检索结果-内蒙古大学图书馆

Improved Speech Emotion Recognition Focusing on High-Level Data Representations and Swift Feature Extraction Calculation

引用

computers, Materials & Continua 2023年第12期77卷 2915-2933页

作者： Akmalbek Abdusalomov Alpamis Kutlimuratov Rashid Nasimov Taeg Keun Whangbo Department of Computer Engineering Gachon UniversitySujeong-GuSeongnam-SiGyeonggi-Do13120Korea Department of AI.Software Gachon UniversitySeongnam-Si13120Korea Department of Artificial Intelligence Tashkent State University of EconomicsTashkent100066Uzbekistan

The performance of a speech emotion recognition(SER)system is heavily influenced by the efficacy of its feature extraction *** study was designed to advance the field of SER by optimizing feature extraction tech-niques,specifically through the incorporation of high-resolution Mel-spectrograms and the expedited calculation of Mel Frequency Cepstral Coefficients(MFCC).This initiative aimed to refine the system’s accuracy by identifying and mitigating the shortcomings commonly found in current ***,the primary objective was to elevate both the intricacy and effectiveness of our SER model,with a focus on augmenting its proficiency in the accurate identification of emotions in spoken *** research employed a dual-strategy approach for feature ***,a rapid computation technique for MFCC was implemented and integrated with a Bi-LSTM layer to optimize the encoding of MFCC ***,a pretrained ResNet model was utilized in conjunction with feature Stats pooling and dense layers for the effective encoding of Mel-spectrogram *** two sets of features underwent separate processing before being combined in a Convolutional Neural Network(CNN)outfitted with a dense layer,with the aim of enhancing their representational *** model was rigorously evaluated using two prominent databases:CMU-MOSEI and *** findings include an accuracy rate of 93.2%on the CMU-MOSEI database and 95.3%on the RAVDESS *** exceptional performance underscores the efficacy of this innovative approach,which not only meets but also exceeds the accuracy benchmarks established by traditional models in the field of speech emotion recognition.

关键词： Feature extraction MFCC ResNet speech emotion recognition

来源：评论

学校读者我要写书评

暂无评论

Visual object tracking:Progress,challenge,and future

引用

The Innovation 2023年第2期4卷 19-20页

作者： Libo Zhang Heng Fan Institute of Software Chinese Academy of SciencesBeijing 100190China Department of Computer Science and Engineering University of North TexasDentonTX 76206USA Nanjing Institute of Software Technology Nanjing 210000China

Visual object tracking aims to continuously localize the target object of interest in a video *** one of the most fundamental problems in computer vision,visual object tracking has a long list of critical applications including video surveillance,autonomous driving,human-machine interaction,augmented reality,robotics,etc.,in which the tracking system provides the capacity to report target positions in real time for subsequent visual *** the past decades,visual object tracking has been extensively explored and has witnessed considerable progress,especially in deep-learning-based tracking.

关键词： Visual visual computer

来源：评论

学校读者我要写书评

暂无评论

A Security Model of Multihospital FHIR Database Authorization Based on Secret Sharing and Blockchain

引用

IEEE Internet of Things Journal 2024年第6期11卷 10325-10335页

作者： Yang, Ching-Nung Li, Peng Cheng, Hsiang-Han Kuo, Hsin-Chuan Lu, Ming-Chan Xiong, Lizhi National Dong Hwa University Department of Computer Science and Information Engineering Hualien97401 Taiwan North China Electric Power University Department of Mathematics and Physics Hebei Key Laboratory of Physics and Energy Technology Baoding071003 China Nanjing University of Information Science and Technology School of Computer and Software Nanjing210044 China

