检索结果-内蒙古大学图书馆

Threats to medical diagnosis systems: analyzing targeted adversarial attacks in deep learning-based COVID-19 diagnosis

引用

Soft Computing 2025年第3期29卷 1879-1896页

作者： Haque, Sheikh Burhan Ul Zafar, Aasim Haq, Sheikh Riyaz Ul Haque, Sheikh Moeen Ul Ahmad, Mohassin Roshan, Khushnaseeb School of Computer Science Engineering and Technology Bennett University Uttar Pradesh Greater Noida India Department of Computer Science Aligarh Muslim University Uttar Pradesh Aligarh202002 India Department of Computer Science Engineering Guru Nanak Institution Ibrahimpatnam Telangana Hyderabad501506 India Department of Electronics and Communication Guru Nanak Institution Ibrahimpatnam Telangana Hyderabad501506 India

Deep and machine learning models have become pivotal in medical image analysis, especially for diagnosing COVID-19 using X-rays and CT scans. While these models, including transfer learning-based approaches, have achieved high accuracy, they remain highly vulnerable to adversarial attacks, which can manipulate input data and cause misclassification, posing critical risks in clinical applications. This study introduces a novel approach to addressing this issue by systematically evaluating the impact of adversarial attacks on COVID-19 diagnosis models built with two leading architectures, VGG-16 and DenseNet-121, using the Fast Gradient Sign Method (FGSM). The FGSM attack causes a dramatic drop in accuracy, reducing VGG-16’s accuracy from 95.12 to 9.97% and DenseNet-121’s from 96.51 to 10.13%. To counter these vulnerabilities, we propose a novel defense mechanism that combines adversarial training with Gaussian noise data augmentation, a dynamic approach that generates perturbations across various epsilon values during the training phase. This innovative method significantly enhances model robustness, restoring accuracy to over 92% on adversarial examples. These findings emphasize the need for strong defense mechanisms in deep learning models for COVID-19 diagnosis, ensuring reliability and security against adversarial threats in clinical environments. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

IoT-Powered Health Monitoring System for Protecting Vital Organs Through Cloud-Based Diagnosis

IoT-Powered Health Monitoring System for Protecting Vital Or...

引用

5th International Symposium on Signal and Image Processing, ISSIP 2024

作者： Singh, Jagendra Saraswat, Mala Upreti, Kamal Agrawal, Gaurav Hasan, Dler Salih Shaik, Nazeer School of Computer Science Engineering and Technology Bennett University Greater Noida India School of Computer Science Engineering & Technology Bennett University Greater Noida India Delhi-NCR Ghaziabad India KIET Group of Institution Ghaziabad India Department of Computer Science & Information Tech. University of Salahaddin-Erbil Erbil Iraq Department of Computer Science & Engineering Srinivasa Ramanujan Institute of Technology Autonomous Anantapur India

ISBN: (纸本)9789819795147

The main objective of this research was the development and evaluation of an IoT- and machine learning-based health monitoring system capable of protecting patient’s vital organs through cloud diagnosis. This could be achieved by connecting a set of sensors, including temperature, pressure, heart rate, and oxygen sensors, to the patient and allowing them to communicate with the cloud to transmit real-time data via IoT technologies. The data could be further analyzed and predicted using cloud-based machine learning algorithms. This study investigated the performance of different machine learning models, including Artificial Neural Networks (ANN), Support Vector Machines (SVM), Naive Bayes (NB), and Negative Decision Trees (DT), for the purpose of patient’s health prediction based on the sensor data. After experimentation and evaluation, we found that the ANN model demonstrated the best predictive ability, with an accuracy level of 99.45%. The SVM, NB, and DT models also demonstrated good performance, with the accuracies of 96.5%, 94.34%, and 91.2%, respectively. Therefore, this research demonstrated that IoT and machine learning technologies could be successfully employed in healthcare for remote patient monitoring and timely prediction. The created system allows for real-time monitoring, which enables early prediction, potentially leading to improved patient outcomes, cost savings, and higher efficiency of provided care. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Remote patient monitoring

来源：评论

学校读者我要写书评

暂无评论

PHORTEX: Physically-Informed Operational Robotic Trajectories for Scientific Expeditions

Field Robotics

引用

Field Robotics 2025年 4卷 138-181页

作者： Victoria L. Preston Genevieve E. Flaspohler John W. Fisher Anna P. M. Michel Nicholas Roy Applied Ocean Physics and Engineering Massachusetts Institute of Technology and Woods Hole Oceanographic Institution Joint Program Cambridge MA 02139 Electrical Engineering and Computer Science Massachusetts Institute of Technology and Woods Hole Oceanographic Institution Joint Program Cambridge MA 02139 Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology Cambridge MA 02139 Applied Ocean Physics and Engineering Woods Hole Oceanographic Institution Woods Hole MA 02543

