检索结果-内蒙古大学图书馆

Evaluation of Deep Learning Models for Person Authentication Based on Touch Gesture

computer systems science & engineering 2022年第8期42卷 465-481页

作者： Asrar Bajaber Mai Fadel Lamiaa Elrefaei Computer Science Department Faculty of Computing and Information TechnologyKing Abdulaziz UniversityJeddahSaudi Arabia Electrical Engineering Department Faculty of Engineering at ShoubraBenha UniversityCairo11629Egypt

Touch gesture biometrics authentication system is the study of user's touching behavior on his touch device to identify *** features traditionally used in touch gesture authentication systems are extracted using hand-crafted feature extraction *** this work,we investigate the ability of Deep Learning(DL)to automatically discover useful features of touch gesture and use them to authenticate the *** different models are investigated Long-Short Term Memory(LSTM),Gated Recurrent Unit(GRU),Convolutional Neural Network(CNN)combined with LSTM(CNN-LSTM),and CNN combined with GRU(CNN-GRU).In addition,different regularization techniques are investigated such as Activity Regularizer,Batch Normalization(BN),Dropout,and *** deep networks were trained from scratch and tested using TouchAlytics and BioIdent datasets for dynamic touch *** result reported in terms of authentication accuracy,False Acceptance Rate(FAR),False Rejection Rate(FRR).The best result we have been obtained was 96.73%,96.07%and 96.08%for training,validation and testing accuracy respectively with dynamic touch authentication system on TouchAlytics dataset with CNN-GRU DL model,while the best result of FAR and FRR obtained on TouchAlytics dataset was with CNN-LSTM were FAR was 0.0009 and FRR was *** BioIdent dataset the best results have been obtained was 84.87%,78.28%and 78.35%for Training,validation and testing accuracy respectively with CNN-LSTM *** use of a learning based approach in touch authentication system has shown good results comparing with other state-of-the-art using TouchAlytics dataset.

关键词： Touch authentication system touch gestures behavioral biometric deep learning classification CNN RNN LSTM

来源：评论

学校读者我要写书评

暂无评论

Enhanced Speech Emotion and Gender Recognition Using Hybrid CNN-LSTM Models 4

Enhanced Speech Emotion and Gender Recognition Using Hybrid ...

引用

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Priyadharshini, S. Sundar, G. Naveen Narmadha, D. Thangavel, Senthil Kumar Ajibesin, Adeyemi Abel Kolandapalayam Shanmugam, Selvanayaki Karunya Institute of Technology and Sciences Department of Computer Science and Engineering Coimbatore India Amrita School of Computing Department of Computer Science and Engineering Coimbatore India Cape Peninsula University of Technology Faculty of Informatics and Design Department of Information Technology South Africa Ashland University Department of Mathematics and Computer Science United States

ISBN: (纸本)9798331523923

The current paper proposes a new approach for peripheral speech emotion analysis and gender estimation incorporating the best machine learning architectures such as CNNs and LSTMs. Its correct depiction of emotions and the variation of the gendered speech to indicate manifold signal-to-noise ratio make the approach accommodate the difficulty inherent in recognizing emotions from the recording of voices as well as predicting the gender of a speaker. It is then able to ally with preprocessing and collection of a vast range of different speech samples, feature extraction of pitch, tone and spectral data. These features serve as input to the CNNs and LSTMs: LSTMs work well at temporal regular features and the CNNs work well in feature extraction by location (spatio feature). The approach is tested on the RAVDESS and IEMOCAP datasets and establishes a near perfect match to prior approaches with reference to recognition accuracy of emotion analysis and gender prediction. Thus, applying the identified dual method approach, which could be described by such characteristics as highly accurate data pre-preprocessing, clear indication of the features of interest, a different CNN-LSTM model joint training, it offers a reasonably good platform to gain certain insights into such characteristics of the speech as our experiment demonstrates. This work offers satisfactory configurations on concerns such as human computer relation, customer relation and mental health surveillance to suggest that other applications could be achieved in future. © 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

