检索结果-内蒙古大学图书馆

DeepCNN:Spectro-temporal feature representation for speech emotion recognition

CAAI Transactions on Intelligence Technology 2023年第2期8卷 401-417页

作者： Nasir Saleem Jiechao Gao Rizwana Irfan Ahmad Almadhor Hafiz Tayyab Rauf Yudong Zhang Seifedine Kadry Department of Electrical Engineering Faculty of Engineering and TechnologyGomal UniversityD.I.KhanPakistan Department of Computer Science University of VirginiaCharlottesvilleVirginiaUSA Department of Information Technology College of Computing and Information Technology at KhulaisUniversity of JeddahJeddahSaudi Arabia Department of Computer Engineering and Networks College of Computer and Information SciencesJouf UniversitySkaka AljoufSaudi Arabia Centre for Smart Systems AI and CybersecurityStaffordshire UniversityStoke‐on‐TrentUK School of Computing and Mathematical Sciences University of LeicesterLeicesterUK Department of Applied Data Science Noroff University CollegeKristiansandNorway Artificial Intelligence Research Center(AIRC) Ajman UniversityAjmanUnited Arab Emirates Department of Electrical and Computer Engineering Lebanese American UniversityByblosLebanon

Speech emotion recognition(SER)is an important research problem in human-computer interaction *** representation and extraction of features are significant challenges in SER *** the promising results of recent studies,they generally do not leverage progressive fusion techniques for effective feature representation and increasing receptive *** mitigate this problem,this article proposes DeepCNN,which is a fusion of spectral and temporal features of emotional speech by parallelising convolutional neural networks(CNNs)and a convolution layer-based *** parallel CNNs are applied to extract the spectral features(2D-CNN)and temporal features(1D-CNN)representations.A 2D-convolution layer-based transformer module extracts spectro-temporal features and concatenates them with features from parallel *** learnt low-level concatenated features are then applied to a deep framework of convolutional blocks,which retrieves high-level feature representation and subsequently categorises the emotional states using an attention gated recurrent unit and classification *** fusion technique results in a deeper hierarchical feature representation at a lower computational cost while simultaneously expanding the filter depth and reducing the feature *** Berlin database of Emotional Speech(EMO-BD)and Interactive Emotional Dyadic Motion Capture(IEMOCAP)datasets are used in experiments to recognise distinct speech *** efficient spectral and temporal feature representation,the proposed SER model achieves 94.2%accuracy for different emotions on the EMO-BD and 81.1%accuracy on the IEMOCAP dataset *** proposed SER system,DeepCNN,outperforms the baseline SER systems in terms of emotion recognition accuracy on the EMO-BD and IEMOCAP datasets.

关键词： decision making deep learning

来源：评论

学校读者我要写书评

暂无评论

Exploring the Impact of Random Distribution Choices on Particle Swarm Optimization: An Initial Analysis 27

Exploring the Impact of Random Distribution Choices on Parti...

引用

27th International Conference on Knowledge Based and intelligent Information and engineering Sytems, KES 2023

作者： Kolodziejczyk, Joanna Tarasenko, Yuliia Sulikowski, Piotr Research Team on Intelligent Decision Support Systems Department of Artificial Intelligence Methods and Applied Mathematics Faculty of Computer Science and Information Technology West Pomeranian University of Technology in Szczecin ul. Zolnierska 49 Szczecin71-210 Poland National Institute of Telecommunications ul. Szachowa 1 Warsaw04-894 Poland Department of Information Systems Engineering Faculty of Computer Science and Information Technology West Pomeranian University of Technology in Szczecin ul. Zolnierska 49 Szczecin71-210 Poland