Mobile robots are increasingly used to collect valuable in situ samples during scientific expeditions. However, many phenomena of scientific interest—deep-sea hydrothermal plumes, algal blooms, warm-core eddies, and lava flows—are spatiotemporal distributions that evolve on spatial and temporal scales that complicate sample collection. Here, we consider the problem of charting the space-time dynamics of deep-sea hydrothermal plumes with the state-of-the-art autonomous underwater vehicle (AUV) Sentry. In the hydrothermal plume charting problem, the plume state is driven by complicated and unobserved dynamics in the deep sea. To effectively sample the moving plume, an autonomy system must infer plume dynamics from sparse, point observations, while respecting operational constraints of AUV Sentry that restrict the set of possible trajectories to nonadaptive, uniform-coverage patterns. We frame the plume charting problem as a sequential decision-making problem and formulate a mission planner PHORTEX (PHysically-informed Operational Robotic Trajectories for Expeditions) that strategically designs full mission trajectories for Sentry, where each mission plan is informed by the observations of the last. PHORTEX is composed of a trajectory optimizer, which maximizes expected samples collected within a moving plume, and PHUMES (PHysically-informed Uncertainty Models for Environment Spatiotemporality), a modeling framework that leverages an embedded simulator of idealized plume physics as an inductive bias to enable dynamics learning from extreme partial observations and a few Sentry deployments. In both simulation and in field trials at a hydrothermal site in the Gulf of California, we demonstrate that Sentry using PHORTEX learns to track a moving hydrothermal plume and gather samples that significantly improve upon baseline spatial and temporal diversity for use in downstream science tasks.

关键词： Trajectory Sensors Oceans Vehicle dynamics Robot sensing systems Adaptation models Spatiotemporal phenomena Decision making Marine robots Environmental monitoring Mobile robots

来源：评论

学校读者我要写书评

暂无评论

SHE-Net: Syntax-Hierarchy-Enhanced Text-Video Retrieval

引用

IEEE Transactions on Circuits and Systems for Video technology 2025年

作者： Yu, Xuzheng Jiang, Chen Dong, Xingning Gan, Tian Yang, Ming Guo, Qingpei Institution of Ant Group Co. Ltd Hangzhou310023 China Shandong University School of Computer Science and Technology Qingdao266237 China

The user base of short video apps has experienced unprecedented growth in recent years, resulting in a significant demand for video content analysis. In particular, text-video retrieval, which aims to find the top matching videos given text descriptions from a vast video corpus, is an essential function, the primary challenge of which is to bridge the modality gap. Nevertheless, most existing approaches treat texts merely as discrete tokens and neglect their syntax structures. Moreover, the abundant spatial and temporal clues in videos are often under-utilized due to the lack of interaction with text. To address these issues, we argue that using texts as guidance to focus on relevant temporal frames and spatial regions within videos is beneficial. In this paper, we propose a novel Syntax-Hierarchy-Enhanced text-video retrieval method (SHE-Net) that exploits the inherent semantic and syntax hierarchy of texts to bridge the modality gap from two perspectives. First, to facilitate a more fine-grained integration of visual content, we employ the text syntax hierarchy, which reveals the grammatical structure of text descriptions, to guide the visual representations. Second, to further enhance the multi-modal interaction and alignment, we also utilize the syntax hierarchy to guide the similarity calculation. We evaluated our method on four public text-video retrieval datasets of MSR-VTT, MSVD, DiDeMo, and ActivityNet. The experimental results and ablation studies confirm the advantages of our proposed method. © 2025 IEEE.

关键词： Video analysis

来源：评论

学校读者我要写书评

暂无评论

Securing cell scheduling function in TSCH-based industrial IoT networks

引用

Ad Hoc Networks 2025年 175卷

作者： Tapadar, Karnish N.A. Khatua, Manas Venkatesh, Tamarapalli Department of Computer Science and Engineering Shiv Nadar Institution of Eminence Uttar Pradesh Gautam Buddha Nagar201314 India Department of Computer Science and Engineering Indian Institute of Technology Guwahati Assam Guwahati781039 India

