检索结果-内蒙古大学图书馆

2nd International Conference on Automation, computing and Renewable Systems, ICACRS 2023

作者： Desai, Dhyani Dhaval Mittapalli, Jishnu Saurav Tyagi, Karmanya School of Computing Science and Engineering Vellore Institute of Technology Chennai India

ISBN: (纸本)9798350340235

S kin is one of the most versatile and is one of the largest organs in the body. It has many important functions, it regulates the temperature of the body and at the same time also protects our internal organs from external damage. This outer layer shields the body from outside particles including harmful UV rays, bacteria, and chemicals, and other substances. Without proper care and maintenance, the skin can become dry, irritated, and more susceptible to infection and disease. S imilar to other bodily organs, the skin needs care and maintenance for its healthy functi oning. WHO says that the world's most widespread health issues are mainly skin conditions, ranking as the third most frequent cause of health issues. Additionally, they are one of the leading causes of disability and are among the most common reasons for visits to outpatient clinics. The World Health Organization has reported a noticeable increase of skin cancer in the last few years, it also identified UV radiation as a leading cause. present a multi-filter deep neural decision forest-based method determining which category the ES D disease belongs to. Data used in this project includes both histopathological and also the clinical attributes of various patients suffering from EDS . The proposed multi-filter feature selection method identifies the most optimal features and attributes contributing to disease detection and improves its performance. After generating the feature set a deep neural decision forest is utilized for determining the category of the disease. To evaluate more on this particular method, various criteria were taken and checked with other conventional classification approaches. © 2023 IEEE.

关键词： ESD prediction Modern technologies Skin issues

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Based Computer Vision Bound Fall Detection for Elderly People 21

Deep Learning Based Computer Vision Bound Fall Detection for...

引用

21st IEEE Student Conference on Research and Development, SCOReD 2023

作者： Abdoul-Halim, Mohamed Abdallah Vengusamy, Sivakumar Asia Pacific University of Technology and Innovation Faculty of Computing Engineering and Technology School of Computing Science and Software Kuala Lumpur Malaysia

ISBN: (纸本)9798350318821

Due to the devastating effects, such as increased mortality and morbidity, falls among the elderly are a significant health issue globally. Supporting the elderly in their daily activities is a significant problem for society because they are the age group with the largest rate of population growth. An automated fall detection system has gained popularity in the healthcare sector due to the social and financial benefits it offers. Vision-based fall detection systems have a great promise now that Smart Homes are a growing trend and there are more cameras in our everyday environments. An autonomous real-time fall detection system based on vision is given in this paper. In this research, we suggested a 3D RGB camera-based method for fall detection. Machine learning algorithms, which were trained on characteristics retrieved by a deep learning-based computer vision algorithm, are used to distinguish between occlusion, falling, and routine everyday activities. Deep learning algorithms are used to identify people in videos. Two datasets - one developed locally and the other made public - were used for the experimental validation of the suggested methodology. Several assessment metrics are computed for evaluation. This analysis demonstrated the efficacy of the suggested solution. Temporal characteristics in a video series are captured using motion history images, and spatial features are then effectively retrieved for classification using a depth-wise convolutional neural network. © 2023 IEEE.

关键词： Fall detection

来源：评论

学校读者我要写书评

暂无评论

VTensor:Using Virtual Tensors to Build a Layout-Oblivious AI Programming Framework

引用

Journal of Computer Science & technology 2023年第5期38卷 1074-1097页

作者：俞峰赵家程崔慧敏冯晓兵薛京灵 Institute of Computing Technology Chinese Academy of SciencesBeijing 100190China School of Computer Science and Technology University of Chinese Academy of SciencesBeijing 100080China School of Computer Science and Engineering University of New South WalesSydney 1466Australia

Tensors are a popular programming interface for developing artificial intelligence(AI)*** refers to the order of placing tensor data in the memory and will affect performance by affecting data locality;therefore the deep neural network library has a convention on the *** AI applications can use arbitrary layouts,and existing AI systems do not provide programming abstractions to shield the layout conventions of libraries,operator developers need to write a lot of layout-related code,which reduces the efficiency of integrating new libraries or developing new ***,the developer assigns the layout conversion operation to the internal operator to deal with the uncertainty of the input layout,thus losing the opportunity for layout *** on the idea of polymorphism,we propose a layout-agnostic virtual tensor programming interface,namely the VTensor framework,which enables developers to write new operators without caring about the underlying physical layout of *** addition,the VTensor framework performs global layout inference at runtime to transparently resolve the required layout of virtual tensors,and runtime layout-oriented optimizations to globally minimize the number of layout transformation *** results demonstrate that with VTensor,developers can avoid writing layout-dependent *** with TensorFlow,for the 16 operations used in 12 popular networks,VTensor can reduce the lines of code(LOC)of writing a new operation by 47.82%on average,and improve the overall performance by 18.65%on average.

