检索结果-内蒙古大学图书馆

3rd International Conference on Emerging Smart Technologies and Applications, eSmarTA 2023

作者： Saeed, Mamoon M. Rashad Mohammed, Husam Nedhal Hazaea Gazem, Othman Abdulkafi Saeed, Rashid A. Ahmed Morei, Hossam Mohammed Thabet Eidah, Aimen Ebdulkreem Gaid, AbdulGuddoos S.A. Ameen Saif Al-Uosfi, Ameen Sami Qasem Al-Madhagi, Mohamed Galal Faculty of Engineering Department of Communications and Electronics Engineering Yemen College of Computers and Information Technology Taif University Department of Computer Engineering Taif21944 Saudi Arabia Taiz University Faculty of Engineering & Information Technology Dept. of Communication & Computer Engineering Taiz Yemen

ISBN: (纸本)9798350305333

The development witnessed by the world of science and technology and the emergence of the Internet, where cybersecurity has become one of the most important areas that are growing rapidly every day, and one of its goals is to maintain access to users at any time. Where it is noted that the biggest enemy for the availability is Distributed Denial of Service (DDoS) attack, which works to prevent access to the service and slow down the service. Through this paper, machine learning will be used to discover the DDoS attack and know its type to be aware of it and take the necessary measures for that. Where the CICDDoS2019 dataset will be used. After it is studied, analyzed, cleaned and the best algorithm was selected. Five classification algorithms (Random Forest, Decision Tree, SVM, Naive Bayes, and xgboost) were used to train and test the data from the datasets, and it can be said that of the five, Random Forest algorithms had the highest level of accuracy (99.95426%). © 2023 IEEE.

关键词： Denial-of-service attack

来源：评论

学校读者我要写书评

暂无评论

Unravelling stress levels in continuous speech through optimal feature selection and deep learning 2

Unravelling stress levels in continuous speech through optim...

引用

2nd International Conference on Machine Learning and Data engineering, ICMLDE 2023

作者： Duvvuri, Kavya Kanisettypalli, Harshitha Masabattula, Teja Nikhil Vekkot, Susmitha Gupta, Deepa Zakariah, Mohammed Department of Computer Science & Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Bengaluru India Department of Electronics & Communication Engineering Amrita School of Engineering Amrita Vishwa Vidyapeetham Bengaluru India Department of Computer Engineering College of Computer and Information Sciences King Saud University Riyadh Saudi Arabia

Stress is a psychological or emotional strain that occurs due to adverse experiences in human life. This paper showcases the application of deep learning in detecting stress levels in continuous audio signals in the Distress Analysis Interview Corpus Wizard of Oz (DAIC-WOZ) database. The features that have been experimented with are Gammatone Frequency Cepstral Coefficients (GFCC), Log Filter Bank (Log-Filter Bank), Mel Frequency Cepstral Coefficients (MFCC), chroma, and Linear Predictive Coding (LPC). Five deep learning models were evaluated: Long Short-Term Memory (LSTM), Convolutional Neural Network (CNN), Bidirectional LSTM (Bi-LSTM), k-fold CNN with the k value as 5, and a fusion model of CNN, LSTM, and attention. Upon evaluating the performance metrics of all the models, it is concluded that the k-fold CNN model with k as 5 performs well with continuous audio signals. The model has achieved an accuracy of 80% when it is trained on MFCC, GFCC, and Log-F Bank features which are observed to be the optimal features in the stress analysis. © 2024 Elsevier B.V.. All rights reserved.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Multilayer Neural Network Based Speech Emotion Recognition for Smart Assistance

引用

computers, Materials & Continua 2023年第1期74卷 1523-1540页

作者： Sandeep Kumar MohdAnul Haq Arpit Jain C.Andy Jason Nageswara Rao Moparthi Nitin Mittal Zamil S.Alzamil Department of Computer Science and Engineering Koneru Lakshmaiah Education FoundationVaddeswaramAP522502India Department of Computer Science College of Computer and Information SciencesMajmaah University11952Al-MajmaahSaudi Arabia Department of Computer Science and Engineering Teerthanker Mahaveer UniversityMoradabadUttar Pradesh244001India Department of Electronics and Communication Engineering Sreyas Institute of Engineering and TechnologyHyderabad500068India University Centre for Research and Development Chandigarh UniversityMohali140413PunjabIndia

