检索结果-内蒙古大学图书馆

International Conference on Radiation Effects of Electronic Devices (ICREED)

作者： He Lyu Bo Mei Pengchao Xue Bo Wang Rigen Mo Qifei Yuan Wu Gao School of Computer Science and Technology Northwestern Polytechnical University Xi'an China China Aerospace Components Engineering Center China Academy of Space Technology Beijing China

ISBN: (数字)9798331549299

ISBN: (纸本)9798331549305

Single Event Effects (SEEs) pose significant reliability challenges to deep neural networks (DNNs), particularly in aerospace environments characterized by radiation exposure. This paper introduces a comprehensive fault injection (FI) framework for systematic vulnerability assessment and mitigation of SEEs in DNN architectures. We propose a Progressive Bit Search (PBS) technique to efficiently identify sensitive layers within DNNs, combined with Triple Modular Redundancy (TMR) for hardening critical layers. Experimental results on YOLOv5 demonstrate that our approach improves fault injection evaluation efficiency by over tenfold while enhancing SEE hardening capability by more than 24 times, with a resource cost increase of less than 10%. This work addresses the critical gap between software-based FI simulations and hardware-accurate reliability assessment, providing a practical solution for radiation-hardened DNN design in aerospace applications.

关键词： YOLO Fault diagnosis Radiation effects Systematics Costs Radiation hardening (electronics) Prevention and mitigation Redundancy Artificial neural networks Reliability engineering

来源：评论

学校读者我要写书评

暂无评论

LLM for Question Generation and Validation to Enhance School Level Student Assessment

LLM for Question Generation and Validation to Enhance School...

引用

Pervasive Computing and Social Networking (ICPCSN), International Conference on

作者： Adithya D Varma Sruthy Anand Akshay Krishnan Thekkedath Kiran P Niranjan Prasanth Sethuraman N Rao Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Amritapuri India Center for Wireless Networks & Applications (WNA) Amrita Vishwa Vidyapeetham Amritapuri India

ISBN: (数字)9798331535193

ISBN: (纸本)9798331535209

Recent advancements in large language models (LLMs) have accelerated the growth of several AI-based solutions in the daily lives of people, including in the field of education. Using LLM in education can potentially automate various aspects of the teaching-learning process. This work explores how LLMs can assist educators in generating questions for student assessment. Using sophisticated prompt engineering, a system has been developed to generate multiple levels of questions from a single topic, enabling teachers to evaluate and curate a variety of questions attuned to the diverse needs of learners. This innovative approach diverges from conventional ICT-based techniques that primarily rely on keyword matching and superficial metrics. The system generates questions, taking into account the semantic meaning and contextual relevance. Furthermore, LLM evaluation metrics have been applied to assess the methods used for the generation of questions, and the results are presented accordingly.

关键词： Measurement Pervasive computing Social networking (online) Large language models Semantics Education Taxonomy computer architecture Question generation Prompt engineering

来源：评论

学校读者我要写书评

暂无评论

A Lightweight CNN Based on Transfer Learning for COVID-19 Diagnosis

引用

computers, Materials & Continua 2022年第7期72卷 1123-1137页

作者： Xiaorui Zhang Jie Zhou Wei Sun Sunil Kumar Jha Wuxi Research Institute Nanjing University of Information Science&TechnologyWuxi214100China Engineering Research Center of Digital Forensics Ministry of EducationJiangsu Engineering Center of Network MonitoringSchool of Computer and SoftwareNanjing University of Information Science&TechnologyNanjing210044China Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology(CICAEET) Nanjing University of Information Science&TechnologyNanjing210044China School of Automation Nanjing University of Information Science&TechnologyNanjing 210044 China IT Fundamentals and Education Technologies Applications University of Information Technology and Management in RzeszowRzeszow Voivodeship100031Poland

The key to preventing the COVID-19 is to diagnose patients quickly and *** have shown that using Convolutional Neural Networks(CNN)to analyze chest Computed Tomography(CT)images is helpful for timely COVID-19 ***,personal privacy issues,public chest CT data sets are relatively few,which has limited CNN’s application to COVID-19 ***,many CNNs have complex structures and massive *** if equipped with the dedicated Graphics Processing Unit(GPU)for acceleration,it still takes a long time,which is not conductive to widespread *** solve above problems,this paper proposes a lightweight CNN classification model based on transfer *** the lightweight CNN MobileNetV2 as the backbone of the model to solve the shortage of hardware resources and computing *** order to alleviate the problem of model overfitting caused by insufficient data set,transfer learning is used to train the *** study first exploits the weight parameters trained on the ImageNet database to initialize the MobileNetV2 network,and then retrain the model based on the CT image data set provided by *** results on a computer equipped only with the Central Processing Unit(CPU)show that it consumes only 1.06 s on average to diagnose a chest CT *** to other lightweight models,the proposed model has a higher classification accuracy and reliability while having a lightweight architecture and few parameters,which can be easily applied to computers without GPU ***:***/ZhouJie-520/paper-codes.

