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

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

Multi-channel CNN to classify Nepali COVID-19 related tweets using hybrid features

引用

Journal of Ambient Intelligence and Humanized Computing 2024年第3期15卷 2047-2056页

作者： Sitaula, Chiranjibi Shahi, Tej Bahadur Department of Electrical and Computer Systems Engineering Monash University Wellington Rd ClaytonVIC3800 Australia Earth Observation and AI Research Group Department of Infrastructure Engineering The University of Melbourne ParkvilleVIC3010 Australia School of Engineering and Technology Central Queensland University Rockhampton Australia Central Department of Computer Science and Information Technology Tribhuvan University TU Rd Kathmandu Kirtipur44618 Nepal

Because of the current COVID-19 pandemic’s increasing fears among people, it has triggered several health complications such as depression and anxiety. Such complications have not only affected developed countries but also developing countries such as Nepal. These complications can be understood from peoples’ tweets and comments posted online after their felicitous analysis and sentiment classification. Nevertheless, owing to the limited number of tokens and words in each tweet, it is crucial to capture multiple pieces of information associated with them for better understanding. In this study, we, first, represent each tweet by combining both syntactic and semantic information, called hybrid features. The syntactic information is generated from the bag-of-words method, whereas the semantic information is generated from the combination of the fastText-based (ft) and domain-specific (ds) methods. Second, we design a novel multi-channel CNN (MCNN) model, which ensembles the multiple CNNs, to capture multi-scale information for better classification. Last, we evaluate the efficacy of both the proposed feature extraction method and the MCNN model classifying tweets into three sentiment classes (positive, neutral, and negative) on the NepCOV19Tweets dataset, which is the only public COVID-19 tweets dataset in the Nepali language. The evaluation results show that the proposed hybrid features outperform individual feature extraction methods with the highest classification accuracy of 69.7% and the MCNN model outperforms the existing methods with the highest classification accuracy of 71.3% during classification. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2023.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Behavior Trees and State Machines in Robotics Applications

引用

IEEE Transactions on Software engineering 2023年第9期49卷 4243-4267页

作者： Ghzouli, Razan Berger, Thorsten Johnsen, Einar Broch Wasowski, Andrzej Dragule, Swaib Chalmers University of Technology Department of Computer Science and Engineering Gothenburg40530 Sweden Ruhr University Bochum Faculty of Computer Science Bochum44801 Germany Chalmers University of Gothenburg Department of Computer Science and Engineering Gothenburg40530 Sweden University of Oslo Department of Informatics Oslo0316 Norway IT University of Copenhagen Software Development Group Copenhagen2300 Denmark

Autonomous robots combine skills to form increasingly complex behaviors, called missions. While skills are often programmed at a relatively low abstraction level, their coordination is architecturally separated and often expressed in higher-level languages or frameworks. State machines have been the go-to language to model behavior for decades, but recently, behavior trees have gained attention among roboticists. Originally designed to model autonomous actors in computer games, behavior trees offer an extensible tree-based representation of missions and are claimed to support modular design and code reuse. Although several implementations of behavior trees are in use, little is known about their usage and scope in the real world. How do concepts offered by behavior trees relate to traditional languages, such as state machines? How are concepts in behavior trees and state machines used in actual applications? This paper is a study of the key language concepts in behavior trees as realized in domain-specific languages (DSLs), internal and external DSLs offered as libraries, and their use in open-source robotic applications supported by the Robot Operating System (ROS). We analyze behavior-tree DSLs and compare them to the standard language for behavior models in robotics: state machines. We identify DSLs for both behavior-modeling languages, and we analyze five in-depth. We mine open-source repositories for robotic applications that use the analyzed DSLs and analyze their usage. We identify similarities between behavior trees and state machines in terms of language design and the concepts offered to accommodate the needs of the robotics domain. We observed that the usage of behavior-tree DSLs in open-source projects is increasing rapidly. We observed similar usage patterns at model structure and at code reuse in the behavior-tree and state-machine models within the mined open-source projects. We contribute all extracted models as a dataset, hoping to inspire the commu

关键词： Modeling languages

来源：评论

学校读者我要写书评

暂无评论

Advanced Brain Tumor Segmentation Using UNet and Multiple Residual Networks 2

Advanced Brain Tumor Segmentation Using UNet and Multiple Re...

引用

2nd IEEE International Conference on Networking and Communications, ICNWC 2024

作者： Ramya, D. Manigandan, S.K. Velmurugan, J. Vishnukumar, A. Umarani, V. Reddy, P. V. Sai Ram Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Department of Information Technology Chennai India Vel Tech High Tech Dr.Rangarajan Dr.Sakunthala Engineering College Department of Information Technology Chennai India Saveetha School of Engineering Department of Computer Science and Engineering Chennai India Rajalakshmi Engineering College Department of Computer Science and Business Systems Chennai India Saveetha Engineering College Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350365269

Accurate brain tumors segmentation is essential for precise diagnosis, planning, treatment, and monitoring of the tumor. However, the variations in tumor size, shape, and location, automating this process can be challenging. Segmentation using manual method is both time-taking and can produce inconsistent results. A promising solution to automated brain tumor segmentation is through deep learning approach that use convolutional neural networks. The models that have used U-Net shown considerable promise in enhancing the precision and effectiveness of automated Brain tumor segmentation. Still, there is a scope for improvement in accurate segmentation of brain MRI images. The segmentation of Brain MRI Images greatly helps in earlier diagnosis of Brain tumor effectively. The proposed model using ResNet, ResNext, and Inception as a backbone of U-Net with BraTs 2020 dataset could potentially reduce the workload of radiologists and provide more consistent results across experts. Future research can explore the use of other architectures or hybrid models to enhance brain tumor segmentation performance. © 2024 IEEE.

关键词： Tumors

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

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

LDPSA: A Large Dataset of Persian Sentiment Analysis 10

LDPSA: A Large Dataset of Persian Sentiment Analysis

引用

10th International Conference on Web Research, ICWR 2024

作者： Nazarizadeh, Ali Samavati, Taha Mansouri, Sina Sayyadpour, Minoo Islamic Azad University Central Tehran Branch Department of Computer Engineering Tehran Iran Iran University of Science and Technology Faculty of Computer Engineering Tehran Iran K. N. Toosi University of Technology Faculty of Computer Engineering Tehran Iran Kharazmi University Dept. Math and Computer Science Tehran Iran

ISBN: (纸本)9798350394986

Today, data is more valuable to us than gold. When observing the environment, a substantial amount of data, particularly textual information, can be identified, tagged, prepared, and published in the form of a corpus or datasets. The primary objective of our paper is to gather, prepare, tag, and develop a vast dataset of Fidibo users' opinions regarding educational content and e-books. This dataset enables in-depth analysis of emotions and opinion mining, particularly within the educational content realm. A common flaw in nearly all similar datasets in the Farsi language is their restriction to user opinions on services and products available on online platforms. The dataset we refer to as LDPSA (A Large Dataset of Persian Sentiment Analysis) offers several advantages over comparable datasets in the Persian language. Notably, this dataset consists of 253,368 comments, each categorized into 5 classes. LDPSA represents the sole extensive Iranian dataset suitable for scrutinizing educational content and e-books. Moreover, significant insights were gleaned from data analysis. For example, during the COVID-19 pandemic, Iranian individuals dedicated more time to studying and engaging with educational platforms significantly. Nearly 80% of users expressed favorable opinions concerning the informational materials available on the Fidibo website. Users' inclination towards utilizing audio books has escalated, along with other analysis referenced in the paper. © 2024 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

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

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：