Leveraging AI to Unlock the Potential of Data science 15

Leveraging AI to Unlock the Potential of Data Science

引用

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

作者： Yadav, Rakesh Kumar Sudhamsu, Gadug Goyal, Manish Kumar Yuvaraj, S. Deshpande, Leena A. Maharishi University of Information Technology Maharishi School of Engineering and Technology Uttar Pradesh India Faculty of Engineering and Technology Department of Computer Science and Engineering Karnataka Bangalore India Vivekananda Global University Department of Computer Science & Application Jaipur India Prince Shri Venkateshwara Padmavathy Engineering College Department of Electronics and Communication Engineering Chennai127 India Vishwakarma Institute of Technology Department of Computer Engineering Pune India

ISBN: (纸本)9798350370249

The application of synthetic Intelligence (AI) to records science has spread out a massive array of new possibilities. Via the combination of advanced evaluation strategies, effective understanding-pushed system gaining knowledge of algorithms, and modern computing architectures, AI is allowing researchers to quick and as it should be discover insights from huge and complicated datasets. Furthermore, AI tools are offering corporations with the ability to make higher and more knowledgeable choices from the evaluation of hundreds of thousands of statistics points. The skills of information technology powered by means of AI are revolutionizing industries which includes healthcare, finance, and manufacturing-producing savings, uncovering efficiencies, and identifying new opportunities. As AI-driven records technology maintains to strengthen, organizations that capitalize on its ability stand to gain precious insights and unlock new degrees of overall performance. © 2024 IEEE.

关键词： Smart manufacturing

来源：评论

学校读者我要写书评

暂无评论

Investigating the Ethical Implications of Artificial Intelligence and Establishing Guidelines for Responsible AI Development

Investigating the Ethical Implications of Artificial Intelli...

引用

2024 International Conference on Advances in Computing Research on science engineering and Technology, ACROSET 2024

作者： Sukumar, R. Gambhir, Vinima Seth, Jyoti Faculty of Engineering and Technology Department of Electronics and Communication Engineering Bangalore India Atlas SkillTech University Department of Isme Mumbai India Vivekananda Global University Department of Computer Science & Engineering Jaipur India

ISBN: (纸本)9798350388800

Now more than ever, artificial intelligence (AI) presents both unprecedented potential and difficulties. This article delves deeply into the ethical concerns raised by AI and lays forth principles that should be followed in the creation of ethical AI systems. In the opening, we recognize the revolutionary potential of AI as well as the ethical quandaries it poses. In order to guarantee that AI technologies are created and implemented in a responsible and fair way, a deep ethical examination is required in light of the proliferation of autonomous systems. To address these ethical difficulties, we suggest the adoption of an Ethical Analysis Framework (EAF). The Ethical Assessment Framework (EAF) provides a framework for systematically assessing the fairness, transparency, privacy, accountability, and bias of AI systems. It's a cornerstone for the community of AI ethics researchers, developers, and policymakers working together to keep AI honest. Our approach places special importance on the gathering and preparation of data. We emphasize how important ethically sound data is in defining the moral implications of AI. We found that when compared to other approaches to assessing the morality of AI, our suggested technique consistently outperformed the others. The suggested technique establishes itself as an innovative and effective way of navigating the growing ethical environment by providing a systematic approach to addressing AI's ethical implications and supporting responsible AI research. For instance, as compared to more conventional methods, our technique increased fairness evaluations by an average of 15%. In conclusion, there is a wide range of concerns related to the morality of AI that must be constantly monitored and addressed via joint effort. Our method places an emphasis on making sure AI is progressing in a way that is responsible, ethical, and fair to all members of society. © 2024 IEEE.

