检索结果-内蒙古大学图书馆

Addressing Imbalance in Health Datasets: A New Method NR-Clustering SMOTE and Distance Metric Modification

computers, Materials & Continua 2025年第2期82卷 2931-2949页

作者： Hairani Hairani Triyanna Widiyaningtyas Didik Dwi Prasetya Afrig Aminuddin Department of Electrical Engineering and Informatics Faculty of EngineeringUniversitas Negeri MalangMalang65145Indonesia Department of Computer Science Universitas BumigoraMataram83127Indonesia Department of Computer Graphic and Multimedia Faculty of ComputingCollege of Computing and Applied SciencesUniversiti Malaysia Pahang Al-Sultan AbdullahPekan26600Malaysia

An imbalanced dataset often challenges machine learning, particularly classification methods. Underrepresented minority classes can result in biased and inaccurate models. The Synthetic Minority Over-Sampling Technique (SMOTE) was developed to address the problem of imbalanced data. Over time, several weaknesses of the SMOTE method have been identified in generating synthetic minority class data, such as overlapping, noise, and small disjuncts. However, these studies generally focus on only one of SMOTE’s weaknesses: noise or overlapping. Therefore, this study addresses both issues simultaneously by tackling noise and overlapping in SMOTE-generated data. This study proposes a combined approach of filtering, clustering, and distance modification to reduce noise and overlapping produced by SMOTE. Filtering removes minority class data (noise) located in majority class regions, with the k-nn method applied for filtering. The use of Noise Reduction (NR), which removes data that is considered noise before applying SMOTE, has a positive impact in overcoming data imbalance. Clustering establishes decision boundaries by partitioning data into clusters, allowing SMOTE with modified distance metrics to generate minority class data within each cluster. This SMOTE clustering and distance modification approach aims to minimize overlap in synthetic minority data that could introduce noise. The proposed method is called “NR-Clustering SMOTE,” which has several stages in balancing data: (1) filtering by removing minority classes close to majority classes (data noise) using the k-nn method;(2) clustering data using K-means aims to establish decision boundaries by partitioning data into several clusters;(3) applying SMOTE oversampling with Manhattan distance within each cluster. Test results indicate that the proposed NR-Clustering SMOTE method achieves the best performance across all evaluation metrics for classification methods such as Random Forest, SVM, and Naїve Bayes, compared t

关键词： SMOTE modification Clustering-SMOTE manhattan distance

来源：评论

学校读者我要写书评

暂无评论

A novel self-supervised sentiment classification approach using semantic labeling based on contextual embeddings

引用

Multimedia Tools and Applications 2025年第12期84卷 10195-10220页

作者： Alizadeh, Mousa Seilsepour, Azam School of Engineering RMIT University MelbourneVIC Australia Department of Computer Engineering Central Tehran Branch Islamic Azad University Tehran Iran

Sentiment Analysis (SA) is a domain or context-oriented task since the sentiment words convey different sentiments in various domains. As a result, the domain-independent lexicons cannot correctly recognize the sentiment of domain-dependent words. To address this problem, this paper proposes a novel self-supervised SA method based on semantic similarity, contextual embedding, and Deep Learning Techniques. It introduces a new Pseudo-label generator that estimates the pseudo-labels of samples using semantic similarity between the samples and their sentiment words. It proposes two new concepts to calculate semantic similarity: The Soft-Cosine Similarity of a sample with its Positive words (SCSP) and the Soft-Cosine Similarity of a document with its Negative words (SCSN). Then, the Pseudo-label generator uses these concepts and the number of sentiment words to estimate the label of each sample. Later on, a novel method is proposed to find the samples with highly accurate pseudo-labels. Finally, a hybrid classifier, composed of a Convolutional Neural Network (CNN) and a Gated Recurrent Unit (GRU), is trained using these highly accurate pseudo-labeled data to predict the label of unseen data. The comparison of the proposed method with the lexicons and other similar existing methods demonstrates that the proposed method outperforms them in terms of accuracy, precision, recall, and F1 score. © The Author(s) 2024.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Developing phoneme-based lip-reading sentences system for silent speech recognition

引用

CAAI Transactions on Intelligence Technology 2023年第1期8卷 129-138页

作者： Randa El-Bialy Daqing Chen Souheil Fenghour Walid Hussein Perry Xiao Omar HKaram Bo Li School of Engineering London South Bank UniversityLondonUK Faculty of Informatics and Computer Science British University in EgyptCairoEgypt School of Electronics and Informatics Northwestern Polytechnical UniversityXi'anChina

Lip-reading is a process of interpreting speech by visually analysing lip *** research in this area has shifted from simple word recognition to lip-reading sentences in the *** paper attempts to use phonemes as a classification schema for lip-reading sentences to explore an alternative schema and to enhance system *** classification schemas have been investigated,including characterbased and visemes-based *** visual front-end model of the system consists of a Spatial-Temporal(3D)convolution followed by a 2D *** utilise multi-headed attention for phoneme recognition *** the language model,a Recurrent Neural Network is *** performance of the proposed system has been testified with the BBC Lip Reading Sentences 2(LRS2)benchmark *** with the state-of-the-art approaches in lip-reading sentences,the proposed system has demonstrated an improved performance by a 10%lower word error rate on average under varying illumination ratios.

