IEEE Transactions on Information Forensics and Security 2025年 20卷 1993-2005页

作者： Wang, Likai Zhang, Xiangqun Han, Ruize Wei, Yanjie Wang, Song Feng, Wei Tianjin University College of Intelligence and Computing Tianjin300350 China Shenzhen University of Advanced Technology Faculty of Computer Science and Control Engineering Shenzhen518107 China Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China

Person re-identification (Re-ID) is a classical computer vision task and has significant applications for public security and information forensics. Recently, long-term Re-ID with clothes-changing has attracted increasing attention. However, existing methods mainly focus on image-based setting, where richer temporal information is overlooked. In this paper, we focus on the relatively new yet practical problem of Clothes-Changing Video-based Re-ID (CCVReID), which is less studied. First, given the dataset shortage, we build two new benchmark datasets for CCVReID problem, including a large-scale synthetic video dataset and a real-world one, both containing human sequences with various clothing changes. Moreover, we systematically study this problem by simultaneously considering the classical appearance feature and temporal feature contained in the video. We develop a dual-branch fusion framework that makes use of the information from both clothes-aware appearance feature and clothes-free gait feature. For better information fusion, a confidence-guided re-ranking strategy is proposed to adaptively balance the weight of these two categories of features. We have released the benchmark and code proposed in this work to the public at https://***/kkw98/CCVReID. © 2025 IEEE.

关键词： Reamers

来源：评论

学校读者我要写书评

暂无评论

An Improved and Optimized Random Forest Based Approach to Predict the Software Faults

引用

SN computer science 2024年第5期5卷 530页

作者： Thomas, Nikhil Saji Kaliraj, S. Department of Computer Science and Engineering Manipal Academy of Higher Education Dubai United Arab Emirates Department of Information and Communication Technology Manipal Institute of Technology Manipal Academy of Higher Education Manipal 576104 India

Effective software fault prediction is crucial for minimizing errors during software development and preventing subsequent failures. This research introduces an enhanced Random Forest-based approach for predicting software faults, specifically focusing on the NASA JM1 dataset. The dataset comprises 21 software metrics indicating the presence or absence of faults in a module, and it is utilized to evaluate the proposed approach. The study delves into the intricacies of the NASA dataset, detailing the cleaning process and addressing class imbalance through Synthetic Minority Over-sampling Technique (SMOTE). The core of our approach involves the implementation and fine-tuning of the Random Forest classifier, with a specific focus on optimizing hyperparameters to enhance predictive accuracy. In comparative evaluations with standard machine learning models, our proposed approach demonstrated superior performance, achieving an accuracy of 82.96% and an F1 score of 89.53%. Notably, we emphasize the significance of software defects and their potential to cause failures and crashes during software development, leading to substantial organizational losses. The paper provides a comprehensive examination of different aspects of the machine learning model, offering detailed insights, examples, and illustrative figures to enhance the understanding of our proposed approach. © The Author(s) 2024.

关键词： Class Imbalance NASA Defect Data Random Forest, Optimization SMOTE Software Fault Prediction

来源：评论

学校读者我要写书评

暂无评论

Multi-Task Learning for Alzheimer's Disease Diagnosis and Mini-Mental State Examination Score Prediction

引用

Big Data Mining and Analytics 2024年第3期7卷 828-842页

作者： Jin Liu Xu Tian Hanhe Lin Hong-Dong Li Yi Pan Hunan Provincial Key Lab on Bioinformatics School of Computer Science and EngineeringCentral South UniversityChangsha 410083China Xinjiang Engineering Research Center of Big Data and Intelligent Software School of SoftwareXinjiang UniversityUrumqi 830091China School of Science and Engineering University of DundeeDundeeDD14HNUK Faculty of Computer Science and Control Engineering Shenzhen Institute of Advanced TechnologyChinese Academy of SciencesShenzhen 518055China

