检索结果-内蒙古大学图书馆

Aspect Level Songs Rating Based Upon Reviews in English

computers, Materials & Continua 2023年第2期74卷 2589-2605页

作者： Muhammad Aasim Qureshi Muhammad Asif Saira Anwar Umar Shaukat Atta-ur-Rahman Muhammad Adnan Khan Amir Mosavi Department of Computer Science Bahria University Lahore54000Pakistan Lahore Institute of Science and Technology Lahore 54792Pakistan Department of Multidisciplinary Engineering Texas A&M UniversityCollege Station77843USA Department of Computer Science College of Computer Science and Information Technology(CCSIT)Imam Abdulrahman Bin Faisal University(IAU)P.O.Box 1982Dammam 31441Saudi Arabia Department of Software Gachon UniversitySeongnam13120Korea John von Neumann Faculty of Informatics Obuda UniversityBudapest1034Hungary Institute of Information Engineering Automation and MathematicsSlovak University of Technology in BratislavaBratislava81107Slovakia Faculty of Civil Engineering TU-DresdenDresden01062Germany

With the advancements in internet facilities,people are more inclined towards the use of online *** service providers shelve their items for *** users post their feedbacks,reviews,ratings,*** the use of the *** enormous increase in these reviews has raised the need for an automated system to analyze these reviews to rate these *** Analysis(SA)is a technique that performs such decision *** research targets the ranking and rating through sentiment analysis of these reviews,on different *** a case study,Songs are opted to design and test the decision *** aspects of songs namely music,lyrics,song,voice and video are *** the reason,reviews of 20 songs are scraped from YouTube,pre-processed and formed a *** machine learning algorithms—Naïve Bayes(NB),Gradient Boost Tree,Logistic Regression LR,K-Nearest Neighbors(KNN)and Artificial Neural Network(ANN)are *** performed the best with 74.99%*** are validated using K-Fold.

关键词： Machine learning natural language processing songs reviews:sentiment analysis songs rating aspect level sentiment analysis reviews analysis text classification music

来源：评论

学校读者我要写书评

暂无评论

ECAvatar: 3D Avatar Facial Animation with Controllable Identity and Emotion 24

ECAvatar: 3D Avatar Facial Animation with Controllable Ident...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Yu, Minjing Pang, Delong Kang, Ziwen Sun, Zhiyao Lv, Tian Sheng, Jenny Yi, Ran Wen, Yu-Hui Liu, Yong-Jin College of Intelligence and Computing Tianjin University Tianjin China Department of Computer Science and Technology Tsinghua University Beijing China Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China School of Computer and Information Technology Beijing Jiaotong University Beijing China

ISBN: (纸本)9798400706868

Speech-driven 3D facial animation has attracted considerable attention due to its extensive applicability across diverse domains. The majority of existing 3D facial animation methods ignore the avatar's expression, while emotion-controllable methods struggle with specifying the avatar's identity and portraying various emotional intensities, resulting in a lack of naturalness and realism in the animation. To address this issue, we first present an Emolib dataset containing 10,736 expression images with eight emotion categories, i.e., neutral, happy, angry, sad, fear, surprise, disgust, and contempt, where each image is accompanied by a corresponding emotion label and a 3D model with expression. Additionally, we present a novel 3D facial animation framework that operates with unpaired training data. This framework produces emotional facial animations aligned with the input face image, effectively conveying diverse emotional expressions and intensities. Our framework initially generates lip-synchronized and expression models separately. These models are then combined using a fusion network to generate face models that effectively synchronize with speech while conveying emotions. Moreover, the mouth structure is incorporated to create a comprehensive face model. This model is then fed into our skin-realistic renderer, resulting in a highly realistic animation. Experimental results demonstrate that our approach outperforms state-of-the-art 3D facial animation methods in terms of realism and emotional expressiveness while also maintaining precise lip synchronization. The Emolib dataset is available at https://***/yuminjing/***. © 2024 ACM.

关键词： Animation

来源：评论

学校读者我要写书评

暂无评论

Cyber Security Analysis and Evaluation for Intrusion Detection Systems

引用

computers, Materials & Continua 2022年第7期72卷 1765-1783页

作者： Yoosef B.Abushark Asif Irshad Khan Fawaz Alsolami Abdulmohsen Almalawi Md Mottahir Alam Alka Agrawal Rajeev Kumar Raees Ahmad Khan Department of Computer Science Faculty of Computing and Information TechnologyKing Abdulaziz UniversityJeddah21589Saudi Arabia Department of Electrical and Computer Engineering Faculty of EngineeringKing Abdulaziz UniversityJeddah21589Saudi Arabia Department of Information Technology Babasaheb Bhimrao Ambedkar UniversityLucknow226025Uttar PradeshIndia Department of Computer Science and Engineering Babu Banarasi Das UniversityLucknow226028India