关键词： artificial intelligence(AI)programming layout-oblivious tensor processing

来源：评论

学校读者我要写书评

暂无评论

Enhanced Detection of Glass Insulator Defects Using Improved Generative Modeling and Faster RCNN 18

Enhanced Detection of Glass Insulator Defects Using Improved...

引用

18th CIRP Conference on Computer Aided Tolerancing, CAT 2024

作者： Ning, Pin Jin, Jin Xu, Yuanping Kong, Chao Zhang, Chaolong Tang, Dan Huang, Jian Xu, Zhijie Li, Tukun School of Software Engineering Chengdu University of Information Technology Chengdu China School of Computing and Engineering University of Huddersfield Queensgate Huddersfield United Kingdom

The precise defect detections for glass insulators are of utmost importance to ensure their safety and functionality. Therefore, this study proposes an improved defect detection algorithm based on the optimized deep learning network. The collected glass insulator data was limited in size. Even after data augmentation, it remained insufficient for the training requirements of deep learning models. In this study, employing the improved Denoising Diffusion Probabilistic Models (DDPM) generative model to expand the glass insulator data. The glass insulator defect images generated by the improved noise-fitting network exhibit enhanced quality and high fidelity. Through manual selection and iterative experiments, a total of 1200 images were curated, constituting the glass insulator defect dataset for training and test of deep learning models. Faster RCNN was chosen as the defect detection model, and its VGG16 feature extraction network was replaced with ResNet50 to address the issue of gradient vanishing caused by excessive network stacking. Additionally, the Feature Pyramid Network (FPN) structure was introduced to enhance semantic extraction for different defect scales. The Kmeans++ algorithm was utilized to improve the proposal box generation parameters in RPN. Compared to the baseline Faster RCNN model's mAP of 72.7%, our improved version achieved a significant increase, reaching a mAP of 85.9%. © 2024 The Authors. Published by Elsevier B.V.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

An Improved PointNet++ Based Method for 3D Point Cloud Geometric Features Segmentation in Mechanical Parts 18

An Improved PointNet++ Based Method for 3D Point Cloud Geome...

引用

18th CIRP Conference on Computer Aided Tolerancing, CAT 2024

作者： Zhang, Peng Kong, Chao Xu, Yuanping Zhang, Chaolong Jin, Jin Li, Tukun Jiang, Xiangqian Tang, Dan School of Software Engineering Chengdu University of Information Technology Chengdu China School of Computing and Engineering University of Huddersfield Queensgate Huddersfield United Kingdom

The extraction of geometric features such as holes, arcs, and surfaces of mechanical parts is crucial for quality control. The existing methods for geometrical feature segmentations on 3D point clouds still have limitations, especially for simultaneously extracting multiple types of geometric features from comprehensive workpieces. To this end, this study investigates segmentation methods that take 3D point cloud datasets of mechanical parts as inputs, and employs an improved PointNet++ deep learning model to solve this extraction difficulty. Firstly, the Set Abstraction module in PointNet++ was modified by incorporating Self-Attention mechanisms to increase interactivity and global correlation among data points. Then, the local feature extraction Multilayer Perceptron (MLP) from PointNet-Transformer was integrated to enhance the feature extraction accuracy. Due to the inherent class imbalance issue, the Focal Tversky Loss is employed as the loss function to ensure that geometric features with relatively lower proportions can be fully trained. Finally, the Statistical filtering algorithm is utilized to mitigate noise and attenuate subtle irregularities, such that the smoothness of geometric features can be substantially enhanced. The experimental results demonstrate that the proposed model achieves an accuracy of 86.6% on geometric feature segmentations and a mean Intersection over Union (mIoU) of 0.84. The comparison with the original PointNet++ proves that the proposed method can improve accuracy and mIoU by 3.7% and 0.03 respectively. © 2024 The Authors. Published by Elsevier B.V.

