检索结果-内蒙古大学图书馆

Traditional Chinese Medicine Health Status Identification with Graph Attention Network 1

4th International Conference on Machine Learning for Cyber Security, ML4CS 2022

作者： Fu, Amin Ma, Jishun Wang, Chuansheng Zhou, Changen Li, Zuoyong Teng, Shenghua College of Electronic and Information Engineering Shandong University of Science and Technology Qingdao266590 China Department of Automatic Control Technical Polytechnic University of Catalonia Barcelona08034 Spain Research Base of Traditional Chinese Medicine Syndrome Fujian University of Traditional Chinese Medicine Fuzhou350122 China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control College of Computer and Control Engineering Minjiang University Fuzhou350121 China

ISBN: (数字)9783031200960

ISBN: (纸本)9783031200953

The Traditional Chinese Medicine Health Status Identification plays an important role in TCM diagnosis and prescription recommendation. In this paper, we propose a method of Status Identification via Graph Attention Network, named SIGAT, which captures the complex medical correlation in the symptom-syndrome graph. More specifically, we construct a symptom-syndrome graph in that symptoms are taken as nodes and the edges are connected by syndromes. And we realize automatic induction of symptom to state element classification by using the attention mechanism and perceptron classifier. Finally, we conduct experiments by using hamming loss, coverage, 0/1 error, ranking loss, average precision, macro-F1 score, and micro-F1 score as evaluation metrics. The results demonstrate that the SIGAT model outperforms comparison algorithms on Traditional Chinese Medicine Prescription Dictionary dataset. The case study results suggest that the proposed method is a valuable way to identify the state element. The application of the graph attention network classification algorithm in TCM health status identification is of high precision and methodological feasibility. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Minimization of Dynamic Programming Algorithm by Three-dimension Model Collison Test Fitting

Minimization of Dynamic Programming Algorithm by Three-dimen...

引用

作者： Zhongming Yang Lu Xiaohui Lilong Huang Jun Yu Jianhui Yang College of Computer Engineering Technical Guangdong Polytechnic of Science and Technology College of information Technology Jiaxing Vocational Technical College South China University of Technology

In the collision test of simulating object in reality in Unity 3D, the common method taken for non-convex model is convex decomposition. While there exist various kinds of de composition towards models of different forms, it is a combination optimization issue which haven't got the optimized algorithm and which is tedious and time-consuming. While the method of directly judging whether the point is in the inner model or not shows clearer logic and faster judging speed. This judging method can be used in the establishment of non-convex model in computer. The non-convex model,after convex decomposed, is converted into several convex models of fitting model which is then operated collision test. This test method shows a characteristic of simplicity, high-speed and high university.

关键词： collision detection Dynamic Programming model fit

来源：评论

学校读者我要写书评

暂无评论

Convolutional Bi-GRU-based prediction model for Climate Indicators

Convolutional Bi-GRU-based prediction model for Climate Indi...

引用

International Conference on Electronics technology (ICET)

作者： Tsung-Ming Lo Hong-Tao Zhang Yun-Bing He Yi-Zhi Liu Wan-Ying Zhang Qiong-Dan Liang Zhen Bei Guangdong-Taiwan College of Industrial Science & Technology Dongguan University of Technology Dongguan China School of Traffic Information Engineering Guangxi Vocational and Technical College of Communications Nanning China Department of Public administration Nanfang College Guangzhou Guangzhou China School of Electrical and Computer Engineering Nanfang College-Guangzhou Guangzhou China Intelligent Manufacturing Engineering Dongguan University of Technology Dongguan China

