检索结果-内蒙古大学图书馆

Journal of Biotech Research 2024年 19卷 258-268页

作者： Tan, Yanli Zhao, Yongqiang Wang, Jin Li, Guoqin Department of Electronic Engineering Taiyuan Institute of Technology Shanxi Taiyuan China Faculty of Computer and Mathematical Sciences University Teknologi MARA Selangor Shah Alam Malaysia

Tumors are one of the main causes of global mortality, and early diagnosis and precise treatment affect the survival rate of patients. Traditional image analysis relies on the professional knowledge and experience of radiologists. Manually labeling and analyzing tumor cells is laborious and subjective, which may lead to variability and inconsistency in diagnostic results. This study proposed a convolutional model based on a single-stage object detector. To address the shortcomings of the single-stage object detector model, the receptive field was introduced to improve the depth of information extraction, and an attention mechanism was also introduced to enhance its focus. The model was used to recognize pathological tissue slice images and classify tumors. The results indicated that, when the dataset size reached around 200, the performance of each model reached its maximum and showed convergence. When the dataset size was 500, the accuracy values of the single-stage target detector model, the single-stage target detector model based on receptive field, and the proposed model were 0.89, 0.91, and 0.98 with root mean square errors of 0.15, 0.14, and 0.09, respectively. Among the three models, the recognition accuracies of the proposed model for breast cancer, lung cancer, brain cancer, kidney cancer, head and neck cancer, and liver cancer were 92.3%, 93.9%, 88.8%, 82.2%, 93.1%, and 83.2%, respectively. The average recognition time for tumors was within 3 seconds. The proposed model demonstrated outstanding performance across all types of tumors, thereby providing an effective solution for medical image recognition. © (2024), (Bio Tech System). All rights reserved.

关键词： Tumors

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Survey of Recent Transformers in Image,Video and Diffusion Models

引用

computers, Materials & Continua 2024年第7期80卷 37-60页

作者： Dinh Phu Cuong Le Dong Wang Viet-Tuan Le College of Computer Science and Electronic Engineering Hunan UniversityChangsha410082China Faculty of Information Technology Yersin University of Da LatDa Lat66100Vietnam Faculty of Information Technology Ho Chi Minh City Open UniversityHo Chi Minh City722000Vietnam

Transformer models have emerged as dominant networks for various tasks in computer vision compared to Convolutional Neural Networks(CNNs).The transformers demonstrate the ability to model long-range dependencies by utilizing a self-attention *** study aims to provide a comprehensive survey of recent transformerbased approaches in image and video applications,as well as diffusion *** begin by discussing existing surveys of vision transformers and comparing them to this ***,we review the main components of a vanilla transformer network,including the self-attention mechanism,feed-forward network,position encoding,*** the main part of this survey,we review recent transformer-based models in three categories:Transformer for downstream tasks,Vision Transformer for Generation,and Vision Transformer for *** also provide a comprehensive overview of recent transformer models for video tasks and diffusion *** compare the performance of various hierarchical transformer networks for multiple tasks on popular benchmark ***,we explore some future research directions to further improve the field.

关键词： Transformer vision transformer self-attention hierarchical transformer diffusion models

来源：评论

学校读者我要写书评

暂无评论

Classification of Football Player Actions Using Sensing Data 3

Classification of Football Player Actions Using Sensing Data

引用

3rd International Conference on Image Processing and Robotics, ICIPRoB 2024

作者： Hirasawa, Yukito Kinoshita, Yuichiro Kamarudin, Latifah Munirah Zakaria, Ammar University of Yamanashi Department of Computer Science and Engineering Yamanashi Japan Universiti Malaysia Perlis Faculty of Electronic Engineering and Technology Perlis Malaysia

ISBN: (纸本)9798350374766

This study classifies the actions of football players using sensing data acquired from wearable sensors attached to players and the ball. More than 800 sensing data with the labels of five types of player actions were created as a dataset. The neural networks were trained using 19 input items created by considering time-series variations in player and ball locations. The trained neural network model demonstrated a classification accuracy of 84.0%. The model successfully obtained sufficient accuracy for all types of *** results demonstrate that the sensing data and created input items can be effectively utilized for classifying the actions of football player. © 2024 IEEE.

