检索结果-内蒙古大学图书馆

Facial Depression Estimation via Multi-Cue Contrastive Learning

IEEE Transactions on Circuits and Systems for Video Technology 2025年第6期35卷 6007-6020页

作者： Wang, Xinke Xu, Jingyuan Sun, Xiao Li, Mingzheng Hu, Bin Qian, Wei Guo, Dan Wang, Meng Anhui University School of Artificial Intelligence Hefei230601 China Hefei Comprehensive National Science Center Institute of Artificial Intelligence Hefei230031 China Hefei University of Technology School of Computer Science and Information Engineering Hefei230601 China University of Science and Technology of China Institute of Advanced Technology Hefei230094 China Beijing Institute of Technology School of Medical Technology Beijing100081 China

Vision-based depression estimation is an emerging yet impactful task, whose challenge lies in predicting the severity of depression from facial videos lasting at least several minutes. Existing methods primarily focus on fusing frame-level features to create comprehensive representations. However, they often overlook two crucial aspects: 1) inter- and intra-cue correlations, and 2) variations among samples. Hence, simply characterizing sample embeddings while ignoring to mine the relation among multiple cues leads to limitations. To address this problem, we propose a novel Multi-Cue Contrastive Learning (MCCL) framework to mine the relation among multiple cues for discriminative representation. Specifically, we first introduce a novel cross-characteristic attentive interaction module to model the relationship among multiple cues from four facial features (e.g., 3D landmarks, head poses, gazes, FAUs). Then, we propose a temporal segment attentive interaction module to capture the temporal relationships within each facial feature over time intervals. Moreover, we integrate contrastive learning to leverage the variations among samples by regarding the embeddings of inter-cue and intra-cue as positive pairs while considering embeddings from other samples as negative. In this way, the proposed MCCL framework leverages the relationships among the facial features and the variations among samples to enhance the process of multi-cue mining, thereby achieving more accurate facial depression estimation. Extensive experiments on public datasets, DAIC-WOZ, CMDC, and E-DAIC, demonstrate that our model not only outperforms the advanced depression methods but that the discriminative representations of facial behaviors provide potential insights about depression. Our code is available at:https://***/xkwangcn/***. © 1991-2012 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Adaptable Individualized Investment Recommendation System

Adaptable Individualized Investment Recommendation System

引用

2024 IEEE International Conference on Electronic Systems and Intelligent Computing, ICESIC 2024

作者： Sabiyath Fatima, N. Noor Alleema, N. Mahesh, C. Umanesan, R. Senthil, K. Santhosh Kumar, P. B.S.Abdur Rahman Crescent Institute of Science and Technology Department of Computer Science and Engineering Chennai India Vel Tech Rangarajan Dr. Sagunthala R and D Institute of Science and Technology Department of Computer Science and Engineering Chennai India Panimalar Engineering College Department of Information Technology Chennai India Saveetha University Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering Chennai India SRM Institute of Science and Technology Department of Computer Science and Engineering Ramapuram Chennai India

ISBN: (纸本)9798331522988

Internetization has played a massive role in the rapid development and growth of the financial investment industry. Due to the rapid development, there is a demand for more financial knowledge services to help make well-informed investments. Accessing and conducting investments through online financial platforms has made the field highly accessible. This has made the investment recommendation system a popular research area. Personalized recommendations will help the user make investments that are safe for their financial situation and also suit their particular needs and interests. This work proposes a method where investment recommendations are given based on three key factors. The user interest sectors, risk appetite-based clustering, and market sentiment of the stock. These factors will be calculated by the use of Lasso regression, SVM, stepwise regression, generalized boosted regression, random forest, ridge regression and fuzzy clustering. Based on these three factors, the proposed method results in investment recommendations made for users that are personalized to the specific user. This allows existing investors to gain new opportunities and new investors to start investing with lower amount of risk using the information available. © 2024 IEEE.