关键词： Ethical technology

来源：评论

学校读者我要写书评

暂无评论

Distance-based mutual congestion feature selection with genetic algorithm for high-dimensional medical datasets

引用

Neural Computing and Applications 2025年第8期37卷 6217-6232页

作者： Nematzadeh, Hossein Mani, Joseph Nematzadeh, Zahra Akbari, Ebrahim Mohamad, Radziah Modern College of Business and Science Muscat Oman Department of Electrical Engineering and Computer Science Florida Institute of Technology MelbourneFL32901 United States Otolaryngology Department School of Medicine Emory University AtlantaGA30322 United States Department of Computer Engineering Sari Branch Islamic Azad University Sari Iran Faculty of Computing Universiti Teknologi Malaysia Skudai81310 Malaysia

Abstract: Feature selection poses a challenge in high-dimensional datasets, where the number of features exceeds the number of observations, as seen in microarray, gene expression, and medical datasets. There is not a universally optimal feature selection method applicable to any data distribution, and as a result, the literature consistently endeavors to address this issue. One recent approach in feature selection is termed frequency-based feature selection. However, existing methods in this domain tend to overlook feature values, focusing solely on the distribution in the response variable. In response,this paper introduces the Distance-based Mutual Congestion (DMC) as a filter method that considers both the feature values and the distribution of observations in the response variable. DMC sorts the features of datasets, and the top 5% are retained and clustered by KMeans to mitigate multicollinearity. This is achieved by randomly selecting one feature from each cluster. The selected features form the feature space, and the search space for the Genetic Algorithm with Adaptive Rates (GAwAR) will be approximated using this feature space. GAwAR approximates the combination of the top 10 features that maximizes prediction accuracy within a wrapper scheme. To prevent premature convergence, GAwAR adaptively updates the crossover and mutation rates. The hybrid DMC-GAwAR is applicable to binary classification datasets, and experimental results demonstrate its superiority over some recent works. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

An energy-aware routing scheme based on a virtual relay tunnel in flying ad hoc networks

引用

Alexandria engineering Journal 2024年 91卷 249-260页

作者： Hosseinzadeh, Mehdi Ali, Saqib Mohammed, Adil Hussein Lansky, Jan Mildeova, Stanislava Yousefpoor, Mohammad Sadegh Yousefpoor, Efat Hassan Ahmed, Omed Rahmani, Amir Masoud Mehmood, Asif Institute of Research and Development Duy Tan University Da Nang Viet Nam School of Medicine and Pharmacy Duy Tan University Da Nang Viet Nam Department of Information Systems College of Economics and Political Science Sultan Qaboos University Al Khoudh Muscat Oman Department of Communication and Computer Engineering Faculty of Engineering Cihan University-Erbil Kurdistan Region Iraq Department of Computer Science and Mathematics Faculty of Economic Studies University of Finance and Administration Prague Czech Republic Department of Computer Engineering Dezful Branch Islamic Azad University Dezful Iran Department of Information Technology University of Human Development Sulaymaniyah Iraq Future Technology Research Center National Yunlin University of Science and Technology Yunlin Taiwan Department of Biomedical Engineering Gachon University Gyeonggi-do Seongnam-si13120 Korea Republic of

Flying ad hoc networks (FANETs) tackle diverse challenges, for example, dynamic topological structure, high mobility of nodes, low density, and energy restrictions. These challenges make problems in designing reliable and stable routing in FANETs. Hence, the design of a routing algorithm is essential for transferring data between drones. In this paper, an energy-aware routing scheme based on a virtual relay tunnel (EARVRT) is proposed in flying ad hoc networks. EARVRT includes a virtual relay tunnel (VRT) that manages relay nodes in the route discovery process and lowers network overhead. Moreover, three metrics, namely route energy, hop counts, and a new metric called path correlation are regarded in the path selection operation. Note that correlation is defined with regard to two scales, including the cosine similarity of two nodes and their distance. EARVRT is evaluated according to delay, network longevity, consumed energy, and packet delivery rate. Then, our scheme is compared with three methods, namely LoCaL, O-LAR, and PSO-GLFR. These results show the superiority and success of EARVRT in comparison with other algorithms. © 2024 The Author(s)

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

Convolutional Neural Network-based image tamper detection with Error Level Analysis 2

Convolutional Neural Network-based image tamper detection wi...

