检索结果-内蒙古大学图书馆

Optimization of Energy and Security in Mobile Sensor Network Using Classification Based Signal processing in Heterogeneous Network

引用

JOURNAL OF SIGNAL processing SYSTEMS FOR SIGNAL image AND VIDEO TECHNOLOGY 2023年第2-3期95卷 153-160页

作者： Ramesh, S. Nirmalraj, S. Murugan, S. Manikandan, R. Al-Turjman, Fadi Vignan Fdn Sci Technol Res Dept Guntur Andhra Pradesh India Sathyabama Inst Sci & Technol Sch Elect & Elect Chennai Tamil Nadu India Sri Aravindar Engn Coll Dept CSE Sedarapet Tamil Nadu India SASTRA Deemed Univ Sch Comp Thanjavur India Near East Univ Artificial Intelligence Engn Dept Res Ctr AI & IoT Mersin 10 Ankara Turkey

The use of mobile devices has been growing rapidly and at the same time mobile applications has attained increasing popularity. Moreover, mobile services have introduced unexpected demands on the infrastructure of mobile and wireless networking. Recently, Mobile Sensor networks (MSNs) has developed a class of popular sensor network where mobility has the major responsibility in executing the application. Since the deployment of a sensor network is not completely static, the mobility factor has plenty of challenges which have to be solved including coverage, connectivity, and energy consumption. The aim of this article is to design a robust procedure to handle the challenges of mobile sensors network by providing a secure and energy-efficient communication. In this article swarms of sensors are able to move while maintaining the optimal distance among sensor *** security and energy of the signal transmission has been enhanced using multi-path link routing protocol (MLRP) and a hybrid-based TEEN (H-TEEN) protocol. Transmitted signalshave been classified via a recurrent neural networks (RNN). The simulation results show that this proposed model is able to effectively detect malicious nodes and balance the energy so that the lifespan of MSN can be prolonged.

关键词： MSNs Secure Energy-efficient MLRP H-TEEN RNN

来源：评论

学校读者我要写书评

暂无评论

Challenges in Implementing artificial Intelligence on the Raspberry Pi 4, 5 and 5 with AI HAT

Challenges in Implementing Artificial Intelligence on the Ra...

引用

2024 International Conference on Computing, Communication, Cybersecurity and AI

作者： Steadman, Phil Jenkins, Paul Rathore, Rajkumar Singh Hewage, Chaminda Cardiff Metropolitan Univ Cybersecur & Informat Networks Ctr Llandaff CampusWestern Ave Cardiff CF5 2YB Wales

ISBN: (纸本)9783031744426;9783031744433

As technology interacts with all areas of daily life, similarly the risks from cybersecurity attacks have increased proportionally. Furthermore, as the demand for computer-controlled devices and infrastructure has increased, and whilst devices have miniaturized, cybersecurity has not kept pace. Therefore, the importance ofmalware detection for smaller devices is a necessity. artificial Intelligence (AI) is improving malware detection, however, training AI models traditionally demands powerful computational resources, far more powerful than the capabilities of lightweight devices such as the Raspberry Pi. Researchers have explored alternative methodologies to adapt AI training to these constraints, given the limited performance while maintaining reliability. This paper examines the design and construction of a lightweight secure network infrastructure tailored to the Raspberry Pi's capabilities. Key considerations include network segmentation, firewall implementation, and device configurationmanagement using automation. Networking setups prioritise wired connectivity for low-latency, high-security applications, and implementing security measures such as browser proxy containers and VPN forwarding to mitigate potential threats, particularly in environments prone to malware infiltration. Training challenges on small-board computers reveal the limitations of Raspberry Pi's computational power for AI training. Comparative data identifies the delta between Raspberry Pi's and conventional computing devices, concluding the need for more powerful platforms for efficient AI training.

关键词： Raspberry Pi artificial Intelligence Convolutional neural networks. image processing Malware

来源：评论

学校读者我要写书评

暂无评论

A Rapid Recognition Method for Transformer Partial Discharge Fault Patterns Based on Improved DSCNN 24

A Rapid Recognition Method for Transformer Partial Discharge...

