检索结果-内蒙古大学图书馆

Sustainable Expert systems (ICSES), International Conference on

作者： P. Ananthi K Nirmala Devi T. E. Ramya P. Shanmugapriya T. Aradhya Department of Computer Technology Kongu Engineering College Perundurai Erode Tamil Nadu Department of Computer Applications Madanapalle Institute of Technology & Science M.Sc Software Systems Kongu Engineering College Perundurai Erode Tamil Nadu

ISBN: (数字)9798331540364

ISBN: (纸本)9798331540371

Medical diagnosis is one of the areas that has been greatly influenced by the progress of computer vision technologies. This study presents a unique approach for the detection and counting of blood cells in hematology: You Only Look One algorithm version 7 (YOLOv7). YOLO is designed for real-time object detection, making it ideal for applications such as blood vessel detection where speed is critical. The architecture allows the model to process images faster than other recognition models, such as R-CNN or SSD, which is very important for situations that require fast results, such as analysis automatic blood at clinical sites. The purpose of the proposed method is to overcome the shortcomings of conventional methods and to accurately and quickly identify blood cells in mechanical images. The YOLOv7 model has been utilizedbecause it can detect objects in real-time with highprecision and speed. The methodology for bloodcell counting involves the use of YOLOv7 togenerate bounding boxes around each detectedblood cell in an image, where the count of these bounding boxes directly corresponds to the number of cells. This advancement in hematology not onlyimproves blood cell analysis efficiency but also expedites the process of diagnosing and planningtreatment in various medical situations. This paper details how YOLOv7 was modified and adjusted to meet the specific requirements of hematologicalimage analysis, including training models, preparing datasets, and evaluating performance. The study also addresses the potential impact of this technology on clinical workflows, highlightinghow it might help medical practitioners make decisions more quickly and intelligently. Hematology analysis systems including YOLOv7 are able to improve laboratory diagnostics and help patients by providing better care and results. This workconcludes by demonstrating the revolutionary potential of YOLOv7 in blood cell identificationand counting in hematology, paving the way for accurate and better

关键词： Analytical models Accuracy Computational modeling Cells (biology) Real-time systems Reliability Object recognition Medical diagnosis Blood Medical diagnostic imaging

来源：评论

学校读者我要写书评

暂无评论

CollectiveSFT: Scaling Large Language Models for Chinese Medical Benchmark with Collective Instructions in Healthcare

arXiv

引用

arXiv 2024年

作者： Zhu, Jingwei Tan, Minghuan Yang, Min Li, Ruixue Alinejad-Rokny, Hamid School of Software Engineering University of Science and Technology of China Hefei China Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China Xiangshui County Party School Yancheng China School of Biomedical Engineering UNSW Sydney Australia

The rapid progress in Large Language Models (LLMs) has prompted the creation of numerous benchmarks to evaluate their capabilities. This study focuses on the Comprehensive Medical Benchmark in Chinese (CMB) [25], showcasing how dataset diversity and distribution in supervised fine-tuning (SFT) may enhance LLM performance. Remarkably, We successfully trained a smaller base model to achieve scores comparable to larger models, indicating that a diverse and well-distributed dataset can optimize performance regardless of model size. This study suggests that even smaller models may reach high performance levels with carefully curated and varied datasets. By integrating a wide range of instructional content, our approach addresses potential issues such as data quality inconsistencies. Our results imply that a broader spectrum of training data may enhance a model's ability to generalize and perform effectively across different medical scenarios, highlighting the importance of dataset quality and diversity in fine-tuning processes. © 2024, CC BY-NC-SA.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Hot Spot Locating and Optimization of Calculation Errors in Arithmetic Expressions 7

Hot Spot Locating and Optimization of Calculation Errors in ...