关键词： Geometry

来源：评论

学校读者我要写书评

暂无评论

Adaptive Web Application Firewall for Multi-Threat Detection 5

Adaptive Web Application Firewall for Multi-Threat Detection

引用

5th International Conference on IoT Based Control Networks and Intelligent Systems, ICICNIS 2024

作者： Maheshwari, Muskan Nayak, Aniket Sethy, Asmit Sujatha, G. College of Engineering and Technology School of Computing SRM Institute of Science and Technology Kattankulathur Department of Networking and Communications Chennai India

ISBN: (纸本)9798331518097

Cyber threats targeting web applications have increased in frequency and sophistication, thus the need of such applications to be protected with advanced mechanisms. We introduce in this paper an Adaptive Web Application Firewall WAF that is capable of protecting applications from a wide range of threats that includes but are not limited to SQL injection, DDoS attacks, directory traversal, and CSRF. Using machine learning and traffic analysis, the proposed ABS adapts in real-time to the changing attack vectors and axes of engagement against web applications that are already compromised. With the ever-growing amount of incoming traffic, it is the Adaptive WAF that will enable web applications to maintain various forms of attacks and in the process develop varied defensive approaches. This paper explores how the Adaptive WAF can be used to enhance AWS security, integrity, and availability through the reduction of available cyber risk. The KNN model, with its introduction, strengthens the system further by highly increasing the precision and accuracy of the classification of web attacks to a level of 80.3% in terms of accuracy and 74.8% in terms of precision. This model enables the reliable detection of threats through distinguishing between malicious patterns with fewer false positives, thus further enhancing the ability of the system to detect and respond accordingly to the various web-based threats. © 2024 IEEE.

关键词： Adaptive Web Application Firewall Internet machine learning security protocols web application

来源：评论

学校读者我要写书评

暂无评论

Blockchain-Enabled Secure, Fair and Scalable Data Sharing in Zero-Trust Edge-End Environment

引用

IEEE Journal on Selected Areas in Communications 2025年第6期43卷 2056-2069页

作者： Xu, Xiaolong Meng, Ke Xiang, Haolong Cui, Guangming Xia, Xiaoyu Dou, Wanchun Nanjing210044 China Nanjing University of Information Science and Technology School of Software and the Jiangsu Province Engineering Research Center of Advanced Computing and Intelligent Services Nanjing210044 China RMIT University School of Computing Technologies MelbourneVIC3000 Australia Nanjing University State Key Laboratory for Novel Software Technology Nanjing210023 China

In edge computing, the Zero-Trust Security Model (ZTSM), as a key enabling technology for next-generation networks, plays a crucial role in providing authentication for addressing data sharing concerns, such as frequent data breaches, data misuse, and cyberattacks. However, due to the complexity and diversity of edge environments, ZTSM struggles to meet the security requirements of data sharing frameworks solely through enhanced authentication. Consequently, such frameworks with ZTSM still face challenges in ensuring data integrity, evaluating various node behaviors, and coping with the increasing complexity of node attributes. To address these issues, we propose a blockchain-enabled secure, fair and scalable data sharing framework in a zero-trust edge-end environment in this paper. Specifically, we first propose a Merkle forest-based data storage model for the classified storage of loosely coupled data, consequently enhancing the scalability of the model. Then, we design a node behavior-based reputation assessment mechanism to ensure fairness during data sharing. Moreover, a data sharing protocol supervised by smart contract is proposed, working with the aforementioned storage and assessment schemes, to ensure the security of data sharing. Finally, comprehensive security analysis validates the security, fairness and scalability of the proposed framework. Extensive experimental results show that, as transaction volume grows, the time cost of data traversal in the storage model becomes progressively more efficient. Additionally, when the size of the smart contract is increased tenfold, the maximum time cost of the data sharing protocol rises by only 4.98 times. © 1983-2012 IEEE.

