检索结果-内蒙古大学图书馆

Machine learning in diagnosis of coronary artery disease

Chinese Medical Journal 2021年第4期134卷 401-403页

作者： Hao Ling Zi-Yuan Guo Un-Lin Tan Ren-Chu Guan Jing-Bo Chen Chun-Li Department of Cardiology the Second Hospital of Jilin UniversityChangchunJilin 130012China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education College of Computer Science and TechnologyJilin UniversityChangchunJilin 130012China

Cardiovascular diseases continue to be the foremost cause of death among both males and females worldwide.[1]Coronary artery disease(CAD)represents a major subtype of cardiovascular *** evidence has highlighted a worldwide increase in incidence of CAD clinical manifestations regardless of geographical region.[2]Despite a steady decline in CAD mortality in western countries over the past few decades,approximately one-third of the population suffering from CAD will succumb to the *** and accurate diagnostic decisions are crucial for patients with CAD and aid in guidance for effective treatment.

关键词： CAD diagnosis continue

来源：评论

学校读者我要写书评

暂无评论

Unboxing the black-box of deep learning based reconstruction of undersampled MRIs 4

Unboxing the black-box of deep learning based reconstruction...

引用

4th Italian Workshop on Explainable Artificial Intelligence, XAI.it 2023

作者： Chatterjee, Soumick Das, Arnab Khatun, Rupali Nürnberger, Andreas Genomics Research Centre Human Technopole Milan Italy Faculty of Computer Science Otto von Guericke University Magdeburg Magdeburg Germany Data and Knowledge Engineering Group Otto von Guericke University Magdeburg Magdeburg Germany German Research Centre for Artificial Intelligence Kaiserslautern Germany Translational Radiobiology Department of Radiation Oncology Universitätsklinikum Erlangen Erlangen Germany Department of Radiation Oncology Universitätsklinikum Erlangen Friedrich-Alexnder-Universität Erlangen-Nürnberg Erlangen Germany Comprehensive Cancer Centre Erlangen-EMN Erlangen Germany Centre for Behavioural Brain Sciences Magdeburg Germany

Deep learning has emerged as a very important area of research and has shown immense potential in solving different kinds of problem, including in the medical field. For tasks like undersampled MRI reconstruction - the process of speeding up MRI acquisition with the help of undersampling, deep learning has shown its dominance over the years. But one of the major problems with deep learning is trust: Complex reasonings done by these models appear black-box to the users. Therefore, to build trust and better acceptability, it is important to open up this black-box nature of these models. For classification models, several approaches have been proposed. Nevertheless, for models dealing with inverse problems, like the reconstruction of the undersampled MRIs, it is more challenging as the output of the model has the same number of output pixels as the input, making the interpretability of such models more complex. This research explores different methods to understand the working mechanism of a deep learning model for the task of undersampled MRI reconstruction. © 2023 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).

关键词： Inverse problems

来源：评论

学校读者我要写书评

暂无评论

Learning Fair Representations through Uniformly Distributed Sensitive Attributes

Learning Fair Representations through Uniformly Distributed ...

引用

Secure and Trustworthy Machine Learning (SaTML), IEEE Conference on

作者： Patrik Joslin Kenfack Adín Ramírez Rivera Adil Mehmood Khan Manuel Mazzara Machine Learning and Knowledge Representation Lab Innopolis University Innopolis Russia Department of Informatics Digital Signal Processing and Image Analysis (DSB) group University of Oslo Oslo Norway School of Computer Science University of Hull Hull UK Institute of Software Development and Engineering Innopolis University Innopolis Russia

Machine Learning (ML) models trained on biased data can reproduce and even amplify these biases. Since such models are deployed to make decisions that can affect people's lives, ensuring their fairness is critical. One approach to mitigate possible unfairness of ML models is to map the input data into a less-biased new space by means of training the model on fair representations. Several methods based on adversarial learning have been proposed to learn fair representation by fooling an adversary in predicting the sensitive attribute (e.g., gender or race). However, adversarial-based learning can be too difficult to optimize in practice; besides, it penalizes the utility of the representation. Hence, in this research effort we train bias-free representations from the input data by inducing a uniform distribution over the sensitive attributes in the latent space. In particular, we propose a probabilistic framework that learns these representations by enforcing the correct reconstruction of the original data, plus the prediction of the attributes of interest while eliminating the possibility of predicting the sensitive ones. Our method leverages the inability of Deep Neural Networks (DNNs) to generalize when trained on a noisy label space to regularize the latent space. We use a network head that predicts a noisy version of the sensitive attributes in order to increase the uncertainty of their predictions at test time. Our experiments in two datasets demonstrated that the proposed model significantly improves fairness while maintaining the prediction accuracy of downstream tasks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Internet of Things (IoT) Insights in the Healthcare Sector: A Topic Modelling Approach

Internet of Things (IoT) Insights in the Healthcare Sector: ...