关键词： Convolutional neural networks chest computed tomography image COVID-19 transfer learning mobileNetv2

来源：评论

学校读者我要写书评

暂无评论

A Real-time Cutting Model Based on Finite Element and Order Reduction

引用

computer Systems science & engineering 2022年第10期43卷 1-15页

作者： Xiaorui Zhang Wenzheng Zhang Wei Sun Hailun Wu Aiguo Song Sunil Kumar Jha Wuxi Research Institute Nanjing University of Information Science&TechnologyWuxi214100China Engineering Research Center of Digital Forensics Ministry of EducationJiangsu Engineering Center of Network MonitoringSchool of Computer and SoftwareNanjing University of Information Science&TechnologyNanjing210044China School of Automation Nanjing University of Information Science&TechnologyNanjing210044China State Key Laboratory of Bioelectronics Jiangsu Key Lab of Remote Measurement and ControlSchool of Instrument Science and EngineeringSoutheast UniversityNanjing210096China IT Fundamentals and Education Technologies Applications University of Information Technology and Management in RzeszowRzeszow Voivodeship100031Poland

Telemedicine plays an important role in Corona Virus Disease 2019(COVID-19).The virtual surgery simulation system,as a key component in telemedicine,requires to compute in ***,this paper proposes a realtime cutting model based on finite element and order reduction method,which improves the computational speed and ensure the real-time *** proposed model uses the finite element model to construct a deformation model of the virtual ***,a model order reduction method combining proper orthogonal decomposition and Galerkin projection is employed to reduce the amount of deformation *** addition,the cutting path is formed according to the collision intersection position of the surgical instrument and the lesion area of the virtual ***,the Bezier curve is adopted to draw the incision outline after the virtual lung has been ***,the simulation system is set up on the PHANTOM OMNI force haptic feedback device to realize the cutting simulation of the virtual *** results show that the proposed model can enhance the real-time performance of telemedicine,reduce the complexity of the cutting simulation and make the incision smoother and more natural.

关键词： Virtual surgery cutting model finite element model model order reduction Bezier curve

来源：评论

学校读者我要写书评

暂无评论

IM-Diff: Implicit Multi-Contrast Diffusion Model for Arbitrary Scale MRI Super-Resolution

引用

IEEE Journal of Biomedical and Health Informatics 2025年第6期29卷 4200-4212页

作者： Liu, Lanqing Zou, Jing Xu, Cheng Wang, Kang Lyu, Jun Xu, Xuemiao Hu, Zhanli Qin, Jing The Hong Kong Polytechnic University Centre for Smart Health School of Nursing 999077 Hong Kong Nanyang Technological University School of Mechanical and Aerospace Engineering 639798 Singapore Harvard Medical School Department of Psychiatry Brigham and Women's Hospital BostonMA02115 United States South China University of Technology Guangdong Engineering Center for Large Model and GenAI Technology School of Computer Science and Engineering Guangzhou510640 China Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Lauterbur Research Center for Biomedical Imaging Shenzhen518172 China CAS SIAT-PolyU Multi-modal Medical Molecular Imaging Joint Laboratory 999077 Hong Kong

Diffusion models have garnered significant attention for MRI Super-Resolution (SR) and have achieved promising results. However, existing diffusion-based SR models face two formidable challenges: 1) insufficient exploitation of complementary information from multi-contrast images, which hinders the faithful reconstruction of texture details and anatomical structures;and 2) reliance on fixed magnification factors, such as 2× or 4×, which is impractical for clinical scenarios that require arbitrary scale magnification. To circumvent these issues, this paper introduces IM-Diff, an implicit multi-contrast diffusion model for arbitrary-scale MRI SR, leveraging the merits of both multi-contrast information and the continuous nature of implicit neural representation (INR). Firstly, we propose an innovative hierarchical multi-contrast fusion (HMF) module with reference-aware cross Mamba (RCM) to effectively incorporate target-relevant information from the reference image into the target image, while ensuring a substantial receptive field with computational efficiency. Secondly, we introduce multiple wavelet INR magnification (WINRM) modules into the denoising process by integrating the wavelet implicit neural non-linearity, enabling effective learning of continuous representations of MR images. The involved wavelet activation enhances space-frequency concentration, further bolstering representation accuracy and robustness in INR. Extensive experiments on three public datasets demonstrate the superiority of our method over existing state-of-the-art SR models across various magnification factors. © 2013 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

MURDOC: Transforming Pixels into Perception for Camouflage Detection 43

MURDOC: Transforming Pixels into Perception for Camouflage D...

