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

Encryption Algorithm for Securing Non-Disclosure Agreements in Outsourcing Offshore Software Maintenance

引用

computers, Materials & Continua 2022年第11期73卷 3827-3845页

作者： Atif Ikram Masita Abdul Jalil Amir Bin Ngah Nadeem Iqbal Nazri Kama Azri Azmi Ahmad Salman Khan Yasir Mahmood Assad Alzayed Faculty of Ocean Engineering Technology and Informatics University Malaysia TerengganuKuala TerengganuMalaysia Department of Computer Science&Information Technology Faculty of Information TechnologyThe University of LahoreLahore54000Pakistan Department of Software Engineering Faculty of Information TechnologyThe University of LahoreLahore54000Pakistan Advanced Informatics Department Razak Faculty of Technology and InformaticsUniversiti Teknologi Malaysia54100Kuala LumpurMalaysia Computer Science and Information Systems Department College of Business Studies Public Authority for Applied Education and Training(PAAET)AdailiyaKuwait

Properly created and securely communicated,non-disclosure agreement(NDA)can resolve most of the common disputes related to outsourcing of offshore software maintenance(OSMO).Occasionally,these NDAs are in the form of *** the work is done offshore,these agreements or images must be shared through the Internet or stored over the *** breach of privacy,on the other hand,is a potential threat for the image owners as both the Internet and cloud servers are not void of *** article proposes a novel algorithm for securing the NDAs in the form of *** an agreement is signed between the two parties,it will be encrypted before sending to the cloud server or travelling through the public network,the *** the image is input to the algorithm,its pixels would be scrambled through the set of randomly generated rectangles for an arbitrary amount of *** confusion effects have been realized through an XOR operation between the confused image,and chaotic ***,5D multi-wing hyperchaotic system has been employed to spawn the chaotic vectors due to good properties of chaoticity it *** machine experimentation and the security analysis through a comprehensive set of validation metric vividly demonstrate the robustness,defiance to the multifarious threats and the prospects for some real-world application of the proposed encryption algorithm for the NDA images.

关键词： Non-disclosure agreement encryption decryption secret key chaoticmap confusion diffusion

来源：评论

学校读者我要写书评

暂无评论

A 1D Residual CNN with SMOTE-Tomek and Cosine Annealing for Enhanced ECG Arrhythmia Classification 16

A 1D Residual CNN with SMOTE-Tomek and Cosine Annealing for ...

引用

16th IEEE Latin American Symposium on Circuits and systems, LASCAS 2025

作者： Jiang, Feng Lim, Yang Wei Ahmad, Siti Anom Ahmad, Faisul Arif Ismail, Luthffi Idzhar Hussein, Ahmed Faeq Rokhani, Fakhrul Zaman Universiti Putra Malaysia Department of Computer and Communication Systems Engineering Faculty of Engineering Malaysia Universiti Putra Malaysia Department of Electrical and Electronics Engineering Faculty of Engineering Malaysia Al-Nahrain University Department of Biomedical Engineering Faculty of Engineering Baghdad Iraq

ISBN: (纸本)9798331522124

This paper proposes a 1D residual convolutional neural network (CNN) for classifying arrhythmias based on electrocardiogram (ECG) signals. The additional residual blocks and skip connections effectively alleviate the gradient problem in deep neural networks by providing a direct path for gradient propagation and enhancing the feature information propagation. In addition, the SMOTE-Tomek technique was demonstrated in this work to mitigate the effects of class imbalance caused by a large amount of data during model training and effectively increase the SNR of the training set. The robustness of the model is increased by adding the cosine annealing technique and L 2 regularization. The proposed model was evaluated with various performance metrics, resulting in an accuracy of 9 8. 7 4 %, sensitivity of 9 8. 3 5 %, specificity of 9 1. 8 6 %, precision of 9 7. 9 5 %, and F1 score of 9 8. 1 4 % on the MIT-BIH Arrhythmia Database. The result shows better performance for classifying previously unseen data for the proposed approach as compared to the state-of-the-art works. © 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