引用

IEEE UP Section Conference on Electrical computer and Electronics (UPCON)

作者： Nilesh Vasant Ingale Vinay Kumar Nassa Modi Bhumika Kumarbha Bhavana Jamalpur Anita Gehlot M. Kalyan Chakravarthi Department of Computer Engineering COET North Maharashtra Knowledge Jalagaon G.H. Raisoni Institute of Engineering and Business Management Jalgaon Department of Information Communication Technology(ICT) Tecnia Institute of Advanced Studies(Delhi) Affiliated with Guru Gobind Singh Indraprastha University Shri. C. J. Patel College of Computer Studies Sankalchand Patel University Visnagar School of Computer Science and Artificial Intelligence SR University Warangal Telangana India Uttaranchal Institute of Technology Uttaranchal University School of Electronics Engineering VIT-AP University Amaravathi India

With an invention of Internet of Things (IoT), both traditional and digital realms are rapidly integrating, thereby changing the livelihood of people in such a manner, that were unimaginable merely just a decade ago. IoTs have created a big effect so far despite being in their nascent stage, especially in the healthcare (HC) sector. This research seeks to uncover essential themes hidden within limited, yet expanding scholarly papers on IoT applications in HC. By performing topic modeling, we were able to pinpoint 5 key experiment groups, including confidentiality and safety, wirelessly networking techniques, apps, dataset, smarter well-being and cloud. Study findings demonstrate that societal issues have not received much emphasis as compared to technological issues in HC IoT exploration. With regard to classifying and analyzing the selected topics, our paper offers suggestions for further investigation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Finding Informative Comments for Video Viewing

引用

SN computer science 2020年第1期1卷 1-14页

作者： Choi, Seungwoo Segev, Aviv Knowledge Service Engineering KAIST 291 Daehak-ro Daejeon South Korea Department of Computer Science University of South Alabama 150 Jaguar Drive Mobile AL United States

Of all the information-sharing methods on the Web, video is a factor with increasing importance and will continue to influence the future Web environment. Various services such as YouTube, Vimeo, and Liveleak are information-sharing platforms that support uploading UGC (user-generated content) to the Web. Users tend to seek related information while or after watching an informative video when they are using these Web services. In this situation, the best way of satisfying information needs of this kind is to find and read the comments on Web services. However, existing services only support sorting by recentness (newest one) or rating (high LIKES score). Consequently, the search for related information is limited unless the users read all the comments. Therefore, we suggest a novel method to find informative comments by considering original content and its relevance. We developed a set of methods composed of measuring informativeness priority, which we define as the level of information provided by online users, classifying the intention of the information posted online, and clustering to eliminate duplicate themes. The first method of measuring informativeness priority calculates the extent to which the comments cover all the topics in the original contents. After the informativeness priority calculation, the second method classifies the intention of information posted in comments. Then, the next method picks the most informative comments by applying clustering methods to eliminate duplicate themes using rules. Experiments based on 20 sampled videos with 1000 comments and analysis of 1861 TED talk videos and 380,619 comments show that the suggested methods can find more informative comments compared to existing methods such as sorting by high LIKES score. © 2019, Springer Nature Singapore Pte Ltd.

关键词： Information needs Information sharing Informativeness Online comments Video service

来源：评论

学校读者我要写书评

暂无评论

Data Hiding Technique Using Differential Evolution 1

引用

2nd International Conference on Emerging Trends and Advances in Electrical engineering and Renewable Energy, ETAEERE 2020

作者： Basu, Sharbari Debnath, Arunothpol Basu, Abhishek Sankar Das, Tirtha Chattopadhyay, Avik Saha, Anirban Department of Computer Science Maulana Abul Kalam Azad University of Technology Kolkata India Department of Electronics and Communication RCC Institute of Information Technology Kolkata India Department of Electronics and Communication Ramkrishna Mahato Government Engineering College Purulia India Department of Radio Physics and Electronics University of Calcutta Kolkata India Department of Mathematics Supreme Knowledge Foundation Group of Institutions Kolkata India