关键词： Decentralized finance

来源：评论

学校读者我要写书评

暂无评论

Deepfake Detection using XAI based Deep Fusion Models 2

Deepfake Detection using XAI based Deep Fusion Models

引用

2nd International Conference on Computational Intelligence, Communication Technology and Networking, CICTN 2025

作者： Anitha, A. Saju, Lis Maria Kamaraj, Balakrishnan School of Computer Science Engineering and Information Systems Vellore Institute of Technology Tamil Nadu Vellore India Madurai Medical College Tamilnadu Madurai India

ISBN: (纸本)9798331530389

Deepfake technology has rapidly evolved, posing a serious threat to the authenticity of digital media and contributing to the spread of misinformation. The manipulation of media content raises significant concerns across sectors like politics, entertainment, and social media, undermining public trust in digital information. In response, this research proposes an advanced deepfake detection model that integrates Explainable Artificial Intelligence (XAI) techniques within a hybrid deep learning architecture. The proposed model combines ResNet50 and Vision Transformer (ViT) to capture spatial and contextual features effectively. While exploring additional methods such as facial landmark detection and frequency domain analysis, the final model focuses on the ResNet50-ViT combination for its superior performance to fusion model. To ensure transparency, the model employs XAI techniques such as LIME (Local Interpretable Model-agnostic Explanations) and SHAP (SHapley Additive explanations), offering interpretability by revealing the key factors that influence its predictions. This dual focus on high detection accuracy and interpretability ensures that the model not only detects deepfakes effectively but also builds trust in automated decision-making processes. By leveraging cutting-edge deep learning and XAI methods, this framework offers a more reliable, transparent, and adaptable solution for preserving digital media authenticity across various applications, ultimately contributing to combating misinformation and fostering trust in digital content. © 2025 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Blockchain-based knowledge-aware semantic communications for remote driving image transmission

引用

Digital Communications and Networks 2025年第2期11卷 317-325页

作者： Yangfei Lin Tutomu Murase Yusheng Ji Wugedele Bao Lei Zhong Jie Li Department of Computer and Network Engineering University of Electro-CommunicationsChofuTokyo 182-8585Japan Information Technology Center Nagoya UniversityNagoya 464-8601Japan National Institute of Informatics(NII) Tokyo 101-8430Japan Hohhot Minzu College Hohhot 010051China Toyota Motor Corporation Tokyo 112-8701Japan Department of Computer Science and Engineering Shanghai Jiaotong UniversityShanghai 200240China

Remote driving,an emergent technology enabling remote operations of vehicles,presents a significant challenge in transmitting large volumes of image data to a central *** requirement outpaces the capacity of traditional communication *** tackle this,we propose a novel framework using semantic communications,through a region of interest semantic segmentation method,to reduce the communication costs by transmitting meaningful semantic information rather than bit-wise *** solve the knowledge base inconsistencies inherent in semantic communications,we introduce a blockchain-based edge-assisted system for managing diverse and geographically varied semantic segmentation knowledge *** system not only ensures the security of data through the tamper-resistant nature of blockchain but also leverages edge computing for efficient ***,the implementation of blockchain sharding handles differentiated knowledge bases for various tasks,thus boosting overall blockchain *** results show a great reduction in latency by sharding and an increase in model accuracy,confirming our framework's effectiveness.

关键词： Semantic communication Remote driving Semantic segmentation Blockchain Knowledge base management

来源：评论

学校读者我要写书评

暂无评论

The Calibration of Single Beam Distance Sensors based on Machine Learning Methods

The Calibration of Single Beam Distance Sensors based on Mac...

引用

2023 IEEE International Conference on Big Data, BigData 2023

作者： Biernacki, Piotr Ziebinski, Adam Syu, Jia-Hao Lin, Jerry Chun-Wei Silesian University of Technology Institute of Theoretical and Applied Informatics Polish Academy of Sciences Institute of Informatics Gliwice Poland Silesian University of Technology Institute of Informatics Gliwice Poland National Taiwan University Department of Computer Science and Information Engineering Taipei Taiwan

ISBN: (纸本)9798350324457

Smart cities require the use of many different types of sensors to make the communication, and distance sensors are one of the most commonly used elements in transportation systems and related infrastructures. The introduction of increasingly advanced autonomous systems in many areas of smart cities requires high measurement precision of the sensors used. High precision is essential for proper operation, long-term use, and safety in machine-to-machine or machine-to-human interactions. This paper presents a comparison of the accuracy of distance measurements for two commercially available single-beam LiDARs and two ultrasonic sensors. The aim of the research was to develop a calibration method in order to improve the accuracy of distance sensors. Based on the collected distance measurements, the sensors were calibrated using selected machine learning algorithms. The results of the experiments show the effectiveness of the proposed calibration methods, which yield an average mean absolute error (MAE) of 1.76 E-05 meters (m) and a root mean square error (RMSE) of 1.33 E-04 m for the tested sensors. © 2023 IEEE.