Particle Swarm Optimization (PSO) is a robust stochastic optimization algorithm for solving complex and constrained optimization problems. This paper aims to systematically investigate the influence of diverse random number distributions on the learning parameters of PSO and evaluate the algorithm's sensitivity based on these parameters. To this end, several exhaustive numerical experiments were conducted on several test functions, including asymmetric Sphere, Easom, and Csendes. Initially, appropriate random distributions were identified for the learning parameters and proceeded to compare these distributions using all potential combinations. The sensitivity of PSO to these parameters was evaluated using the mean best score, the relative proximity of the best particle to the theoretical optimum, and the average objective function evaluations. The most significant contribution of this research lies in the insights derived from the experimental data. The discovery was that highly skewed and long-tailed distributions such as Chi, Chi-square, Lomax, and Exponential often underperform. On the other hand, distributions that are bounded proportionally to the problem domain consistently surpass the performance of the standard uniform distribution. These findings significantly enhance the understanding of PSO algorithms and provide valuable guidelines for their practical deployment. © 2023 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (https://***/licenses/by-nc-nd/4.0)

关键词： Particle Swarm Optimization random number distribution stochastic optimization

来源：评论

学校读者我要写书评

暂无评论

Hybrid Machine Learning Approach of "KNN – LSTM" for detection of Brain Tumour in MR images 15

Hybrid Machine Learning Approach of "KNN – LSTM" for detect...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Uganya, G. Gunale, Anuja Govindrao Kulkarni, Shruthi V. Rajalakshmi, D. Valsaraj, Vani Srividhya, B. Department of ECE Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology Chennai India Department of Computer Engineering UPL University of Sustainable Technology Block no 402 Ankleshwar-Valia Road Gujarat Vataria India Department of AIML HKBK College of Engineering opposite manyata tech park Nagawara Karnataka Bengaluru India Department of Data Science and Business Systems SRM Institute of Science and Technology Kattankulathur Chennai India Department of Computer Application Faculty of Humanities and Sciences SRM Institute Of Science and Technology Tamil Nadu Chengalpattu India

ISBN: (纸本)9798350370249

Now a days, more existing techniques are available to found tumours on brain from MR images. But still the researchers are concentrated on to detect the brain tumour accurately with less time. So, this work proposed the hybrid machine learning algorithm of "K-Nearest Neighbour – Long Short-Term Memory" ("KNN-LSTM") with increased ‘accuracy’, ‘sensitivity’, ‘specificity’, with less ‘time consumption’. In this work, the brain tumour is identified by predicting the MR images from huge dataset with usage of machine learning approach of "KNN-LSTM". Brain tumour detection is difficult when to compare the abnormal and typical tissues of large capacity. In order to enable a speedy recovery following therapy, brain tumours should be identified as soon as feasible. If the brain tumour is discovered early on, patients can benefit from improved care. Due to the irregular spreading of the abrasions, brain tumours are still difficult to identify even with intensive study. Sometimes the tiny tumours look like normal, but it is challenging to find it. So, the techniques are need to increase the classification accuracy, and selecting the useful features. This paper proposes a hybrid machine learning model "KNN-LSTM" for categorizing the tumours with predicting through MR images. MRI brain imaging collection is used for our experimentation. The "KNN" algorithm usage is to extract the important characteristics from pictures once the data has been pre-processed effectively. The proposed work predicts the brain tumour with 99.15% of ‘accuracy’, 98% of ‘sensitivity’, 97.12% of ‘specificity’ and testing time consumption of 0.5 minutes. © 2024 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Optimized Hybrid CNN-GRU Approach for Accurate Prediction of Cardiovascular Diseases: Integrating Medical Imaging and Clinical data

Optimized Hybrid CNN-GRU Approach for Accurate Prediction of...

引用

Communication, Control and intelligent systems (CCIS)

作者： Prasanna V Suresh Kumar N Divyaprabha P R Sundaram Department of Data Science and Business Systems School of Computing Faculty of Engineering and Technology SRM Institute of Science and Technology Chennai India Department of Information Technology Sri Ramakrishna Engineering College Coimbatore India Department of Computer Science and Engineering Sri Ramakrishna Engineering College Coimbatore India Department of Computer Science and Engineering Ganesh College of Engineering Salem India