ISBN: (数字)9789811587528

ISBN: (纸本)9789811587511

The method of data hiding has become one of the most trustworthy techniques to combat the malicious attacks on communication networks. Among various data hiding methods, watermark has turned one of its foremost technique, in which an image is veiled in a cover image. The paper proposes a Differential Evolution based watermark technique that eases to locate the covert region for data hiding where the unwanted attacks can almost be nullified. Least Significant Bits are used for veiling the watermark. The proposed scheme is carried out in the spatial domain. The experimental results show the competent quality of images are restored even after various attacks, as well as the watermark itself, is still in a recognizable state. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

CLDG: Contrastive Learning on Dynamic Graphs

CLDG: Contrastive Learning on Dynamic Graphs

引用

International Conference on Data engineering

作者： Yiming Xu Bin Shi Teng Ma Bo Dong Haoyi Zhou Qinghua Zheng Department of Computer Science and Technology Xi’an Jiaotong University China Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering Xi’an Jiaotong University China Department of Distance Education Xi’an Jiaotong University China School of Software Beihang University China Advanced Innovation Center for Big Data and Brain Computing Beihang University China

The graph with complex annotations is the most potent data type, whose constantly evolving motivates further exploration of the unsupervised dynamic graph representation. One of the representative paradigms is graph contrastive learning. It constructs self-supervised signals by maximizing the mutual information between the statistic graph’s augmentation views. However, the semantics and labels may change within the augmentation process, causing a significant performance drop in downstream tasks. This drawback becomes greatly magnified on dynamic graphs. To address this problem, we designed a simple yet effective framework named CLDG. Firstly, we elaborate that dynamic graphs have temporal translation invariance at different levels. Then, we proposed a sampling layer to extract the temporally-persistent signals. It will encourage the node to maintain consistent local and global representations, i.e., temporal translation invariance under the timespan views. The extensive experiments demonstrate the effectiveness and efficiency of the method on seven datasets by outperforming eight unsupervised state-of-the-art baselines and showing competitiveness against four semi-supervised methods. Compared with the existing dynamic graph method, the number of model parameters and training time is reduced by an average of 2,001.86 times and 130.31 times on seven datasets, respectively. The code and data are available at: https://***/yimingxu24/CLDG.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Smart Optimization of Semiconductors in Photovoltaic-Thermoelectric Systems Using Recurrent Neural Networks

引用

International Journal of Energy Research 2023年第1期2023卷

作者： Alghamdi, Hisham Maduabuchi, Chika Okoli, Kingsley Albaker, Abdullah Alatawi, Ibrahim Alsafran, Ahmed S. Alkhedher, Mohammad Chen, Wei-Hsin Electrical Engineering Department College of Engineering Najran University Najran55461 Saudi Arabia Department of Nuclear Science and Engineering Massachusetts Institute of Technology CambridgeMA United States Artificial Intelligence Laboratory University of Nigeria Nsukka Enugu Nsukka410001 Nigeria Department of Computer Science and Knowledge Discovery Saint Petersburg Electrotechnical University LETI Saint Petersburg197022 Russia Department of Electrical Engineering College of Engineering University of ha'Il Ha'il81451 Saudi Arabia Department of Mechanical Engineering College of Engineering University of ha'Il Ha'il81451 Saudi Arabia Department of Electrical Engineering College of Engineering King Faisal University Al-ahsa31982 Saudi Arabia Department of Mechanical and Industrial Engineering Abu Dhabi University Abu Dhabi59911 United Arab Emirates Department of Aeronautics and Astronautics National Cheng Kung University Tainan701 Taiwan Research Center for Smart Sustainable Circular Economy Tunghai University Taichung407 Taiwan Department of Mechanical Engineering National Chin-Yi University of Technology Taichung411 Taiwan

In the relentless pursuit of sustainable energy solutions, this study pioneers an innovative approach to integrating thermoelectric generators (TEGs) and photovoltaic (PV) modules within hybrid systems. Uniquely, it employs neural networks for an exhaustive analysis of a plethora of parameters, including a diverse spectrum of semiconductor materials, cooling film coefficients, TE leg dimensions, ambient temperature, wind speed, and PV emissivity. Leveraging a rich dataset, the neural network is meticulously trained, revealing intricate interdependencies among parameters and their consequential impact on power generation and the efficiencies of TEG, PV, and integrated PV-TE systems. Notably, the hybrid system witnesses a striking 23.1% augmentation in power output, escalating from 0.26 W to 0.32 W, and a 20% ascent in efficiency, from 14.68% to 17.62%. This groundbreaking research illuminates the transformative potential of integrating TEGs and PV modules and the paramountcy of multifaceted parameter optimization. Moreover, it exemplifies the deployment of machine learning as a powerful tool for enhancing hybrid energy systems. This study, thus, stands as a beacon, heralding a new chapter in sustainable energy research and propelling further innovations in hybrid system design and optimization. Through its novel approach, it contributes indispensably to the arsenal of clean energy solutions. © 2023 Hisham Alghamdi et al.