Secret sharing (SS) is a threshold technology that shares a secret value by generating and distributing n shares in the way that a set of any k shares can recover the secret. On the other hand, blockchain is a decentralized system establishing a secure data structure for storing data in the form of a hash chain. Combining SS and blockchain is definitely a promising paradigm in the data security field. Recently, the fast healthcare interoperability resources (FHIRs) standard is defined for medical data exchange across various medical institutions. In this article, we combine SS, ElGamal's encryption/decryption, and blockchain to propose a multihospital FHIR database authorization (MFDA). To achieve a secure MFDA, the group-based SS (GSS) and the notion using GSS on exponent (referred to as EGSS) are proposed. The secrets of GSS and EGSS have the discrete logarithm problem (DLP) relation, on which the secrets can be used as ElGamal's private key and public key, respectively. Also, their shares will have DLP relation. By uploading public shares of EGSS on blockchain and using private shares of GSS in a private network, we can recover ElGamal's public key from a deployed smart contract on blockchain and recover ElGamal's private key from a qualified set. Meantime, when recovering private key, the private shares of GSS can be authenticated by public shares on blockchain to check tampering and corrupted of private shares during the communication in a private network. Theorems, examples, and experiments demonstrate that the proposed MFDA has efficient and secure database authorization. © 2014 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

RGB-T object tracking with adaptive decision fusion 2

RGB-T object tracking with adaptive decision fusion

引用

2nd International Conference on Algorithms, Microchips, and Network Applications, AMNA 2023

作者： Bai, Yida Yang, Ming Department of Software Engineering College of Computer & Information Science Southwest University Chongqing400715 China Department of Computer Science College of Computer & Information Science Southwest University Chongqing400715 China

ISBN: (纸本)9781510664791

Visual object tracking is a traditional task in computer vision, which has developed with several decades. With the development of machine learning, correlation filter (CF) has been proposed with satisfying performance and very high framerate. Though the CF framework has numerous strengths in this task, the tracker is fragile to miss the target in several scenes, including extreme illumination, target occlusion and deformation. Recently, thermal modality, which detects the target’s temperature, is robust to the night scenes and can provide a precise target contour. In this paper, we propose a CF based tracker with decision fusion strategy for visible-thermal (RGB-T) tracking. First, we introduce multi-modal KCF trackers as our baseline. Then, we design a decision fusion method considering the Peak-to-Side Rate (PSR) of the score maps, thereby achieving an adaptive fusing those modalities and avoiding model’s heterogeneity. In the experiments, our tracker has validated on the public dataset, namely GTOT. Compared with two uni-modality trackers, the proposed tracker with real-time speed has shown superior results on both target localization and scale estimation. © 2023 SPIE.

关键词： Target tracking

来源：评论

学校读者我要写书评

暂无评论

A Secure and Efficient Framework for Multi-Round Data Trading Over the Internet of Artificially Intelligent Things

引用

IEEE Internet of Things Magazine 2022年第1期5卷 119-124页

作者： Zheng, Xu Zhang, Lizong Hui, Bei Tian, Ling Cai, Zhipeng School of Computer Science and Engineering University of Electronic Science and Technology of China China School of Information and Software Engineering University of Electronic Science and Technology of China China Georgia State University Department of Computer Science United States

IoT data trading has greatly benefited the popularization of both the Internet of Things (IoT) and Artificial Intelligence of Things (AIoT). Current solutions mainly treat the dataset owned by each device as a commodity and focus on maintaining a data market. Meanwhile, inspired by recent achievements in distributed machine learning and federated learning, AIoT can actually realize its services by retaining the data locally on devices and only exchanging model parameters. However, existing IoT data trading methods fail to meet this secure and efficient process. Therefore, this article proposes a novel framework for data trading over AIoT. It allows the service provider to trade on deep learning model training instead of purchasing the full datasets. Key factors for the security issues and data pricing are addressed for the framework, including the design of the learning parameters and the comprehensive privacy concerns. Then a novel data trading strategy is proposed for the service provider to jointly maintain the model performance and the budget consumption. Evaluation results reveal the improvements on the model performance. Finally, some open problems in the design of data trading in AIoTs are discussed. © 2018 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

An Intelligent Thyroid Diagnosis System Utilizing Multiple Ensemble and Explainable Algorithms with Medical Supported Attributes

