检索结果-内蒙古大学图书馆

Dual Dynamic Consistency Regularization for Semi-Supervised Domain Adaptation

IEEE Access 2024年 12卷 36267-36279页

作者： Ngo, Ba Hung Lam, Ba Thinh Nguyen, Thanh Huy Dinh, Quang Vinh Choi, Tae Jong Chonnam National University Graduate School of Data Science Gwangju61186 Korea Republic of University of Science Faculty of Information Technology Ho Chi Minh City700000 Viet Nam National Cheng Kung University Department of Biomedical Engineering Tainan70101 Taiwan Vietnamese-German University School of Electrical Engineering and Computer Science Ho Chi Minh City72000 Viet Nam

The Vision Transformer (ViT) model serves as a powerful model to capture and comprehend global information, particularly when trained on extensive datasets. Conversely, the Convolutional Neural Network (CNN) model is beneficial to training with small datasets for retaining essential local information. Inspired by these properties of ViT and CNN models, we introduce a hybrid framework that smoothly increases the cross-domain generalization in Semi-supervised Domain Adaptation (SSDA). To achieve this goal, we first train the ViT model on abundant labeled source data, while the CNN model is trained on a few labeled target samples. Then, these models dynamically exchange their knowledge for potential generalization to unlabeled target data via the proposed method, named Dual Dynamic Consistency Regularization (D2CR). Specifically, the ViT model provides its pseudo labels to update the global perspective for the CNN model. Similarly, the CNN model offers pseudo labels to complement the local perspective for the ViT model. The previous methods use a fixed threshold algorithm for the pseudo-labeling process. However, we utilize the dynamic threshold strategy to create pseudo labels for the bi-directional consistency regularization learning between the ViT and CNN models. We verify our approach across several SSDA benchmark datasets. The outstanding experimental results provide strong evidence of the effectiveness and superiority of our approach over previous state-of-the-art SSDA methods. © 2013 IEEE.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of a Robotic Stone Machining System

Design and Implementation of a Robotic Stone Machining Syste...

引用

2023 IEEE IAS Global Conference on Emerging Technologies, GlobConET 2023

作者： Nguyen-Vinh, Khuong Hattotuwa, Dilsha Damruwan Dewasurendra, Hasindu RMIT University School of Science Engineering and Technology Ho Chi Minh City Viet Nam VSB-Technical University of Ostrava Faculty of Electrical Engineering and Computer Science Ostrava Czech Republic

ISBN: (纸本)9798350331790

Industry 4.0 has brought about an era of digital transformation in smart manufacturing processes. Machining is one such vastly developing field with the application of industrial robots (IR) as a more efficient and flexible alternative to traditional CNC machines. Therefore, it is justifiable to study the different operating principles and mechanisms of a robotic machining system that has the potential to innovate this industry in a safe and automated environment. This paper highlights the key concepts involved in robot machining and details the design and implementation of a practical work cell incorporating a serial robot: ABB IRB 6700. The station utilizes an external rotating worktable, spindle, and a tool magazine among other hardware to achieve a fully operating machining, specifically cutting and milling station. First, the tools are assembled in an optimum configuration to support stone and marble milling tasks. Then, an offline simulation is carried out in a CAD/CAM environment to generate and optimize the robot path before using this data in Robotstudio to test the actual setup. As a result, a feasible and effective robotic stone machining system was developed with the capacity to substitute the widely used CNC machines in the near digital future. © 2023 IEEE.

关键词： 3D modeling

来源：评论

学校读者我要写书评

暂无评论

Robust Machine Learning Technique to Classify COVID-19 Using Fusion of Texture and Vesselness of X-Ray Images

引用

computer Modeling in engineering & sciences 2024年第2期138卷 1981-2004页

作者： Shaik Mahaboob Basha Victor Hugo Cde Albuquerque Samia Allaoua Chelloug Mohamed Abd Elaziz Shaik Hashmitha Mohisin Suhail Parvaze Pathan Department of Electronics and Communication Engineering N.B.K.R.Institute of Science&TechnologyVidyanagarAndhra Pradesh524413India Department of Teleinformatics Engineering Federal University of CearáFortaleza60455-970Brazil Information Technology Department College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityRiyadh84428Saudi Arabia Department of Mathematics Faculty of ScienceZagazig UniversityZagazig44519Egypt Faculty of Computer Science and Engineering Galala UniversitySuez435611Egypt Artificial Intelligence Research Center(AIRC) College of Engineering and Information TechnologyAjman UniversityAjmanUnited Arab Emirates Department of Electrical and Computer Engineering Lebanese American UniversityByblos13-5053Lebanon Department of Avionics Indian Institute of Space Science and TechnologyThiruvananthapuramKerala695547India Department of Veterinary Clinical Sciences University of MinnesotaSt.PaulMinnesota55108USA