关键词： Wearable sensors

来源：评论

学校读者我要写书评

暂无评论

Cumulative histogram as a feature selection technique for anomaly detection

引用

Multimedia Tools and Applications 2025年第12期84卷 10095-10107页

作者： Nassar, Mostafa Salama, Rania A. Saleeb, Adel A. El-bahnasawy, Nirmeen A. Ahmed, Hossam Eldin H. Abd El-Samie, Fathi E. Department of Electronics and Electrical Communications Engineering Faculty of Electronic Engineering Menoufia University Menouf32952 Egypt Department of Information Technology Faculty of Computers and Information Suez University Suez Egypt Department of Information Technology College of Computer and Information Sciences Princess Nourah Bint Abdulrahman University Riyadh11671 Saudi Arabia

The enhancement of Intrusion Detection Systems (IDS) is required to ensure protection of network resources and services. This is a hot research topic, especially in the presence of advanced intrusions and attacks. This paper provides a comparison between Distributed Cumulative Histogram (DCH) as a Feature Selection (FS) technique, Information Gain Ratio (IGR) FS and wrapper-based FS in terms of accuracy and Root Mean Square Error (RMSE). The utilization of DCH of the traffic instances in normal and attack cases allows us to compare the traffic charts. We can observe the difference between effective features and less effective ones. We verify the feasibility of using DCH as an FS technique in the field of anomaly detection with just six selected features giving more accurate results with most classifiers compared to the IGR and wrapper-based FS. We applied our experiments on the modern UNSW dataset with the WEKA simulation platform that contains a group of classification, feature reduction and selection techniques. © The Author(s) 2024.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Centromere Landscapes Resolved from Hundreds of Human Genomes

引用

Genomics, Proteomics & Bioinformatics 2024年第5期22卷 61-71页

作者： Shenghan Gao Yimeng Zhang Stephen J. Bush Bo Wang Xiaofei Yang Kai Ye School of Automation Science and Engineering Faculty of Electronic and Information EngineeringXi'an Jiaotong UniversityXi'an 710049China School of Computer Science and Technology Faculty of Electronic and Information EngineeringXi'an Jiaotong UniversityXi'an 710049China MOE Key Lab for Intelligent Networks&Networks Security Faculty of Electronic and Information EngineeringXi'an Jiaotong UniversityXi'an 710049China Center for Mathematical Medical The First Affiliated HospitalXi'an Jiaotong UniversityXi'an 710061China School of Life Science and Technology Xi'an Jiaotong UniversityXi'an 710049China Faculty of Science Leiden UniversityLeiden 2311 EZThe Netherlands

High-fidelity(HiFi)sequencing has facilitated the assembly and analysis of the most repetitive region of the genome,the ***,our current understanding of human centromeres is based on a relatively small number of telomere-to-telomere assemblies,which have not yet captured its full *** this study,we investigated the genomic diversity of human centromere higher order repeats(HORs)via both HiFi reads and haplotype-resolved assemblies from hundreds of samples drawn from ongoing pangenome-sequencing projects and reprocessed them via a novel HOR annotation pipeline,*** used this wealth of data to provide a global survey of the centromeric HOR landscape;in particular,we found that 23 HORs presented significant copy number variability between *** detected three centromere genotypes with unbalanced population frequencies on chromosomes 5,8,and *** inter-assembly comparison of HOR loci further revealed that while HOR array structures are diverse,they nevertheless tend to form a number of specific landscapes,each exhibiting different levels of HOR subunit expansion and possibly reflecting a cyclical evolutionary transition from homogeneous to nested structures and back.

