检索结果-内蒙古大学图书馆

A hybrid explainable ensemble transformer encoder for pneumonia identification from chest X-ray images

Journal of Advanced Research 2023年 48卷 191-211页

作者： Ukwuoma, Chiagoziem C. Qin, Zhiguang Belal Bin Heyat, Md Akhtar, Faijan Bamisile, Olusola Muaad, Abdullah Y. Addo, Daniel Al-antari, Mugahed A. School of Information and Software Engineering University of Electronic Science and Technology of China Sichuan Chengdu China IoT Research Center College of Computer Science and Software Engineering Shenzhen University Guangdong Shenzhen 518060 China Centre for VLSI and Embedded System Technologies International Institute of Information Technology Telangana Hyderabad 500032 India Department of Science and Engineering Novel Global Community Educational Foundation Hebersham 2770 NSW Australia School of Computer Science and Engineering University of Electronic Science and Technology of China Sichuan Chengdu 611731 China Sichuan Industrial Internet Intelligent Monitoring and Application Engineering Technology Research Center Chengdu University of Technology Chengdu China Department of Studies in Computer Science University of Mysore Manasagangothri Mysore India Department of Artificial Intelligence College of Software & Convergence Technology Daeyang AI Center Sejong University Seoul 05006 South Korea

Introduction: Pneumonia is a microorganism infection that causes chronic inflammation of the human lung cells. Chest X-ray imaging is the most well-known screening approach used for detecting pneumonia in the early stages. While chest-Xray images are mostly blurry with low illumination, a strong feature extraction approach is required for promising identification performance. Objectives: A new hybrid explainable deep learning framework is proposed for accurate pneumonia disease identification using chest X-ray images. Methods: The proposed hybrid workflow is developed by fusing the capabilities of both ensemble convolutional networks and the Transformer Encoder mechanism. The ensemble learning backbone is used to extract strong features from the raw input X-ray images in two different scenarios: ensemble A (i.e., DenseNet201, VGG16, and GoogleNet) and ensemble B (i.e., DenseNet201, InceptionResNetV2, and Xception). Whereas, the Transformer Encoder is built based on the self-attention mechanism with multilayer perceptron (MLP) for accurate disease identification. The visual explainable saliency maps are derived to emphasize the crucial predicted regions on the input X-ray images. The end-to-end training process of the proposed deep learning models over all scenarios is performed for binary and multi-class classification scenarios. Results: The proposed hybrid deep learning model recorded 99.21% classification performance in terms of overall accuracy and F1-score for the binary classification task, while it achieved 98.19% accuracy and 97.29% F1-score for multi-classification task. For the ensemble binary identification scenario, ensemble A recorded 97.22% accuracy and 97.14% F1-score, while ensemble B achieved 96.44% for both accuracy and F1-score. For the ensemble multiclass identification scenario, ensemble A recorded 97.2% accuracy and 95.8% F1-score, while ensemble B recorded 96.4% accuracy and 94.9% F1-score. Conclusion: The proposed hybrid deep learning framewo

关键词： Chest X-ray imaging Explainable artificial intelligence (XAI) Pneumonia identification Self-attention network Transfer ensemble learning Transformer encoder (TE)

来源：评论

学校读者我要写书评

暂无评论

LESSONS LEARNED FROM THE COVID-19 PANDEMIC: AN ANALYSIS OF REGIONAL PHILIPPINE DATA AND COVID-19 OUTCOMES

LESSONS LEARNED FROM THE COVID-19 PANDEMIC: AN ANALYSIS OF R...