引用

2nd IEEE International Conference on Intelligent and Innovative Technologies in Computing, Electrical and Electronics, ICIITCEE 2024

作者： Manjunatha, S. Swetha, M.D. Rashmi, S. Subramanian, Ananda Kumar Vinoth Kumar, V. Mallikarjuna Swamy, S. Global Academy of Technology Department of Information Science and Engineering Bengaluru India BNM Institute of Technology Department of Computer Science and Engineering Bengaluru India Bengaluru India Vit - University School of Computer Science Engineering Dept of Computational Intelligence Vellore India Vit - University School of Computer Science Engineering and Information Systems Vellore India Jss Academy of Technical Education Dept of Electronics and Communication Engineering Bengaluru India

ISBN: (纸本)9798350306415

Photography is the most important, powerful, and reliable means of expression. Today, digital images not only provide disinformation but also act as agents for secret communication. Users and editing professionals work with digital images for a variety of purposes. Images are often regarded as facts or proof of reality, so they are misleading and fake news or publications of any form that use images manipulated in a highly misleading way. To recognize image tampering needs multiple image data and a model that can handle all the pixels in the image. Furthermore, training the data more efficiently and needed flexibility support everyday use. Models based on Deep learning such as Convolutional Neural Networks with error level analysis (ELA) are the perfect solution. © 2024 IEEE.

关键词： Convolutional Neural Network Deep Learning Efficiency Error Level Analysis Image Forgery Detection

来源：评论

学校读者我要写书评

暂无评论

Two-Stage Fine-Tuning For Low-resource Englishbased Creole with Pre-Trained LLMs

Two-Stage Fine-Tuning For Low-resource Englishbased Creole w...

引用

2023 IEEE Asia-Pacific Conference on computer science and Data engineering, CSDE 2023

作者： Amanda Tan, Shu Hui Aung, Eint Sandi Yamana, Hayato Department of Computer Science and Communications Engineering Waseda University Tokyo Japan Waseda University Faculty of Science and Engineering Tokyo Japan

ISBN: (纸本)9798350341072

Sentiment analysis adopts natural language processing (NLP) techniques to determine the emotional tone of the text. Sentiment analysis research has predominantly been conducted on commonly spoken languages, such as English and Mandarin Chinese. However, less widely spoken languages, such as Englishbased Creoles, have received limited attention due to the need for large-scale labeled datasets. English-based Creoles are derived from English, resulting in many similarities with English. However, English-based Creoles differ from English in some aspects, making the Creole unintelligible to other English speakers. In sentiment analysis research conducted on Singapore English-based Creole (Singlish), most existing research does not leverage the capabilities of large-language models, such as pretrained BERT. To our knowledge, only Gotera et al.'s work relates to a large-language model;however, their contribution is creating a new pre-trained model for Singlish. However, creating a new pre-trained model is computationally expensive, and pre-training a less widely spoken language will result in ineffective because of the small dataset. Hence, we propose a new two-stage fine-tuning framework for pre-trained models, targeting a low-resource English-based Creole, Singlish. Our proposed framework initially clusters the dataset into two based on each data point's percentage of English words. Then, two-stage fine-tuning is performed by transferring the pre-trained BERT model onto the clustered dataset with the higher English percentage in the first stage. The model is further transferred onto the clustered dataset with the lower English percentage in the second stage. Our proposed framework outperforms the traditional fine-tuning framework, achieving a weighted F1 score of 0.8344 for sentiment analysis. © 2023 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

A novel deep learning approach for arrhythmia prediction on ECG classification using recurrent CNN with GWO

引用

International Journal of Information Technology (Singapore) 2024年第1期16卷 577-585页

作者： Singh, Prem Narayan Mahapatra, Rajendra Prasad Department of Computer Science and Engineering Faculty of Engineering and Technology SRM Institute of Science and Technology NCR Campus Delhi-NCR Campus Delhi-Meerut Road Modinagar Uttar Pradesh Ghaziabad 201204 India