引用

7th International Symposium on Advances in Electrical, Electronics, and Computer engineering

作者： Jinchen, Xu Yuanyuan, Xia Jiangwei, Hao Hao, Cao State Key Laboratory of Mathematical Engineering and Advanced Computing No. 62 Science Avenue High-Tech Zone Henan Zhengzhou450001 China National Key Laboratory of Science and Technology on Integrated Information Systems Technology Institute of Software Chinese Academy of Sciences No. 4 Zhongguancun South Fourth Street Haidian District Beijing10190 China

ISBN: (纸本)9781510656437

Error analysis is an important support for improving the precision of floating-point calculations. However, the floating-point error distribution does not have dominant characteristics, making it difficult to optimize floating-point calculation precision. This paper proposes the LFEE (Locating hot spots of floating-point expression errors) algorithm. The algorithm analyzes the error detection result of the expression to obtain the error hot spot, i.e., the step with the maximum error in the expression calculation sequence, followed by preforming precision optimization scheme for the error hot spot. The experimental results show that the LFEE algorithm can accurately locate the error hot spots and improve the accuracy of the function by optimizing the error hot spots. © 2022 SPIE. All rights reserved.

关键词： Error detection

来源：评论

学校读者我要写书评

暂无评论

Scheduling Periodic Real-Time Tasks with Inter-Task Synchronisation

Scheduling Periodic Real-Time Tasks with Inter-Task Synchron...

引用

Mediterranean Conference on Embedded Computing (MECO)

作者： Luká š Kohú tka Institute of Informatics Information Systems and Software Engineering Slovak University of Technology in Bratislava Bratislava Slovakia

This paper presents a new FPGA-based task scheduler that has a dedicated support of periodic hard real-time tasks in addition to aperiodic tasks. Whenever a period of a periodic task is elapsed, the task is scheduled automatically. The proposed scheduler is using Earliest Deadline First (EDF) algorithm. For task synchronisation, the scheduler supports temporary suspension of tasks with automatic resumption of tasks. Thanks to FPGA implementation of the scheduler and its priority queues, the scheduler operations take two clock cycles regardless of the number of tasks. The paper contains synthesis results for Intel FPGA Cyclone V.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fruit and Vegetable Detection with Calorie Estimation Built on Mobilenetv2

Fruit and Vegetable Detection with Calorie Estimation Built ...

引用

International Conference on Advances in Information technology (ICAIT)

作者： Sengottaiayn N Hamsanandhini S Rajesh Sharma R Akey Sungheetha Monika M Ketema Adare Computer Science & Engineering Alliance University Bengaluru India Department of Computer Technology Kongu Engineering College Erode India MSc Software Systems Kongu Engineering College Erode India Department of Computer Science and Engineering Adama Science and Technology University Adama Ethiopia

ISBN: (数字)9798350383867

ISBN: (纸本)9798350383874

Fruit and Vegetable Recognition with Calorie Estimation based on Mobilenetv2 is a pioneering research endeavor aimed at leveraging deep learning techniques to enhance dietary monitoring and health management. Building upon the success of neural network models in various domains, this study explores the application of Mobilenetv2 and EfficientNet architecture for accurately identifying fruits and vegetables from images and estimating their respective caloric content. The research dataset comprises meticulously curated images of diverse fruits and vegetables, ensuring comprehensive coverage across different categories. Through rigorous experimentation and evaluation, the proposed model demonstrates remarkable accuracy in fruit and vegetable recognition, achieving an impressive accuracy rate of 97.6%. Moreover, the incorporation of calorie estimation adds a novel dimension to dietary analysis, enabling users to make informed decisions regarding their nutritional intake. The findings of this research not only contribute to the advancement of computer vision techniques but also hold significant implications for personalized nutrition tracking and health- conscious applications.

关键词： Deep learning Computer vision Accuracy Architecture Neural networks Buildings Estimation Computer architecture Information technology Monitoring

来源：评论

学校读者我要写书评

暂无评论

Human Emotions Classification Using EEG via Audiovisual Stimuli and AI

引用

Computers, Materials & Continua 2022年第12期73卷 5075-5089页

作者： Abdullah A Asiri Akhtar Badshah Fazal Muhammad Hassan A Alshamrani Khalil Ullah Khalaf A Alshamrani Samar Alqhtani Muhammad Irfan Hanan Talal Halawani Khlood M Mehdar Radiological Sciences Department College of Applied Medical SciencesNajran UniversityNajranSaudi Arabia Faculty of Computer Science and Engineering GIK Institute of Engineering Sciences and TechnologyTopi23460Pakistan Department of Electrical Engineering University of Engineering and TechnologyMardan23200Pakistan Department of Software Engineering University of MalakandDir LowerPakistan Department of Computer Science and Information Systems College of EngineeringNajran University Saudi ArabiaNajran61441Saudi Arabia Electrical Engineering Department College of EngineeringNajran University Saudi ArabiaNajran61441Saudi Arabia Computer Science Department College of Computer Science and Information SystemsNajran UniversityNajranSaudi Arabia Anatomy Department Medicine CollegeNajran UniversityNajranSaudi Arabia