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第6期5卷 2840-2855页

作者： Sutradhar, Ananda Al Rafi, Mustahsin Ghosh, Pronab Shamrat, F M Javed Mehedi Moniruzzaman, Md. Ahmed, Kawsar Azad, A.K.M. Bui, Francis M. Chen, Li Moni, Mohammad Ali Daffodil International University Department of Computer Science and Engineering Dhaka1216 Bangladesh Lakehead University Department of Computer Science Thunder BayONP7B 5E1 Canada University of Malaya Department of Computer System and Technology Kuala Lumpur50603 Malaysia Lakehead University Department of Software Engineering Thunder BayONP7B 5E1 Canada University of Saskatchewan Department of Electrical and Computer Engineering SaskatoonSK S7N 5A9 Canada Imam Mohammad Ibn Saud Islamic University Faculty of Science Department of Mathematics and Statistics Riyadh13318 Saudi Arabia Charles Stuart University AI and Cyber Futures Institute BathurstNSW2795 Australia

The widespread impact of thyroid disease and its diagnosis is a challenging task for healthcare experts. The conventional technique for predicting such a vital disease is complex and time-consuming. A data-driven approach may offer predictive solutions, but it relies on all relevant attributes, which are computationally expensive. Hence, we propose a novel machine learning (ML) based disease prediction system that could potentially predict it by considering three crucial steps. First, to reduce the dimension of the dataset, three feature selection techniques were employed, including feature importance (FIS), information gain selections (IGS), and least absolute shrinkage and selection operator (LAS). Moreover, recommended medical references were considered while developing a feature set having the identical attributes as high-risk factors (HRF). Second, the models, including the three stage hybrid classifier (3SHC) and the three stage hybrid artificial neural network (3SHANN), are used as classifiers on the training data set. Third, a local interpretable model-agnostic explanations (LIME) to the 3SHC with the HRF samples was applied to individually explain the predictions. Then, the overall behaviors of both gender and age categories were explored with the help of a partial dependence plot (PDP). Finally, the proposed system is validated with extensive experiments, where the 3SHC achieves an accuracy (ACC) of 99.29%, which can play a crucial role in preventing thyroid disease and alleviating stress in the healthcare sector. © 2020 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Occluded Person Re-Identification using Region-based Convolutional Neural Networks 23

Occluded Person Re-Identification using Region-based Convolu...

引用

3rd International Conference on Human Machine Interaction, ICHMI 2023

作者： Islam, Atiqul Tsun, Mark Tee Kit Bee Theng, Lau Chua, Caslon Faculty of Engineering Computing & Science Swinburne University of Technology Sarawak Campus Kuching Malaysia Department of Computer Science and Software Engineering Swinburne University of Technology Melbourne Australia

ISBN: (纸本)9798400700088

The ability to continuously follow a target person in a dynamically changing environment remains a major challenge that indoor companion robots confront. Ongoing human following is complicated by close similarity matching and target occlusions. Person Re-Identification (re-ID) is a computer vision task that can help with the problem of intentional or unintentional occlusion of the subject or person of interest. Numerous research has been conducted on re-ID where the basic assumption is that the gallery set will only have non-occluded person images. This paper examines the problem from a human detection perspective and surveys the state-of-the-art of person re-ID, their achievement and shortcomings. A region-based convolutional neural network (R-CNN) Re-ID is proposed in this research. The findings from the prototyping and evaluation demonstrate that the proposed person Re-ID model is reliable for indoor re-ID situations. Thus, future works in this direction include investigating other factors, such as the number of persons in a scene and varying viewing angles of the probed target person, which can impact the performance of the proposed re-ID model. © 2023 ACM.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Semantic-Aware Pseudo-Labeling for Unsupervised Meta-Learning

引用

IEEE Transactions on Pattern Analysis and Machine Intelligence 2025年第7期47卷 5475-5488页

作者： Ouyang, Tianran Dong, Xingping Ye, Mang Du, Bo Shao, Ling Shen, Jianbing Wuhan University School of Computer Science National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan430072 China University of Chinese Academy of Sciences UCAS-Terminus AI Lab Beijing101408 China University of Macau State Key Laboratory of Internet of Things for Smart City Department of Computer and Information Science 314100 China