In recent years, one of the most active research areas has been examining and categorizing heartbeats and brain traces connected with various types of arrhythmia and seizure. In this paper, we examine various classification methods that can be used to study and categorize electrocardiogram (ECG) signals. The proposed research evaluates the ECG signals and the Recurrent Convolutional Neural Network classification technique. The PTB Diagnostic ECG and MIT-BIH arrhythmias Databases are employed for the training and testing. The Recurrent CNN (RCNN) and the Grey Wolf Optimization (GWO) methods improve the performance matrices of machine learning compared to other techniques in the literature. The outcome performs superior to the norms currently being utilized for classification. The system's accuracy is 98%, higher than the results obtained by similar machine learning and supervised machine learning methods. The proposed research has been compared with Decision Tree, K-Nearest Neighbors algorithm, Random Forest, Support Vector Machines algorithm and Logistic Regression, and it is seen that the proposed method has the highest accuracy. Although the accuracies of the other algorithms are above 90%, they are not as efficient as the proposed algorithm. © 2023, The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of computer Applications and Management.

关键词： Arrhythmia prediction ECG Classification GWO Optimization RCNN

来源：评论

学校读者我要写书评

暂无评论

Improved Multileader Optimization with Shadow Encryption for Medical Images in IoT Environment

引用

computers, Materials & Continua 2023年第2期74卷 3133-3149页

作者： Mesfer Al Duhayyim Mohammed Maray Ayman Qahmash Fatma S.Alrayes Nuha Alshuqayran Jaber S.Alzahrani Mohammed Alghamdi Abdullah Mohamed Department of Computer Science College of Sciences and Humanities-AflajPrince Sattam Bin Abdulaziz UniversitySaudi Arabia Department of Information Systems College of Computer ScienceKing Khalid UniversityAbhaSaudi Arabia Department of Information Systems College of Computer and Information SciencesPrincess Nourah Bint Abdulrahman UniversityP.O.Box 84428Riyadh 11671Saudi Arabia Department of Information Systems College of Computer and Information SciencesImam Mohammad Ibn Saud Islamic UniversitySaudi Arabia Department of Industrial Engineering College of Engineering at AlqunfudahUmm Al-Qura UniversitySaudi Arabia Department of Information and Technology Systems College of Computer Science and EngineeringUniversity of JeddahJeddahSaudi Arabia Research Centre Future University in EgyptNew Cairo11845Egypt

Nowadays,security plays an important role in Internet of Things(IoT)environment especially in medical services’domains like disease prediction and medical data *** healthcare sector,huge volumes of data are generated on a daily basis,owing to the involvement of advanced health care *** general terms,health care images are highly sensitive to alterations due to which any modifications in its content can result in faulty *** the same time,it is also significant to maintain the delicate contents of health care images during reconstruction ***,an encryption system is required in order to raise the privacy and security of healthcare data by not leaking any sensitive *** current study introduces Improved Multileader Optimization with Shadow Image Encryption for Medical Image Security(IMLOSIE-MIS)technique for IoT *** aim of the proposed IMLOSIE-MIS model is to accomplish security by generating shadows and encrypting them *** do so,the presented IMLOSIE-MIS model initially generates a set of shadows for every input medical ***,shadow image encryption process takes place with the help of Multileader Optimization(MLO)withHomomorphic Encryption(IMLO-HE)technique,where the optimal keys are generated with the help of MLO *** the receiver side,decryption process is initially carried out and shadow image reconstruction process is *** experimentation analysis was carried out on medical images and the results inferred that the proposed IMLOSIE-MIS model is an excellent performer compared to other *** comparison study outcomes demonstrate that IMLOSIE-MIS model is robust and offers high security in IoT-enabled healthcare environment.

关键词： Medical image security image encryption shadow images homomorphic encryption optimal key generation

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：