ISBN: (数字)9798331528201

ISBN: (纸本)9798331528218

As the primary cause of death globally, cardiovascular diseases (CVDs) demand precise and timely prediction to enhance patient outcomes. Other examples of conventional approaches for CVD prediction include statistical models as well as machine learning models such as a single model that often struggle to address complex and comprehensive data from clinical records and Medical Imaging. To address these issues, the concept proposed here is to integrate the medical imaging data with clinical data as new apart from utilizing the hybrid CNN–GRU model to predict cardiovascular diseases with higher accuracy and interpretability. While the GRU module deals with the time sequences of clinical data including past history and other test results, the CNN module is to extract the spatial features from the medical images. Thus, by integrating these modules, it is more accurate to predict the data of the patient as a synergy of spatial and temporal arrangements. Cross-validation techniques and performance indices are used for model training and testing on a diverse data set containing imaging and other clinical-related data. Experimental results depict that the suggested hybrid CNN-GRU model performs much better than the traditional approaches and has higher levels of predicted accuracy and robustness. It is also feasible to generalize this integrated strategy to other medical disorder where multi-modal data analysis is crucial, besides enhancing the capacity to estimate CVDs. The findings underline the importance of integrating doctors’ information with radiological images and applying new patterns of neural networks to augmenting clinical judgment. The suggested work is implemented using python.

关键词： Analytical models Accuracy data analysis Computational modeling Predictive models Feature extraction data models Convolutional neural networks Cardiovascular diseases Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

Unprecedented Smart Algorithm for Uninterrupted SDN Services During DDoS Attack

引用

Computers, Materials & Continua 2022年第1期70卷 875-894页

作者： Muhammad Reazul Haque Saw Chin Tan Zulfadzli Yusoff Kashif Nisar Rizaludin Kaspin Iram Haider Sana Nisar J.P.C.Rodrigues Bhawani Shankar Chowdhry Muhammad AslamUqaili Satya Prasad Majumder Danda B.Rawat Richard Etengu Rajkumar Buyya Faculty of Computing&Informatics Multimedia UniversityPersiaranMultimediaCyberjaya63100SelangorMalaysia Faculty of Engineering Multimedia UniversityPersiaran MultimediaCyberjaya63100SelangorMalaysia Faculty of Computing and Informatics University Malaysia SabahJalan UMSKota Kinabalu Sabah88400Malaysia Telekom Malaysia Research&Development TM Innovation Centre63000CyberjayaSelangorMalaysia Federal University of Piauí(UFPI) TeresinaPIBrazil Instituto de Telecomunica珲es 6201-001Covilh?Portugal National Center of Robotics and Automation-Condition Monitoring Systems Lab MUETJamshoroPakistan Department of Electrical and Electronic Engineering BUETDhaka1205Bangladesh Department of Electrical Engineering and Computer Science Data Science and Cybersecurity CenterHoward UniversityWashingtonDCUSA Cloud Computing and Distributed Systems(CLOUDS)Laboratory School of Computing and Information SystemsThe University of MelbourneMelbourneVIC 3053Australia

In the design and planning of next-generation Internet of Things(IoT),telecommunication,and satellite communication systems,controller placement is crucial in software-defined networking(SDN).The programmability of the SDN controller is sophisticated for the centralized control system of the entire ***,it creates a significant loophole for the manifestation of a distributed denial of service(DDoS)attack ***,recently a Distributed Reflected Denial of Service(DRDoS)attack,an unusual DDoS attack,has been ***,minimal deliberation has given to this forthcoming single point of SDN infrastructure failure ***,recently the high frequencies of DDoS attacks have increased *** this paper,a smart algorithm for planning SDN smart backup controllers under DDoS attack scenarios has *** proposed smart algorithm can recommend single or multiple smart backup controllers in the event of DDoS *** obtained simulated results demonstrate that the validation of the proposed algorithm and the performance analysis achieved 99.99%accuracy in placing the smart backup controller under DDoS attacks within 0.125 to 46508.7 s in SDN.

