检索结果-内蒙古大学图书馆

SSRN 2023年

作者： Siddiqui, Maraj Uddin Ahmed Arfeen, Asad National Center for Cyber Security NED University of Engineering and Technology Karachi75270 Pakistan Computer and Information Systems Engineering NED University of Engineering and Technology Karachi75270 Pakistan

The modern wireless ecosystem requires new radio accessing techniques as well as modification in conventional frameworks to readily enable 5G and beyond (B5G) (also referred to as sixth-generation (6G)) mobile communication. Massive multiple-input-multiple-output (M-MIMO) is one of the promising B5G networks technology that groups small-size antenna elements at both the transmitter and receiver sides and uses an uncomplicated signaling processing method. Along with M-MIMO, sub-millimeter wave, hybrid beamforming, tera-hertz, and artificial intelligence are also regarded as the principal technologies for supporting different wireless service classes and use cases in B5G/6G networks. Recently, numerous studies have been performed on the viability, processing, computing, and intelligent learning methods of contemporary technologies. Likewise, it is prudent to completely understand and realize the importance of collaborative operation of conventional and modern radio accessing methods to make the forthcoming user/machine-centric networks stringent. In this review article, we present a detailed description of the combined operation of different wireless enabling technologies for B5G/6G networks, highlighting the M-MIMO antenna system. We also discuss the issues restricted in the full-potential operation of modern accessing schemes with the healthy approaches proposed by the researchers lately in the literature. Open issues and future research directions are also delineated to shed light on the necessary steps for achieving future indispensable discoveries. © 2023, The Authors. All rights reserved.

关键词： MIMO systems

来源：评论

学校读者我要写书评

暂无评论

An Automated Deep Neural Network (DNN) and Support Vector Machine (SVM) Model for Facial Emotion Classification

An Automated Deep Neural Network (DNN) and Support Vector Ma...

引用

Research Methodologies in Knowledge Management, Artificial Intelligence and Telecommunication engineering (RMKMATE), International Conference on

作者： Jagadish S Kallimani Rajeshwari S B Asmathunnisa N Sanjeetha R Department of Artificial Intelligence and Machine Learning M S Ramaiah Institute of Technology Bangalore India Department of Information Science and Engineering M S Ramaiah Institute of Technology Bangalore India Department of Computer Science and Engineering M S Ramaiah Institute of Technology Bangalore India Visvesvaraya Technological University Belagavi Karnataka India Department of Computer Science and Engineering (Cyber Security) Sambhram Institute of Technology Bangalore India

ISBN: (数字)9798331598488

ISBN: (纸本)9798331598495

Facial emotion recognition (FER) is a main artificial intelligence (AI) technology that decodes and analyses emotional expressions on human faces utilizing computer vision methods. FER identifies and categorizes a wide range of emotions automatically utilizing machine learning (ML) models, particularly deep neural networks (DNN), such as surprise, pleasure, sorrow, rage, and others. Dealing using variances in lighting, locations, and facial expressions is one of the challenges of FER, as is ensuring that the method simplifies adequately to various emotions and populations. This study proposes a simple DNN-SVM automatic method as a potential solution to FER. The method extracts features utilizing a DNN, pre-processes images utilizing certain methodologies, and then classifies them utilizing a Support Vector Machine (SVM). The input images are first pre-processed utilizing face detection, histogram equalization, gamma correction, and scaling methods. Second, the images are processed utilizing custom single DNNs to extract deep features. Finally, SVM classifies the resulting features. The experiment shows that the suggested structure, which uses an ensemble of DL methods, outperforms a single model. In summary, the suggested model will improve the efficacy of FER classification outcomes and solve FER2013 with 98.85% accuracy, while also managing imbalanced datasets and multi-class classification, making it suitable for use in online learning applications.