Day by day,biometric-based systems play a vital role in our daily *** paper proposed an intelligent assistant intended to identify emotions via voice message.A biometric system has been developed to detect human emotions based on voice recognition and control a few electronic peripherals for alert *** proposed smart assistant aims to provide a support to the people through buzzer and light emitting diodes(LED)alert signals and it also keep track of the places like households,hospitals and remote areas,*** proposed approach is able to detect seven emotions:worry,surprise,neutral,sadness,happiness,hate and *** key elements for the implementation of speech emotion recognition are voice processing,and once the emotion is recognized,the machine interface automatically detects the actions by buzzer and *** proposed system is trained and tested on various benchmark datasets,i.e.,Ryerson Audio-Visual Database of Emotional Speech and Song(RAVDESS)database,Acoustic-Phonetic Continuous Speech Corpus(TIMIT)database,Emotional Speech database(Emo-DB)database and evaluated based on various parameters,i.e.,accuracy,error rate,and *** comparing with existing technologies,the proposed algorithm gave a better error rate and less *** rate and time is decreased by 19.79%,5.13 *** the RAVDEES dataset,15.77%,0.01 s for the Emo-DB dataset and 14.88%,3.62 for the TIMIT *** proposed model shows better accuracy of 81.02%for the RAVDEES dataset,84.23%for the TIMIT dataset and 85.12%for the Emo-DB dataset compared to Gaussian Mixture Modeling(GMM)and Support Vector Machine(SVM)Model.

关键词： Speech emotion recognition classifier implementation feature extraction and selection smart assistance

来源：评论

学校读者我要写书评

暂无评论

Classification of Bipolar Disorder Using Deep Learning Models on fMRI Data 1

引用

3rd International Conference on Innovations in Computational Intelligence and computer Vision, ICICV 2022

作者： Chauhan, Harsh Gadhiya, Poojan Sharma, Abhishek Department of Computer Science and Engineering The LNM Institute of Information Technology Rajasthan Jaipur302031 India Department of Electronics and Communication Engineering The LNM Institute of Information Technology Rajasthan Jaipur302031 India

ISBN: (数字)9789819926022

ISBN: (纸本)9789819926015

The use of functional magnetic resonance imaging (fMRI) has been widely used to detect brain abnormalities linked to Bipolar Disorder. These borderline diseases are either inherited or the result of parental exposure to great stress and worry during a child’s formative years. Using machine learning models to predict such diseases has been widely adopted, but deep learning models are gone unseen. Our experiments are conducted on fMRI datasets consisting of bipolar disorder subjects and other neuropsychiatric disease subjects. The fMRI data passes through a pipeline that preprocesses the image, extracts time series, and removes non-essential features before passing it to the deep learning models. Preprocessing is performed on FuNP software rather than normal software like fMRIprep. The preprocessed fMRI image is converted to a NIFT1 object that allows us to extract the time series of an image. Spatial maps of the time series reveal there are many irrelevant components not contributing to the training of our model, so feature selection was a necessary approach to reduce space as well as time. We find it by taking an average of all brain signals in all components of all Bipolar Subjects to estimate which brain signals affect which region of our brain. This helps us to pick out only the important components which will contribute to being an actual feature in our input. The features then come down to the two models ANN and LSTM. Results show that deep learning models like ANN are not too efficient with neuroinformatics diseases due to the low availability of datasets, but recurrent neural networks have proved to be efficient. The deep learning model achieves 72% accuracy in predicting the correct classes for the dataset. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2023.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

Improving Tomato Disease Diagnosis Through ResNet50: An Innovative Approach 4

Improving Tomato Disease Diagnosis Through ResNet50: An Inno...

引用

4th International Conference on Sustainable Expert Systems, ICSES 2024

作者： Dhamotharan, R. Raj, J. Relin Francis Krishnan, R. Santhana Kavitha, S. Soundiraraj, N. Kumar, V. Vinoth Kalasalingam Academy of Research and Education Department of Computer Science and Information Technology Krishnankoil India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Electronics and Communication Engineering Chennai India Scad College of Engineering and Technology Department of Electronics and Communication Engineering Cheranmahadevi India Velammal College of Engineering and Technology Department of Computer Science and Engineering Madurai India Psna College of Engineering and Technology Department of Electrical and Electronics Engineering Dindigul India Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Department of Electronics and Communication Engineering Chennai India

ISBN: (纸本)9798331540364

Tomato crops are vulnerable to numerous diseases that can severely affect both yield and quality. Early and precise identification of these diseases is indispensable for implementing active management and intervention measures. This research introduces an advanced approach to tomato disease detection by employing the ResNet50 architecture, pretrained on the ImageNet dataset. Through transfer learning, the ResNet50 model leverages its pre-learned features to classify tomato plant images affected by diseases such as Tomato Mosaic Virus (ToMV), Bacterial Spot, Blossom End Rot, Early Blight, and Late Blight. The ResNet50 model is fine-tuned with custom classification layers tailored to the specific diseases, allowing it to achieve high accuracy in disease detection. Preliminary results indicate that the ResNet50 model significantly outperforms traditional machine learning approaches, demonstrating its efficacy in accurately diagnosing tomato diseases. This study provides an effective solution for improving disease detection in tomatoes and highlights the transformative role of deep learning in advancing agricultural practices, fostering sustainability, and enhancing productivity. © 2024 IEEE.