ISBN: (数字)9798350363951

ISBN: (纸本)9798350363968

Climate prediction is critical to a wide range of fields, from agriculture to public health, but traditional methods face challenges due to the complexity and time-space characteristics of climate data. Machine learning techniques provide a promising solution by effectively extracting features from climate indicator data. In this study, we propose a new method for predicting climate indicators by combining CNN-Bi-GRU models with FNN networks. Through evaluation, our method demonstrates excellent prediction performance in terms of RMSE and MAE on both test and training sets, and robust convergence behavior is observed in model training. In addition, our method achieves high accuracy in predicting key climate metrics such as temperature and rain frequency, providing valuable information for understanding climate dynamics. Comparison experiments with LSTM-FNN, Double-LSTM, BiLSTM, and Bi-GRU models highlight the superiority of the CNNBi-GRU approach, especially in reducing temperature prediction errors. In conclusion, this study presents a promising approach to climate prediction that can enhance our understanding of climate variability and support informed decision making in various industries.

关键词： Training Measurement Accuracy Rain Predictive models Feature extraction Data models

来源：评论

学校读者我要写书评

暂无评论

A Critical Review Analysis of the Opportunities and Potential of Implementing Cloud Computing System for Large Scale Ad Hoc Network 2

A Critical Review Analysis of the Opportunities and Potentia...

引用

2nd International Conference on Advance Computing and Innovative Technologies in engineering, ICACITE 2022

作者： Gowtham, M.S. Shenbagharaman, A. Shunmugapriya, B. Nagavarapu, Sateesh Olga, Antonyuk ECE Karpagam Institute of Technology Tamilnadu Coimbatore India CSE National Engineering College Kovilpatti India Computer Science and Engineering Malla Reddy Institute of Technology Telangana Secunderabad India National Technical University of Ukraine 'Igor Sikorsky Kyiv Polytechnic Institute' Faculty of Sociology and Law Department of Economic and Administrative Law Kyiv Ukraine

ISBN: (纸本)9781665437899

The increase in the usage of various computing and mobile devices has resulted in implementing large scale ad hoc networks as the user demand is on the rise and companies' find it difficult to invest more in the IT infrastructure to meet the surging demand. The traditional model of networking enables the mobile devices to face various issues like lower bandwidth, mobility, security and storage et. Hence, in order to meet the overall service requirement and to enhance the overall efficiency of the network, cloud computing was introduced. The implementation of these devices tends to support in every node, it enhances better communication in a better range towards another nodes. There is a critical administration and support devices from everywhere in an effective manner. Hence the new paradigm of implementing cloud computing support the computing and medical devices in the neighbouring network. The ad hoc network supports in covering larger area base and hence cloud computing supports them in enhancing the effectiveness of operations. This study covers in addressing the critical determinants of analysing the overall opportunities and potential in implementing cloud computing for ad hoc networks. The major factors considered are enhancing the processing capabilities using cloud computing, scalability of network and autonomous and independent networking support. These aspects promote enhanced ad hoc networking for enhancing communication between the devices, enable the organisation to spend less on the IT infrastructure © 2022 IEEE.

关键词： Mobile ad hoc networks

来源：评论

学校读者我要写书评

暂无评论

Fingerprint Matching for Noisy and Distorted Patterns Using a Siamese Network With ResNet50 and Multihead Attention

引用

IEEE Access 2025年 13卷 88047-88064页

作者： Sawhney, Tinny Sharma, Ashu Abrol, Pawanesh Kumar Lehana, Parveen Chaahat Yadav, Vaishali Scherer, Rafal Kulakov, Oleksii Ali Alzubi, Ahmad University of Jammu DSP Laboratory Department of Electronics Jammu180006 India University of Jammu Department of Computer Science and IT Jammu180006 India Chitkara University Institute of Engineering and Technology Chitkara University Department of Computer Science and Engineering Punjab Rajpura140401 India Manipal University Jaipur Department of Computer Science & Communication Engineering Jaipur303007 India Czestochowa University of Technology Department of Artificial Intelligence Częstochowa42-200 Poland Faculty of Informatics and Software Engineering National Technical University of Ukraine "Igor Sikorsky Kyiv Polytechnic Institute" Kyiv03056 Ukraine King Saud University Community College Department of Computer Science Riyadh11451 Saudi Arabia