关键词： deep learning deep neural networks lip-reading phoneme-based lip-reading spatial-temporal convolution,transformers

来源：评论

学校读者我要写书评

暂无评论

A Self-Adapting and Efficient Dandelion Algorithm and Its Application to Feature Selection for Credit Card Fraud Detection

引用

IEEE/CAA Journal of Automatica Sinica 2024年第2期11卷 377-390页

作者： Honghao Zhu MengChu Zhou Yu Xie Aiiad Albeshri IEEE School of Computer and Information Engineering Bengbu UniversityBengbu 233030China School of Information and Electronic Engineering Zhejiang Gongshang UniversityHangzhou 310018China Helen and John C.Hartmann the Department of Electrical and Computer EngineeringNew Jersey Institute of TechnologyNewark NJ 07102 USA College of Information Engineering Shanghai Maritime UniversityShanghai 201306China Department of Computer Science King Abdulaziz UniversityJeddah 21481Saudi Arabia

A dandelion algorithm(DA) is a recently developed intelligent optimization algorithm for function optimization problems. Many of its parameters need to be set by experience in DA,which might not be appropriate for all optimization problems. A self-adapting and efficient dandelion algorithm is proposed in this work to lower the number of DA's parameters and simplify DA's structure. Only the normal sowing operator is retained;while the other operators are discarded. An adaptive seeding radius strategy is designed for the core dandelion. The results show that the proposed algorithm achieves better performance on the standard test functions with less time consumption than its competitive peers. In addition, the proposed algorithm is applied to feature selection for credit card fraud detection(CCFD), and the results indicate that it can obtain higher classification and detection performance than the-state-of-the-art methods.

关键词： Credit card fraud detection(CCFD) dandelion algorithm(DA) feature selection normal sowing operator

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Approach for Hand Gesture Recognition:Applications in Deaf Communication and Healthcare

引用

computers, Materials & Continua 2024年第1期78卷 127-144页

作者： Khursheed Aurangzeb Khalid Javeed Musaed Alhussein Imad Rida Syed Irtaza Haider Anubha Parashar Department of Computer Engineering College of Computer and Information SciencesKing Saud UniversityP.O.Box 51178Riyadh11543Kingdom of Saudi Arabia Department of Computer Engineering College of Computing and InformaticsUniversity of SharjahSharjah27272United Arab Emirates Laboratory Biomechanics and Bioengineering University of Technology of CompiegneCompiegne60200France Department of Computer Science and Engineering Manipal University JaipurJaipur303007India

Hand gestures have been used as a significant mode of communication since the advent of human *** facilitating human-computer interaction(HCI),hand gesture recognition(HGRoc)technology is crucial for seamless and error-free *** technology is pivotal in healthcare and communication for the deaf *** significant advancements in computer vision-based gesture recognition for language understanding,two considerable challenges persist in this field:(a)limited and common gestures are considered,(b)processing multiple channels of information across a network takes huge computational time during discriminative feature ***,a novel hand vision-based convolutional neural network(CNN)model named(HVCNNM)offers several benefits,notably enhanced accuracy,robustness to variations,real-time performance,reduced channels,and ***,these models can be optimized for real-time performance,learn from large amounts of data,and are scalable to handle complex recognition tasks for efficient human-computer *** proposed model was evaluated on two challenging datasets,namely the Massey University Dataset(MUD)and the American Sign Language(ASL)Alphabet Dataset(ASLAD).On the MUD and ASLAD datasets,HVCNNM achieved a score of 99.23% and 99.00%,*** results demonstrate the effectiveness of CNN as a promising HGRoc *** findings suggest that the proposed model have potential roles in applications such as sign language recognition,human-computer interaction,and robotics.