Machine learning is a technique that is widely employed in both the academic and industrial sectors all over the *** learning algorithms that are intuitive can analyse risks and respond swiftly to breaches and security *** is crucial in offering a proactive security system in the field of *** real time,cybersecurity protects information,information systems,and networks from *** the recent decade,several assessments on security and privacy estimates have noted a rapid growth in both the incidence and quantity of cybersecurity *** an increasing rate,intruders are breaching information *** detection,software vulnerability diagnosis,phishing page identification,denial of service assaults,and malware identification are the foremost cyber-security concerns that require efficient *** have tried a variety of approaches to address the present cybersecurity obstacles and *** a similar vein,the goal of this research is to assess the idealness of machine learning-based intrusion detection systems under fuzzy conditions using a Multi-Criteria Decision Making(MCDM)-based Analytical Hierarchy Process(AHP)and a Technique for Order of Preference by Similarity to Ideal-Solutions(TOPSIS).Fuzzy sets are ideal for dealing with decision-making scenarios in which experts are unsure of the best course of *** projected work would support practitioners in identifying,prioritising,and selecting cybersecurityrelated attributes for intrusion detection systems,allowing them to design more optimal and effective intrusion detection systems.

关键词： Cybersecurity machine learning AHP-TOPSIS fuzzy logic intrusion detection systems

来源：评论

学校读者我要写书评

暂无评论

MAD-ANET:Malware Detection Using Attention-Based Deep Neural Networks

引用

computer Modeling in engineering & sciences 2025年第4期143卷 1009-1027页

作者： Waleed Khalid Al-Ghanem Emad Ul Haq Qazi Tanveer Zia Muhammad Hamza Faheem Muhammad Imran Iftikhar Ahmad Department of Computer Engineering College of Computer and Information SciencesKing Saud UniversityRiyadh11362Saudi Arabia Centre of Artificial Intelligence Naif Arab University for Security SciencesRiyadh14812Saudi Arabia School of Arts and Sciences The University of Notre DameSydneyNSW 2007Australia Center for Smart Analytics Institute of InnovationScience and SustainabilityFederation University AustraliaBerwickVIC 3806Australia Department of Information Technology Faculty of Computing and Information TechnologyKing Abdulaziz UniversityJeddah21589Saudi Arabia

In the current digital era,new technologies are becoming an essential part of our ***,the number ofmalicious software ormalware attacks is rapidly *** is no doubt,themajority ofmalware attacks can be detected by most antivirus ***,such types of antivirus programs are one step behind malicious *** to these dilemmas,deep learning become popular in the detection and classification of malicious ***,researchers have significantly focused on finding solutions for malware attacks by analyzing malicious samples with the help of different techniques and *** this research,we presented a lightweight attention-based novel deep Convolutional Neural Network(DNN-CNN)model for binary and multi-class malware classification,including benign,trojan horse,ransomware,and *** applied the Principal Component Analysis(PCA)technique for feature extraction for binary *** used the Synthetic Minority Oversampling Technique(SMOTE)to handle the imbalanced data during multi-class *** proposed attention-based malware detectionmodel is trained on the benchmarkmalware memory dataset named *** indicate that our model obtained high accuracy for binary and multi-class classification,99.5% and 97.9%,respectively.

关键词： Attention-based CNN malware detection machine learning deep learning classification

来源：评论

学校读者我要写书评

暂无评论

Multi-View Human Activity Recognition in Ambient Assisted Living Using Lightweight Deep Learning Models 5

Multi-View Human Activity Recognition in Ambient Assisted Li...

引用

5th International Conference on Electrical, Communication and computer engineering, ICECCE 2024

作者： Bari, Ahsanul Karim, Hezerul Abdul Farid, Fahmid Al Asaduzzaman, Mina Amirabdollahian, Farshid Mansor, Sarina Multimedia University Faculty of Engineering Cyberjaya63100 Malaysia Multimedia University Faculty of Information Science and Technology Melaka63100 Malaysia University of Hertfordshire Faculty of Engineering and Computer Science Hatfield United Kingdom

ISBN: (纸本)9798331529437

Human Activity Recognition (HAR) is crucial for the development of intelligent assistive technologies in Ambient Assisted Living (AAL) environments. This paper proposes an innovative method for Multi-View Human Activity Recognition (MV-HAR) using lightweight deep learning models, specifically MobileNet and Cyclone-CNN (CCNet), to achieve quick and precise activity detection. Utilizing the Robot House Multi-View Human Activity Recognition (RHM-HAR) dataset, which contains four different views-front, back, ceiling (omni), and mobile robot-our models effectively address challenges related to viewpoint variation and motion dynamics. The dataset includes 14 multi-view daily living action classes, providing a balanced set of synchronized human actions suitable for multi-domain neural network learning. MobileNet and CCNet are employed for their high recognition accuracy, computational efficiency, and real-time application capabilities in AAL scenarios. We propose a Mutual information (MI)-based method to assess the redundancy and relevance of each viewpoint, ensuring the fusion of multi-view data with minimum redundancy and maximum relevance. Benchmarking results demonstrate that multi-view combinations significantly enhance recognition performance compared to single-view models, particularly in complex activities involving high levels of movement. © 2024 IEEE.