引用

2nd International Conference on Advances in artificial Intelligence and applications, AAIA 2024

作者： Zhou, Zhengqin Zhan, Hao Cai, Yuru Yang, Xu Zhou, Wen Liu, Mengna Wuhan NARI Limited Liability Company State Grid Electric Power Research Institute Hubei Wuhan China NARI Group Corporation State Grid Electric Power Research Institute Jiangsu Nanjing China

ISBN: (纸本)9798400712883

Pattern recognition of partial discharge (PD) is a key focus in the condition assessment of power equipment. The strong feature extraction capabilities demonstrated by deep learning in the fields of image and signal processing have made it a new trend in PD pattern recognition research. This paper proposes a method for PD pattern recognition based on an improved Deep Separable Convolutional neural Network (DSCNN). The method first introduces an improved model of the DSCNN, secondly, utilizes a PD experimental detection platform to obtain Ultra-High Frequency (UHF) signals from partial discharges, and employs the S-transform to generate the time-frequency spectrum corresponding to the time-domain signals;then, it uses the improved DSCNN model to classify the time-frequency spectrum for the identification of PD types. The results show that the PD pattern recognition model proposed in this paper has a good recognition accuracy;compared to traditional deep learning models, the optimized model proposed in this paper reduces the scale of parameters and inference time, which is conducive to improving fault diagnosis speed. © 2024 Copyright held by the owner/author(s).

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Reservoir Computing for Early Stage Alzheimer's Disease Detection

引用

IEEE ACCESS 2022年 10卷 59821-59831页

作者： Mwamsojo, Nickson Lehmann, Frederic El-Yacoubi, Mounim A. Merghem, Kamel Frignac, Yann Benkelfat, Badr-Eddine Rigaud, Anne-Sophie IP Paris Elect & Phys Dept Telecom Sudparis SAMOVAR F-91120 Palaiseau France IP Paris Telecom Sudparis SAMOVAR Commun Images & Informat Proc Dept F-91120 Palaiseau France Huawei Technol France F-92100 Boulogne France Hop Broca AP HP Grp Hosp Cochin Paris Ctr Pole Gerontol F-75013 Paris France

artificial neural networks (ANNs) have amassed unprecedented success in information processing ranging from image recognition to time series prediction. The success can largely be attributed to the availability of large datasets for training and the increased complexity of the models. Unfortunately, for some applications only a limited amount of samples is available for training. Fewer training samples increases the risk of over-fitting and poor generalization especially in high complexity models. Moreover, complex models with a large number of trainable parameters require more energy to train and optimize compared to simpler ones. In this paper, to the best of our knowledge, we propose the first use of ANNs for Early Stage Alzheimer Disease classification (ES-AD) from the handwriting (HW). We propose using a framework for building Recurrent neural networks (RNNs) known as Reservoir Computing (RC), both numerically and experimentally, that simplifies training by optimizing the output layer only. We also propose the Bidirectional Long Term Short Term (BiLSTM) and Convolutional neural Network (CNN) methods for comparison. For a fairer comparison, we not only consider the accuracies but also the energy costs incurred to obtain the respective accuracies in order to assess the accuracy-efficiency trade-off. Our numerical and experimental results show that RC yields a classification accuracy of 85%, which is 3% worse than that of BiLSTM and 2% better than that of CNN, at a relatively lower training and significantly lower inference costs. We hope that our findings highlight the importance of examining the accuracy-efficiency trade-off of various models in the community in order to reduce the overall impact of ANNs training on the environment.

关键词： Training Alzheimer's disease Task analysis Costs Reservoirs Convolutional neural networks Recurrent neural networks Alzheimer's artificial neural networks handwriting reservoir computing green AI

来源：评论

学校读者我要写书评

暂无评论

A Verilog based Approach for Object Detection using CNN 5

A Verilog based Approach for Object Detection using CNN

引用

5th IEEE Global Conference for Advancement in Technology, GCAT 2024

作者： Quadros, Samson Swaraj Adityakrishna, S. Pande, Kirti S. Amrita Vishwa Vidyapeetham Amrita School of Engineering Department of Electronics and Communication Engineering Bengaluru India