In unsupervised meta-learning, the clustering-based pseudo-labeling approach is an attractive framework, since it is model-agnostic, allowing it to synergize with supervised algorithms to learn from unlabeled data. However, the pseudo-labels suffer from clustering noise and semantic chaos problems, further impacting the effectiveness of meta-learning. In this paper, we analyze and optimize the pseudo-labeling process, including encoding and clustering, aiming to generate semantic-like pseudo-labels to narrow the gap between unsupervised and supervised meta-learning. First, during the encoding, we observe that the embedding space of existing methods lacks clustering-friendly properties, which is the primary reason for clustering noise. To address this issue, we minimize the inter-to-intra-class similarity ratio to generate clustering-friendly embedding features and validate our approach through comprehensive experiments. Then, during the clustering, we find that the semantic quality of pseudo-labels is not adequately controlled, resulting in semantic chaos of pseudo-labels. We propose a semantic-stability index to measure the semantic quality of pseudo-labels quantitatively. Based on this index, we propose the Semantic-aware Pseudo-label Reassignment mechanism to generate semantic-like pseudo-labels for all samples. Our approach is model-agnostic and can easily be integrated into existing supervised methods. To demonstrate its generalization ability, we integrate it into two representative algorithms: MAML and EP. The results on three main few-shot benchmarks clearly show that the proposed method achieves significant improvement compared to state-of-the-art models. Notably, our approach also outperforms the corresponding supervised method in three tasks. © 1979-2012 IEEE.

关键词： Latent semantic analysis

来源：评论

学校读者我要写书评

暂无评论

Enhancing Autonomous Driving with Pre-trained Imitation and Reinforcement Learning

Enhancing Autonomous Driving with Pre-trained Imitation and ...

引用

2025 International Conference on Electronics, Information, and Communication, ICEIC 2025

作者： Choi, Jeong-Hwan Kim, Dong-Han Yoo, Ji-Sang Kim, Beom-Joon Hwang, Jun-Tae DongSeoul University Department of Electronic Engineering Seongnam Korea Republic of Kyung Hee University Department of Computer Engineering Yongin Korea Republic of Kyung Hee University Department of Artificial Intelligence Yongin Korea Republic of Kyung Hee University Department of Software Convergence Yongin Korea Republic of

ISBN: (纸本)9798331510756

This paper proposes a method that combines imitation learning and reinforcement learning to improve the learning performance of autonomous vehicles. The actor model was pre-trained using expert demonstration data from the CARLA simulator, and then integrated into PPO-based reinforcement learning. The experimental results showed that the model combining imitation learning outperformed the model using only reinforcement learning, particularly in the early stages of training. However, this study is limited by using only image data, and future research will incorporate vehicle position and speed information for enhanced results. © 2025 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Comparative Study for Identifying and Categorizing DDoS Attacks 21

Comparative Study for Identifying and Categorizing DDoS Atta...

引用

21st International Learning and Technology Conference, L and T 2024

作者： Saad, Asaad B. Hossny, Eman Omara, Fatma A. Cairo University Faculty of Computers and Artificial Intelligence Software Engineering Department Cairo Egypt Cairo University Faculty of Computers and Artificial Intelligence Computer Science Department Cairo Egypt

ISBN: (纸本)9798350393569

Distributed Denial of Service, known as DDoS attacks, significantly compromise network security and availability. Certain DDoS detection methods utilize machine learning techniques, whereas others are based on statistical techniques. Therefore, this study provides a classification of the currently available DDoS detection techniques based on these two methodologies, strengths, and limitations. In addition, a comparative study of some DDoS detection techniques proposed in recent years is presented. We obtained similar results in related studies using different datasets. Thus, the compared DDoS techniques were dataset-independent. Finally, this study highlights areas for further research and improvement. © 2024 IEEE.

关键词： Network security

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：