关键词： SDN smart algorithm RTZLK-DAASCP DDoS attack DRDoS

来源：评论

学校读者我要写书评

暂无评论

Unraveling Batch Normalization for Realistic Test-Time Adaptation

arXiv

引用

arXiv 2023年

作者： Su, Zixian Guo, Jingwei Yao, Kai Yang, Xi Wang, Qiufeng Huang, Kaizhu Department of Intelligent Science Xi’an Jiaotong-Liverpool University Suzhou China Faculty of Science and Engineering University of Liverpool Liverpool United Kingdom Data Science Research Center Duke Kunshan University Kunshan China

While recent test-time adaptations exhibit efficacy by adjusting batch normalization to narrow domain disparities, their effectiveness diminishes with realistic mini-batches due to inaccurate target estimation. As previous attempts merely introduce source statistics to mitigate this issue, the fundamental problem of inaccurate target estimation still persists, leaving the intrinsic test-time domain shifts unresolved. This paper delves into the problem of mini-batch degradation. By unraveling batch normalization, we discover that the inexact target statistics largely stem from the substantially reduced class diversity in batch. Drawing upon this insight, we introduce a straightforward tool, Test-time Exponential Moving Average (TEMA), to bridge the class diversity gap between training and testing batches. Importantly, our TEMA adaptively extends the scope of typical methods beyond the current batch to incorporate a diverse set of class information, which in turn boosts an accurate target estimation. Built upon this foundation, we further design a novel layer-wise rectification strategy to consistently promote test-time performance. Our proposed method enjoys a unique advantage as it requires neither training nor tuning parameters, offering a truly hassle-free solution. It significantly enhances model robustness against shifted domains and maintains resilience in diverse real-world scenarios with various batch sizes, achieving state-of-the-art performance on several major benchmarks. Code is available at https://***/kiwi12138/RealisticTTA. Copyright © 2023, The Authors. All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Improving Motor Imagery Classification in BCI systems Using EMD and Multi-Layer CNNs

Improving Motor Imagery Classification in BCI Systems Using ...

引用

International eConference on Computer and Knowledge engineering (ICCKE)

作者： Reza Arghand Ali Chaibakhsh Moein Radman Intelligent Systems and Advanced Control Lab Faculty of Mechanical Engineering University of Guilan Rasht Guilan Iran Brain-Computer Interfacing and Neural Engineering Laboratory University of Essex School of Computer Science and Electronic Engineering Colchester United Kingdom

ISBN: (数字)9798331511272

ISBN: (纸本)9798331511289

Brain-Computer Interface (BCI) systems are relatively new technologies that could play a significant role in aiding the recovery of impaired activities resulting from neuromuscular disabilities in affected individuals. Accurate recognition and classification of motor imagery in BCI systems present a challenge, leading to extensive research in recent years aimed at improving the accuracy of these systems. In this study, a combination of the Empirical Mode Decomposition (EMD) method and a multi-layer Convolutional Neural Network (CNN) is employed. Initially, the signal is decomposed into Intrinsic Mode Functions (IMFs) using EMD, and all IMFs across all trials are analyzed to select the best ones, which are then fed into the CNN as inputs. Additionally, the study incorporates the fusion of three CNN networks, each corresponding to a different IMF. The features extracted from these networks are combined and used to train an SVM classifier. The proposed method achieved an accuracy of 86.1% on the BCI-2a 2008 dataset, outperforming other state-of-the-art approaches.

关键词： Support vector machines Knowledge engineering Accuracy Image recognition Empirical mode decomposition Neuromuscular Motors Feature extraction Brain-computer interfaces Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A data-Driven Approach to MBTI Personality Classification: Insights from Machine Learning Models

A Data-Driven Approach to MBTI Personality Classification: I...

引用

International Conference on Computational Intelligence and Communication Networks (CICN)

作者： Fares A. Dael Symbat Maidanova Ibraheem Shayea Gulnara Abitova Aigul Seraly Management Information Systems İzmir Bakırçay University İzmir Turkey Computational and Data Science Astana IT University Astana Kazakhstan Electronic and Communication Engineering Istanbul Technical University Istanbul Turkey Intelligent Systems and Cybersecurity Astana IT University Astana Kazakhstan