关键词： Fruits

来源：评论

学校读者我要写书评

暂无评论

Lung Cancer Detection Through Filtration and Segmentation via Neural-Network 3

Lung Cancer Detection Through Filtration and Segmentation vi...

引用

3rd International Conference on Advancement in electronics and communication engineering, AECE 2023

作者： Raj, Mrinal Sahare, Parul Pandey, Nachiketa Kalinga Institute of Industrial Technology Department of Computer Science and Engineering Bhubaneswar India Indian Institutes of Information Technology Department of Electronics and Communication Engineering Nagpur India

ISBN: (纸本)9798350330724

Cancer is a threat in which the cell starts to grow abnormally and it does not function like a normal cell. When the cancerous cell begin to develop in lungs it is called as lung cancer. Lung cancer is one of the most significantly diagnosed form of *** is getting hard for many doctors to state the conclusion after looking at the Computed Tomography(CT) image. So, there is a need to detect lung cancer at an early stage possible. An improvised version of VGG-19 Model is proposed for detection of lung cancer in this paper. At first filtration an d segmentation of lesion from CT scan images of lungs is performed. Median and Gaussian filters a re included i n t he fi ltration me thod whereas, segmentation work involves the Gaussian mixture model, Fuzzy-C-Means and proposed mean-based segmentation. The proposed work is evaluated on the publically available Data Bowl 2017 database and compared with other state-of-the-art approaches. It is observed that in the filtration part, Gaussian filter provides the highest accuracy of 99.02% where as mean-based segmentation outperforms other methods with an accuracy of 94.13%. © 2023 IEEE.

关键词： computerized tomography

来源：评论

学校读者我要写书评

暂无评论

An authenticated spectrum acquirement and transmission of encrypted images over fusion centre

引用

Multimedia Tools and Applications 2024年 1-24页

作者： V, Thanikaiselvan Y, PiyaDessi S, Renuga devi Shanthini, S. Suba Mahalingam, Hemalatha S, Aashiq Banu R, Dhivya V.M, Padmapriya Amirtharajan, Rengarajan School of Electronics Engineering Vellore Institute of Technology Vellore Vellore India School of Information Technology Vellore Institute of Technology Vellore India Department of Electrical and Computer Engineering Faculty of Engineering King Abdulaziz University Jeddah22254 Saudi Arabia System Engineering Department Military Technological College Muscat Oman Department of Electronics and Communication Engineering Mepco Schlenk Engineering College Tamilnadu Sivakasi626005 India Department of Computer Sciences Marquette University MilwaukeeWI53233 United States School of Electrical & amp Electronics Engineering SASTRA Deemed University 613 401 Thanjavur India

These days, spectrum insufficiency is the most common issue. If the number of smartphone users who access the radio spectrum grows, the radio spectrum becomes increasingly scarce. Certain types of technology equipment are designed to work only within a specific spectrum range, and there is rivalry in specifications for various other applications. As a result, this paper effectively exploits a licensed user’s unused spectrum to reduce the crowded spectrum and eradicate the Radio spectrum shortage. Licensed primary users (PUs) and secondary users (SUs) would be accepted into a Fusion Centre (FC) based on a spectrum framework with authentication. The approved PUs begin by updating their information to FC1;thenceforth, encryption is performed on the information uploaded to FC1. This information from FC1 is stored in Cloud Storage after encryption using the Blowfish algorithm & De-oxy DNA, a fast encryption algorithm. Following that, FC2, connected to the same cloud environment, downloads the PU data uploaded. The spectrum is then allocated to the authenticated SU linked to FC2 based on signal conditions and priority. This proposed method also avoids any delay in the network and encryption by acquiring a fast encryption algorithm, making the system faster and avoiding the Primary User Emulation (PUE) attack. Later, the time taken for the Tiny Encryption Algorithm (TEA) and the Blowfish/DNA algorithm are compared to validate the run time for different input images. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Predicting Schizophrenia from fMRI Using Deep Learning 1

引用

3rd International Conference on Innovations in Computational Intelligence and computer Vision, ICICV 2022

作者： Kardani, Shail Sharma, Raghav Sharma, Abhishek Deparment of Computer Science Engineering The LNM Institute of Information Technology Rajasthan Jaipur302031 India Deparment of Electronics and Communication Engineering The LNM Institute of Information Technology Rajasthan Jaipur302031 India