引用

2023 Philippine Geomatics Symposium, PhilGEOS 2023

作者： Gaano, J.B. Rule, C. Celeste, J. Bongolan, V.P. Rivera, R.L. Caoili, S.E. System Modeling and Simulation Lab Department of Computer Science College of Engineering University of the Philippines – Diliman Quezon City Philippines Center for Informatics University of San Agustin Iloilo Philippines College of Social Work and Community Development UP Diliman Philippines UP College of Medicine Philippines

Variations in indicators which may affect COVID-19 outcomes exist among regions in the Philippines. These variations suggest that the impacts of the pandemic differ not only between countries but also within regions and local areas in a country. This study aims to investigate COVID-19 outcomes (case fatality rate or CFR, incidence rate and hospitalization rate) over time and their correlation with regional healthcare and population factors during different phases of the pandemic across the 17 regions of the Philippines. These outcomes were chosen because they are readily available from government data sources, and are simple to work with. We mark five 100-day time periods of the COVID-19 pandemic in the country. The COVID-19 dataset was based on data maintained by the Department of Health (DOH). Spearman’s rank correlation coefficient analysis was used to examine the link between COVID-19 outcomes region-specific indicators referring to population and access to health care resources. Despite their higher vaccination coverage, regions with greater access to health care resources may still be susceptible to future COVID-19 outbreaks due to their urban and densely populated nature. However, vaccines remain effective in reducing COVID-19 hospitalizations in these regions. Therefore, it is crucial to focus on increasing vaccination coverage in rural, underserved regions and implement targeted outbreak control measures in densely populated areas. © Author(s) 2024.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Brain Tumour Identification Using MRI Images: Classification and Optimization Based Random-Coupled Neural Network with Cat Hunting Optimization

Brain Tumour Identification Using MRI Images: Classification...

引用

Machine Learning and Autonomous systems (ICMLAS), International Conference on

作者： Nandini N P. Vanajakshi Vidyarani H J Vani B A Vinod Kumar K P Shwethasree R Department of Computer Science and Engineering Dr. Ambedkar Institute of Technology Bangalore Karnataka Department of Information Science and Engineering Vivekananda Institute of Technology Bangalore Karnataka Department of Computer Science and Business System Dr. Ambedkar Institute of Technology Bangalore Karnataka Department of Information Science and Engineering Sri Krishna Institute of Technology Bangalore Karnataka Department of Computer Science and Engineering Dr Ambedkar Institute of Technology Bangalore Karnataka

ISBN: (数字)9798331505745

ISBN: (纸本)9798331505752

Tumors in the brains may be Benign or malignant but they are growths of cells in the brain. Aches, seizures, vomiting, dementia, and impaired vision are generic symptoms of the ailment. In early diagnosis, detection of the disease and determining the right treatment method for the patients MRI scans are important. There are a number of Deep Learning-based detection techniques available, however their accuracy and error rates may be low. This study uses a Random-Coupled Neural Network with Cat Hunting Optimization (RCNNet-CHOpt) to identify and classify brain tumor in order to get around these issues. Only one kind of BraTS dataset is used by the suggested approach: The filters to enhance image quality and reduce noise, the input images are pre-processed using the Adaptive and Propagated Mesh Filtering (APMF). This is followed by feature extraction and classification using Mellin Transform (M-Trans) with Random-Coupled Neural Network (R-CNN). When combined, these two networks can accurately classify the images and identify important elements. Finally, to increase accuracy, the weight parameter of R-CNN is modified using the Cat Hunting Optimization (CHO) technique. The proposed method has a 99.8% recall and a 99.9% accuracy rate, outperforming existing methods. Among the primary advantages of the RCNNet-CHOpt are decreased false-positive rates and enhanced precision in identifying intricate brain tumor formations. Hence, it is an especially useful tool for clinical use in the identification of brain tumor because most of these applications manage large volumes of medical data.

关键词： Accuracy Magnetic resonance imaging Noise Brain tumors Medical treatment Transforms Real-time systems Optimization Biological neural networks Monitoring

来源：评论

学校读者我要写书评

暂无评论

A Transformer-Based Spatio-Temporal Graph Neural Network for Anomaly Detection on Dynamic Graphs 12th

A Transformer-Based Spatio-Temporal Graph Neural Network for...