关键词： computer vision deep learning gait recognition sign language recognition machine learning

来源：评论

学校读者我要写书评

暂无评论

New Antenna Array Beamforming Techniques Based on Hybrid Convolution/Genetic Algorithm for 5G and Beyond Communications

引用

computer Modeling in engineering & Sciences 2024年第3期138卷 2749-2767页

作者： Shimaa M.Amer Ashraf A.M.Khalaf Amr H.Hussein Salman A.Alqahtani Mostafa H.Dahshan Hossam M.Kassem Electronics and Communications Engineering Department Higher Institute of Engineering and TechnologyKafr ElsheikhEgypt Electronics and Electrical Communications Engineering Department Faculty of EngineeringMinia UniversityMiniaEgypt Electronics and Electrical Communications Engineering Department Faculty of EngineeringTanta UniversityTantaEgypt Electronics and Electrical Communications Engineering Department Faculty of EngineeringHorus University EgyptNew DamiettaEgypt Department of Computer Engineering College of computer and Information SciencesKing Saud UniversityRiyadh11543Saudi Arabia School of Computing Mathematics and EngineeringCharles Sturt UniversityBathurstNSW2795Australia

Side lobe level reduction(SLL)of antenna arrays significantly enhances the signal-to-interference ratio and improves the quality of service(QOS)in recent and future wireless communication systems starting from 5G up to ***,it improves the array gain and directivity,increasing the detection range and angular resolution of radar *** study proposes two highly efficient SLL reduction *** techniques are based on the hybridization between either the single convolution or the double convolution algorithms and the genetic algorithm(GA)to develop the Conv/GA andDConv/GA,*** convolution process determines the element’s excitations while the GA optimizes the element *** M elements linear antenna array(LAA),the convolution of the excitation coefficients vector by itself provides a new vector of excitations of length N=(2M−1).This new vector is divided into three different sets of excitations including the odd excitations,even excitations,and middle excitations of lengths M,M−1,andM,*** the same element spacing as the original LAA is used,it is noticed that the odd and even excitations provide a much lower SLL than that of the LAA but with amuch wider half-power beamwidth(HPBW).While the middle excitations give the same HPBWas the original LAA with a relatively higher *** the increased HPBWof the odd and even excitations,the element spacing is optimized using the ***,the synthesized arrays have the same HPBW as the original LAA with a two-fold reduction in the ***,for extreme SLL reduction,the DConv/GA is *** this technique,the same procedure of the aforementioned Conv/GA technique is performed on the resultant even and odd excitation *** provides a relatively wider HPBWthan the original LAA with about quad-fold reduction in the SLL.

关键词： Array synthesis convolution process genetic algorithm(GA) half power beamwidth(HPBW) linear antenna array(LAA) side lobe level(SLL) quality of service(QOS)

来源：评论

学校读者我要写书评

暂无评论

Combined Architecture of Destination Sequence Distance Vector (DSDV) Routing with Software Defined Networking (SDN) and Blockchain in Cyber-Physical Systems

引用

computers, Materials & Continua 2025年第2期82卷 2311-2330页

作者： Jawad Ahmad Ansari Mohamad Khairi Ishak Khalid Ammar School of Electrical and Electronic Engineering Engineering CampusUniversiti Sains MalaysiaNibong TebalPulau Pinang11800Malaysia Department of Electrical and Computer Engineering College of Engineering and Information TechnologyAjman UniversityAjman346United Arab Emirates

Cyber-Physical System (CPS) devices are increasing exponentially. Lacking confidentiality creates a vulnerable network. Thus, demanding the overall system with the latest and robust solutions for the defence mechanisms with low computation cost, increased integrity, and surveillance. The proposal of a mechanism that utilizes the features of authenticity measures using the Destination Sequence Distance Vector (DSDV) routing protocol which applies to the multi-WSN (Wireless Sensor Network) of IoT devices in CPS which is developed for the Device-to-Device (D2D) authentication developed from the local-chain and public chain respectively combined with the Software Defined Networking (SDN) control and monitoring system using switches and controllers that will route the packets through the network, identify any false nodes, take preventive measures against them and preventing them for any future problems. Next, the system is powered by Blockchain cryptographic features by utilizing the TrustChain features to create a private, secure, and temper-free ledger of the transactions performed inside the network. Results are achieved in the legitimate devices connecting to the network, transferring their packets to their destination under supervision, reporting whenever a false node is causing hurdles, and recording the transactions for temper-proof records. Evaluation results based on 1000+ transactions illustrate that the proposed mechanism not only outshines most aspects of Cyber-Physical systems but also consumes less computation power with a low latency of 0.1 seconds only.

关键词： DSDV intelligent authentication SDN control&monitoring blockchain recording of transactions

来源：评论

学校读者我要写书评

暂无评论

Optimizing Power Allocation and Beamforming in mmWave-NOMA Downlink with Deep Reinforcement Learning

Optimizing Power Allocation and Beamforming in mmWave-NOMA D...