关键词： Assistive technology

来源：评论

学校读者我要写书评

暂无评论

Multimodal Deep Learning for Cardiovascular Risk Stratification: Integrating Retinal Biomarkers and Cardiovascular Signals for Enhanced Heart Attack Prediction

引用

IEEE Access 2025年 13卷 99672-99689页

作者： K. Sathya G. Magesh School of Computer Science Engineering and Information Systems Vellore Institute of Technology Vellore India

Cardiovascular diseases, particularly myocardial infarction, have remained a significant cause of death around the world. Therefore, dedicated non-invasive risk prediction frameworks are required. Conventional measures for risk prediction among most heterogeneous patients, such as the Framingham Risk Score and ASCVD calculator, are often less precise and poorly generalizable as they fail to capture individual variations in the mechanisms. This study seeks to present a new multimodal deep learning model developed for cardiovascular risk stratification by fusing retinal microvascular features with cardiovascular physiological signals. The pipeline includes a Hierarchical Retinal Vessel Graph Transformer (HRV-GT) for graph-based vascular representation, Spectro-Temporal Cardiovascular Transformer (STC-T) for capturing short- and long-term signal variability, Sparse Manifold Multimodal Fusion (SMM Fusion) for joint alignment of features, Evolutionary Feature Selection with Clinical Prior Constraints (EFS-CP), and a Contrastive Hierarchical Risk Classifier (CHRC-Net) for decision modeling structured. The model was evaluated across the UK Biobank and SEED datasets (n = 55,000), achieving an AUC of 0.97, sensitivity of 91%, and specificity of 89%, with more than 35% better performance than existing models in reducing misclassification. Clinically interpretable biomarkers that combine high computational efficiency (inference time $\approx \; 37$ ms) affirm its design for real-world deployment in preventive cardiovascular screening processes.

关键词： Feature extraction Deep learning Biomarkers Biological system modeling Transformers Predictive models Imaging Heart rate variability Accuracy Retinal vessels

来源：评论

学校读者我要写书评

暂无评论

Enhancing Cloud Infrastructure Security with GraphSAGE-Based Intrusion Detection Systems 1

Enhancing Cloud Infrastructure Security with GraphSAGE-Based...

引用

1st International Conference on Intelligent Systems and Computational Networks, ICISCN 2025

作者： Kumar, G. Nanda Kishor Syed, Shakir Mogal, Amit Karbhari Abid, Tahera Perada, Anvesh Suneetha, Sampathirao University of South Florida United States Malla Reddy University Department of Computer Science and Engineering Hyderabad India Bargersville IN United States Mvp Samaj's Cmcs College Department of Computer Science and Application Nashik India Nawab Shah Alam Khan College of Engineering and Technology Department of Information Technology Hyderabad India Drexel University Department of Electrical and Computer Engineering Philadelphia United States Koneru Lakshmaiah Education Foundation Department of Computer Science and Engineering Vaddeswaram India

ISBN: (纸本)9798331529246

Cloud computing provides scalable and adaptable infrastructure however is significantly susceptible to cyber-attacks. This work presents a hybrid methodology that integrates the GOA and GA for feature selection, alongside the Residual GraphSAGE model for intrusion detection. The hybrid GOA-GA method enhances feature selection by optimizing the balance between exploration and exploitation, mitigating overfitting, and augmenting classification performance. The Residual GraphSAGE model alleviates over smoothing while effectively capturing node and edge interactions for precise intrusion classification. Assessment on a benchmark dataset reveals exceptional performance, attaining an accuracy of 91.74%, surpassing established models such as GCN and ResNet. This study emphasizes the need of hybrid optimization and sophisticated graph-based learning in improving cloud infrastructure security. © 2025 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

Region-adaptive Concept Aggregation for Few-shot Visual Recognition

引用

Machine Intelligence Research 2023年第4期20卷 554-568页

作者： Mengya Han Yibing Zhan Baosheng Yu Yong Luo Han Hu Bo Du Yonggang Wen Dacheng Tao School of Computer Science National Engineering Research Center for Multimedia SoftwareWuhan UniversityWuhan430072China Hubei Luojia Laboratory Wuhan430072China School of Computer Science The University of SydneySydney2006Australia JD Explore Academy Beijing101116China School of Information and Electronics Beijing Institute of TechnologyBeijing100081China School of Computer Science and Engineering Nanyang Technological UniversitySingapore639798Singapore

