检索结果-内蒙古大学图书馆

32nd ACM International Conference on Multimedia, MM 2024

作者： Wang, Wenxuan Wang, Chenglei Qi, Huihui Ye, Menghao Qian, Xuelin Wang, Peng Zhang, Yanning School of Computer Science Northwestern Polytechnical University China Natl. Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Shaanxi Xi'an China School of Automation Northwestern Polytechnical University The BRain and Artificial INtelligence Lab Shaanxi Xi'an China

ISBN: (纸本)9798400706868

With the wide application of deep neural network models in various computer vision tasks, there has been a proliferation of adversarial example generation strategies aimed at deeply exploring model security. However, existing adversarial training defense models, which rely on single or limited types of attacks under a one-time learning process, struggle to adapt to the dynamic and evolving nature of attack methods. Therefore, to achieve defense performance improvements for models in long-term applications, we propose a novel Sustainable Self-Evolution Adversarial Training (SSEAT) framework. Specifically, we introduce a continual adversarial defense pipeline to realize learning from various kinds of adversarial examples across multiple stages. Additionally, to address the issue of model catastrophic forgetting caused by continual learning from ongoing novel attacks, we propose an adversarial data replay module to better select more diverse and key relearning data. Furthermore, we design a consistency regularization strategy to encourage current defense models to learn more from previously trained ones, guiding them to retain more past knowledge and maintain accuracy on clean samples. Extensive experiments have been conducted to verify the efficacy of the proposed SSEAT defense method, which demonstrates superior defense performance and classification accuracy compared to competitors. © 2024 ACM.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Parameter sensitivity analysis of the myocardial cell models in ischemia and screening of drug targets

Parameter sensitivity analysis of the myocardial cell models...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Jun Liu Cuiping Liang Kuanquan Wang School of Computer Science and Technology Harbin Institute of Technology (HIT) Harbin China Beijing Institute of Computer Technology and Application Beijing China

Previous studies have shown that coronary artery occlusion can cause myocardial ischemia, which can induce ventricular tachycardia or fibrillation. According to the time sequence, myocardial ischemia can be divided into different pathological stages: the ischemia 1a stage (0-15 minutes), the ischemia 1b stage (15-45 minutes), the short-term myocardial infarction (MI) (within a few days) and the long-term MI (within a few weeks). However, few studies give attention to antiarrhythmic drugs directly acting on ion channels for the treatment of myocardial ischemia. The main reason is that the effective targets in myocardial ischemia are unclear. Therefore, based on the technology of electrophysiological simulation, the paper modeled the human ventricular cell model in myocardial ischemia. On this basis, the parameter sensitivity of the model was analyzed and the effective drug targets are selected. Firstly, human ventricular cell models were modeled in ischemia 1a, ischemia 1b, short-term MI and long-term MI based on the experimental data. Then, the sensitivity analysis of output parameters (APA, APD and RP) of the cell model in ischemia was analyzed based on the Sobol method. The results of parameter sensitivity analysis in this paper showed that APD of cell models in ischemia 1a, ischemia 1b and short-term MI was the most sensitive to the change of I KATP , and APA and RP of cells were the most sensitive to the change of [K + ] o . The parameter sensitivity analysis of the cell model in long-term MI showed that APD of cell models was sensitive to I Ks and I CaL , and APA was most sensitive to I Na . Therefore, according to the results of parameter sensitivity analysis, the possible effective targets for the treatment of myocardial ischemia can be preliminarily selected: [K + ] o , I KATP , I CaL and I Na .

关键词：

来源：评论

学校读者我要写书评

暂无评论

Industrial IoT Smart Manufacturing Systems based on Cloud Computing Energy Efficiency Analysis using Machine Learning Algorithms 3

Industrial IoT Smart Manufacturing Systems based on Cloud Co...

引用

3rd International Conference on Electronics and Renewable Systems, ICEARS 2025

作者： Chinnasamy, P. Khan, Patan Feridoz Sasikala, C. Swathi, Mavalluru Kumar, M. Prema Yadav, Ajay Kumar Kalasalingam Academy of Research and Education School of Computing Department of Computer Science and Engineering Tamilnadu India Mohan Babu University School of Computing Department of Computer Science and Engineering Andhra Pradesh Tirupati India Dept of Cse Andhra Pradesh Ananthapuramu India Audisankara College of Engineering and Technology Andhra Pradesh India Dept. of Ece Andhra Pradesh Bhimavaram India United Institute of Management Department of Computer Application Prayagraj India