Electroencephalogram(EEG)is a medical imaging technology that can measure the electrical activity of the scalp produced by the brain,measured and recorded chronologically the surface of the scalp from the *** recorded signals from the brain are rich with useful *** inference of this useful information is a challenging *** paper aims to process the EEG signals for the recognition of human emotions specifically happiness,anger,fear,sadness,and surprise in response to audiovisual *** EEG signals are recorded by placing neurosky mindwave headset on the subject’s scalp,in response to audiovisual stimuli for the mentioned *** a bandpass filter with a bandwidth of 1-100 Hz,recorded raw EEG signals are *** preprocessed signals then further analyzed and twelve selected features in different domains are *** Random forest(RF)and multilayer perceptron(MLP)algorithms are then used for the classification of the emotions through extracted *** proposed audiovisual stimuli based EEG emotion classification system shows an average classification accuracy of 80%and 88%usingMLP and RF classifiers respectively on hybrid features for experimental signals of different *** proposed model outperforms in terms of cost and accuracy.

关键词： Electroencephalography emotion classification signal processing multilayer perceptron random forest

来源：评论

学校读者我要写书评

暂无评论

A Model-Based Approach to Automotive Feature Development for Updates and Upgrades

A Model-Based Approach to Automotive Feature Development for...

引用

2023 IEEE International Conference on Service-Oriented System engineering (SOSE)

作者： Marc Schindewolf Jan Willem Wittler Thomas Kühn Daniel Grimm Eric Sax Institut für Technik der Informationsverarbeitung Karlsruhe Institute of Technology Karlsruhe Germany Dependability of Software-intensive Systems Karlsruhe Institute of Technology Karlsruhe Germany Software Engineering and Programming Languages Martin Luther University Halle-Wittenberg Halle-Wittenberg Germany

The automotive industry faces challenges due to the increasing demand for customization and individualization by consumers. With a wide range of equipment levels and feature options, it has become impossible to test all possible configurations for a single vehicle during development and especially for vehicles already in service. As a basis for solving these challenges, integrated approaches for the development of upgradeable vehicles are required. In this context, future upgrade options should be considered and planned already in the design stage to enable sustainable business models for next vehicle generations. This paper proposes a refined variability model that combines two existing approaches to address the challenges faced by the industry. The same model can perform buildability or upgradeability checks and dynamic allocation optimization. The model is evaluated qualitatively by three exemplary use cases.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Review of the State-of-the-Art of Data Gloves 8

Review of the State-of-the-Art of Data Gloves

引用

8th IEEE International Symposium on Smart Electronic systems, iSES 2022

作者： Pan, Mingzhang Tang, Yingzhe Li, Hongqi Guangxi Key Laboratory of Manufacturing System & Advanced Manufacturing Technology School of Mechanical Engineering Guangxi University Nanning530004 China Brain-Controlled Intelligent Systems Laboratory School of Software Northwestern Polytechnical University Xi'an710072 China Yangtze River Delta Research Institute of NPU Taicang215400 China

ISBN: (纸本)9798350399226

Human-machine interaction has been the focus of recent research, with data gloves as one of the approaches gaining popularity for their high accuracy and convenience. This paper summarizes the latest research status of data gloves with a focus on the area of glove-based gesture recognition. The core technology of gesture recognition is described in detail from data processing to classification, and a quantitative analysis of the recent research is conducted. We found that though studies on applications and algorithms are the mainstream, the hardware design also accounts for a pretty large proportion of about 30%. Moreover, the number of gestures, subjects, and algorithms for majority of relevant studies has been summarized. © 2022 IEEE.