ISBN: (纸本)9798350376685

A Convolutional neural Network (CNN) are a class of artificial neural networks specifically designed to process data with a grid-like topology, such as images, making them well-suited for tasks like image recognition and classification, object detection, and speech recognition. However, their current software implementations leave much to be desired regarding energy efficiency, speed, performance and scalability. Hardware-based implementation of CNNs has several significant advantages over software, including faster data processing due to the parallel execution of hardware-based FPGAs and ASICs, which are necessary for real-time applications. They are more energy-efficient and have consistent, predictable performance. In this paper, we present the implementation of CNN on Verilog. We implemented a highly optimized CNN regression model architecture for object detection having an accuracy of 97%. The entire design was made on Verilog, allowing easy transferability to both FPGA and ASIC platforms. The proposed work is compared to the current standard for software implementations - Google Colab. The results obtained show considerable speed up and improved performance. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Echomed: A CNN-Based Approach to Endocarditis Detection and Recovery Prediction 4

Echomed: A CNN-Based Approach to Endocarditis Detection and ...

引用

4th International Conference on Ubiquitous Computing and Intelligent Information Systems, ICUIS 2024

作者： Divyarupakala, D. Vignesh, S. Selvam, M. St. Joseph's Institute of Technology Tamil Nadu Chennai600 119 India

ISBN: (数字)9798331529635

ISBN: (纸本)9798331529635

image processing has wide ranges of applications not only in disease diagnosis, especially cardiovascular disease but many more. Endocarditis is that disease pertaining to heart which requires proper method for its diagnosis so that the treatment could be effective. The present methods are time-consuming without an indication of prognosis of the recovery of the patient. EchoMed: A CNN-Based Approach to Endocarditis Detection and Recovery Prediction'. Only titled work, this comprises an innovative solution using Convolutional neural networks that can help analyze the ECHO scan images for detecting Endocarditis. The model doesn't only detect the presence but also gives the patient a chance for recovery along with proper medication based on the predictions by Decision Tree. This interaction will be a result of how by automating the diagnostic and recover recommendation process, EchoMed aims to enhance clear decision, improves the patient outcomes. This research provides the potential of artificial intelligence on revolutionizing medical diagnosis. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

artificial Intelligence and image processing applications for High-Throughput Phenotyping

Artificial Intelligence and Image Processing Applications fo...

引用

作者： Margapuri, Venkata Siva Kumar Kansas State University

学位级别：Ph.D., Doctor of Philosophy

The areas of Computer Vision and Scientific Computing have witnessed rapid growth in the last decade with the fields of industrial robotics, automotive and healthcare acting as the primary vehicles for research and advancement. However, related research in other fields, such as agriculture, remains an understudied problem. This dissertation explores the application of Computer Vision and Scientific Computing in an agricultural domain known as High-throughput Phenotyping (HTP). HTP is the assessment of complex seed traits such as growth, development, tolerance, resistance, ecology, yield, and the measurement of parameters that form more complex traits. The dissertation makes the following contributions: The first contribution is the development of algorithms to estimate morphometric traits such as length, width, area, and seed kernel count using 3-D graphics and static image processing, and the extension of existing algorithms for the same. The second contribution is the development of lightweight frameworks to aid in synthetic image dataset creation and image cropping for deep neural networks in HTP. Deep neural networks require a plethora of training data to yield results of the highest quality. However, no such training datasets are readily available for HTP research, especially on seed kernels. The proposed synthetic image generation framework helps generate a profusion of training data at will to train neural networks from a meager samples of seed kernels. Besides requiring large quantities of data, deep neural networks require the input to be a certain size. However, not all available data are in the size required by the deep neural networks. The proposed image cropper helps to resize images without resulting in any distortion, thereby, making image data fit for consumption. The third contribution is the design and analysis of supervised and self-supervised neural network architectures trained on synthetic images to perform the tasks of seed kernel classificati

关键词： artificial intelligence Computer vision High-throughput phenotyping image processing

来源：评论

学校读者我要写书评

暂无评论

IEEE Open Journal of the Solid-State Circuits Society Special Section on Custom Circuits and Architectures for Energy-Efficient Machine Learning

IEEE OPEN JOURNAL OF THE SOLID-STATE CIRCUITS SOCIETY

引用

IEEE OPEN JOURNAL OF THE SOLID-STATE CIRCUITS SOCIETY 2022年 2卷 217-218页

作者： Seo, Jae-Sun Arizona State Univ Sch Elect Comp & Energy Engn Tempe AZ 85281 USA

Machine learning (ML) and artificial intelligence (AI) have been successful in many practical applications, e.g., image/speech/video recognition, object detection/tracking, natural language processing, etc. To efficiently execute such AI/ML algorithms, there have been large advances in custom hardware accelerator designs, such as digital systolic arrays of processing engines (PEs), and analog or digital circuits for in-/near-memory computing for deep neural networks (DNNs) [1] , [2] .