ISBN: (纸本)9798331509675

With open connectivity and emergent computing, the Industrial Internet of Things (IIoT) combined with cloud computing resources provides significant breakthroughs in the field of industrial automation. These developments lead to the evolution of supplemental services, which improve automation in the production and industrial sectors. This research proposes novel technique in smart manufacturing system based on cloud computing with IIoT in energy efficiency using machine learning. Here the smart manufacturing process has been analysed based on IIoT with cloud computing network, where the energy efficiency is analysed using virtual machine-based reinforcement markov chain based linear regression. Experimental analysis has been carried out in terms of latency, energy efficiency, task response time, accuracy. proposed technique obtained 97% of Latency, 95% of Energy efficiency, 98% of Accuracy, 94% of Task response time. © 2025 IEEE.

关键词： Smart manufacturing

来源：评论

学校读者我要写书评

暂无评论

Using analytic hierarchy process to evaluate deep learning for infrared target recognition

引用

Multimedia Tools and applications 2024年第38期83卷 86229-86245页

作者： Xu, Laixiang Cao, Bingxu Wei, Xinhong Li, Bei Su, Jingfeng Ning, Shiyuan Zhao, Junmin School of Computer and Data Science Henan University of Urban Construction Pingdingshan467036 China School of Information Engineering Luohe Vocational Technology College Henan University of Technology Luohe Institute of Technology Luohe462000 China School of Computer and Data Science Innovation Laboratory of Smart Traffic and Big Data Development of Hainan Province Pingdingshan467036 China School of Computer and Data Science Research Center of Smart City and Big Data Engineering of Henan Province Henan University of Urban Construction Pingdingshan467036 China Department of Software Information China Electronics Technology Group Corporation 36-th Research Institute Jiaxing314033 China School of Computer and Data Science Research Center of Smart City and Big Data Engineering of Henan Province Research Center of Intelligent Campus Application Engineering of Henan Province Innovation Laboratory of Smart Traffic and Big Data Development of Hainan Province Henan University of Urban Construction Pingdingshan467036 China

In order to promote the evaluation performance of deep learning infrared automatic target recognition (ATR) algorithms in the complex environment of air-to-air missile research, we proposed an analytic hierarchy process (AHP) evaluation system consisting of the target recognition ability, the generalization recognition ability, the anti-interference ability, the background suppression ability, and the cost metrics ability. According to detailed quantitative analysis and experimental results, we establish probability evaluation models and get their probability values. Compared with traditional evaluation systems, our proposed method implementation is showing high reliability. Similar superior performances are also achieved, such as quick, comprehensive, and scientific. Through the above research, the key technology of deep learning performance evaluation in automatic target recognition has been broken through, which provides some basis and guidance for the analysis of infrared imaging-guided weapon systems. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Infrared imaging

来源：评论

学校读者我要写书评

暂无评论

Stage Wise Classification and Prediction of Non-Alcoholic Fatty Liver Disease using Hybrid Approach 2

Stage Wise Classification and Prediction of Non-Alcoholic Fa...

引用

2nd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2024

作者： Prabagaran, A. Balamurugan, N.M. Kalavathi, S. Padmanabhan, P. Angelin Blessy, J. Gupshup Technology India Pvt Ltd Bengaluru India Sri Venkateswara College of Engineering Department of Computer Science and Engineering Chennai India Sri Venkateswara College of Engineering Department of Information Technology Chennai India Noida Institute of Engineering & Technology Department of CSE Uttar Pradesh Greater Noida201306 India School of Computing Science and Engineering Galgotias Univeristy Dept of Computer Application India

ISBN: (纸本)9798350327533

The world's most serious chronic liver condition is Non-Alcoholic Fatty Liver Disease (NAFLD). The early stage prediction saved people's lives. Recent machine and deep learning, help to predict and classify diseases. The main goal of this work is to make an advanced prediction system that uses plasma lipid data and MRI images to predict the stage-wise classification of NAFLD images. The four main stages of liver disease are normal, steatosis, steatohepatitis, and cirrhosis. The machine and deep learning techniques to identify and classify cirrhosis disease in NAFLD. This research study proposes a machine and deep learning techniques with features that classify and predict the NAFLD. The random forest algorithm is used to predict the disease images into binary classifications, and a deep neural network is used for stage-wise classification. Initially, different features are used to classify the liver. This work uses 52 features, such as GLGCM and GLCM to predict and classify the fatty liver. The proposed method combined the initial prediction features using the random forest method and deep neural network to classify different stages of livers images. The experimental work is done with the help of MRI images and various iterations for evaluation. The experimental results were evaluated using three metrics, such as specificity, sensitivity, and accuracy. The predicted values of this methodology were 96.26%, 95.7%, and 97.6%. © 2024 IEEE.