关键词： Data integrity

来源：评论

学校读者我要写书评

暂无评论

Novel multi‐domain attention for abstractive summarisation

引用

CAAI Transactions on Intelligence technology 2023年第3期8卷 796-806页

作者： Chunxia Qu Ling Lu Aijuan Wang Wu Yang Yinong Chen College of Computer Science and Engineering Chongqing University of TechnologyChongqingChina School of Computing and Augmented Intelligence Arizona State UniversityTempeArizonaUSA

The existing abstractive text summarisation models only consider the word sequence correlations between the source document and the reference summary,and the summary generated by models lacks the cover of the subject of source document due to models'small *** order to make up these disadvantages,a multi‐domain attention pointer(MDA‐Pointer)abstractive summarisation model is proposed in this ***,the model uses bidirectional long short‐term memory to encode,respectively,the word and sentence sequence of source document for obtaining the semantic representations at word and sentence ***,the multi‐domain attention mechanism between the semantic representations and the summary word is established,and the proposed model can generate summary words under the proposed attention mechanism based on the words and ***,the words are extracted from the vocabulary or the original word sequences through the pointer network to form the summary,and the coverage mechanism is introduced,respectively,into word and sentence level to reduce the redundancy of sum-mary ***,experiment validation is conducted on CNN/Daily Mail *** evaluation indexes of the model without and with the coverage mechanism are improved respectively,and the results verify the validation of model proposed by this paper.

关键词： abstractive summarisation attention mechanism Bi‐LSTM coverage mechanism pointer network

来源：评论

学校读者我要写书评

暂无评论

High-Efficiency Asymmetrically Designed Three-Phase Virtual 48-Pulse Power Supply for Electrolytic Hydrogen

引用

IEEE Transactions on Power Electronics 2025年第8期40卷 10335-10342页

作者： Tian, Hanlei Cui, Haoran Han, Wei Sathik M, Jagabar Liang, Guozhuang Chen, Maolin Mekhilef, Saad Electrical Engineering School of Hebei University of Science and Technology Shijiazhuang050091 China Sustainable Energy and Environment Thrust Guangzhou511453 China The Hong Kong University of Science and Technology Department of Electronic and Computer Engineering Hong Kong Hong Kong SRM Institute of Science and Technology Faculty of Engineering and Technology Kattankulathur603203 India Sichuan University College of Electrical Engineering Chengdu610065 China Swinburne University of Technology School of Science Computing and Engineering Technologies MelbourneVIC3122 Australia

To address the low-voltage, high-current requirements in hydrogen production applications, a virtual 48-pulse three-phase rectifier is proposed, and achieves the equivalent performance of four parallel 12-pulse rectifiers (12-PR). The proposed approach builds upon the conventional 12-PR design and incorporates novel asymmetric current injection units (ACIU). The ACIU is installed on the dc side of the ac-dc converter, generating a specific current at the dc link to modulate and enhance the operating modes of the 12-PR. Consequently, the 12-pulse is extended to 48, resulting in an almost sinusoidal input current with a total harmonic distortion of 3.2% and an output current with a ripple rate of 2.3%, thus significantly improving power quality. Furthermore, the asymmetric design of the current injection units eliminates the need for a phase-shifting transformer. The efficacy of the proposed rectifier for electrolytic hydrogen production is validated using a 2.2-kW experimental prototype. © 1986-2012 IEEE.

关键词： Voltage Hydrogen Rectifiers Production Windings Circuits Inductors Transformers Harmonic analysis Electrochemical processes

来源：评论

学校读者我要写书评

暂无评论

Weather Prediction from Historical Data using Big Data Technologies 5

Weather Prediction from Historical Data using Big Data Techn...

引用

5th International Conference on IoT Based Control Networks and Intelligent Systems, ICICNIS 2024

作者： Choudha, Shaurya Singh, Aniruddh Kumar, Aman Gouthaman, P. School of Computing College of Engineering and Technology Department of Networking and Communications SRM Institute of Science and Technology Kattankulathur603203 India

ISBN: (纸本)9798331518097

Weather forecasting is an important function in a variety of activities such as agriculture, environment monitoring, and disaster management among others. Today with the development of technology, vast amounts of meteorological data are able to be collected and analyzed with the intention of improving prediction accuracy. The purpose of this work is to analyze the contribution of Big Data frameworks such as, Hadoop, MapReduce and Apache Spark in effective weather prediction processes. In a distributed system, historical weather data, satellite images and sensor readings are kept and manipulated through the HDFS storage. For effective data manipulation, MapReduce and Spark are used along with Hive and Pig for searching large datasets. Predictive analytics are performed using machine learning algorithms included in the MLlib package of Spark. These results are presented using the Tableau application, which shows the speed and accuracy of this Big Data approach in comparison to classical ones. The proposed work ends with a look into the prospects of Big Data in the field of weather forecasting and relevant problems in this area. © 2024 IEEE.

关键词： MapReduce

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：