关键词： Support vector machines Emotion recognition Accuracy Computational modeling Psychology Artificial neural networks Machine learning Feature extraction Robustness Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Multi-Objective Discrete Extremal Optimization of Variable-Length Blocks-Based CNN by Joint NAS and HPO for Intrusion Detection in IIoT

引用

IEEE Transactions on Dependable and Secure Computing 2025年

作者： Lu, Kang-Di Huang, Jia-Cheng Zeng, Guo-Qiang Chen, Min-Rong Geng, Guang-Gang Weng, Jian Donghua University College of Information Science and Technology Shanghai201620 China Jinan University College of Cyber Security The National Joint Engineering Research Center of Network Security Detection and Protection Technology Guangzhou510632 China South China Normal University School of Computer Science Guangzhou510631 China

Industrial Internet of Things (IIoT) is an important part of industrial infrastructure but facing serious and evolving security threats in recent years. Deep learning has been widely considered as a promising solution for enhancing the security of IIoT. However, these existing deep learning models utilized in the intrusion detection of IIoT are manually developed that not only greatly rely on the experience of the designers but also is lack of utility due to the high model complexity. By taking into account the trade-off between the model performance and model complexity, this paper makes the first attempt to propose a multi-objective joint optimization method of neural architecture search (NAS) and hyper-parameter optimization (HPO) based on multi-objective discrete extremal optimization (MODEO) to automatically design a lightweight convolutional neural network (CNN) for the intrusion detection task of IIoT, abbreviated as MODEO-CNN. A novel hybrid variable-length encoding strategy is developed by combing binary and integer encoding to characterize both the neural architectures including the number of blocks, the blocks-based network topology and the corresponding architecture parameters in CNN block, and some important hyper-parameters including batch size, learning rate, weight optimizer and regularization. The individual-based discrete multi-objective evolutionary process of MODEO is designed to obtain the Pareto-optimal CNN models. Three widely-used IIoT intrusion detection datasets, including the Gas Pipeline, BoT-IoT, and Power System Attack datasets, have been used to illustrate the superiority of the proposed MODEO-CNN over the state-of-the-art hand-craft models and two single-objective fixed-length blocks-based NAS models in terms of accuracy, precision, recall, F1-Score, and model's million floating point operations. © 2004-2012 IEEE.

关键词： Encoding (symbols)

来源：评论

学校读者我要写书评

暂无评论

An Efficient Medical Image Deep Fusion Model Based on Convolutional Neural Networks

引用

computers, Materials & Continua 2023年第2期74卷 2905-2925页

作者： Walid El-Shafai Noha A.El-Hag Ahmed Sedik Ghada Elbanby Fathi E.Abd El-Samie Naglaa F.Soliman Hussah Nasser AlEisa Mohammed E.Abdel Samea Department of Electronics and Electrical Communications Engineering Faculty of Electronic EngineeringMenoufia UniversityMenouf32952Egypt Security Engineering Laboratory Department of Computer SciencePrince Sultan UniversityRiyadh11586Saudi Arabia Higher Institute of Commercial Science Management Information SystemsEl-Mahala El-KobraEgypt Department of the Robotics and Intelligent Machines Faculty of Artificial IntelligenceKafrelsheikh UniversityKafr El-SheikhEgypt Department of Industrial Electronics and Control Engineering Faculty of Electronic EngineeringMenoufia UniversityMenouf32952Egypt Department of Information Technology College of Computer and Information SciencesPrincess Nourah Bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Computer Sciences College of Computer and Information SciencesPrincess Nourah Bint Abdulrahman UniversityRiyadhSaudi Arabia Medical Imaging and Interventional Radiology National Liver InstituteMenoufia UniversityEgypt

Medical image fusion is considered the best method for obtaining one image with rich details for efficient medical diagnosis and *** learning provides a high performance for several medical image analysis *** paper proposes a deep learning model for the medical image fusion *** model depends on Convolutional Neural Network(CNN).The basic idea of the proposed model is to extract features from both CT and MR ***,an additional process is executed on the extracted *** that,the fused feature map is reconstructed to obtain the resulting fused ***,the quality of the resulting fused image is enhanced by various enhancement techniques such as Histogram Matching(HM),Histogram Equalization(HE),fuzzy technique,fuzzy type,and Contrast Limited Histogram Equalization(CLAHE).The performance of the proposed fusion-based CNN model is measured by various metrics of the fusion and enhancement *** realistic datasets of different modalities and diseases are tested and ***,real datasets are tested in the simulation analysis.