关键词： Cirrhosis Hybrid Method Random Forest-Deep Neural Network Stage Wise Classification

来源：评论

学校读者我要写书评

暂无评论

Developing Campus Digital Twin with Integrated 3D Point Clouds and 3D Modeling Techniques

Developing Campus Digital Twin with Integrated 3D Point Clou...

引用

International Conference on Cybernetics and Intelligent System (ICORIS)

作者： Ryan Nathan Utama Jonathan Sutjiatmadja Fabrian Osmond Lucas Stefan Alexander A S Gunawan Andry Chowanda Edy Irwansyah Fabian Surya Pramudya Game Application & Technology Department School of Computer Science Bina Nusantara University Jakarta Indonesia Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798331539603

ISBN: (纸本)9798331539610

Exploring digital twin technology through the creation of 3D digital model offers a powerful tool for enhancing real-time monitoring, predictive analysis, and optimization of complex systems. The purpose of this study is to develop a 3D digital model of our building campus as the first step towards developing a digital twin of the university. In this study, we develop a digital model with integrated 3D point clouds and 3D modeling techniques. By scanning the physical model of the campus, data in the form of point clouds is extracted and unnecessary noise is deleted using Autodesk Recap Pro. These point clouds are used as a benchmark to ensure the 3D models created using Blender are as accurate as possible to the physical model. After successfully creating the digital model, several features/interactions are implemented using Unity to mimic the physical model, thus developing the digital twin. The digital twin of the campus will be used to develop a virtual tour of the campus. We concluded that the 3D digital model of the campus was successfully developed, despite the time-consuming nature of the process. We hope that this study serves as a reference to optimize and enhance digital twin development in the future.

关键词： Point cloud compression Solid modeling Three-dimensional displays Buildings Benchmark testing Feature extraction Data models Real-time systems Digital twins Data mining

来源：评论

学校读者我要写书评

暂无评论

The Preparation Method, Resistive Switching Mechanism and application Prospects of Memristor 7

The Preparation Method, Resistive Switching Mechanism and Ap...

引用

7th International Conference on Electrical, Mechanical and computer Engineering, ICEMCE 2023

作者： Li, Jiao Zhao, Ximei Lei, Tengfei Chai, Lin Wang, Shi Yu, Yuna Collaborative Innovation Center of Memristive and Computing Application Qilu Institute of Technology Jinan250200 China School of Intelligent Manufacturing and Control Engineering Qilu Institute of Technology Jinan250200 China College of Computer and Communication Engineering Qilu Institute of Technology Jinan250200 China

ISBN: (纸本)9798350382877

Memristors have also become one of the most promising research hotspots for solving data storage and computing problems faced in the big data era. As an emerging electronic device, memristor has potentially important applications in information storage and processing. This paper constructs a rod-shaped TiO2-x nanoscale memristor with FTO/TiO2-x/Cu structure, whose reliability is based on the memory behavior and its conversion mechanism. Research progress including materials, preparation methods, resistive switching mechanism and application prospects are described. First, the constituent materials of memristor are introduced, focusing on metal oxides and organic materials such as titanium oxide (TiO2). The choice of these materials is critical to memristor performance and applications. Secondly, the advantages and limitations of the preparation methods are discussed. Then the resistance switching mechanism of memristor was studied in depth, focusing on the generation principle and adjustment mechanism of memristor effect. These include important concepts such as charge migration, Schottky barrier formation and oxygen vacancy drift, which help to understand the electrical properties of memristors. In addition, we explore the prospects of memristors in practical applications. Finally, past and current work in this field is summarized, and the prospects and challenges of memristorrelated research are prospected. © 2023 IEEE.

关键词： Memristors

来源：评论

学校读者我要写书评

暂无评论

Nature Inspired Meta-Heuristic Algorithms based Load Balancing in Fog Computing Environment 7

Nature Inspired Meta-Heuristic Algorithms based Load Balanci...