Dermatoglyphics, the study of unique ridge patterns on fingertips, plays a crucial role in fingerprint-based identification. However, skin conditions such as psoriasis, eczema, and verruca vulgaris can distort these patterns. This distortion creates challenges for fingerprint matching systems in forensic science and biometric authentication. This paper proposes a Siamese network with a modified ResNet50 architecture and multihead attention mechanisms to improve fingerprint matching under such distortions. The Siamese network enables the system to compare fingerprint pairs effectively, even under distortions. The modified ResNet50 architecture captures intricate ridge patterns, while the multihead attention mechanisms focus on critical fingerprint regions. Overall, the proposed approach enhances the system’s ability to learn discriminative features. As a result, it can effectively differentiate between matched and unmatched fingerprint pairs, even in the presence of moderate to extreme noise. The proposed system was trained on the Sokoto coventry fingerprint dataset (SOCOFing) and a custom dataset. Experimental results demonstrate high accuracy, with the system achieving 99.47% accuracy under low noise conditions and 90% under moderate noise. However, performance declined to 55.56% under extreme distortions. A comparative analysis highlighted the superiority of the proposed system over widely used minutiae-based methods. The latter exhibited a significant drop in matching scores, falling below 15% for highly distorted fingerprints. These findings underscore the limitations of traditional fingerprint recognition techniques and highlight the effectiveness of proposed approach in handling dermatoglyphic distortions. © 2013 IEEE.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

U-SEANNET: A SIMPLE, EFFICIENT AND APPLIED U-SHAPED NETWORK FOR DIAGNOSIS OF NASAL DISEASES ON NASAL ENDOSCOPIC IMAGES

arXiv

引用

arXiv 2023年

作者： Yue, Yubiao Xue, Jun Wang, Chao Liang, Haihua Li, Zhenzhang College of Mathematics and Systems Science Guangdong Polytechnic Normal University Guangzhou China School of Biomedical Engineering Guangzhou Medical University Guangzhou China School of Computer Science and Technology Anhui University Anhui China

Numerous studies have affirmed that deep learning models can facilitate early diagnosis of lesions in endoscopic images. However, the lack of available datasets stymies advancements in research on nasal endoscopy, and existing models fail to strike a good trade-off between model diagnosis performance, model complexity and parameters size, rendering them unsuitable for real-world application. To bridge these gaps, we created the first large-scale nasal endoscopy dataset, named 7-NasalEID, comprising 11,352 images that contain six common nasal diseases and normal samples. Subsequently, we proposed U-SEANNet, an innovative U-shaped architecture, underpinned by depth-wise separable convolution. Moreover, to enhance its capacity for detecting nuanced discrepancies in input images, U-SEANNet employs the Global-Local Channel Feature Fusion module, enabling it to utilize salient channel features from both global and local contexts. To demonstrate U-SEANNet’s potential, we benchmarked U-SEANNet against seventeen modern architectures through five-fold cross-validation. The experimental results show that U-SEANNet achieves a commendable accuracy of 93.58%. Notably, U-SEANNet’s parameters size and GFLOPs are only 0.78M and 0.21, respectively. Our findings suggest U-SEANNet is the state-of-the-art model for nasal diseases diagnosis in endoscopic images. Copyright © 2023, The Authors. All rights reserved.

关键词： Endoscopy

来源：评论

学校读者我要写书评

暂无评论

Bankruptcy Prediction using Emperor Penguin Optimizer with Deep Learning Model on Qualitative Dataset 5

Bankruptcy Prediction using Emperor Penguin Optimizer with D...