关键词： Image fusion CNN deep learning feature extraction evaluation metrics medical diagnosis

来源：评论

学校读者我要写书评

暂无评论

CervixMed: Detecting Cervical Cancer based on combinational data using Hybrid architecture

CervixMed: Detecting Cervical Cancer based on combinational ...

引用

2023 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2023

作者： Gupta, Debashis Golder, Aditi Haque, Md. Mahfuzul Moni, Mohammad Ali Wake Forest University Department of Computer Science NC United States Jahangirnagar University Institute of Information Technology Dhaka Bangladesh Bangladesh Army University of Science and Technology Department of Computer Science and Engineering Saidpur Bangladesh Charles Stuart University Ai and Cyber Futures Institute BathurstNSW2795 Australia

ISBN: (纸本)9798350382204

Cervical cancer is women's second most frequent malignancy globally, with a 60% mortality rate. Early identification through routine checkups is crucial because cervical cancer has a long latent period and begins with no overt signs. One of the most evident barriers to not having an early detection is the time required for the diagnostic process, which also accounts for indifference regarding its automation. These uncertainties occur for several reasons, while one of the most prominent causes is providing the report by the computer-aided diagnostic process only based on the patient's information in tabular form or only predicting the patient's cervix image. In this study, we proposed three concepts 1. Hybrid Architecture, 2. CervixMed, a novel CNN-based architecture, and 3. GUI (Graphical User Interface). In Hybrid Architecture, we propose a methodology that takes both types of data, i.e., tabular and image, and then merges the prediction provided by the models and shows the final output. For tabular data classification, we use traditional-machine learning models like KNN, SVM, LR, and RF, where LR and SVM provided the best accuracy of 99%. On the other hand, the image data is classified into one of the five categories using our novel lightweight CNN-based architecture, CervixMed, that outperforms other pre-trained models like DenseNet121, DenseNet169, DenseNet201, ResNetl52v2, and VGG19 by 94% in accuracy and 98% in sensitivity. The hybrid architecture combines the abovementioned models and chooses the best pair regarding accuracy. In this study, we demonstrated that combining LR and SVM with CervixMed outperforms the other combinations by 96.5% accuracy. Lastly, we demonstrated the methodology of the proposed GUI for interacting with the end-users with this hybrid model. © 2023 IEEE.

关键词： Graphical user interfaces

来源：评论

学校读者我要写书评

暂无评论

Assessing Chronic Kidney Disease Prediction Models: A Comparative Analysis of Smart AI and Intelligent Machine Learning Approaches

Assessing Chronic Kidney Disease Prediction Models: A Compar...

引用

Advancements in Smart, Secure and Intelligent Computing (ASSIC), International Conference on

作者： Smit Thacker Ravirajsinh Vaghela Computer Engineering Gujarat Technological University (GTU) Ahmedabad India Department of Cyber Security and Digital Forensic National Science Forensic University Gandhinagar India

Millions of individuals worldwide suffer from chronic kidney disease (CKD). Early identification and treatment prevent CKD and improve patient outcomes. Machine learning can analyze enormous volumes of medical data and find patterns that could help detect CKD early. The current study uses a massive dataset of clinical records, laboratory test results, and patient demographics. Feature selection and data processing improve data integrity. LR, SVM, RF, and deep neural networks have been built and tested using the dataset. Sensitivity, AUC-ROC, Accuracy, and specificity are used to evaluate CKD model performance. The results show that machine learning algorithms can accurately identify early CKD risk factors. Future studies may combine real-time data streams with personalized patient data to increase CKD detection algorithms' accuracy and therapeutic value.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Facial Image Recognition Using Transfer Learning: A Brief Review

Facial Image Recognition Using Transfer Learning: A Brief Re...