Manual investigation of chest radiography(CXR)images by physicians is crucial for effective decision-making in COVID-19 ***,the high demand during the pandemic necessitates auxiliary help through image analysis and machine learning *** study presents a multi-threshold-based segmentation technique to probe high pixel intensity regions in CXR images of various pathologies,including normal *** information is extracted using gray co-occurrence matrix(GLCM)-based features,while vessel-like features are obtained using Frangi,Sato,and Meijering *** learning models employing Decision Tree(DT)and RandomForest(RF)approaches are designed to categorize CXR images into common lung infections,lung opacity(LO),COVID-19,and viral pneumonia(VP).The results demonstrate that the fusion of texture and vesselbased features provides an effective ML model for aiding *** ML model validation using performance measures,including an accuracy of approximately 91.8%with an RF-based classifier,supports the usefulness of the feature set and classifier model in categorizing the four different ***,the study investigates the importance of the devised features in identifying the underlying pathology and incorporates histogrambased *** analysis reveals varying natural pixel distributions in CXR images belonging to the normal,COVID-19,LO,and VP groups,motivating the incorporation of additional features such as mean,standard deviation,skewness,and percentile based on the filtered ***,the study achieves a considerable improvement in categorizing COVID-19 from LO,with a true positive rate of 97%,further substantiating the effectiveness of the methodology implemented.

关键词： Chest radiography(CXR)image COVID-19 classifier machine learning random forest texture analysis

来源：评论

学校读者我要写书评

暂无评论

Adversarial Learning Aided Malicious Network Traffic Detection Based on EDE Framework

Adversarial Learning Aided Malicious Network Traffic Detecti...

引用

2023 IEEE/CIC International Conference on Communications in China, ICCC 2023

作者： Zhang, Lanping Wang, Yu Ohtsuki, Tomoaki Adebisi, Bamidele Wu, Hsiao-Chun Gui, Guan Njupt College of Telecommunications and Information Engineering Nanjing China Keio University Department of Information and Computer Science Yokohama Japan Manchester Metropolitan University Faculty of Science and Engineering Manchester United Kingdom Louisiana State University School of Electrical Engineering and Computer Science United States

ISBN: (纸本)9798350345384

With the increasing number of new malicious software and network attacks, anomalous network traffic detection technology needs to continuously identify unknown attacks in order to adapt to complex network environments. In this paper, we propose a novel adversarial learning aided malicious network traffic detection (AMD) method based on encoder-decoder-encoder (EDE) framework. The proposed AMD method detects unknown anomalies in a single type of semi-supervised form and converts network traffic data into pictures for later processing. First, an anomalous network traffic detection model consisting of two encoders, a decoder and a discriminator is introduced. Second, by using the visibility of normal samples and the unrecognizability of unknown anomaly samples, the difference between the two samples is enlarged to facilitate effective sample detection. Finally, experiments show that the proposed model detects anomalies in targeted space and is robust to complex and noisy network environments. At the same time, compared to traditional machine learning methods, AMD's shows performance improvement of up to 40%. © 2023 IEEE.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Link Quality-Aware Geographic Predictive Routing for V2V Network Based on GPSR

Link Quality-Aware Geographic Predictive Routing for V2V Net...

引用

2023 International Technical Conference on Circuits/Systems, computers, and Communications, ITC-CSCC 2023

作者： Harayama, Michiko Mishioka, Masahiro Gifu University Faculty of Engineering Dept. Electrical Electronic and Computer Engineering Japan Grad. Sch. Natural Science and Technology Gifu University Dept. Intelligence Science and Engineering Japan

ISBN: (纸本)9798350326413

In recent years, advances in automotive IoT technology have not only improved automated driving and driving convenience but have also led to a diminishing number of traffic accidents. Vehicle Ad-hoc Networks (VANETs) have attracted much attention because automotive IoT is based on wireless communications. Ad-hoc routing protocols that apply the characteristics of vehicle-to-vehicle (V2V) networks are needed. One of them is Greedy Perimeter Stateless Forwarding (GPSR), a routing protocol using geographic information. It uses Global Positioning System (GPS) information for routing. However, GPSR may increase the packet drop rate due to radio attenuation and fading. Therefore, C. Li et al. proposed to select the next hop by evaluating the link quality. However, due to the large moving speed of the node, the next hop may be out of the radio propagation range at the communication timing. Therefore, in this study, we propose a new routing method that combines the future location prediction proposed by Z.S. Houssaini et al. The effectiveness of the method is demonstrated by simulations using ns-3 with traffic data acquired by SUMO. © 2023 IEEE.