Accurately diagnosing Alzheimer's disease is essential for improving elderly ***,accurate prediction of the mini-mental state examination score also can measure cognition impairment and track the progression of Alzheimer's ***,most of the existing methods perform Alzheimer's disease diagnosis and mini-mental state examination score prediction separately and ignore the relation between these two *** address this challenging problem,we propose a novel multi-task learning method,which uses feature interaction to explore the relationship between Alzheimer's disease diagnosis and minimental state examination score *** our proposed method,features from each task branch are firstly decoupled into candidate and non-candidate parts for ***,we propose feature sharing module to obtain shared features from candidate features and return shared features to task branches,which can promote the learning of each *** validate the effectiveness of our proposed method on multiple *** Alzheimer's disease neuroimaging initiative 1 dataset,the accuracy in diagnosis task and the root mean squared error in prediction task of our proposed method is 87.86%and 2.5,*** results show that our proposed method outperforms most state-of-the-art *** proposed method enables accurate Alzheimer's disease diagnosis and mini-mental state examination score ***,it can be used as a reference for the clinical diagnosis of Alzheimer's disease,and can also help doctors and patients track disease progression in a timely manner.

关键词： multi-task learning Alzheimer's disease diagnosis mini-mental state examination score prediction

来源：评论

学校读者我要写书评

暂无评论

Solarsense: Enhancing Energy Efficiency Through Iot-Enabled Solar Tracking 2

Solarsense: Enhancing Energy Efficiency Through Iot-Enabled ...

引用

2nd IEEE International Conference on Interdisciplinary Approaches in technology and Management for Social Innovation, IATMSI 2024

作者： Thopate, Kaushalya Gawade, Mayuri Kakade, Surabhi Bahir, Suvarna Kulkarni, Mukund Jaiswal, Krishna Nilesh Computer Engineering Vishwakarma Institute of Technology Pune India Artificial Intelligence and Data Science Vishwakarma Institute of Technology Pune India Computer Engineering Trinity Academy of Engineering Pune India Electronics and Telecommunication Vishwakarma Institute of Technology Pune India

ISBN: (纸本)9798350360523

The surging global demand for energy is primarily fueled by a burgeoning world population and elevated living standards. However, with traditional fossil fuels like oil dwindling in availability, there is an urgent need to shift towards renewable energy sources. Given the rapid progress in renewable energy technologies, a key objective of the project is to develop a solar energy tracking panel that can rotate for enhanced power generation. This innovative panel, capable of adjusting its position to optimize energy output by tracking the sun, proves invaluable in monitoring power consumption. The design of this rotatable solar energy tracking panel, incorporating four essential components (solar energy tracking panels, light-dependent resistors (LDRs), an Arduino, and a motor), is intricately explained in this study. This configuration not only serves as an advanced educational tool but also provides engineering technology students with a comprehensive understanding of alternative energy sources like solar power. © 2024 IEEE.

关键词： Fossil fuels

来源：评论

学校读者我要写书评

暂无评论

Detection and Classification of Indian Classical Bharathanatyam Mudras Using Enhanced Deep Learning Technique 3

Detection and Classification of Indian Classical Bharathanat...

引用

3rd International Conference on Innovations in science and technology for Sustainable Development, ICISTSD 2022

作者： Haridas, Sneha Ramani Bai, V. Vidya Academy of Science and Technology Dept. of Computer Science and Engineering Thrissur India Vidya Academy of Science and Technology Computer Science and Engineering Thrissur India

ISBN: (纸本)9781665499361

Indian Classical dance forms like bharathanatyam are composed of advanced hand gestures, facial expressions moreover as body moments. Because of its complexity, identifying each mudra in bharathanatyam is extremely difficult. This paper demonstrates a massive Convolutional Neural Network (CNN) that was trained on Google Colaboratory using a single step model, You Only Look Once version 3 (YOLOv3), to analyze images in the dataset and detect and classify the mudras. Open datasets of mudras are not presently available. So Bharatanatyam mudra dataset of single hand gesture images of 28 classes was created. This proposed system is, as far as we know, the first attempt in this subject. YOLOv3 was never used to detect mudras. YOLOv3 divides the image into sectors, predicts bounding boxes, and calculates probability for each. These bounding boxes are then weighted according to the projected probability, and the model is then able to detect the object based on the final weights. The neural network was able to correctly generate test data after being trained, with a mean average precision (mAP) of 73%. © 2022 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