引用

43rd AIAA DATC/IEEE Digital Avionics Systems Conference, DASC 2024

作者： Hogue, Debra Kastl, Zak Karch, Joseph Nguyen, Don Schley, Lacey Lewis, Justin Connelly, Shane Weaver, Chris School of Computer Science The University of Oklahoma United States Us Air Force's 76th Software Engineering Group United States Oklahoma Aerospace and Defense Innovation Institute The University of Oklahoma United States The University of Oklahoma Department of Psychology Center for Applied Social Research United States

ISBN: (纸本)9798350349610

The MURDOC project introduces an application to enhance trustworthiness and explainability in computer vision models, focusing on camouflage detection. It aims to address the need for transparent and interpretable AI systems in sensitive domains such as security and defense. MURDOC integrates advanced eXplainable AI techniques including off-ramps for collecting interpretable insights, attention mechanisms for high-lighting relevant features, and a user-centric image pre-processing tool within the visualization interface. This paper offers an assessment of MURDOC's potential impact on trustworthiness and explainability in camouflaged object detection tasks. It discusses and assesses the potential effectiveness of off-ramps in gathering XAI output at various model stages, such as feature maps, attention mechanisms, and activation maps. Additionally, the paper investigates how user-driven image pre-processing mechanisms may enhance the trustworthiness of the model's predictions and decisions, allowing users to modify the input and observe prediction changes. As a work in progress, the development of MURDOC shows promise in bridging the gap for transparency and interpretability in camouflage detection. The paper also discusses the challenges, future directions, and potential applications of MURDOC's capabilities in diverse domains requiring transparent and trustworthy AI systems. The source code for the version of MURDOC in this paper is available on GitHub at: https://***/Department-70/DASC-2024. © 2024 IEEE.

关键词： Camouflage

来源：评论

学校读者我要写书评

暂无评论

Genetic Algorithm-Based Feature Selection for Accurate Breast Cancer Classification

Genetic Algorithm-Based Feature Selection for Accurate Breas...

引用

2023 International Conference on IT and Industrial Technologies, ICIT 2023

作者： Shabbir, Attia Ali, Raja Hashim Shabbir, Muhammad Zeeshan Abideen, Zain Ul Khan, Talha Ali Ijaz, Ali Zeeshan Ali, Nisar Imad, Muhammad Bakar, Muhammad Abu Gik Institute of Engg. Sciences & Technology Faculty of Computer Science & Engineering Topi Pakistan University of Europe for Applied Sciences Dept. of Technology & Software Engineering Berlin Germany Department of Electrical Engineering Lahore Pakistan BCMaterials Basque Center for Materials Applications & Nanostructure Basque Country Leioa Spain University of Regina Faculty of Electronic Systems Engineering Regina Canada

ISBN: (纸本)9798350315974

Breast cancer is a significant global healthcare challenge, particularly in developing and underdeveloped countries, with profound physical, emotional, and psychological consequences, including mortality. Timely diagnosis and accurate treatment are crucial in addressing this issue. We propose the utilization of a feature selection technique to identify the most relevant features from among all features for breast cancer diagnosis, and show that Genetic Algorithms are impressive for this task. The study compares the results of GA with no selection and an alternative method, Principle Component Analysis (PCA). Three machine learning models, all based on supervised learning with data split into training and test data, are employed for binary classification using the selected feature subset. The evaluation metrics employed encompass accuracy, precision, recall, and F1-score. Among the selected models, Random Forest demonstrates the most favorable outcomes, achieving an accuracy score of 0.96, precision score of 0.96, recall value of 0.98, and an F1-score of 0.97. These results underscore the effectiveness of GA in feature selection for breast cancer diagnosis. Consequently, the integration of Genetic Algorithms (GA) with Random Forest showcases the superior performance among the evaluated models. © 2023 IEEE.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Decision Support System for Spontaneous Volunteers During Emergency Response

Decision Support System for Spontaneous Volunteers During Em...