引用

12th CCF Conference on BigData, BigData 2024

作者： Gao, Yuanjun Zhu, Quntao Shi, Xuanhua Jin, Hai National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China

ISBN: (纸本)9789819610235

Dynamic graphs have emerged as a pivotal data structure underpinning real-world network applications. Against this backdrop, detecting anomalies in dynamic graphs has become particularly important, serving as a foundation for multiple downstream tasks. However, existing research has been limited by only considering the simplistic spatial features of the target edge and being confined to local spatial structures. This confinement imposes significant limitations on model performance. Furthermore, current models have not adequately addressed the issue of missing node attributes, relying solely on one-hot encoding to represent nodes, which restricts the expressive capacity of spatial features. In response to these challenges, we propose an end-to-end transformer-based spatio-temporal graph neural network model called TransSTGNN for detecting anomalous edges on dynamic graphs. This model innovatively integrates the graph convolution network with the transformer model to extract multi-dimensional spatial features of the target edge. Simultaneously, TransSTGNN incorporates a novel node enhancement module that reinforces the representation capability of spatial features by encoding the spatial attributes of nodes, effectively tackling the problem of missing node attributes. Extensive experiments confirm that TransSTGNN surpasses the state-of-the-art methods in anomaly detection on six benchmark datasets and effectively resolves the challenges mentioned above. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Spatio-temporal data

来源：评论

学校读者我要写书评

暂无评论

A Comparative Analysis of Artificial Intelligence and Business Intelligence Using Big Data Analytics 1

A Comparative Analysis of Artificial Intelligence and Busine...

引用

1st International Conference on Advances in computer science, Electrical, Electronics, and Communication Technologies, CE2CT 2025

作者： Marella, Bhagath Chandra Chowdari Vegineni, Gopi Chand Addanki, Sireesha Ellahi, Ehsan Arun Kumar, K. Mandal, Rishabh Insights & Data Department of Financial Services Capgemini India Enrollment and Eligibility Team India System soft Technologies LLC India Cleveland State University Department of Information Systems OH United States Tula's Institute Department of Computer Science and Engineering UK Dehradun India India

ISBN: (纸本)9798331518578

Business intelligence (BI) encompasses the tools and uses to gather, combine, examine, and display data about a specific firm. Using historical and current efficiency comparisons, these structures assist in formulating plans and choices to achieve better outcomes in the future. Additionally, it helps firms determine which business issues and industry trends require attention. It has several benefits, such as increasing responsibility and efficiency, but it carries some disadvantages, such as being expensive, complicated, and time-consuming to adopt. Using big data-driven approaches to optimize talent recruitment is essential for improved decisions in the cutthroat world of BI. The efficacy of many machine learning algorithms to increase recruiting performance and accuracy is compared in this investigation. For optimizing, cross-validating, and hyperparameter modification were employed. The Random Forest (RF) algorithm has the greatest accuracy (92.9%), trailed by the Gradient Boosting Classifying system (92.6%) and the neural network (NNs) models (92.7%). These findings imply that sophisticated ML algorithms, in particular RF and NN, can greatly improve BI platforms' hiring procedures. Recruiters can benefit from this research's insightful recommendations for incorporating advanced ML methods into talent recruitment plans. © 2025 IEEE.

关键词： Data accuracy

来源：评论

学校读者我要写书评

暂无评论

Unlocking the potential of RNN and CNN models for accurate rehabilitation exercise classification on multi-datasets

引用

Multimedia Tools and Applications 2025年第3期84卷 1261-1301页

作者： Zaher, Moamen Ghoneim, Amr S. Abdelhamid, Laila Atia, Ayman Software Engineering Program Faculty of Computers & Artificial Intelligence—Helwan University Cairo Ain Helwan11795 Egypt Computer Science Department Faculty of Computers & Artificial Intelligence—Helwan University Cairo Ain Helwan11795 Egypt Information System Department Faculty of Computers & Artificial Intelligence—Helwan University Cairo Ain Helwan11795 Egypt Cairo Ain Helwan11795 Egypt Giza October12451 Egypt