关键词： machine learning sensors calibration single-beam distance sensors

来源：评论

学校读者我要写书评

暂无评论

Adversarial learning for Mirai botnet detection based on long short-term memory and XGBoost

引用

International Journal of Cognitive Computing in engineering 2024年第1期5卷 153-160页

作者： Vajrobol, Vajratiya Gupta, Brij B. Gaurav, Akshat Chuang, Huan-Ming Institute of Informatics and Communication University of Delhi India International Center for AI and Cyber Security Research and Innovations. Asia University Taiwan Department of Computer Science and Information Engineering Asia University Taichung413 Taiwan Ronin Institute MontclairNJ United States Department of Information Management National Yunlin University of Science and Technology Yunlin Taiwan Symbiosis International University Pune India Department of Electrical and Computer Engineering Lebanese American University Beirut1102 Lebanon Dehradun India

In today's world, where digital threats are on the rise, one particularly concerning threat is the Mirai botnet. This malware is designed to infect and command a collection of Internet of Things (IoT) devices. The use of Mirai attacks has intensified in recent times, thus threatening the smooth operation of numerous devices that are connected to a network. Such attacks carry adverse consequences that include interference with services or the leakage of confidential information. To fight this growing threat, smart and flexible detection techniques are required to counter the new methods cyber attackers use. The aim of this research is to develop a resilient defense against Mirai botnet attacks. The Long Short Term Memory term (LSTM) and XGBoost combined have the best performance of 97.7% accuracy score. With this combination, the aim is to strengthen our cyber defenses against sophisticated and dynamically operating Mirai botnets to further enhance the security of our digital world. © 2024

关键词： Botnet

来源：评论

学校读者我要写书评

暂无评论

Privacy-preserved learning from non-i.i.d data in fog-assisted IoT:A federated learning approach

引用

Digital Communications and Networks 2024年第2期10卷 404-415页

作者： Mohamed Abdel-Basset Hossam Hawash Nour Moustafa Imran Razzak Mohamed Abd Elfattah Faculty of Computers and Informatics Zagazig UniversityZagazigSharqiyah44519Egypt School of Engineering and Information Technology University of New South Wales@ADFACanberraACT2600Australia Deakin University Geelong Waurn Ponds CampusAustralia Computer Science Department Misr Higher Institute for Commerce and ComputersMansoura35511Egypt

With the prevalence of the Internet of Things(IoT)systems,smart cities comprise complex networks,including sensors,actuators,appliances,and cyber *** complexity and heterogeneity of smart cities have become vulnerable to sophisticated cyber-attacks,especially privacy-related attacks such as inference and data poisoning *** Learning(FL)has been regarded as a hopeful method to enable distributed learning with privacypreserved intelligence in IoT *** though the significance of developing privacy-preserving FL has drawn as a great research interest,the current research only concentrates on FL with independent identically distributed(i.i.d)data and few studies have addressed the non-i.i.d *** is known to be vulnerable to Generative Adversarial Network(GAN)attacks,where an adversary can presume to act as a contributor participating in the training process to acquire the private data of other *** paper proposes an innovative Privacy Protection-based Federated Deep Learning(PP-FDL)framework,which accomplishes data protection against privacy-related GAN attacks,along with high classification rates from non-i.i.d ***-FDL is designed to enable fog nodes to cooperate to train the FDL model in a way that ensures contributors have no access to the data of each other,where class probabilities are protected utilizing a private identifier generated for each *** PP-FDL framework is evaluated for image classification using simple convolutional networks which are trained using MNIST and CIFAR-10 *** empirical results have revealed that PF-DFL can achieve data protection and the framework outperforms the other three state-of-the-art models with 3%–8%as accuracy improvements.

关键词： Privacy preservation Federated learning Deep learning Fog computing Smart cities

来源：评论

学校读者我要写书评

暂无评论

Ultrasound Image Analysis in Breast Cancer: A Comparative Study of Decision Trees and Random Forests 16

Ultrasound Image Analysis in Breast Cancer: A Comparative St...

引用

16th IEEE International Conference on Computational Intelligence and Communication Networks, CICN 2024

作者： Sivagami, S. Sathya, A. Afsin, S. Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Department of Computer Science and Engineering India Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Tamilnadu Chennai India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Department of Bio Informatics Tamil Nadu Chennai India