引用

5th International Conference on Smart Systems and Inventive technology, ICSSIT 2023

作者： Abrol, Vijay Singh, Priyanka Subhashini, R. Kumar, A. Sasi Singh, Kamlesh Mannar, B. Raja Uttam Group of Institutions Department of Computer Science Uttar Pradesh Agra India Sgsj Government Polytechnic Department of Technical Education Uttar Pradesh Bulandshahr India Sona College of Technology Department of Information Technology Tamil Nadu Salem India Mentor-IT - Inurture Education Solutions Pvt Ltd Bangalore Department of Cloud Technology and Data Science Institute of Engineering and Technology Srinivas University Srinivas Nagar Mukka Surathkal Dakshina Kannada District Karnataka State Mangalore574146 India Graphic Era Hill University Dehradun Campus Department of Computer Science and Engineering Dehradun India Sri Venkateswara University Department of Commerce Andhra Pradesh Tirupati India

ISBN: (纸本)9781665474672

Bankruptcy prediction and credit risk study are amongstthe most important problems in the domain of financial and accounting decision making. Evolving an effectual Classification Rule Induction (CRD) structure for bankruptcy prediction and credit risk examination at suitable time is vital to avoid the business communities being bankrupt. Classical statistical approaches and Artificial Intelligence (AD) play an important role in bankruptcy prediction and credit risks. Most previous research works can be executed on quantitative approaches but some studies are presented on qualitative approaches for improvising the efficiency of bankruptcy prediction techniques. This study focuses on the development of Bankruptcy Prediction using Emperor Penguin optimizer with Deep Learning (BP-EPODL) model on Qualitative Dataset. The projected BP-EPODL technique identifies the existence of bankruptcy or not. Here, the BP-EPODL technique exploits EPO algorithm for the choice of optimum features. For bankruptcy prediction, the BP-EPODL technique applies Long Short Term Memory (LS TM) model. At last, Adam optimizer is applied as a hyperparameter tuning technique for the IS TM model. The experimental validation of the BP-EPODL technique is tested on benchmark qualitative dataset. The obtained values inferred that the BP-EPODLtechnique has shown effectual results over other models. © 2023 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Financial Market Sentiment Prediction technology and Application Based on Machine Learning Model 2

Financial Market Sentiment Prediction Technology and Applica...

引用

2nd International Conference on Advance Computing and Innovative Technologies in engineering, ICACITE 2022

作者： Mousa, Saeed Ramkumar, Gowtham Mohamma, Aram Jawhar Othman, Bestoon Narayana, M Srinivasa Pant, Bhasker University of Lille for Science and Technology Department of Clerse France SRM Institute of Science and Technology Department of Commerce College of Science and Humanities Kattankulathur Chennai India Erbil Technical Administrative College Erbil Polytechnic University Department of Accounting Techniques Erbil Iraq Koya Technical Institute Erbil Polytechnic University Business Administration Iraq College of Administration and Economics Nawroz University Department of Business Administration Duhok Iraq Kl Business School K L University Koneru Lakshmaiah Education Foundation Vijayawada India Graphic Era Deemed to Be University Department of Computer Science & Engineering Uttarakhand Dehradun India

ISBN: (纸本)9781665437899

In the real word, a variety of situation may occur where strategy control becomes mandatory to make effective decision. In order to meet this requirements, combination of reinforcement learning and sentiment analysis is important that also may help to show theoretical research direction. This research work displays the feature of the machine learning related to the sentiment analysis and deep reinforcement learning to determine the Financial Market sensitivity. The experimental results can help to achieve better gains by demonstrating the advantages of the machine learning based model over existing traditional reinforcement learning model for predicting financial market. © 2022 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Cloud-based Parallel Computing System Via Single-Client Multi-Hash Single-Server Multi-Thread 3

Cloud-based Parallel Computing System Via Single-Client Mult...