ISBN: (数字)9789819926022

ISBN: (纸本)9789819926015

Schizophrenia is a complex and multifaceted disorder that is still not fully understood. However, many processes are known to drive its onset, relapse, symptomatology, and therapy. One possible explanation for Schizophrenia is that the person has difficulty using proper analytic methods to deal with the complexity and variety of the condition. Many AI algorithms have been designed and developed over time specifically for Neuroinformatics. These algorithms have been a go-to for many researchers and scientists, even for those in the medical field. Because of these AI-powered algorithms, Scientists are able to detect various diseases, whether they are related to brain activity or any other organs. Deep Learning is yet another field of Machine Learning which is made by the inspiration of how neural networks are connected inside our brain. These are more flexible than the Scikit-Learn-based Machine Learning models as these Deep Neural Network models don’t often require data preprocessing at initial stages. Not only this fact, but also they are used in various places, for example, processing of unstructured data, including texts and images, feature extraction, etc. In this study, we have attempted to detect Schizophrenia from resting-state functional magnetic resonance images using trained Deep Neural Networks as well as Scikit-Learn-based state-of-the-art Machine Learning models. For the dataset, we have utilized the public COBRE dataset available in the nilearn library, along with some public datasets from OpenfMRI. The Deep Learning models detected Schizophrenia with a reliable performance compared to Scikit-Learn-based Machine Learning models. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2023.

关键词： Magnetic resonance

来源：评论

学校读者我要写书评

暂无评论

QR Code Encryption for improving Bank information and Confidentiality 27

QR Code Encryption for improving Bank information and Confid...

引用

27th International Conference on information Technology, IT 2023

作者： Malallah, Fahad Layth Abduljabbar, Ali I. Shareef, Baraa T. Al-Janaby, Ali Othman Ninevah University College of Electronics Engineering Computer and Information Engineering Department Mosul41002 Iraq Ninevah University Computer Center Mosul41002 Iraq Ahlia University Department of Information Technology Collage of Information Technology Manama Bahrain Ninevah University College of Electronics Engineering Communication Department Mosul41002 Iraq

ISBN: (纸本)9798350397512

Nowadays, storing confidential documents using cloud services is getting popular due to advantages regarding security and fast processing operations. One of the major services of cloud computing is cloud storage, which is conversely raises some issues regarding information security. Storing information for cooperation such as a bank in the cloud needs a fast processing operation to avoid any bottleneck in the work procedure. Therefore, Quick Response (QR) code is highly required to be utilized in these operations. The advantage of the QR code is easier for reading information by just scanning using any reader available on smart devices. The methodology is to integrate the security with QR code to save the text bank information. This is done by converting text to the QR code as an image form, then applying a cryptography algorithm to the QR code image then upload it to the cloud storage. Later on, once the plaintext is required to be reconstructed, the same operations are applied exactly to the encryption phase. In which the same algorithm will be applied for decryption then a QR code reader is used to preview the target bank text. For security matters, a key is used to be embedded in the protection operation. The type of encryption is proposed to be a symmetric One-time-pad (OTP) cryptography algorithm. © 2023 IEEE.

关键词： Cloud storage

来源：评论

学校读者我要写书评

暂无评论

A Hybrid CNN-LSTM-PSO Framework for Enhanced Cybersecurity Threat Detection and Classification

A Hybrid CNN-LSTM-PSO Framework for Enhanced Cybersecurity T...

引用

2025 International Conference on Multi-Agent Systems for Collaborative Intelligence, ICMSCI 2025

作者： Akilandeswari, S. Soumya, T.R. Sumathi, S. Sushith, Mishmala Brinda, V. Rajan, S. E.G.S. Pillay Engineering College Department of Artificial Intelligence & Data Science Nagapattinam611002 India Prathyusha Engineering College Department of Computer Science Engineering Tiruvallur602025 India Velammal Engineering College Department of Electronics and Communication Engineering Chennai600066 India Adithya institute of Technology Department of Information Technology Kurumbapalayam India K.Ramakrishnan College Of Engineering Department of Electronics and Communication Engineering Samayapuram621112 India Velalar College of Engineering and Technology Department of Electronics and Communication Engineering Erode638012 India

ISBN: (纸本)9798331509828

With the advancement of digital era comes an increased value for cybersecurity, and these need to be dealt with using advanced techniques. Deep learning - metaheuristic optimization hybrid model for advanced threat detection and mitigation is presented in this paper. With a Convolutional Neural Network (CNN) for feature extraction and Long Short-Term Memory (LSTM) for sequence analysis, the proposed framework integrates all the modules in order to provide robust cyber-attack detection. In order to optimize the parameters of the model, a Particle Swarm Optimization (PSO) algorithm is used in order to achieve better classification accuracy and faster computation. Benchmark datasets are used for extensive experiments, where existing methods outperformed in terms of precision, recall, and Fl-score. The results demonstrate that with detected flagged FPs and the hybrid model, the increased detection rates are achieved without the reduction in true negatives, rendering it a practical solution for real world applications. This research adds to the field by providing a solution to cybersecurity problems that is scalable and adaptable to the present and beyond. © 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：