ISBN: (数字)9798331505264

ISBN: (纸本)9798331505264

Breast cancer remains a leading cause of cancer-related mortality among women globally, underscoring the critical need for early detection and accurate diagnosis. Ultrasound imaging serves as a non-invasive diagnostic tool for identifying breast abnormalities, yet the complexity of these images presents significant interpretation challenges. This study explores the application of Machine Learning (ML) models, specifically Decision Tree (DT) and Random Forest (RF) classifiers, for the classification of breast cancer ultrasound images into benign, malignant, and normal categories. Data augmentation techniques are employed to address class imbalance and enhance model generalization using the Breast Cancer Ultrasonic Image dataset. Among preprocessing steps, pixel values were normalized to provide a consistent input for the models. RF model performed better than DT with an accuracy of 88.75% against an accuracy of 86.25% and those masks for ultrasound images contribute a lot to the overall classification accuracy. In summary, the results of our study can provide support for grand challenges in health and emphasize implications such as the potentiality of ML models to advance breast cancer diagnosis and it implies a necessity for an even further expansion that will allow complete patient outcomes optimization. © 2024 IEEE.

关键词： Radio frequency Accuracy Ultrasonic imaging Training data Predictive models Breast cancer Data models Decision trees Random forests Tumors

来源：评论

学校读者我要写书评

暂无评论

EfficientNetB0-based Automated Diabetic Retinopathy Classification in Fundus Images 3

EfficientNetB0-based Automated Diabetic Retinopathy Classifi...

引用

3rd International Conference on Automation, Computing and Renewable Systems, ICACRS 2024

作者： Majaw, Ezekiel Alaric Sundar, G. Naveen Narmadha, D. Thangavel, Senthil Kumar Venkatesan Ajibesin, Adeyemi Abel Department of Computer Science and Engineering Karunya Institute of Technology and Sciences Coimbatore India Department of Computer Science and Engineering Amrita School of Computing Coimbatore India Department of Information Technology Faculty of Informatics and Design Cape Peninsula University of Technology South Africa

ISBN: (纸本)9798331532420

The most common cause of blindness among diabetics is diabetic retinopathy. This disease must be detected in its early stages as delaying treatment can result in permanent blindness. In today’s modern world with the development of technologies, automated techniques have improved the accuracy and efficiency of detecting and classifying this disease. This study suggests a deep learning model utilizing EfficientNetB0 that focuses on designing a neural network structure that requires fewer parameters and computations compared to traditional architectures. Further to help in increasing the accuracy, the image is being processed with methods like CLAHE which is an image processing algorithm that helps in enhancing the contrast while keeping the noise of the images as low as possible. Also, augmentation is being done on the images and SMOTE is applied to handle class imbalance. We collected the APTOS Blindness Detection dataset consisting of retinal fundus images. The accuracy that is being obtained from the proposed methodology is 98.78% indicating the model's effectiveness in detection and classifying between the various stages of diabetic retinopathy. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Enhanced Speech Emotion and Gender Recognition Using Hybrid CNN-LSTM Models 4

Enhanced Speech Emotion and Gender Recognition Using Hybrid ...

引用

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Priyadharshini, S. Sundar, G. Naveen Narmadha, D. Thangavel, Senthil Kumar Ajibesin, Adeyemi Abel Kolandapalayam Shanmugam, Selvanayaki Karunya Institute of Technology and Sciences Department of Computer Science and Engineering Coimbatore India Amrita School of Computing Department of Computer Science and Engineering Coimbatore India Cape Peninsula University of Technology Faculty of Informatics and Design Department of Information Technology South Africa Ashland University Department of Mathematics and Computer Science United States

ISBN: (纸本)9798331523923

The current paper proposes a new approach for peripheral speech emotion analysis and gender estimation incorporating the best machine learning architectures such as CNNs and LSTMs. Its correct depiction of emotions and the variation of the gendered speech to indicate manifold signal-to-noise ratio make the approach accommodate the difficulty inherent in recognizing emotions from the recording of voices as well as predicting the gender of a speaker. It is then able to ally with preprocessing and collection of a vast range of different speech samples, feature extraction of pitch, tone and spectral data. These features serve as input to the CNNs and LSTMs: LSTMs work well at temporal regular features and the CNNs work well in feature extraction by location (spatio feature). The approach is tested on the RAVDESS and IEMOCAP datasets and establishes a near perfect match to prior approaches with reference to recognition accuracy of emotion analysis and gender prediction. Thus, applying the identified dual method approach, which could be described by such characteristics as highly accurate data pre-preprocessing, clear indication of the features of interest, a different CNN-LSTM model joint training, it offers a reasonably good platform to gain certain insights into such characteristics of the speech as our experiment demonstrates. This work offers satisfactory configurations on concerns such as human computer relation, customer relation and mental health surveillance to suggest that other applications could be achieved in future. © 2025 IEEE.

关键词： Convolutional neural networks

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：