CD-FL:Cataract Images Based Disease Detection Using Federated Learning

引用

computer systems Science & engineering 2023年第11期47卷 1733-1750页

作者： Arfat Ahmad Khan Shtwai Alsubai Chitapong Wechtaisong Ahmad Almadhor Natalia Kryvinska Abdullah Al Hejaili Uzma Ghulam Mohammad Department of Computer Science College of ComputingKhon Kaen UniversityKhon Kaen40002Thailand College of Computer Engineering and Sciences Prince Sattam bin Abdulaziz UniversityAlkharjSaudi Arabia School of Telecommunication Engineering Suranaree University of TechnologyNakhon Ratchasima30000Thailand Department of Computer Engineering and Networks College of Computer and Information SciencesJouf UniversitySakaka72388Saudi Arabia Information Systems Department Faculty of ManagementComenius University in BratislavaOdbojárovBratislava440Slovakia Faculty of Computers&Information Technology Computer Science DepartmentUniversity of TabukTabuk71491Saudi Arabia Department of Computer Science and Software Engineering International Islamic UniversityIslamabad44000Pakistan

A cataract is one of the most significant eye problems worldwide that does not immediately impair vision and progressively worsens over *** cataract prediction based on various imaging technologies has been addressed recently,such as smartphone apps used for remote health monitoring and eye *** recent years,advances in diagnosis,prediction,and clinical decision support using Artificial Intelligence(AI)in medicine and ophthalmology have been *** to privacy concerns,a lack of data makes applying artificial intelligence models in the medical field *** address this issue,a federated learning framework named CDFL based on a VGG16 deep neural network model is proposed in this *** study collects data from the Ocular Disease Intelligent Recognition(ODIR)database containing 5,000 patient *** significant features are extracted and normalized using the min-max normalization *** the federated learning-based technique,the VGG16 model is trained on the dataset individually after receiving model updates from two *** transferring the attributes to the global model,the suggested method trains the local *** global model subsequently improves the technique after integrating the new *** client analyses the results in three rounds to decrease the over-fitting *** experimental result shows the effectiveness of the federated learning-based technique on a Deep Neural Network(DNN),reaching a 95.28%accuracy while also providing privacy to the patient’s *** experiment demonstrated that the suggested federated learning model outperforms other traditional methods,achieving client 1 accuracy of 95.0%and client 2 accuracy of 96.0%.

关键词： Privacy-preserving cataract disease federated learning fundus images healthcare smartphone applications machine learning

来源：评论

学校读者我要写书评

暂无评论

On Security And Privacy In Smart Metering systems 7

On Security And Privacy In Smart Metering Systems

引用

7th International Conference on Smart and Sustainable Technologies, SpliTech 2022

作者： Bacnar, David Leytner, Lolita Prenc, Rene Jardas, Veljko Lerga, Jonatan University of Rijeka Faculty of Engineering Department of Computer Engineering Rijeka Croatia University of Rijeka Faculty of Engineering Department of Electric Power Systems Rijeka Croatia University of Angers Polytech Angers/Automation and Computer Engineering Department Angers France Jatro D.o.o. Rijeka Croatia

ISBN: (纸本)9789532901160

Smart meters are modernizing the electrical energy systems, solving numerous problems of the classical systems, and introducing new functionalities to the grid. This paper aims to give an insight into these systems in terms of their security and privacy aspects. Special attention is paid to the energy theft problem (meter tampering, physical anti-tampering measures, and theft detection methods). We, next, address other security issues present in remote metering (attack types, risks, and threats to the system). Also, necessary security requirements and signature-based, anomaly-based, and specification-based Intrusion Detection systems (IDS) are defined. We conclude by listing privacy concerns arising due to the remote meters and advanced metering infrastructures (AMI) being installed more and more. © 2022 University of Split, FESB.

关键词： Advanced metering infrastructures

来源：评论

学校读者我要写书评

暂无评论

Influence of donor age on liver transplantation outcomes: A multivariate analysis and comparative study

引用

World Journal of Gastrointestinal Surgery 2024年第2期16卷 331-344页

作者： Miran Bezjak Ivan Stresec Branislav Kocman Stipislav Jadrijević Tajana Filipec Kanizaj Miro Antonijević Bojana Dalbelo Bašić Danko Mikulić Department of Surgery University Hospital MerkurZagreb 10000Croatia Department of Electronics MicroelectronicsComputer and Intelligent SystemsFaculty of Electrical Engineering and ComputingZagreb 10000Croatia Department of Gastroenterology University Hospital MerkurZagreb 10000Croatia Development of Software Nanobit Ltd.Zagreb 10000Croatia