引用

International Conference on Information and Communication Systems (ICICS)

作者： Omar Banimelhem Baghdad Al-Khateeb Department of Network Engineering and Security Jordan University of Science and Technology Irbid Jordan Department of Computer Engineering Jordan University of Science and Technology Irbid Jordan

ISBN: (数字)9798331540760

ISBN: (纸本)9798331540777

Accurate image recognition plays a pivotal role in a wide range of industrial applications. One domain of these applications is facial image recognition. Recently, deep learning (DL) models, which provides high efficiency and accuracy, have been utilized in facial image recognition applications. However, DL-based solutions in such applications need huge amount of data for training the model which will result in increasing the learning duration. Recently, the emergence of transfer learning (TL) has become an innovative solution in enhancing and improving the learning process in developing the machine learning (ML) models for facial image recognition-based applications. optimization of such *** is a kind of DL models which guarantee enhancements in the learning process where the TL-based models don’t need to start the training process from scratch. Moreover, TL ensures effective use of limited data by leveraging pre-trained models and start the learning process from a certain level. Therefore, TL developers can create accurate and powerful AI solutions faster and with fewer resources. This paper presents a brief review for the recently published works in the field of facial image recognition based on transfer learning. The review shows a description of the dataset used in the training process, methodology, and the performance results of each work. Moreover, it highlights the challenges of using TL in facial image recognition-based applications. Some future work directions are also presented in the paper.

关键词： Training Surveys Analytical models Image recognition Accuracy Reviews Face recognition

来源：评论

学校读者我要写书评

暂无评论

Deep-Based Hybrid Model For Enhancing Land Region Prediction Outcomes

Deep-Based Hybrid Model For Enhancing Land Region Prediction...

引用

Emerging Research in Computational Science (ICERCS), International Conference on

作者： Selvapandian D Laxmi Raja Tharageswari K Senthilkumar VM Nikitha JC Hemalatha M Department of Computer Science and Engineering Faculty of Engineering Karpagam Academy of Higher Education Coimbatore India Department of Cyber Security Faculty of Engineering Karpagam Academy of Higher Education Coimbatore India Department of Information Technology Mahendra Institute of Technology Namakkal India Department of Information Technology Nandha Arts and Science College Erode India

ISBN: (数字)9798331534967

ISBN: (纸本)9798331534974

Although satellite data is not a novel approach to mapping wetlands, its accuracy depends on data quality and categorization algorithms, making it a continuous challenge. The increasing accessibility of satellite data and the development of data modelling technologies, such as big data modelling using machine learning (ML) algorithms, have improved the accuracy of this type of mapping. Our work demonstrated a simple, scalable, and reliable wetland classification using linear Support Vector Machine (l-SVM) and unsupervised k-Nearest Neighbor (k-NN) machine learning approaches. Normalized difference vegetation index (NDVI) and normalized difference water index (NDWI), the two primary inputs were modelled using Landsat optical data. Subsequently, l-SVM was used to supervise k-NN data using training data collected from outside observations. The accuracy test results indicate that there is a considerable reduction in error for both optical indices, and all prediction models have an accuracy of about 99%.

