检索结果-内蒙古大学图书馆

7th IET Smart Cities Symposium, SCS 2023

作者： Aljanabi, Mohammad Omran, Alaa Hamza Mijwil, Maad M. Abotaleb, Mostafa El-Kenawy, El-Sayed M. Mohammed, Sahar Yousif Ibrahim, Abdelhameed Department of computer College of Education Aliarqai university Baghdad Iraq University of information technology and communications Baghdad Iraq Computer Techniques Engineering Department Baghdad College of Economic Sciences University Baghdad Iraq Department of System Programming South Ural State University Chelyabinsk Russia Department of Communications and Electronics Delta Higher Institute of Engineering and Technology Egypt Computer Science Department Computer Science &Information Technology College Anbar University Anbar Iraq Computer Engineering and Control Systems Department Faculty of Engineering Mansoura University Mansoura Egypt

ISBN: (纸本)9781839539831

Data poisoning attacks, where adversaries manipulate training data to degrade model performance, are an emerging threat as machine learning becomes widely deployed in sensitive applications. This paper provides a comprehensive overview of data poisoning including attack techniques, adversary incentives, impacts on security and reliability, detection methods, defenses, and key research gaps. We examine label flipping, instance injection, backdoors, and other attack categories that enable malicious outcomes ranging from IP theft to accidents in autonomous systems. Promising detection approaches include statistical tests, robust learning, and forensics. However, significant challenges remain in translating academic defenses like adversarial training and sanitization into practical tools ready for operational use. With safety and trustworthiness at stake, more research on benchmarking evaluations, adaptive attacks, fundamental tradeoffs, and real-world deployment of defenses is urgently needed. Understanding vulnerabilities and developing resilient machine learning pipelines will only grow in importance as data integrity is fundamental to developing safe artificial intelligence. © The Institution of engineering & Technology 2023.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Enabled Object Detection and Tracking Model for Big Data Environment

引用

computers, Materials & Continua 2022年第11期73卷 2541-2554页

作者： K.Vijaya Kumar E.Laxmi Lydia Ashit Kumar Dutta Velmurugan Subbiah Parvathy Gobi Ramasamy Irina V.Pustokhina Denis A.Pustokhin Department of Computer Science and Engineering Vignan’s Institute of Engineering for WomenVisakhapatnam530049India Department of Computer Science and Engineering Vignan’s Institute of Information TechnologyVisakhapatnam530049India Department of Computer Science and Information System College of Applied SciencesAlMaarefa UniversityRiyadh11597Kingdom of Saudi Arabia Department of Electronics and Communication Engineering Kalasalingam Academy of Research and EducationKrishnankoil626126TamilnaduIndia Department of Computer Science Christ UniversityBangalore560029India Department of Entrepreneurship and Logistics Plekhanov Russian University of Economics117997MoscowRussia Department of Logistics State University of ManagementMoscow109542Russia

Recently,big data becomes evitable due to massive increase in the generation of data in real time ***,object detection and tracking applications becomes popular among research communities and finds useful in different applications namely vehicle navigation,augmented reality,surveillance,*** paper introduces an effective deep learning based object tracker using Automated Image Annotation with Inception v2 based Faster RCNN(AIA-IFRCNN)model in big data *** AIA-IFRCNN model annotates the images by Discriminative Correlation Filter(DCF)with Channel and Spatial Reliability tracker(CSR),named DCF-CSRT *** AIA-IFRCNN technique employs Faster RCNN for object detection and tracking,which comprises region proposal network(RPN)and Fast *** addition,inception v2 model is applied as a shared convolution neural network(CNN)to generate the feature ***,softmax layer is applied to perform classification *** effectiveness of the AIA-IFRCNN method undergoes experimentation against a benchmark dataset and the results are assessed under diverse aspects with maximum detection accuracy of 97.77%.

关键词： Object detection tracking convolutional neural network inception v2 image annotation

来源：评论

学校读者我要写书评

暂无评论

SparseFT: Sparsity-aware Fault Tolerance for Reliable CNN Inference on GPUs 23

SparseFT: Sparsity-aware Fault Tolerance for Reliable CNN In...