WCMIVR: A Web 3.0 Compliant Machine Intelligence Driven Scheme for Video Recommendation 13th

WCMIVR: A Web 3.0 Compliant Machine Intelligence Driven Sche...

引用

13th International Conference on Innovations in Bio-Inspired Computing and Applications, IBICA 2022, and 12th World Congress on Information and Communication Technologies, WICT 2022

作者： Kannan, Beulah Divya Deepak, Gerard Department of Computer Science and Engineering National Institute of Technology Tiruchirappalli India Department of Computer Science and Engineering Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Manipal India

ISBN: (纸本)9783031274985

Video recommendation is the need of the hour in the era of Web 3.0. And there is a need for semantically inclined Web 3.0 compliant framework for video recommendation. In this paper, a WCMIVR framework which is a Web 3.0 compliant web video recommendation framework. WCMIVR has been proposed, although it is a query driven approach, it is centred on staged query enrichment by auxiliary knowledge addition. The proposed WCMIVR model is a knowledge centric semantically inclined framework where the TF-IDF is applied on the documents crawled from the web repository in order to aggregate the enriched categories of videos and also informative words are added from the TF-IDF model. Wikidata and Google Knowledge graph API are standard knowledge stores which are used further used for enrichment of the video categories. Ontology alignment is applied for feature discovery in order to classify the dataset of videos using Machine learning based logistic regression feature controlled classifier. The semantic similarity is calculated using Horn’s index, Twitter semantic similarity and Jaccard similarity which improvisions a strong relevant computation mechanism in order to rank and recommend the videos to the person using it. All in all, the proposed WCMIVR model acquires largest average precision percentage of 97.88, largest average recall percentage of 99.04, largest average percentage of accuracy of 98.46, largest average F-Measure percentage of 98.45 and with the lowest overall FDR measure of 0.03 which makes WCMIVR model the best classifier for web video recommendation which is compliant to Web 3.0. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

A Paradigm Shift in Real-Time Detection: The YOLOv7 Approach to Trainable Freebie Optimization 3

A Paradigm Shift in Real-Time Detection: The YOLOv7 Approach...

引用

3rd International Conference on Electronics and Renewable Systems, ICEARS 2025

作者： Vinitha, A. Jeevitha, S. Kumar, N.B. Mahesh Sathish Kumar, L. Saravanan, D. Karpagam Academy of Higher Education Department of Computer Applications Tamilnadu Coimbatore India Kalasalingam Academy of Research and Education Department of Computer Science and Information Technology Krishnankoil Tamilnadu Virudhunagar India Hindusthan Institute of Technology Computer Science and Engineering Tamil Nadu Coimbatore India Madhya Pradesh Sehore India

ISBN: (纸本)9798331509675

Significant progress has been made in real-time object detection, with YOLOv7 emerging as a state-of-the-art model that achieves the highest levels of accuracy and speed. This study combines Bag-of-Freebies (BoF) strategies with YOLOv7 to improve performance without incurring extra computational expenses. Our tests show that adding BoF preserves real-time inference capabilities while increasing mAP@0.5 by 3.5%. The accuracy and FPS of YOLOv7 with BoF are superior to those of the current YOLO-based models (YOLOv4, YOLOv5, YOLOv6). According to the results, YOLOv7 with BoF sets a new standard for real-time object detection by achieving a mAP@0.5 of 55.3% and 83 FPS on the COCO dataset. © 2025 IEEE.

关键词： Contrastive Learning

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：