引用

2024 IEEE Middle East Conference on Communications and Networking, MECOM 2024

作者： Kasgari, Abbas Akbarpour Chrysostomou, Chrysostomos Frederick University and Frederick Research Center Computer Engineering and Informatics Department of Electrical Engineering Nicosia Cyprus

ISBN: (纸本)9798350376715

The high demand for data rates in the fifth generation (5G) and beyond of wireless communication can be met by the Non-Orthogonal Multiple Access (NOMA) approach in the millimeter-wave (mmWave) frequency band. Joint power allocation and beamforming for 5 G and beyond mmWave-NOMA systems are essential, which can be achieved through optimization approaches. To this end, we have employed a Deep Reinforcement Learning (DRL) approach for policy generation, leading to an optimized sum-rate for users. Unlike existing methods, our approach is not susceptible to channel impulse response (CIR) estimation errors. The actor-critic framework is utilized to measure the immediate reward and provide new actions to maximize the overall Q-value of the network. The immediate reward is defined based on the summation of the rates of two users, considering the minimum guaranteed rate for each user and the total consumed power as constraints. The simulation results demonstrate the superiority of the proposed approach compared to state-of-the-art counterparts, including Time-Division Multiple Access (TDMA) and NLOS-NOMA optimization strategies, in terms of sum-rate of users, while considering both perfect and imperfect channel state information (CSI) at the receiver. This work can also be beneficial for communications in vehicular networks, particularly in applications involving Collective Perception Messages (CPMs) dissemination for autonomous driving. © 2024 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Stress Detection Using EEG Signals: A SVM-Based Classification and Feature Selection Approach 12

Stress Detection Using EEG Signals: A SVM-Based Classificati...

引用

12th Electrical Power, Electronics, Communications, Controls and informatics Seminar, EECCIS 2024

作者： Sifaunnufus, Fi Imanur Bachtiar, Fitra Abdurrachman Prasetio, Barlian Henryranu Brawijaya University Faculty of Computer Science Department of Computer Engineering Malang Indonesia Brawijaya University Faculty of Computer Science Department of Informatics Engineering Malang Indonesia

ISBN: (纸本)9798350379914

Stress is a problem with various adverse effects, such as mental disorders and suicide. With these problems arising, a stress detection system is needed as an initial examination of the level of stress experienced. Generally, stress detection is done with a stress test at a hospital. However, medical examinations done in the hospital require high costs. Another alternative to examine stress levels is by using a biosignal electroencephalogram (EEG), which provides more objective and accurate results. In addition, there is a need to develop a portable device that can be used to detect stress. This study tries to detect stress levels using EEG Signals. The data used in this study is primary data that simulates several stress-level activities. In total, 55 subjects participated in this stress detection research. The received signal goes through preprocessing to clean it from noise and artifacts. The data will be extracted using Power Spectral Density (PSD) into power value for each signal frequency. The preprocessed input signals are then classified into indications of stress levels. This study uses Random Forest, SVM, and Decision Tree. The model is stored on a portable system with Raspberry Pi as the main component. EEG signals are taken using electrodes on Muse 2 and sent to the system. The classification model generates predicted stress levels and is displayed on a 16×2 LCD. SVM as the best model test result achieved a testing accuracy of 1, and an average computation time of 0.92. © 2024 IEEE.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Trust management in online computing environment: a complete review

引用

Journal of Ambient Intelligence and Humanized Computing 2024年第1期15卷 491-545页

作者： Singh, Ashish Chatterjee, Kakali School of Computer Engineering KIIT Deemed to be University Odisha Bhubaneswar751024 India Department of Computer Science and Engineering National Institute of Technology Bihar Patna800005 India

Nowadays, trust management plays a significant role in different applications like commercial applications, Internet of Things (IoT) based applications, social networking applications, cloud computing-based applications, sensor networks, online services, and many more. Thus, it is an important research area for industry and engineering research communities. The concept of trust is mainly derived from long-term sociological and psychological human behaviour. It is used for decision-making purposes in different contexts and perspectives. Many growing research studies address the development of trust computation models using different approaches in different areas, such as cloud computing, P2P networks, online social network, etc. Still, most of the prior work does not provide a comprehensive systematic review of different trust management systems nor provide sufficient details about the computation process. In this paper, we have discussed a systematic review of the existing trust management systems by indicating the limitation of previous works. A systematic review started with research question identification, followed by searching and filtration of relevant works, and ended with a comparison and final report. A detailed comparative study of trust computational models will help understand the security and privacy aspects of trust. This survey provides a detailed study of each trust taxonomy and computation model in different online computing environments. The survey result finds several trust computation techniques. The results also say that trust in the online computing environment provides greater security and protection against several threats and attacks. Despite the potential benefits of trust, the results also included challenges and open research issues that are still opportunities for new researchers. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2023.

关键词： Cloud computing

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：