6TiSCH is a widely adopted low-power networking standard for Industrial IoT applications that provides highly reliable communication with low latency. Cell scheduling is one of the crucial components in 6TiSCH networks, as it determines packet transmission schedules based on time and channel allocation policy. The IETF published the Minimal Scheduling Function (MSF) and associated 6top (6P) protocol to manage cell schedules dynamically. However, security of the 6TiSCH architecture, particularly the vulnerabilities within the MSF and its associated 6P, has not been fully explored in the literature. This paper identifies vulnerabilities present in the MSF and 6P protocol, and demonstrates the feasibility of two different types of attack called cell depletion attack and schedule instability attack. In both attacks, the main objective of adversary is to consume scheduling resources and make the schedule unstable by performing unnecessary and incorrect 6P transactions. These attacks disrupt the communication schedule of victim nodes as well as victims’ successors, thus causing schedule instability, reduced reliability and increased energy consumption. The Minimal Security Framework standardized by IETF cannot handle such attacks on the MSF. Therefore, this paper proposes a comprehensive strategy (SCSF-WELA) that combines rule-based approach and Weak Estimation Learning Automata (WELA) to detect and prevent malicious behaviour by an attacker. The proposed solution integrates into the standard MSF without additional communication overhead. Through extensive simulations using the 6TiSCH simulator, we verify that the impact of these attacks is significant as they can increase schedule instability by four times and the 6P messaging overhead by 42% in a 60-node network. Furthermore, the proposed SCSF-WELA contermeasure shows substantial improvements in network stability, energy efficiency, and overall performance under those attacks. © 2025

关键词： Risk assessment

来源：评论

学校读者我要写书评

暂无评论

GAN Prior-Enhanced Novel View Synthesis from Monocular Degraded Images

引用

IEEE Transactions on Multimedia 2025年

作者： Guo, Kehua Wu, Zheng Wen, Xianhong Guo, Shaojun Xi, Zhipeng Chen, Tianyu Central South University School of Computer Science and Engineering Changsha410083 China Academy of Military Sciences of PLA China National Institution of Defense Technology Innovation China

With the escalating demand for three-dimensional visual applications such as gaming, virtual reality, and autonomous driving, novel view synthesis has become a critical area of research. Current methods mainly depend on multiple views of the same subject to achieve satisfactory results, but there is often a significant lack of available data. Typically, only a single degraded image is available for reconstruction, which may be affected by occlusion, low resolution, or absence of color information. To overcome this limitation, we propose a two-stage feature matching approach designed specifically for single degraded images, leading to the synthesis of high-quality novel perspective images. This method involves the sequential use of an encoder for feature extraction followed by the fine-tuning of a generator for feature matching. Additionally, the integration of an information filtering module proposed by us during the GAN inversion process helps eliminate misleading information present in degraded images, thereby correcting the inversion direction. Extensive experimental results show that our method outperforms existing state-of-the-art single-view novel view synthesis techniques in handling challenges like occluded, grayscale, and low-resolution images. Moreover, the efficacy of our method remains unparalleled even when aforementioned method integrated with image restoration algorithms. © 2025 IEEE.

关键词： Gallium nitride

来源：评论

学校读者我要写书评

暂无评论

Risk Assessment of Global Temperature Anomalies Using Intelligence Frameworks: Evaluating the Impact of Socioeconomic Factors and with a Case Study on Heatstroke Deaths in India

Risk Assessment of Global Temperature Anomalies Using Intell...

引用

Ambient Intelligence in Health Care (ICAIHC), International Conference on

作者： Alok Kumar Pati Jemmut Patnaik Sruti Dash Tuheena Mohanty Alok Ranjan Tripathy Department of Computer Science Ravenshaw University Cuttack India Department of Computer Application Siksha ’O’ Anusandhan Deemed to be University Bhubaneswar India Department of Computer Application Kalinga Institution of Industrial Technology Bhubaneswar India Department of Computer Science & Engg IMIT Cuttack India

ISBN: (数字)9798331530259

ISBN: (纸本)9798331530266

Rising global temperatures due to climate change have significantly increased the risk of heat-related illnesses, particularly heatstroke, in various regions. As global warming continues, it is crucial to understand patterns in heatstroke occurrences to predict and address future impacts. This study uses Machine Learning (ML) techniques to explore the connection between increasing temperatures and heatstroke incidents. ML models analyze extensive datasets containing meteorological data, health records, and geographical variables to uncover correlations between temperature spikes and heatstroke prevalence. The research incorporates supervised learning models such as linear Regression, lasso regression, ridge regression and voting regressor to predict high-risk periods and regions vulnerable to heatstroke. Additionally, time-series analysis and Prophet model is used to forecast future heatstroke cases by identifying climate data trends. These models are trained and validated using historical temperature and heatstroke fatality data from different regions. Preliminary findings indicate that extreme heatwaves, along with humidity and urbanization factors, significantly contribute to heatstroke occurrences. This study, leveraging ML, aims to improve the ability to predict and prevent heat-related health crises, offering valuable insights for public health planning, early-warning systems, and climate adaptation strategies to protect populations from the adverse effects of global warming.