引用

International Conference on Computing and Networking Technology (ICCNT)

作者： Sruthy Anand Sethuraman N Rao A.D. Dev Nandan B.Madan Gopal Madhav A Das Center for Wireless Networks & Applications (WNA) Amrita Vishwa Vidyapeetham Amritapuri India Department of Computer Science and Engineering School of Computing Amrita Vishwa Vidyapeetham Amritapuri India

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

Disasters affect a large number of people yearly and recurrently at many locations. Emergencies compel the local community to participate in disaster response; they are mostly the first responders during any disaster. Hence, it is necessary to devise solutions to support the local community and enhance their resilience. This work proposes a comprehensive platform for the victims, administrators, and volunteers during a catastrophe. It encourages the participation of the local community in managing local resources, requesting help, and getting acknowledged for the service they lend. The platform helps recognize the local community’s strengths and provides a method to receive information from disaster managers. The platform will also bring more situational awareness to disaster managers and volunteers. It also helps disaster managers assess the disaster’s potential impact and vulnerability levels of the community at an early stage. The platform envisions providing a decision support system for the spontaneous volunteers to co-work with disaster managers in a regulated fashion by eliminating fake volunteers and messages. The research also focuses on the characteristics of technology adoption for the widespread acceptance of the solution.

关键词： Decision support systems Social networking (online) Disasters Urban areas Prototypes Disaster management Emergency services Real-time systems Mobile applications Resilience

来源：评论

学校读者我要写书评

暂无评论

Enhancing Urban Home Security: Deep Learning Enabled Vehicle Identification

Enhancing Urban Home Security: Deep Learning Enabled Vehicle...

引用

Emerging Technology (INCET), International Conference for

作者： V S N Lokesh Yarramallu Sanjit Teja Tummalapalli Yatham Nitish Reddy Sruthy Anand Department of Computer Science and Engineering School of Computing Amrita Vishwa Vidyapeetham Amritapuri India Center for Wireless Networks & Applications (WNA) Amrita Vishwa Vidyapeetham Amritapuri India

ISBN: (数字)9798350361155

ISBN: (纸本)9798350361162

The growing rate of crimes in cities is a genuine concern these days. Preventing crimes from happening is a need for the city residents and the administrator community. Various technology-enabled solution approaches can be integrated to prevent crimes in cities. In this work, we explore how the amalgamation of Deep Learning and IoT can prevent crimes and provide enhanced security to citizens. Crimes happen for several reasons, and the right technology-enabled solutions can help prevent crimes by alerting the intended stakeholders on time. This paper focuses on the importance of identifying vehicles and the importance of detecting non-resident vehicles to alert the residents and related security personnel about them. We detailed the steps used to identify the vehicle using YOLOv8. The work also explored various OCR tools to find the best one for number plate identification.

关键词： Deep learning Image color analysis Urban areas Smart homes Safety Planning Security

来源：评论

学校读者我要写书评

暂无评论

Unified regularity measures for sample-wise learning and generalization

引用

Visual Intelligence 2024年第1期2卷 488-507页

作者： Chi Zhang Meng Yuan Xiaoning Ma Yu Liu Haoang Lu Le Wang Yuanqi Su Yuehu Liu Institute of Artificial Intelligence and Robotics Xi’an Jiaotong UniversityXi’an710049China National KeyLaboratory of Human-Machine Hybrid Augmented Intelligence Xi’an Jiaotong UniversityXi’an710049China National Engineering Research Center for Visual Information and Applications Xi’an Jiaotong UniversityXi’an710049China School of Computer Science and Technology Xi’an Jiaotong UniversityXi’an710049China

Fundamental machine learning theory shows that different samples contribute unequally to both the learning and testing *** studies on deep neural networks(DNNs)suggest that such sample differences are rooted in the distribution of intrinsic pattern information,namely sample *** by recent discoveries in network memorization and generalization,we propose a pair of sample regularity measures with a formulation-consistent representation for both ***,the cumulative binary training/generalizing loss(CBTL/CBGL),the cumulative number of correct classifications of the training/test sample within the training phase,is proposed to quantify the stability in the memorization-generalization process,while forgetting/mal-generalizing events(ForEvents/MgEvents),i.e.,the misclassification of previously learned or generalized samples,are utilized to represent the uncertainty of sample regularity with respect to optimization *** effectiveness and robustness of the proposed approaches for mini-batch stochastic gradient descent(SGD)optimization are validated through sample-wise *** training/test sample selection applications show that the proposed measures,which share the unified computing procedure,could benefit both tasks.

关键词： Network generalization Memorization-generalization mechanism Sample regularity Forgetting events Sample reweighting

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：