BACKGROUND The growing disparity between the rising demand for liver transplantation(LT)and the limited availability of donor organs has prompted a greater reliance on older liver ***,utilizing livers from elderly donors has been associated with outcomes inferior to those achieved with grafts from younger *** accounting for additional risk factors,we hypothesize that the utili-zation of older liver grafts has a relatively minor impact on both patient survival and graft *** To evaluate the impact of donor age on LT outcomes using multivariate analysis and comparing young and elderly donor *** In the period from April 2013 to December 2018,656 adult liver transplants were performed at the University Hospital *** multivariate Cox propor-tional hazards models were developed to independently assess the significance of donor *** age was treated as a continuous *** approach involved univariate and multivariate analysis,including variable selection and assessment of interactions and ***,to exemplify the similarity of using young and old donor liver grafts,the group of 87 recipients of elderly donor liver grafts(≥75 years)was compared to a group of 124 recipients of young liver grafts(≤45 years)from the *** rates of the two groups were estimated using the Kaplan-Meier method and the log-rank test was used to test the differences between *** Using multivariate Cox analysis,we found no statistical significance in the role of donor age within the constructed *** when retained during the entire model development,the donor age's impact on survival remained insignificant and transformations and interactions yielded no substantial effects on *** insigni-ficance and low coefficient values suggest that donor age does not impact patient survival in our ***,there was no statistical evidence that the five developed models did not adhe

关键词： Liver transplantation Elderly donors Survival analysis Postoperative complications Cox proportional hazard models

来源：评论

学校读者我要写书评

暂无评论

Practical big data techniques for end-to-end machine learning deployment: a comprehensive review

引用

Discover Data 2025年第1期3卷 1-18页

作者： El-Sayed, Ahmed Abougabal, Mohamed Lazem, Shaimaa Computer and Systems Engineering Department Faculty of Engineering Alexandria University Alexandria Egypt Informatics Research Institute City of Scientific Research and Technological Applications New Borg El-Arab Egypt

In recent years, data generated from diverse sources has grown exponentially, giving rise to new challenges for processing and analysis under the umbrella of “big data". Although various methods and platforms have been proposed to tackle these issues, there is still a need for a conceptual guide that synthesizes state-of-the-art tools and techniques across the full machine learning (ML) workflow. In this survey, we consolidate research on big data infrastructures, distributed processing frameworks, and ML methods, mapping out an end-to-end conceptual framework that can serve as a reference architecture for end-to-end deployment. Specifically, we discuss key aspects of big data analytics (storage solutions, platforms like Hadoop and Spark, NoSQL databases), preprocessing approaches (dimensionality reduction, instance selection, noise handling), ML algorithms (supervised, unsupervised, and emerging deep learning paradigms), and deployment considerations (monitoring, continuous integration, and versioning). By gathering and integrating these elements, our survey provides a comprehensive overview of existing solutions, clarifies the design choices developers must consider, and identifies research gaps that remain to be addressed.

关键词：

来源：评论

学校读者我要写书评

暂无评论

QCRMut: Quantum Circuit Random Mutant generator tool

arXiv

引用

arXiv 2024年

作者： Gil, Sinhué García Díaz, Luis Llana Jarabo, José Ignacio Requeno Dept. of Information Systems and Computing Faculty of Computer Engineering Complutense University of Madrid Madrid Spain

Quantum computing has been on the rise in recent years, evidenced by a surge in publications on quantum software engineering and testing. Progress in quantum hardware has also been notable, with the introduction of impressive systems like Condor boasting 1121 qubits, and IBM Quantum System Two, which employs three 133-qubit Heron processors. As this technology edges closer to practical application, ensuring the efficacy of our software becomes imperative. Mutation testing, a well-established technique in classical computing, emerges as a valuable approach in this context. In our paper, we aim to introduce QCRMut, a mutation tool tailored for quantum programs, leveraging the inherent Quantum Circuit structure. We propose a randomised approach compared to previous works with exhaustive creation processes and the capability for marking immutable positions within the circuit. These features facilitate the preservation of program structure, which is crucial for future applications such as metamorphic testing. © 2024, CC BY-NC-SA.