关键词： Routing protocols

来源：评论

学校读者我要写书评

暂无评论

Noise Reduction in Industry Based on Virtual Instrumentation

引用

computers, Materials & Continua 2021年第10期69卷 1073-1096页

作者： Radek Martinek Rene Jaros Jan Baros Lukas Danys Aleksandra Kawala-Sterniuk Jan Nedoma Zdenek Machacek Jiri Koziorek Faculty of Electrical Engineering and Computer Science Department of Cybernetics and Biomedical EngineeringVSB–Technical University of Ostrava70800Ostrava-PorubaCzechia Faculty of Electrical Engineering Automatic Control and InformaticsOpole University of TechnologyOpolePoland Faculty of Electrical Engineering and Computer Science Department of TelecommunicationsVSB–Technical University of Ostrava70800Ostrava-PorubaCzechia

This paper discusses the reduction of background noise in an industrial environment to extend *** the Industry 4.0 era,the mass development of voice control(speech recognition)in various industrial applications is possible,especially as related to augmented reality(such as hands-free control via voice commands).As Industry 4.0 relies heavily on radiofrequency technologies,some brief insight into this problem is provided,including the Internet of things(IoT)and 5G *** study was carried out in cooperation with the industrial partner Brose CZ spol.s.r.o.,where sound recordings were made to produce a *** experimental environment comprised three workplaces with background noise above 100 dB,consisting of a laser/magnetic welder and a press.A virtual device was developed from a given dataset in order to test selected commands from a commercial speech recognizer from *** tested a hybrid algorithm for noise reduction and its impact on voice command recognition *** virtual devices,the study was carried out on large speakers with 20 participants(10 men and 10 women).The experiments included a large number of repetitions(100 times for each command under different noise conditions).Statistical results confirmed the efficiency of the tested *** welding environment efficiency was 27%before applied filtering,76%using the least mean square(LMS)algorithm,and 79%using LMS+independent component analysis(ICA).Magnetic welding environment efficiency was 24%before applied filtering,70%with LMS,and 75%with LMS+*** workplace environment efficiency showed no success before applied filtering,was 52%with LMS,and was 54%with LMS+ICA.

关键词： 5G hybrid algorithms signal processing speech recognition

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing Marine Stability: A Review of Cutting-Edge Gyro Stabilizer Designs and Techniques for Vessels

引用

IEEE Access 2025年 13卷 89542-89555页

作者： Rahiman, Wan Ghazali, Mohamad Hazwan Mohd Mahmood, Iskandar Al-Thani Universiti Sains Malaysia Engineering Campus School of Electrical and Electronic Engineering Penang Nibong Tebal14300 Malaysia Daffodil International University Daffodil Robotics Lab Department of Computer Science and Engineering Dhaka1216 Bangladesh Universiti Kebangsaan Malaysia Faculty of Engineering and Built Environment Department of Mechanical and Manufacturing Engineering Selangor Bangi43600 Malaysia PETRONAS Research Sdn Bhd Selangor Kajang43000 Malaysia

Advancement in marine vessel stabilization technologies has greatly improved the safety and comfort for crews, cargo, and passengers, while also lowering the risk of capsizing. Marine vessels operating in open waters experience disturbances from unpredictable waves and strong winds, leading to instability and potential accidents. To mitigate these risks, stabilizers are integrated into ships to maintain stability, safety, and seaworthiness. As modern vessels evolve, stabilizers play an increasingly vital role, with gyro stabilizers emerging as a highly effective solution for mitigating roll motion without external appendages. This paper provides a comprehensive review of gyro stabilizer designs and techniques, covering their historical development, mathematical modeling, advantages, limitations, and case studies. A review of current research highlights a strong emphasis on simulating gyro stabilizer control systems, demonstrating their potential in enhancing vessel stability. However, key challenges persist, including accurate wave moment prediction during the design phase and gyroscopic drift, which can impact long-term performance and efficiency. Despite these challenges, recent advancements in control algorithms and optimization techniques have improved gyro stabilizer adaptability under varying sea conditions. By exploring the latest developments, this review serves as a valuable reference for researchers, engineers, and maritime professionals seeking to advance marine stabilization technologies. The findings underscore the potential of next-generation gyro stabilizers, including fiber optic gyros, in achieving higher precision, stability, and operational efficiency. © 2013 IEEE.

关键词： Warships

来源：评论

学校读者我要写书评

暂无评论

Novel Ransomware Hiding Model Using HEVC Steganography Approach

引用

computers, Materials & Continua 2022年第1期70卷 1209-1228页

作者： Iman Almomani Aala AlKhayer Walid El-Shafai Security Engineering Lab Computer Science DepartmentPrince Sultan UniversityRiyadh11586Saudi Arabia Computer Science Department King Abdullah II School for Information TechnologyThe University of Jordan11942Jordan Department of Electronics and Electrical Communications Engineering Faculty of Electronic EngineeringMenoufia UniversityMenouf32952Egypt