Physical rehabilitation is crucial in healthcare, facilitating recovery from injuries or illnesses and improving overall health. However, a notable global challenge stems from the shortage of professional physiotherapists, particularly acute in some developing countries, where the ratio can be as low as one physiotherapist per 100,000 individuals. To address these challenges and elevate patient care, the field of physical rehabilitation is progressively integrating computer Vision and Human Activity Recognition (HAR) techniques. Numerous research efforts aim to explore methodologies that assist in rehabilitation exercises and evaluate patient movements, which is crucial as incorrect exercises can potentially worsen conditions. This study investigates applying various deep-learning models for classifying exercises using the benchmark KIMORE and UI-PRMD datasets. Employing Bi-LSTM, LSTM, CNN, and CNN-LSTM, alongside a Random Search for architectural design and Hyper-parameter tuning, our investigation reveals the (CNN) model as the top performer. After applying cross-validation, the technique achieves remarkable mean testing accuracy rates of 93.08% on the KIMORE dataset and 99.7% on the UI-PRMD dataset. This marks a slight improvement of 0.75% and 0.1%, respectively, compared to previous techniques. In addition, expanding beyond exercise classification, this study explores the KIMORE dataset’s utility for disease identification, where the (CNN) model consistently demonstrates an outstanding accuracy of 89.87%, indicating its promising role in both exercises and disease identification within the context of physical rehabilitation. © The Author(s) 2024.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

EdgeMove: Pipelining Device-Edge Model Training for Mobile Intelligence 23

EdgeMove: Pipelining Device-Edge Model Training for Mobile I...

引用

32nd ACM World Wide Web Conference, WWW 2023

作者： Dong, Zeqian He, Qiang Chen, Feifei Jin, Hai Gu, Tao Yang, Yun School of Computer Science and Technology Huazhong University of Science and Technology China Department of Computing Technologies Swinburne University of Technology Australia School of Information Technology Deakin University Australia School of Computing Macquarie University Australia National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab Huazhong University of Science and Technology Wuhan430074 China

ISBN: (纸本)9781450394161

Training machine learning (ML) models on mobile and Web-of-Things (WoT) has been widely acknowledged and employed as a promising solution to privacy-preserving ML. However, these end-devices often suffer from constrained resources and fail to accommodate increasingly large ML models that crave great computation power. Offloading ML models partially to the cloud for training strikes a trade-off between privacy preservation and resource requirements. However, device-cloud training creates communication overheads that delay model training tremendously. This paper presents EdgeMove, the first device-edge training scheme that enables fast pipelined model training across edge devices and edge servers. It employs probing-based mechanisms to tackle the new challenges raised by device-edge training. Before training begins, it probes nearby edge servers' training performance and bootstraps model training by constructing a training pipeline with an approximate model partitioning. During the training process, EdgeMove accommodates user mobility and system dynamics by probing nearby edge servers' training performance adaptively and adapting the training pipeline proactively. Extensive experiments are conducted with two popular DNN models trained on four datasets for three ML tasks. The results demonstrate that EdgeMove achieves a 1.3 × -2.1 × speedup over the state-of-the-art scheme. © 2023 ACM.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Ubi-Care: An Elderly Life Support Healthcare Framework Based on Ubiquitous Personal Online Data Stores

Ubi-Care: An Elderly Life Support Healthcare Framework Based...