引用

Proceedings of the 32nd International Conference on Parallel Architectures and Compilation Techniques

作者： Gwangeun Byeon Seungtae Lee Seongwook Kim Yongjun Kim Prashant J. Nair Seokin Hong Department of Electrical and Computer Engineering Sungkyunkwan University Department of AI System Engineering Sungkyunkwan University Samsung Electronics The University of British Columbia

ISBN: (纸本)9798350342543

Graphics Processing Units (GPUs), while offering exceptional performance for CNN inference tasks, are susceptible to both transient and permanent hardware faults due to the integration of numerous processing elements and advancements in technology scaling. This paper proposes a novel and cost-effective fault mitigation technique, called Sparsity-aware Fault Tolerance (SparseFT), to ensure reliable CNN inference on GPUs. SparseFT leverages inherent sparsity in the activation maps to detect and correct errors on the processing elements without hardware redundancy. By exploiting the characteristic of dot-products, where multiplications with zero operands are ineffectual, SparseFT dynamically duplicates an effectual computation (i.e., a multiplication with non-zero operands) to the processing element initially assigned to the ineffectual one. It then compares the duplicated computation results to detect errors. Experimental results demonstrate that SparseFT achieves more than 97% error detection coverage with less than 1% performance overhead for the state-of-the-art CNN models.

关键词： CNN

来源：评论

学校读者我要写书评

暂无评论

Identifying Inaccurate Stories: Leveraging High Knowledge and Big Data 15

Identifying Inaccurate Stories: Leveraging High Knowledge an...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Khan, Mohammad Ahmar Verma, Pushpendra Kumar Ghaldiyal, Shivangi Balaji, N.V. Francis, G. Arun Patil, Swati Bula Department of Management Information System College of Commerce & Business Administration Dhofar University Country Sultanate of Oman Oman School of Computer Science and Applications IIMT University Meerut India Department of Computer Applications Invertis University Uttar Pradesh Bareilly India Department of Computer Science Karpagam Academy of Higher Education Tamil Nadu Coimbatore India Department of Electronics and Communication Engineering Karpagam College of Engineering Tamil Nadu Coimbatore India IT Vishwakarma Institute of Technology Pune India

ISBN: (纸本)9798350370249

Research on fake news has gained significant traction in a number of fields, We describe how the issue is tackled from a natural language processing standpoint in this research with the aim of developing identify false material in news. Collecting high-quality data, such as examples of false and actual news stories on a diverse range of subjects, is the key obstacle in this field of study. We examine the available before introducing the site as our lab's gift to the . We provide the whole text of the news that have already been applied based on human evaluation of the articles' authenticity. In order to clarify the gaps and causes of imbalance in the datasets that are now accessible and to direct ongoing attempts, we also conduct an appearance-based experiment. We urge the public to gather more information and make it accessible for study. ©2024 IEEE.

关键词： Data collection

来源：评论

学校读者我要写书评

暂无评论

Optimal Resource Allocation for U-Shaped Parallel Split Learning

Optimal Resource Allocation for U-Shaped Parallel Split Lear...

引用

2023 IEEE Globecom Workshops, GC Wkshps 2023

作者： Lyu, Song Lin, Zheng Qu, Guanqiao Chen, Xianhao Huang, Xiaoxia Li, Pan The University of Hong Kong The Department of Electrical and Electronic Engineering Hong Kong School of Electronics and Communication Engineering Sun Yat-sen University Shenzhen510275 China Case Western Reserve University The Department of Electrical Computer and System Engineering ClevelandOH44106 United States

ISBN: (纸本)9798350370218

Split learning (SL) has emerged as a promising approach for model training without revealing the raw data samples from the data owners. However, traditional SL inevitably leaks label privacy as the tail model (with the last layers) should be placed on the server. To overcome this limitation, one promising solution is to utilize U-shaped architecture to leave both early layers and last layers on the user side. In this paper, we develop a novel parallel U-shaped split learning and devise the optimal resource optimization scheme to improve the performance of edge networks. In the proposed framework, multiple users communicate with an edge server for SL. We analyze the end-to-end delay of each client during the training process and design an efficient resource allocation algorithm, called LSCRA, which finds the optimal computing resource allocation and split layers. Our experimental results show the effectiveness of LSCRA and that U-shaped parallel split learning can achieve a similar performance with other SL baselines while preserving label privacy. © 2023 IEEE.

关键词： 5G/6G edge networks label privacy resource allocation split learning U-shaped network

来源：评论

学校读者我要写书评

暂无评论

The three dimensional dosimetry imaging for automated eye cancer classification using transfer learning model 14

The three dimensional dosimetry imaging for automated eye ca...