关键词： Heating systems Temperature distribution Analytical models Temperature dependence Correlation Urban areas Machine learning Predictive models Data models Global warming Climate change Data analysis

来源：评论

学校读者我要写书评

暂无评论

Risk Assessment of Global Temperature Anomalies Using Intelligence Frameworks: Evaluating the Impact of Socioeconomic Factors and with a Case Study on Heatstroke Deaths in India

Risk Assessment of Global Temperature Anomalies Using Intell...

引用

2025 International Conference on Ambient Intelligence in Health Care, ICAIHC 2025

作者： Pati, Alok Kumar Patnaik, Jemmut Dash, Sruti Mohanty, Tuheena Tripathy, Alok Ranjan Ravenshaw University Department of Computer Science Cuttack03 India Siksha 'O' Anusandhan Deemed to be University Department of Computer Application Bhubaneswar30 India Kalinga Institution of Industrial Technology Department of Computer Application Bhubaneswar24 India Imit Department of Computer Science & Engg Cuttack India

ISBN: (纸本)9798331530259

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

A Novel Deep Learning Approach for Tissue Microstructure Estimation Using Spherical Mean Technique

A Novel Deep Learning Approach for Tissue Microstructure Est...

引用

IEEE International Symposium on Biomedical Imaging

作者： Yiang Pan Yuanjing Feng Jianzhong He Jianan Cui Lei Xie Zan Chen Qingrun Zeng Jiawei Zhang Yan Yu Konstantin K. Kukanov Ye Wu Institution of Information Processing and Automation Zhejiang University of Technology Hangzhou China Polenov Neurosurgery Institute The branch of Almazov National Medical Research Centre School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China

ISBN: (数字)9798331520526

ISBN: (纸本)9798331520533

Multi-shell diffusion magnetic resonance imaging (dMRI) models connect tissue organization with the observed dMRI signals to infer tissue microstructure. Given the highly non-linear nature of these models, several deep network based approaches have been proposed to improve the efficiency and accuracy of tissue microstructure estimation. However, these approaches rely on dMRI data with dense q-space sampling, which can lead to high computational costs. In this work, we propose a novel deep learning framework, termed DeepSMT, which utilizes the spherical mean technique (SMT) to directly estimate NODDI and DKI microstructure. The network comprises an inter-voxel block and a multi-shell feature block that can capture the feature relationship of the average signal between inter-voxels and integrate features from each shell. We validate the effectiveness of our method using the Human Connectome Project dataset. Overall, the DeepSMT has better performance compared to other methods in estimating tissue microstructure.

关键词： Deep learning Training Accuracy Costs Magnetic resonance imaging Computational modeling Estimation Organizations Data models Microstructure

来源：评论

学校读者我要写书评

暂无评论

Generalized Kullback-Leibler Divergence Loss

arXiv

引用

arXiv 2025年

作者： Cui, Jiequan Zhu, Beier Xu, Qingshan Tian, Zhuotao Qi, Xiaojuan Yu, Bei Zhang, Hanwang Hong, Richang College of Computing & Data Science Nanyang Technological University Singapore Department of Computer Science & Engineering The Chinese University of Hong Kong Sha Tin Hong Kong The University of Hong Kong Hong Kong Harbin Institution of Technology China Hefei University of Technology China

In this paper, we delve deeper into the Kullback–Leibler (KL) Divergence loss and mathematically prove that it is equivalent to the Decoupled Kullback-Leibler (DKL) Divergence loss that consists of 1) a weighted Mean Square Error (wMSE) loss and 2) a Cross-Entropy loss incorporating soft labels. Thanks to the decoupled structure of DKL loss, we have identified two areas for improvement. Firstly, we address the limitation of KL loss in scenarios like knowledge distillation by breaking its asymmetric optimization property along with a smoother weight function. This modification effectively alleviates convergence challenges in optimization, particularly for classes with high predicted scores in soft labels. Secondly, we introduce class-wise global information into KL/DKL to reduce bias arising from individual samples. With these two enhancements, we derive the Generalized Kullback–Leibler (GKL) Divergence loss and evaluate its effectiveness by conducting experiments on CIFAR-10/100, ImageNet, and vision-language datasets, focusing on adversarial training, and knowledge distillation tasks. Specifically, we achieve new state-of-the-art adversarial robustness on the public leaderboard — RobustBench and competitive knowledge distillation performance across CIFAR/ImageNet models and CLIP models, demonstrating the substantial practical merits. Our code is available at https://***/jiequancui/DKL. © 2025, CC BY-NC-SA.

关键词： Mean square error

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：