引用

7th International Conference on Parallel, Distributed and Grid Computing, PDGC 2022

作者： Kashyap, Vijaita Ahuja, Rakesh Kumar, Ashok Chitkara University Chitkara University Institute of Engineering and Technology Punjab India Lovely Professional University School of Computer Application Punjab Phagwara India

ISBN: (纸本)9781665454018

LB is simply the methodical distribution of load among many servers. To expedite the handling of customer requests, the fog server manages the substantial data on the cloud server. Data requirements are increasing, and Fog computing (FC) has made data more readily available. Despite the fact that FC overcomes many issues based on user requirements, other challenges still necessitate further effort. The challenge that FC confronts is Load Balancing(LB), which causes an increase in network layer traffic. The cloud layer has previously offered several LB solutions, but development on the fog layer is currently underway. Inadequate LB can lower service quality by delaying response time, processing time, security, and other concerns. This paper describes nature-based meta-heuristic algorithms that are based on LB and are used to the problem of overloaded data on the network. This review has explored some of the unresolved issues of the researchers problems and also a brief review on the advantages and disadvantages of the existing literature's. Some of the challenges has also been discussed. Also, when it comes to LB, writers have concentrated on bandwidth, response time, latency, cost, security, and execution time. © 2022 IEEE.

关键词： Fog computing

来源：评论

学校读者我要写书评

暂无评论

Fall Detection and Alerts in Hearing Aids for Deaf using Generative AI

Fall Detection and Alerts in Hearing Aids for Deaf using Gen...

引用

Computational Intelligence, Communication technology and Networking (CICTN), International Conference on

作者： Bharat Tripathi Madan Lal Saini Manish Jain Apoorva Saxena Narendra Pal Department of Computer Application Allenhouse Institute of Technology Kanpur India Department of Computer Science and Engineering Apex Institute of Technology Chandigarh University Punjab India Department of Computer Application Allenhouse Business School Kanpur India Department of Computer Science & Engineering Axis Institute of Technology & Management Kanpur India Department of Computer Science & Engineering Invertis University Bareilly India

ISBN: (数字)9798331530389

ISBN: (纸本)9798331530396

Individuals with sensorineural hearing loss often experience difficulty comprehending speech when background noise is present. This paper investigates the extent of this problem in various listening scenarios and with different types of background sounds. Additionally, the section explores the contributing factors to this challenge such as reduced audibility, reduced frequency selectivity, loudness recruitment, and dead regions in the cochlea where there are no surviving inner hair cells and or neurons. The sections evaluate different techniques for compensating for the effects of these factors. While signal-processing methods using the output of a single microphone to compensate for reduced frequency selectivity have had limited success, techniques utilizing multiple microphones have proven effective. Amplitude compression has also been effective in compensating for the effects of loudness recruitment, enabling individuals to understand speech across a wide range of sound levels. Next, the paper delves into the technical aspects of implementing fall detection systems in hearing aids. learning algorithms are also investigated for their potential in enhancing fall detection accuracy and minimizing false alarms. Furthermore, the importance of user-friendly interfaces and customization features in ensuring the effectiveness and acceptance of fall detection alerts is also highlighted. The paper also addresses the ethical and privacy considerations associated with fall detection in hearing aids. It emphasizes the need for transparent data handling practices and user consent, while also addressing potential concerns related to user autonomy and intrusion.

关键词： Hair Privacy Neurons Signal processing algorithms Signal processing Hearing aids Fall detection Transient analysis Recruitment Microphones

来源：评论

学校读者我要写书评

暂无评论

A collaborative empirical analysis on machine learning based disease prediction in health care system

引用

International Journal of Information technology (Singapore) 2024年第1期16卷 261-270页

作者： Das, Ayushi Choudhury, Deepjyoti Sen, Arpita Department of IT Techno India University West Bengal Kolkata 700091 India Department of AIML School of CSE Manipal University Jaipur Rajasthan Jaipur 303007 India Department of Computer Application B.P. Podder Institute of Management and Technology West Bengal Kolkata 700091 India

The adaptation of Artificial Intelligence can radically reshape the entire healthcare industry. This paper proposes a comparative analysis of four Machine Learning algorithms namely, k-Nearest Neighbour, Naive Bayes, Decision Tree, and Random Forest. These supervised classifiers are used to predict widely identified diseases based on one’s conspicuous symptoms among a given data-set of common symptoms. In our experiment comparing the different Machine Learning models, Random Forest had obtained the highest accuracy of 99.5%, followed by Decision Tress at 95.8%, K-Nearest Neighbor at 93.4%, and Naive Bayes at 87.7%. This paper represents a state-of-the art comparative analysis which has achieved the higher accuracy than the existing analytical results carried out in earlier research. Finally, a web-based application has also been developed to visualize the predictions in a better way. © 2023, The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of computer applications and Management.

关键词： Decision Tree Healthcare K-Nearest Neighbour Naive Bayes Random Forest

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：