引用

14th International Conference on Computing Communication and Networking Technologies, ICCCNT 2023

作者： Mohammed, Murtuza Ali Mohammed, Vazeer Ali Ramakrishnan, Rakesh Mohammed, Mehmood Ali Logeshwaran, J. Maheswaran, S. Lewis University Department of Computer & Information System IL United States University of the Cumberlands Department of Information Technology Union CityCA United States University of the Cumberlands Department of Information Technology WilliamsburgKY United States Sri Eshwar College of Engineering Department of Electronics and Communication Engineering Tamil Nadu Coimbatore India Kongu Engineering College Department of Electronics and Communication Engineering Tamil Nadu Erode India

ISBN: (纸本)9798350335095

computer vision methods utilizing transfer learning can offer a promising approach for automated eye cancer diagnosis with three-dimensional dosimetry imaging. The latest advances in AI have encouraged researchers to use deep learning models for automated cancer classification. This paper presents a novel approach using three-dimensional dosimetry imaging for automated ocular cancer classification using transfer learning. The approach uses a combination of dataset augmentation methods. The approach is adapted from the popular Inception V3 CNN architecture. Two different feature extraction approaches, namely mean and maximum pooling, are compared while extracting features from the output of the CNN layers. The extracted features are fed to the classifier which uses the SVM with a linear kernel as its decision system. The effectiveness of this method is evaluated on a set of 20 healthy ocular images and 26 suspicious ocular images. The overall classification accuracy achieved with this approach is 94.85%. The results obtained demonstrate that this approach has a promising potential for automated ocular cancer classification with an appropriate transfer learning model. © 2023 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

An innovation prediction of DNA damage of melanoma skin cancer patients using deep learning 14

An innovation prediction of DNA damage of melanoma skin canc...

引用

14th International Conference on Computing Communication and Networking Technologies, ICCCNT 2023

作者： Ramakrishnan, Rakesh Mohammed, Mehmood Ali Mohammed, Murtuza Ali Mohammed, Vazeer Ali Logeshwaran, J. Maheswaran, S. University of the Cumberlands Department of Information Technology Union CityCA United States University of the Cumberlands Department of Information Technology WilliamsburgKY United States Lewis University Department of Computer & Information System IL United States Sri Eshwar College of Engineering Department of Electronics and Communication Engineering Tamil Nadu Coimbatore India Kongu Engineering College Department of Electronics and Communication Engineering Tamil Nadu Erode India

ISBN: (纸本)9798350335095

There are now a variety of intriguing options for the study of genetic data thanks to recent developments in artificial neural networks and deep learning. In this study, we use a deep learning-based prediction model to find possible DNA damage in individuals with melanoma skin cancer. We create a convolutional neural network (CNN) model to forecast the DNA damage susceptibility of melanoma cancer cells using a publically available genome sequencing dataset. This model preprocesses the genomic data, extracts features, and categorises them. Comparing the results of our CNN model with those of a traditional logistic regression model, we find that our CNN reported superior performance in identifying differences between healthy and cancerous samples with an accuracy of nearly 96%. The model can be used to augment the standard clinical diagnosis of melanoma, which only uses visual assessment and histology. By intervening sooner, clinicians can put forward more personalized and informed plans of care and surveillance for each melanoma patient, reducing medical costs and improving the quality of patient diagnosis. © 2023 IEEE.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Performances Comparison of PV/T Solar Plants with Roll-Bond and Sheet-and-Tube Absorbers 3rd

Performances Comparison of PV/T Solar Plants with Roll-Bond ...

引用

3rd International Conference on Electronic engineering and Renewable Energy, ICEERE 2022

作者： El Fouas, Chaimae Hajji, Mohamed El Manssouri, Oussama Bekkay, Hajji Gagliano, Antonio Tina, Giuseppe Marco Laboratory of Renewable Energy Embedded System and Information Processing National School of Applied Sciences Mohammed First University Oujda Morocco Department of Electric Electronics and Computer Engineering University of Catania Catania Italy

ISBN: (纸本)9789811962226

Photovoltaic/thermal unit (PV/T) is an innovative technology that allows the renewable energy production by cogenerating electricity and heat simultaneously. This technology is seemed promising for the energy supply in many applications, especially for building envelope. In the present work, the performances of two different PV/T solar plants with a Roll-bond and PV/T sheet-and-tube absorbers are compared under the operating conditions of Catane, Italy. The performance assessment of theses PV/T solar plant is ensured by the dynamic modeling of two PV/T in MATLAB software. Moreover, the PV/T energy yields for suppling the energy need of a simple building are evaluated. From results, the comparison of the two PV/T systems proves that the "Roll-bond" configuration provides a higher thermal performance with a maximum fluid outlet temperature of 42.13 °C with respect to the standard one of 40 °C "Sheet-and-tube" configuration). In terms of the PV/T energy yields used for the energy supply of a standard building, it’s observed that PV/T" Roll-bond" system is very promising. It can fully cover the energy needs of the building with a total coverage factor of 76.79%. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Buildings