Few-shot learning (FSL) aims to learn novel concepts from very limited examples. However, most FSL methods suffer from the issue of lacking robustness in concept learning. Specifically, existing FSL methods usually ignore the diversity of region contents that may contain concept-irrelevant information such as the background, which would introduce bias/noise and degrade the performance of conceptual representation learning. To address the above-mentioned issue, we propose a novel metric-based FSL method termed region-adaptive concept aggregation network or RCA-Net. Specifically, we devise a region-adaptive concept aggregator (RCA) to model the relationships of different regions and capture the conceptual information in different regions, which are then integrated in a weighted average manner to obtain the conceptual representation. Consequently, robust concept learning can be achieved by focusing more on the concept-relevant information and less on the conceptual-irrelevant information. We perform extensive experiments on three popular visual recognition benchmarks to demonstrate the superiority of RCA-Net for robust few-shot learning. In particular, on the Caltech-UCSD Birds-200-2011 (CUB200) dataset, the proposed RCA-Net significantly improves 1-shot accuracy from 74.76% to 78.03% and 5-shot accuracy from 86.84% to 89.83% compared with the most competitive counterpart.

关键词： Few-shot learning metric-based meta learning concept learning region-adaptive concept-aggregation

来源：评论

学校读者我要写书评

暂无评论

Novel Based Controller Design to Control Grid Systems and to Maintain Stability

Novel Based Controller Design to Control Grid Systems and to...

引用

2023 International Conference on Power Energy, Environment and Intelligent Control, PEEIC 2023

作者： Haripriya Ahmed, Zahid Sing, Navjot Computer Science Engineering Department Bangalore India Vivekananda Global University Department of Computer Science & Application Jaipur India Maharishi University of Information Technology Engineering Department Uttar Pradesh India

ISBN: (纸本)9798350357769

This study presents a novel cooperative control method for an interconnected hybrid DC/AC microgrid that uses an infinite impulses (IIR) filter as its core element. The creation of a digital proportional-resonant (PR) electrical controller forms the basis of the control system. The controller's integrated adaptive neural fuzzy induction system (ANFIS) effectively monitors the system's maximum battery life point (MPP). A particle swarm optimizing (PSO)-programmed ANFIS controls the inverter current that is output, ensuring that solar PV systems using boost converters and inverters may extract maximum power quickly and without oscillation. The suggested PR controller has the ability to cancel harmonics and shows remarkable gain at the resonance frequency. Fast reference signal tracking, flexibility in response to grid rate drift, a simple system design, and the lack of steady-state error are important characteristics. A frequency-domain study of the PR limiter is included in the report. Without changing the figure description, the proposed strategy improves the transient as steady-state responses and helps to stabilize the voltage. © 2023 IEEE.

关键词： Cooperative control Distributed Generation (DG) hybrid AC/DC microgrid converters Microgrid (MG) Power Electronics and Renewable Energy Proportional-Resonant controller Smart Grids

来源：评论

学校读者我要写书评

暂无评论

Leveraging Support Vector Machine for Sports Injury Classification 15

Leveraging Support Vector Machine for Sports Injury Classifi...

引用

15th International Conference on information technology and Electrical engineering, ICITEE 2023

作者： Surasak, Thattapon Praking, Phornnatee Kitchat, Kotcharat King Mongkut's University of Technology North Bangkok Faculty of Applied Science Dept. of Computer and Information Science Bangkok Thailand National Central University Dept. of Computer Science and Information Engineering Taoyuan Taiwan

ISBN: (纸本)9798350304466

This study explores the utility of Support Vector Machines (SVM) for the classification of injuries in Athletes including tennis, table tennis, and badminton. The primary objective of this research was to develop an automated method to detect between normal and injury pose, providing a poten-tially powerful tool for early detection. In other words, this research is the pioneer study to represent one another solution for sports injury classification using the image data apart from the current approaches that might be focused on the sensor-based. Therefore, we collect a dataset from various social media across the three sports, labeled into two categories: 'Normal' and 'Injury'. The SVM model was trained on this dataset, and tuned to optimize its performance in distinguishing the two classes. Achieving an accuracy of 96.63%, the result demonstrates that the SVM model can effectively identify injury patterns in the considered sports. The implications of this study are sig-nificant, presenting the initial steps towards applying computer vision tasks in sports topics. By demonstrating the feasibility of an SVM-based approach to injury detection in these racket sports. © 2023 IEEE.

关键词： Sports

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：