关键词： Application programs

来源：评论

学校读者我要写书评

暂无评论

Enhancing face recognition performance: a comprehensive evaluation of deep learning models and a novel ensemble approach with hyperparameter tuning

引用

Soft Computing 2024年第20期28卷 12399-12424页

作者： Selvaganesan, Jana Sudharani, B. Shekhar, S. N. Chandra Vaishnavi, K. Priyadarsini, K. Raju, K. Srujan Rao, T. Srinivasa Department of Electronics and Communication Engineering Vel Tech Rangarajan Dr. Sagunthala R & ampD Institute of Science and Technology Avadi Tamil Nadu Chennai600062 India Guntur Dist. Andhra Pradesh Vadlamudi India Department of Electronics and Communication Engineering Sreenidhi Institute of Science and Technology Telangana Hyderabad501301 India Department of Computer Science and Engineering Sona College of Technology Tamil Nadu Salem636005 India Department of Data Science and Business Systems School of Computing Faculty of Engineering and Technology SRM Institute of Science and Technology Tamil Nadu Kattankulathur603203 India Department of Computer Science and Engineering CMR Technical Campus Medchal Telangana Hyderabad501401 India Department of Electronics and Communication Engineering Aditya Engineering College Surampalem533437 India

In response to growing security concerns and the increasing demand for face recognition (FR) technology in various sectors, this research explores the application of deep learning techniques, specifically pre-trained Convolutional Neural Network (CNN) models, in the field of FR. The study harnesses the power of five pre-trained CNN models—DenseNet201, ResNet152V2, MobileNetV2, SeResNeXt, and Xception—for robust feature extraction, followed by SoftMax classification. A novel weighted average ensemble model, meticulously optimized through a grid search technique, is introduced to augment feature extraction and classification efficacy. Emphasizing the significance of robust data pre-processing, encompassing resizing, data augmentation, splitting, and normalization, the research endeavors to fortify the reliability of FR systems. Methodologically, the study systematically investigates hyperparameters across deep learning models, fine-tuning network depth, learning rate, activation functions, and optimization methods. Comprehensive evaluations unfold across diverse datasets to discern the effectiveness of the proposed models. Key contributions of this work encompass the utilization of pre-trained CNN models for feature extraction, extensive evaluation across multiple datasets, the introduction of a weighted average ensemble model, emphasis on robust data pre-processing, systematic hyperparameter tuning, and the utilization of comprehensive evaluation metrics. The results, meticulously analyzed, unveil the superior performance of the proposed method, consistently outshining alternative models across pivotal metrics, including Recall, Precision, F1 Score, Matthews Correlation Coefficient (MCC), and Accuracy. Notably, the proposed method attains an exceptional accuracy of 99.48% on the labeled faces in the wild (LFW) dataset, surpassing erstwhile state-of-the-art benchmarks. This research represents a significant stride in FR technology, furnishing a dependable and accurate

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

CAMRI Loss: Improving the Recall of a Specific Class without Sacrificing Accuracy

CAMRI Loss: Improving the Recall of a Specific Class without...

引用

作者： Nishiyama, Daiki Fukuchi, Kazuto Akimoto, Youhei Sakuma, Jun Master's Program in Computer Science Degree Programs in Systems and Information Engineering Graduate School of Science and Technology University of Tsukuba Tsukuba-shi305-8577 Japan RIKEN Center for Advanced Intelligence Project Tokyo103-0027 Japan Department of Computer Science Faculty of Engineering Information and Systems University of Tsukuba Tsukuba-shi305-8577 Japan

In real world applications of multiclass classification models, misclassification in an important class (e.g., stop sign) can be significantly more harmful than in other classes (e.g., no parking). Thus, it is crucial to improve the recall of an important class while maintaining overall accuracy. For this problem, we found that improving the separation of important classes relative to other classes in the feature space is effective. Existing methods that give a class-sensitive penalty for cross-entropy loss do not improve the separation. Moreover, the methods designed to improve separations between all classes are unsuitable for our purpose because they do not consider the important classes. To achieve the separation, we propose a loss function that explicitly gives loss for the feature space, called class-sensitive additive angular margin (CAMRI) loss. CAMRI loss is expected to reduce the variance of an important class due to the addition of a penalty to the angle between the important class features and the corresponding weight vectors in the feature space. In addition, concentrating the penalty on only the important class hardly sacrifices separating the other classes. Experiments on CIFAR-10, GTSRB, and AwA2 showed that CAMRI loss could improve the recall of a specific class without sacrificing accuracy. In particular, compared with GTSRB's second-worst class recall when trained with cross-entropy loss, CAMRI loss improved recall by 9%. © 2023 The Institute of Electronics, Information and Communication Engineers.

关键词： Deep 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：