关键词： Special issues and sections Machine learning artificial intelligence Object detection Speech recognition neural networks Deep learning Tracking Natural language processing Circuits

来源：评论

学校读者我要写书评

暂无评论

An Open-source Cross-Industry and Cloud-agnostic Generative AI Platform

An Open-source Cross-Industry and Cloud-agnostic Generative ...

引用

International Joint Conference on neural networks (IJCNN)

作者： Ali, Abbas Raza Kumar, Kei Siddiqui, Muhammad Ajmal Zahid, Moona Citi Innovat Lab London England Capgemini Tokyo Japan Incept Inst AI Abu Dhabi U Arab Emirates Nvidia Reading Berks England

ISBN: (纸本)9798350359329;9798350359312

Generative AI (GenAI) has recently gained immense popularity within the Machine Learning (ML) field due to its potential for enabling a wide array of applications. Businesses globally are eager to leverage this transformative technology;however, they encounter several challenges in utilizing the technology, including initial and running costs, data protection, infrastructure, adaptability across use-cases, accuracy, ethical implications, and the burgeoning carbon impact of GenAI, which act as barriers to entry. A low-cost, low-carbon impact GenAI platform that exclusively uses open-source components and smaller task-specific Large Language Models (LLMs) is necessary. This paper presents a GenAI platform that employs open-source components and models orchestrated for multiple cross-industry use-cases. The platform is designed to be cloud-provider agnostic, highly secure, scalable, and requires low infrastructure to deploy, thereby using comparatively less energy and having a lower carbon impact. These features enable several advantages, including domain transference, localization in different languages using prompt tuning, and easy deployment of complex multi-modal, cross-industry, cross-domain use-cases. We have tested our platform on numerous use-cases across several key patterns, including text-to-text, text-to-code, text-to-analytics and text-to-image. All these configurations provide a semantic interface to unstructured text, tabular data, images, videos, and speech. The platform, the methodology, and ideas presented in this paper will provide enterprises with a blueprint of how to orchestrate GenAI using open-source components. Our experience building a multi-modal open GenAI platform and our investigation and analyses of primary patterns in enterprise use-cases for GenAI suggest that the proposed low-cost, low-carbon, model-to-the-data platform has the potential to revolutionize the adoption of GenAI technologies within business enterprises. We believe that th

关键词： Generative AI Large Language Models Transformers Natural Language processing Text Generation Code Generation image Generation Low Carbon Emission

来源：评论

学校读者我要写书评

暂无评论

Effective Brain Tumor Detection using Convolutional neural networks 10

Effective Brain Tumor Detection using Convolutional Neural N...

引用

17th INDIACom;2023 10th International Conference on Computing for Sustainable Global Development, INDIACom 2023

作者： Narang, Aman Rajpoot, Aman Singh Jayaraman, Ramkumar Srm Institute of Science and Technology Department of Computing Technologies Chennai India

ISBN: (纸本)9789380544472

In the recent scenario, the move from machine learning to deep learning has played a significant role in various applications such as, healthcare, automation, robotics, etc. Considerign the healthcare, diagnosing diseases, like brain tumor, brest cancer, etc. using Magnetic Resonance Imaging (MRI) images, is a complex process because the images contain various cell/image pixel divisions to identify the condition of the disease. Based on the complexity of the disease, identifying and diagnosing the tumour becomes a challenging task as it may lead to an increase in the medical survey on tumour disease based on the number of patients. In this paper, a Deep Learning (DL) - Convolutional neural networks (CNN) based approach is proposed with the integration of data augmentation and image processing. The proposed approach provides classification of MRI images to diagnose the tumour location on the dense areas based on small tumour cells. The effectiveness of the proposed approach is analyzed based on the data accuracy as it achieves 96% with low complexity rate compared to the existing models such as, CNN and artificial neural networks (ANN) models. © 2023 Bharati Vidyapeeth, New Delhi.

关键词： Convolutional neural networks

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：