引用

2024 IEEE International Conference on systems, Man, and Cybernetics, SMC 2024

作者： Chen, Hong Zhou, Tao Wu, Bo Graduate School of Human Sciences Waseda University Saitama359-1192 Japan Daiichi Institute of Technology Department of Information and Electronics System Engineering Taito Tokyo110-0005 Japan School of Computer Science Tokyo University of Technology Hachioji Tokyo192-0982 Japan

ISBN: (纸本)9781665410205

In recent years, the global aging population has intensified, leading to a sharp increase in social security benefits and caregiving costs. The elderly face greater health risks, and their behaviors often indicate signs of crises and illnesses. The rapid development of IoT technology offers new solutions for detecting abnormal signs, thereby promoting healthy aging, independent living, and social participation for the elderly. However, the diversity of IoT devices has led to the phenomenon of personal data silos. When the elderly leave their usual IoT environment, the issue of continuity in healthcare services becomes more pronounced. To address this issue, this study proposes a decentralized Ubi-Care framework. The framework aims to achieve complete separation of data and applications. It is based on the ActivityPub protocol and integrates various data from wearable devices, smart home sensors, and social networks, storing this data in a ubiquitous personal online data store (UPOD) and assigning different roles based on data type. UPOD applications support bidirectional following, allowing users to access data associated with relevant roles, addressing issues related to data categorization, sharing, privacy, and security. Additionally, this study proposes a method for utilizing complete UPOD data to perform anomaly detection based on the hidden Markov model (HMM). By effectively integrating IoT data into UPOD and enhancing data interoperability. The data-sharing model proposed in this study also facilitates elderly individuals and their family members in sharing relevant data as needed, while ensuring privacy protection. The methods proposed in this study will help prevent accidental injuries and enable early diagnosis of diseases, providing strong technical support for elderly healthcare. © 2024 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

MULTIMODAL LEARNING TO IMPROVE CARDIAC LATE MECHANICAL ACTIVATION DETECTION FROM CINE MR IMAGES

arXiv

引用

arXiv 2024年

作者： Xing, Jiarui Wu, Nian Bilchick, Kenneth C. Epstein, Frederick H. Zhang, Miaomiao Department of Electrical and Computer Engineering University of Virginia United States Department of Computer Science University of Virginia United States Department of Biomedical Engineering University of Virginia Health System United States School of Medicine University of Virginia Health System United States

This paper presents a multimodal deep learning framework that utilizes advanced image techniques to improve the performance of clinical analysis heavily dependent on routinely acquired standard images. More specifically, we develop a joint learning network that for the first time leverages the accuracy and reproducibility of myocardial strains obtained from Displacement Encoding with Stimulated Echo (DENSE) to guide the analysis of cine cardiac magnetic resonance (CMR) imaging in late mechanical activation (LMA) detection. An image registration network is utilized to acquire the knowledge of cardiac motions, an important feature estimator of strain values, from standard cine CMRs. Our framework consists of two major components: (i) a DENSE-supervised strain network leveraging latent motion features learned from a registration network to predict myocardial strains;and (ii) a LMA network taking advantage of the predicted strain for effective LMA detection. Experimental results show that our proposed work substantially improves the performance of strain analysis and LMA detection from cine CMR images, aligning more closely with the achievements of DENSE. © 2024, CC BY.

关键词： Strain

来源：评论

学校读者我要写书评

暂无评论

Stackelberg Game-Driven Computational Offloading in Edge Computing Scenarios

Stackelberg Game-Driven Computational Offloading in Edge Com...

引用

International Conference on Communication Software and Networks, ICCSN

作者： Lan Zhang Chao Bu Key Laboratory of Computer Vision and System of Ministry of Education School of Computer Science and Engineering Tianjin University of Technology Tianjin China

With the number of users that use mobile devices for frequent transactions increasing rapidly, it is a great challenge to guarantee the credibility of transactions. Blockchain is regarded as a practical technology for such demand, however, the limited computing capacity of each user's device becomes a bottleneck. In this paper, the edge computing pattern is introduced to support complex computing for mobile devices of users by renting computing resource from computing service providers. By considering demands of both the user and the service provider, we propose a two-level game approach based on the Stackelberg Game for multiple users and multiple service providers on computing resources renting and pricing. The simulation results show that the proposed mechanism is feasible and effective.

关键词：

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：