来源：评论

学校读者我要写书评

暂无评论

Smart Safety system for Driver and Passenger Protection

Smart Safety System for Driver and Passenger Protection

引用

Data Science, Agents & Artificial Intelligence (ICDSAAI), International Conference on

作者： Sudharsan S Rajesh S Selvam N Sangeeth Raj P S Babu Prasad R Duraimurugan A Department of Electrical and Electronics Engineering M. Kumarasamy College of Engineering Karur Department of Computer Science and Business System M. Kumarasamy College of Engineering Karur

ISBN: (数字)9798331537555

ISBN: (纸本)9798331537562

The Smart Safety system is designed to enhance road safety by monitoring both the driver and passenger activities and ensuring proactive measures are taken to prevent accidents. The system leverages sensors and real-time data monitoring to ensure driver sobriety and attentiveness while also alerting the driver about potential passenger hazards. The system primarily focuses on two areas: driver safety and passenger detection. On the driver’s side, an alcohol sensor detects any sign of intoxication, and an eye-blink sensor monitors the driver’s focus, especially if distracted by using a phone. If intoxication is detected, the vehicle is automatically disabled through the motor control system, and an alert is triggered via an alarm and notification sent to a web-based platform. If the driver is distracted or drowsy, a warning alarm is activated. On the passenger side, an IR sensor and an ultrasonic sensor detect whether passengers are improperly standing or not seated, and a notification is displayed to the driver. The system integrates an Arduino Uno with several sensors, including alcohol, eye-blink, IR, and ultrasonic sensors. The collected data is transmitted wirelessly through a Wi-Fi module to a cloud platform, such as ThingSpeak, and then displayed on a website built with Java, HTML, and JavaScript. The website provides a login interface to enroll driver information and monitor alcohol sensor readings. In case of driver intoxication, the system triggers the suspension of the vehicle by turning off the motor. This smart safety system provides an efficient, real-time mechanism for preventing road accidents by monitoring driver behavior and ensuring passenger safety.

关键词： Cloud computing Motors Sensor systems Real-time systems Road safety Safety Protection Monitoring Intelligent sensors Vehicles

来源：评论

学校读者我要写书评

暂无评论

A Smart and Privacy-Preserving Logistics system Based on IoT and Blockchain Technologies 1

A Smart and Privacy-Preserving Logistics System Based on IoT...

引用

1st International Conference in Advanced Innovation on Smart City, ICAISC 2023

作者： Balfaqih, Mohammed Balfagih, Zain Almohammedi, Akram A. Alfawaz, Khaled M. University of Jeddah Department of Computer and Network Engineering Jeddah Saudi Arabia Effat University Computer of Science Department Jeddah Saudi Arabia King Abdulaziz University Management Information System Department Jeddah Saudi Arabia Sotuh Ural State University Automobile Transportation Department Chelyabinsk Russia Karabiik University Electrical & Electronics Engineering Department Karabük Turkey

ISBN: (纸本)9781665472753

The smart city concept serves the well-being of the urban population in order to improve quality of life in different life aspects including logistic services. However, the continuous growth of logistics volume combined with information opaqueness and process complexity led to challenging issues related to managing the services and information of logistics. Hence, efficient management of logistics activities with traceability and condition monitoring capabilities is required to ensure quality and safe delivery. It is necessary also to ensure the accuracy and dependability of distribution data. In this context, this paper proposes a smart and privacy-preserving logistics system for high-price goods distribution. An intelligent parcel (iParcel) containing piezoresistive sensors is developed to pack delivered goods during shipping process for violation detection such as severe fall or theft. Moreover, smart contracts based on blockchain is also developed for automatic approval and payment with the consideration of distributing the shipping information between legitimate logistics parties only. A zero-knowledge proof is used to conceal blockchain address and prove the authentication. iParcels are automatically tracked and traced in which upon violation occurrence, the contract is cancelled, and the payment is refunded. The transaction fee per party is reasonable for high-price products in the pay of guarantee successful shipment. © 2023 IEEE.

关键词： Smart contract

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：