ISBN: (数字)9798331505264

ISBN: (纸本)9798331505271

The Myers-Briggs Type Indicator (MBTI) is one of the most widely recognized psychological tools for categorizing personality types, often used in various professional and personal development contexts. This study presents a data-driven approach to MBTI personality classification using a range of machine learning models. By leveraging a dataset comprising user responses and linguistic patterns, we aim to predict the MBTI personality types with greater accuracy and reliability. Various models, including Support Vector Machines (SVM), Random Forests, and Gradient Boosting Machines, were evaluated to determine their effectiveness in classifying the 16 MBTI types. Our findings reveal that machine learning models can significantly enhance the predictive accuracy of MBTI classification compared to traditional methods. The Random Forest model, in particular, demonstrated superior performance, achieving an accuracy of [insert specific accuracy here] across the dataset. We also explore the importance of feature selection and data preprocessing in improving model outcomes, highlighting key features that contribute to personality type prediction. The results of this study suggest that a data-driven approach, combined with machine learning techniques, provides a promising avenue for more nuanced and accurate MBTI personality assessments. This approach not only enhances our understanding of personality prediction but also offers practical implications for applications in psychology, human resources, and personal development.

关键词： Support vector machines Accuracy Computational modeling Semantics Psychology Predictive models Linguistics Natural language processing Reliability Random forests

来源：评论

学校读者我要写书评

暂无评论

Detecting Questions in Online Communities: A Machine Learning Approach

Detecting Questions in Online Communities: A Machine Learnin...

引用

International Conference on Computational Intelligence and Communication Networks (CICN)

作者： Dilnaz Omarova Fares A. Dael Ibraheem Shayea Gulnara Abitova Eldos Sailaukhanov Computational and Data Science Astana IT University Astana Kazakhstan Management Information Systems İzmir Bakιrçay University Izmir Turkey Electronic and Communication Engineering Istanbul Technical University Istanbul Turkey Intelligent Systems and Cybersecurity Astana IT University Astana Kazakhstan

ISBN: (数字)9798331505264

ISBN: (纸本)9798331505271

The proliferation of online forums and communities has greatly facilitated knowledge sharing and user support but has also introduced the significant challenge of managing redundant and semantically similar questions. Traditional keyword-based methods have proven inadequate in addressing this issue due to the inherent complexities of natural language, where the same idea can be expressed in numerous ways. This study investigates the use of advanced machine learning algorithms - Logistic Regression, Random Forest, and Gradient Boosting (XGBoost) - to detect semantically similar questions. By employing the Quora Question Pairs dataset, the performance of these models is evaluated using metrics such as accuracy, precision, recall, and F1-score. This research not only provides a comparative analysis of these machine learning models but also suggests a framework for improving information retrieval and user experience in online forums. The study highlights the potential for future integration of deep learning models and advanced semantic understanding techniques to further enhance the detection of semantically similar questions.

关键词： Deep learning Adaptation models Logistic regression Accuracy Semantics User experience Robustness Natural language processing Random forests Context modeling

来源：评论

学校读者我要写书评

暂无评论

Integral Reinforcement Reciprocal Zhang Neural Net for Time-Varying Linear Equations

Integral Reinforcement Reciprocal Zhang Neural Net for Time-...

引用

New Trends in Computational Intelligence (NTCI), International Conference on

作者： Changyuan Wang Long Chen Yunong Zhang Shuai Li Faculty of Science and Technology University of Macau Macau China School of Intelligent Systems Engineering Sun Yat-sen University Shenzhen China Faculty of Information Technology and Electrical Engineering University of Oulu Oulu Finland Technical Research Center of Finland Oulu Finland

ISBN: (数字)9798331517021

ISBN: (纸本)9798331517038

Solving time-varying linear equations is a com-mon challenge encountered in engineering and science. The development of neural dynamic systems has led to the creation of various feedback neural nets that effectively solve continuous time-varying linear equations. In this context, reciprocal Zhang neural net (RZNN) was developed, which is focused by this work, providing an explicit inverse-free continuous model for solving time-varying linear equations. However, the continuous model often struggle with noise interference, e.g., Gaussian noise, during the solving process. This paper enhances RZNN model with an integral reinforcement term to improve robustness of the explicit continuous models with noisy conditions. Furthermore, we optimize the RZNN solving process, making it easier for implementation in circuit systems and numerical simulations.

关键词： Solid modeling Computational modeling Neural networks Interference Numerical simulation Mathematical models Robustness Numerical models Noise measurement Integrated circuit modeling

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：