关键词： Gesture recognition

来源：评论

学校读者我要写书评

暂无评论

Report-Guided Cross-Modal Representation Learning for Predicting EGFR Mutations by Whole Slide Image

Report-Guided Cross-Modal Representation Learning for Predic...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Qiao, Qi Shi, Jun Jiang, Zhiguo Wang, Wei Wu, Haibo Zheng, Yushan Hefei University of Technology School of Computer Science and Information Engineering Hefei230601 China Hefei University of Technology School of Software Hefei230601 China Beihang University Image Processing Center School of Astronautics Beijing102206 China University of Science and Technology of China Division of Life Sciences and Medicine Department of Pathology First Affiliated Hospital of Ustc Hefei230036 China University of Science and Technology of China Intelligent Pathology Institute Division of Life Sciences and Medicine Hefei230036 China Beihang University School of Engineering Medicine Beijing Advanced Innovation Center for Biomedical Engineering Beijing100191 China

ISBN: (纸本)9798350386226

Traditional PCR/NGS-based multigene panel testing is time-consuming and costly. Predicting EGFR mutations directly from H&E stained whole slide images (WSIs) can alleviate these limitations. Furthermore, histopathological reports contain valuable textual information that correlates with tissue areas in WSIs. However, recent research mainly analyses EGFR mutation status only from a single modality, ignoring rich information contained in reports. In this paper, we propose a report-guided cross-modal representation learning method for predicting EGFR mutations by WSIs. Specifically, we reconstruct report-level embeddings through exploring intrinsic relationships between diagnostic words in histopathological reports and tissue areas in WSIs. Finally, reconstructed histopathological report embedding and aggregated WSI embedding are fused for final prediction. More importantly, molecular testing report is also introduced as prior supervision information at the training stage to guarantee semantic consistency of fused feature and molecular report embedding. We evaluate our method on the TCGA-EGFR public benchmark dataset and an in-house clinical dataset (USTC-EGFR). Experimental results demonstrate that our method outperforms existing approaches in EGFR mutation prediction, highlighting the benefits of cross-modal learning in enhancing feature representational ability. The code is available at https://***/HFUT-miaLab/RCRL. © 2024 IEEE.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

A Novel Algorithm for Vertex Sum Distinguishing Total Coloring Based on Multiobjective Optimization

引用

Journal of engineering Science and technology Review 2021年第6期14卷 107-115页

作者： Huanping, Zhao Dangqin, Xue Huojie, Shi School of Computer and Software Nanyang Institute of Technology Nanyang473004 China School of Intelligent Manufactuing Nanyang Institute of Technology Nanyang473004 China Department of Biological Systems Engineering Washington State University PullmanMI98101 United States

Graph coloring is an important research field in graph theory. In vertex sum distinguishing total coloring, the constraint condition, that is, the color sum of each vertex is different from that of its associated edges is added on the basis of the normal total coloring. A novel algorithm was designed to increase the vertex sum distinguishing total coloring effciency. Subobjective functions were designed according to the vertex constraint, edge constraint, vertex-edge constraint, and vertex-edge sum constraint to improve the vertex sum distinguishing total coloring efficiency of random graphs. In each subobjective function, iterative swap was performed step by step using the coloring matrix and color set complement, in which the conflict was handled following the idea of impressed variation, thereby realizing the vertex sum distinguishing total coloring of random graphs. In the end, the lower bound of chromatic number in the vertex sum distinguishing total coloring was proven through the theoretical analysis and experimental comparison. Results demonstrate that when the order of a graph is smaller than 1000 and the edge density is smaller than 0.1, the conflict handling function can be converged at a high rate. When the order of the graph is greater than 1000, the convergence rate of the algorithm declines rapidly, and the accurate coloring result can be obtained only by increasing the coloring quantity, indicating that the vertex sum distinguishing total chromatic number of a connected graph with the order of not smaller than 3 ranged from μΣt(G) to μΣt(G)+3. This finding is consistent with the algorithm analysis result. On this basis, this algorithm can effectively complete the vertex sum distinguishing total coloring of random graphs, and its time complexity does not exceed O(n3). The proposed algorithm provides evidence for exploring complex networks, transportation, and network security © 2021 School of Science, IHU. All rights reserved

关键词： Multiobjective optimization

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：