关键词： Accuracy Normalized difference vegetation index Satellites Machine learning algorithms Normalized difference water index Predictive models Data models Probability distribution Optical sensors Wetlands

来源：评论

学校读者我要写书评

暂无评论

Knee Osteoarthritis Detection Using X-Rays and DNN

Knee Osteoarthritis Detection Using X-Rays and DNN

引用

Applied Artificial Intelligence and Computing (ICAAIC), International Conference on

作者： Vaishnawi Sinha Ebenezer Veemaraj Division of Computer Science and Engineering Karunya Institute of Technology and Sciences Coimbatore Tamil Nadu Division of Data Science and Cyber Security Karunya Institute of Technology and Sciences) Coimbatore Tamil Nadu

ISBN: (数字)9798350375190

ISBN: (纸本)9798350375206

Knee osteoarthritis (OA) is a prevalent degenerative joint disease that affects millions worldwide, leading to pain, disability, and reduced quality of life. Early detection and intervention are crucial for effective management and prevention of disease progression. In this paper, we propose a novel approach for knee OA detection using X-ray images and deep neural networks (DNNs). Specifically, we investigate the performance of two popular DNN architectures: EfficientNet-B5 and DenseNet121. We begin by pre-processing a dataset of knee X-ray images to extract relevant features and mitigate noise. Subsequently, we fine-tune the pre-trained EfficientNet-B5 and DenseNet121 models using transfer learning techniques to adapt them to the task of knee OA detection. We then evaluate and compare the performance of these models in terms of accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC-ROC). Our experimental results demonstrate the efficacy of both EfficientNet-B5 and DenseNet121 architectures in knee OA detection, outperforming traditional machine learning approaches. However, we observe variations in their performance metrics, indicating nuanced differences in their ability to capture and discriminate pathological features in knee X-ray images. Furthermore, we conduct an in-depth analysis to understand the factors contributing to the performance disparities between the two models. Overall, our study contributes to the growing body of research aimed at leveraging DNNs for medical image analysis tasks, particularly in the domain of musculoskeletal disorders. The insights gained from this research can potentially aid clinicians in early diagnosis and personalized treatment planning for knee OA patients, ultimately improving patient outcomes and healthcare efficiency.

关键词： Adaptation models Image analysis Sensitivity Transfer learning Artificial neural networks Feature extraction Task analysis

来源：评论

学校读者我要写书评

暂无评论

Unlearnable 3D point clouds: class-wise transformation is all you need 24

Unlearnable 3D point clouds: class-wise transformation is al...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Xianlong Wang Minghui Li Wei Liu Hangtao Zhang Shengshan Hu Yechao Zhang Ziqi Zhou Hai Jin National Engineering Research Center for Big Data Technology and System and Services Computing Technology and System Lab and Hubei Engineering Research Center on Big Data Security and Hubei Key Laboratory of Distributed System Security and School of Cyber Science and Engineering Huazhong University of Science and Technology School of Software Engineering Huazhong University of Science and Technology Hubei Engineering Research Center on Big Data Security and Hubei Key Laboratory of Distributed System Security and School of Cyber Science and Engineering Huazhong University of Science and Technology National Engineering Research Center for Big Data Technology and System and Services Computing Technology and System Lab and Cluster and Grid Computing Lab and School of Computer Science and Technology Huazhong University of Science and Technology

ISBN: (纸本)9798331314385

Traditional unlearnable strategies have been proposed to prevent unauthorized users from training on the 2D image data. With more 3D point cloud data containing sensitivity information, unauthorized usage of this new type data has also become a serious concern. To address this, we propose the first integral unlearnable framework for 3D point clouds including two processes: (i) we propose an unlearnable data protection scheme, involving a class-wise setting established by a category-adaptive allocation strategy and multi-transformations assigned to samples; (ii) we propose a data restoration scheme that utilizes class-wise inverse matrix transformation, thus enabling authorized-only training for unlearnable data. This restoration process is a practical issue overlooked in most existing unlearnable literature, i.e., even authorized users struggle to gain knowledge from 3D unlearnable data. Both theoretical and empirical results (including 6 datasets, 16 models, and 2 tasks) demonstrate the effectiveness of our proposed unlearnable framework. Our code is available at https://***/CGCL-codes/UnlearnablePC.

关键词：

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：