Ransomware is considered one of the most threatening *** solutions have focused mainly on discriminating ransomware by analyzing the apps themselves,but they have overlooked possible ways of hiding ransomware apps and making them difficult to be detected and then ***,this paper proposes a novel ransomware hiding model by utilizing a block-based High-Efficiency Video Coding(HEVC)steganography *** main idea of the proposed steganography approach is the division of the secret ransomware data and cover HEVC frames into different *** that,the Least Significant Bit(LSB)based Hamming Distance(HD)calculation is performed amongst the secret data’s divided blocks and cover ***,the secret data bits are hidden into the marked bits of the cover HEVC frame-blocks based on the calculated HD *** main advantage of the suggested steganography approach is the minor impact on the cover HEVC frames after embedding the ransomware while preserving the histogram attributes of the cover video frame with a high *** is due to the utilization of an adaptive steganography cost function during the embedding *** proposed ransomware hiding approach was heavily examined using subjective and objective tests and applying different HEVC streams with diverse resolutions and different secret ransomware apps of various *** obtained results prove the efficiency of the proposed steganography approach by achieving high capacity and successful embedding process while ensuring the hidden ransomware’s undetectability within the video *** example,in terms of embedding quality,the proposed model achieved a high peak signal-to-noise ratio that reached 59.3 dB and a low mean-square-error of 0.07 for the examined HEVC ***,out of 65 antivirus engines,no engine could detect the existence of the embedded ransomware app.

关键词： Ransomware embedding steganography HEVC LSB hamming distance applications apk stego security confidentiality

来源：评论

学校读者我要写书评

暂无评论

Kalman Filter for Radon Based Earthquake Early Detection

Kalman Filter for Radon Based Earthquake Early Detection

引用

2024 International Conference on Informatics electrical and Electronics, ICIEE 2024

作者： Putra, Wahyu Sukestyastama Sunarno Mustika, I Wayan Universitas Gadjah Mada Department of Electrical Engineering and Information Technology Yogyakarta Indonesia Universitas AMIKOM Yogyakarta Faculty of Computer Science Yogyakarta Indonesia Universitas Gadjah Mada Department of Nuclear Engineering and Physics Engineering Yogyakarta Indonesia

ISBN: (纸本)9798331519216

Radon measurement for earthquake prediction is challenging due to environmental noise and sensor limitations. Factors such as temperature, humidity, and soil moisture cause fluctuations in radon levels, making distinguishing seismic-related changes from normal variations difficult. In addition, sensor limitations, such as sensor resolution, can reduce the ability of early warning systems to detect precursor signals. In this study, we designed an early earthquake detection method using the Kalman Filter on radon gas concentration data collected using an ion chamber sensor at a sampling interval of 1 minute. The Kalman Filter was applied to overcome the uncertainties in sensor measurements and the radon-earthquake phenomenon. The differences between the filter predictions and the raw sensor data indicate the presence of external factors, possibly earthquake precursors. In all six analyzed events, radon anomalies were effectively captured through the difference of squares, indicating the potential of the method as an early warning system for seismic activity. The proposed method detected radon anomalies 1 to 19 days before an earthquake. © 2024 IEEE.

关键词： Kalman filters

来源：评论

学校读者我要写书评

暂无评论

computer Vision with Machine Learning Enabled Skin Lesion Classification Model

引用

computers, Materials & Continua 2022年第10期73卷 849-864页

作者： Romany F.Mansour Sara A.Althubiti Fayadh Alenezi Department of Mathematics Faculty of ScienceNew Valley UniversityEl-Kharga72511Egypt Department of Computer Science College of Computer and Information SciencesMajmaah UniversityAl-Majmaah11952Saudi Arabia Department of Electrical Engineering College of EngineeringJouf UniversitySakaka72388Saudi Arabia

Recently,computer vision(CV)based disease diagnosis models have been utilized in various areas of *** the same time,deep learning(DL)and machine learning(ML)models play a vital role in the healthcare sector for the effectual recognition of diseases using medical imaging *** study develops a novel computer vision with optimal machine learning enabled skin lesion detection and classification(CVOML-SLDC)*** goal of the CVOML-SLDC model is to determine the appropriate class labels for the test dermoscopic ***,the CVOML-SLDC model derives a gaussian filtering(GF)approach to pre-process the input images and graph cut segmentation is ***,firefly algorithm(FFA)with EfficientNet based feature extraction module is applied for effectual derivation of feature ***,naïve bayes(NB)classifier is utilized for the skin lesion detection and classification *** application of FFA helps to effectually adjust the hyperparameter values of the EfficientNet *** experimental analysis of the CVOML-SLDC model is performed using benchmark skin lesion *** detailed comparative study of the CVOML-SLDC model reported the improved outcomes over the recent approaches with maximum accuracy of 94.83%.

关键词： Skin lesion detection dermoscopic images machine learning deep learning graph cut segmentation EfficientNet

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：