关键词： Centromere sequence Genome evolution High-fidelity sequencing technology Higher order repeat annotation Human population

来源：评论

学校读者我要写书评

暂无评论

Deep Learning for Cross-Domain Few-Shot Visual Recognition: A Survey

引用

ACM Computing Surveys 2025年第8期57卷 1-37页

作者： Xu, Huali Zhi, Shuaifeng Sun, Shuzhou Patel, Vishal Liu, Li College of Computer Science Nankai University Tianjin China College of Electronic Science and Technology National University of Defense Technology Changsha China Faculty of Information Technology and Electrical Engineering University of Oulu Oulu Finland Johns Hopkins University Baltimore United States

While deep learning excels in computer vision tasks with abundant labeled data, its performance diminishes significantly in scenarios with limited labeled samples. To address this, Few-shot learning (FSL) enables models to perform the target tasks with very few labeled examples by leveraging prior knowledge from related tasks. However, traditional FSL assumes that both the related and target tasks come from the same domain, which is a restrictive assumption in many real-world scenarios where domain differences are common. To overcome this limitation, Cross-domain few-shot learning (CDFSL) has gained attention, as it allows source and target data to come from different domains and label spaces. This article presents the first comprehensive review of Cross-domain Few-shot Learning (CDFSL), a field that has received less attention compared to traditional FSL due to its unique challenges. We aim at providing both a position article and a tutorial for researchers, covering key problems, existing methods, and future research directions. The review begins with a formal definition of CDFSL, outlining its core challenges, followed by a systematic analysis of current approaches, organized under a clear taxonomy. Finally, we discuss promising future directions in terms of problem setups, applications, and theoretical advancements. © 2025 Copyright held by the owner/author(s).

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Shadow Extraction and Elimination of Moving Vehicles for Tracking Vehicles

引用

computers, Materials & Continua 2023年第11期77卷 2009-2030页

作者： Kalpesh Jadav Vishal Sorathiya Walid El-Shafai Torki Altameem Moustafa HAly Vipul Vekariya Kawsar Ahmed Francis MBui Department of Electronics&Communication Engineering Faculty of Engineering and TechnologyParul Institute of Engineering and TechnologyParul UniversityVadodaraGujarat391760India Department Electronics and Electrical Communications Engineering Faculty of Electronic EngineeringMenoufia UniversityMenouf32952Egypt Computer Science Department Community CollegeKing Saud UniversityRiyadh11362Saudi Arabia Electronics and Communications Engineering Department College of Engineering and TechnologyArab Academy for ScienceTechnology and Maritime TransportAlexandria1029Egypt Department of Computer Engineering Faculty of Engineering and TechnologyParul Institute of Engineering and TechnologyParul UniversityVadodaraGujarat391760India Department of Electrical and Computer Engineering University of Saskatchewan57 Campus DriveSaskatoonSK S7N5A9Canada

Shadow extraction and elimination is essential for intelligent transportation systems(ITS)in vehicle tracking *** shadow is the source of error for vehicle detection,which causes misclassification of vehicles and a high false alarm rate in the research of vehicle counting,vehicle detection,vehicle tracking,and *** of the existing research is on shadow extraction of moving vehicles in high intensity and on standard datasets,but the process of extracting shadows from moving vehicles in low light of real scenes is *** real scenes of vehicles dataset are generated by self on the Vadodara–Mumbai highway during periods of poor illumination for shadow extraction of moving vehicles to address the above *** paper offers a robust shadow extraction of moving vehicles and its elimination for vehicle *** method is distributed into two phases:In the first phase,we extract foreground regions using a mixture of Gaussian model,and then in the second phase,with the help of the Gamma correction,intensity ratio,negative transformation,and a combination of Gaussian filters,we locate and remove the shadow region from the foreground *** to the outcomes proposed method with outcomes of an existing method,the suggested method achieves an average true negative rate of above 90%,a shadow detection rate SDR(η%),and a shadow discrimination rate SDR(ξ%)of 80%.Hence,the suggested method is more appropriate for moving shadow detection in real scenes.