关键词： Hybrid systems

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study on Cyber security Technology in Big data Cloud Computing Environment

A Comparative Study on Cyber security Technology in Big data...

引用

International Conference on Contemporary Computing and Informatics (IC3I)

作者： Amit Kumar Jain Tripti Misra Neha Tyagi M V Suresh Kumar Bhasker Pant Department of Computer Science Delhi University Delhi Deutche Telecom Digital Labs Gurugram Haryana India Department of IT Knowledge Park 3 G. L Bajaj Institute of Technology & Management Greater Noida India Department of Law Koneru Lakshmaiah Education Foundation Green Fields Vaddeswaram Guntur Department of Computer Science & Engineering Graphic Era Deemed to be University Dehradun Uttarakhand Guntur

Protection of networks, programs and systems from cyberattacks is the practice of cybersecurity technology. The cyberattacks are capable of gaining access for deleting or altering of data that are sensitive, demanding money from the users and obstruction of regular operations of corporates. In the present situation many devices are getting smarter than that of the hackers and humans that makes the tasks difficult for implementing the measures of cybersecurity. In terms of cyber security, the ability of collecting huge amount of data is known as big data analytics. The functions are performed through displaying, interpretation and extraction of the insights of future that can enable early detection of catastrophic cyber threats and attacks. Organizations can better understand all the activities and acts that could potentially result in cyber-attacks by having a stronger and more effective cyber defensive posture. As offices became more remote, cloud computing became crucial for gaining access to important documents, programs, and computing resources. Although connection can be both a benefit and a curse, as easily accessible files can become an easy target for hostile actors, we expect the global economy to transfer even more into the cloud over time. Therefore, efforts in strengthening cybersecurity measures are vital to safeguard distant vaults of sensitive data. The management depends on a combination of technology and advice to secure the cloud. It involves managing the framework, information applications, safe-secure guidelines, consistency leads, and secure infrastructure data applications that pertain to cloud computing. The same principles that underpin security for modern cloud computing platforms and historic knowledge centers are secrecy, integrity, and usability. The novel method of DDoS attack detection is proposed.

关键词： Performance evaluation Cloud computing Privacy Systems operation Organizations computer crime Usability

来源：评论

学校读者我要写书评

暂无评论

GEOM-GCN: GEOMETRIC GRAPH CONVOLUTIONAL NETWORKS 8

GEOM-GCN: GEOMETRIC GRAPH CONVOLUTIONAL NETWORKS

引用

8th International Conference on Learning Representations, ICLR 2020

作者： Pei, Hongbin Wei, Bingzhe Chang, Kevin Chen-Chuan Lei, Yu Yang, Bo College of Computer Science and Technology Jilin University China Department of Electrical and Computer Engineering University of Illinois Urbana-Champaign United States Department of Computer Science University of Illinois Urbana-Champaign United States Department of Computing Hong Kong Polytechnic University Hong Kong Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education China

Message-passing neural networks (MPNNs) have been successfully applied to representation learning on graphs in a variety of real-world applications. However, two fundamental weaknesses of MPNNs' aggregators limit their ability to represent graph-structured data: losing the structural information of nodes in neighborhoods and lacking the ability to capture long-range dependencies in disassortative graphs. Few studies have noticed the weaknesses from different perspectives. From the observations on classical neural network and network geometry, we propose a novel geometric aggregation scheme for graph neural networks to overcome the two weaknesses. The behind basic idea is the aggregation on a graph can benefit from a continuous space underlying the graph. The proposed aggregation scheme is permutation-invariant and consists of three modules, node embedding, structural neighborhood, and bi-level aggregation. We also present an implementation of the scheme in graph convolutional networks, termed Geom-GCN, to perform transductive learning on graphs. Experimental results show the proposed Geom-GCN achieved state-of-the-art performance on a wide range of open datasets of graphs. © 2020 8th International Conference on Learning Representations, ICLR 2020. All rights reserved.

关键词： Message passing

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：