引用

3rd International Conference on Advance of Sustainable engineering and its Application, ICASEA 2021

作者： Rashid, Zryan Najat Zeebaree, Subhi R. M. Sadeeq, Mohammed A. M. Zebari, Rizgar R. Shukur, Hanan M. Alkhayyat, Ahmed Sulaimani Polytechnic University Information Technology Dept. Sulemani Iraq Duhok Polytechnic University Technical College of Engineering Energy Department Duhok Iraq Duhok Polytechnic University Technical College of Administration Information Technology Mangement Department Duhok Iraq Nawroz University Computer Science Dept. Duhok Iraq Al-Kitab University Dept. Computer Engineering Kirkuk Iraq Islamic University Najaf Technical Engineering Dept. Najaf Iraq

ISBN: (纸本)9781665497367

Parallel Distributed Processing is a relatively new method. Distributed cloud connects data and applications delivered by utilizing cloud computing technologies from several geographical locations. When something is distributed in IT, it is transferred among multiple systems located across diverse areas. The expanse of information besides the interval it takes towards analyzing adding to monitoring projected results efficiently and effectively has been dramatically enhanced. This paper presented a system to assist users in doing composite tasks interactively with the least processing time. Distributed-Parallel-Processing (DPP) and CloudComputing (CC) are the two most great technologies, can process and answer the user problem quickly. Developing a suggested system used several sources (source generators, under-test load, computing machines, and processing units) and (webservers) through the cloud. Hash codes are generated on the client-side and sent towards the webserver. The webserver delivers these does to cracking servers that have been specified. It has been verified that while employing light load (single hash-code) with multi-servers and multiprocessors, the suggested system gives improved efficiency (in terms of Kernel-burst, User-bust, and Total-execution) timings. Although it has been demonstrated that employing large loads (many under-testing codes) with many computing machines using multiprocessors improves the system's performance. The suggested computational system outperforms it in terms of parallel processing. The proposed method took these situations into account due to the code-breaking influences by two precarious criteria (minimal breaking-time besides cost-effective usage of computer resources). © 2021 IEEE.

关键词： Distributed cloud

来源：评论

学校读者我要写书评

暂无评论

The Role of Parallel Computing Towards Implementation of Enhanced and Effective Industrial Internet of Things (IOT) Through Manova Approach 2

The Role of Parallel Computing Towards Implementation of Enh...

引用

2nd International Conference on Advance Computing and Innovative Technologies in engineering, ICACITE 2022

作者： Mohseni, Milad Othman, Bestoon Abdulmaged Raturi, Preeti Mishra, A.B. Priya, S.Janu Saravanan, V. Tabriz Iran Business Administration Koya Technical Institute Erbil Polytechnic University Erbil Iraq Tula's Institute India International Institute of Management Studies Maharashtra Pune India K.Ramakrishnan College of Engineering Anna University India College of Engineering and Technology Dambi Dollo University Department of Computer Science Dambi Dollo Ethiopia

ISBN: (纸本)9781665437899

Parallel computing is considered one of the major computing models that have the potential of performing multiple tasks within a single device. Incorporation of parallel computing in implementing IoT in industrial operations, the accuracy of data extraction and data analysis is ensured that makes the decision-making process more effective. Relying largely on technological innovations, IIoT has aimed at incorporating various computing models into its operations to enhance its efficiencies in industrial operations and data accumulation. Considering this scenario, a survey to understand the role of PC in IIoT implementation has been executed here concerning 51 participants from various industries. Results drawn from this survey responses has assisted in identifying the effectiveness of parallel computing in implementing enhanced and effective IIoT. Here it has been discussed about the SPSS, in SPSS total 4 variables are used one independent variable and the 3 dependent variable has been used. The independent variable which has been used is named as Parallel Computing IIOT, the 3 dependent variable used is the Accuracy of Parallel computing, Effectiveness of parallel computing, role of parallel computing in processing data. On the other hand, ANOVA, reliability test have been performed in SPSS as per MANOVA approaches for evaluating the parallel computing on IIOT. © 2022 IEEE.

关键词： Internet of things

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：