关键词： Change illuminations ImageJ software intelligent traffic systems mixture of Gaussian model National Institute of Health vehicle tracking

来源：评论

学校读者我要写书评

暂无评论

Invariant of Enhanced AES Algorithm Implementations Against Power Analysis Attacks

引用

computers, Materials & Continua 2022年第7期72卷 1861-1875页

作者： Nadia Mustaqim Ansari Rashid Hussain Sheeraz Arif Syed Sajjad Hussain Department of Electronic Engineering Dawood University of Engineering&TechnologyKarachiPakistan Faculty of Engineering Sciences and Technology Hamdard UniversityKarachiPakistan Faculty of Information Technology Salim Habib UniversityKarachiPakistan Faculty of Computer Sciences SZABISTKarachiPakistan

The security of Internet of Things(IoT)is a challenging task for researchers due to plethora of IoT *** Channel Attacks(SCA)are one of the major *** prime objective of SCA is to acquire the information by observing the power consumption,electromagnetic(EM)field,timing analysis,and acoustics of the ***,the attackers perform statistical functions to recover the *** Encryption Standard(AES)algorithm has proved to be a good security solution for constrained IoT *** paper implements a simulation model which is used to modify theAES algorithm using logicalmasking *** invariant of the AES algorithm hides the array of bits during substitution byte transformation of *** model is used against SCAand particularly Power Analysis Attacks(PAAs).Simulation model is designed on MATLAB *** will give better solution by hiding power profiles of the IoT devices against *** future,the lightweight AES algorithm with false key mechanisms and power reduction techniques such as wave dynamic differential logic(WDDL)will be used to safeguard IoT devices against side channel attacks by using Arduino and field programmable gate array(FPGA).

关键词： Side channel attacks power analysis attacks network security masking advance encryption standard

来源：评论

学校读者我要写书评

暂无评论

Mitigating Power System Oscillations in PMSGWind Integrated Grids Using Power electronics and Inertia Control: A Comprehensive Review 16

Mitigating Power System Oscillations in PMSGWind Integrated ...

引用

16th Annual Power electronics, Drive Systems, and Technologies Conference, PEDSTC 2025

作者： Sabo, Aliyu Jibia, Kabir Garba Shahinzadeh, Hossein Hayati, Mohammad Mohsen Abapour, Mehdi Gharehpetian, Gevork B. Department of Electrical and Electronic Engineering Malaysia Amirkabir University of Technology Tehran Polytechnic Department of Electrical Engineering Tabriz Iran Faculty of Electrical and Computer Engineering Tabriz Iran

ISBN: (纸本)9798331533946

The growing demand for reliable and sustainable energy has driven researchers and engineers to explore renewable energy sources to complement traditional power grids. Wind energy conversion systems (WECS), particularly those using permanent magnet synchronous generators (PMSG), are among the most widely adopted renewable energy solutions. Integrating WECS into traditional grids introduces challenges, including power system oscillations, especially during disturbances or faults. Inertia control and power electronics converters are pivotal in mitigating these oscillations and ensuring grid stability. This review investigates the design and optimization of damping controllers, emphasizing their integration with excitation systems to enhance the dynamic performance of PMSG-based wind integrated grids. Additionally, the role of power electronics in control strategies and inertia emulation for stable grid operation is discussed. The findings highlight the critical importance of advanced control measures in addressing the inherent uncertainties of renewable energy systems integrated with conventional grids. © 2025 IEEE.

关键词： Synchronous generators

来源：评论

学校读者我要写书评

暂无评论

Fine Tuned DBN Model for Food Ingredient Recognition: Introduction to Self-improved Tasmanian Devil Optimization Algorithm

Fine Tuned DBN Model for Food Ingredient Recognition: Introd...

引用

2023 IEEE International Conference on Integrated Circuits and Communication Systems, ICICACS 2023

作者： Madival, Sharanabasappa A. Jawaligi, Shivkumar S. Sharnbasva University Faculty of Engineering & Technology Department of Computer Science and Engineering Kalburgi India Sharnbasva University Faculty of Engineering & Technology Department of Electronic and Communication Engineering Kalburgi India

ISBN: (纸本)9798350398465

Food recognition has captivated much significance for health-related appliances. The traditional schemes mainly concern on the classification of food depending on its names and disregards the basic ingredient compositions. However, owing to shortage of datasets with labels of ingredient, the issues on food ingredient recognition (FIR) is often unnoticed. This work develops a new FIR approach, where, textual features, SIFT and deep features are derived. Then, the DBN classifier is deployed for the recognition of food ingredients. To get a precise recognition, tuning the weights of DBN is done via Improved TDO (ITDO) model. © 2023 IEEE.

关键词： FIR filters

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：