检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Mollah, Muhammad Baqer Wang, Honggang Fang, Hua Dept. of Electrical and Computer Engineering University of Massachusetts Dartmouth MA02747 United States Dept. of Graduate Computer Science and Engineering Yeshiva University NY10016 United States Dept. of Computer and Information Science University of Massachusetts Dartmouth MA02747 United States

Beamforming techniques are considered as essential parts to compensate the severe path loss in millimeter-wave (mmWave) communications by adopting large antenna arrays and formulating narrow beams to obtain satisfactory received powers. However, performing accurate beam alignment over such narrow beams for efficient link configuration by traditional beam selection approaches, mainly relied on channel state information, typically impose significant latency and computing overheads, which is often infeasible in vehicle-to-vehicle (V2V) communications like highly dynamic scenarios. In contrast, utilizing out-of-band contextual information, such as vehicular position information, is a potential alternative to reduce such overheads. In this context, this paper presents a deep learning-based solution on utilizing the vehicular position information for predicting the optimal beams having sufficient mmWave received powers so that the best V2V line-of-sight links can be ensured proactively. After experimental evaluation of the proposed solution on real-world measured mmWave sensing and communications datasets, the results show that the solution can achieve up to 84.58% of received power of link status on average, which confirm a promising solution for beamforming in mmWave at 60 GHz enabled V2V communications. Copyright © 2024, The Authors. All rights reserved.

关键词： Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Genetic Testing of Huntington's Disease by Facial Examination of a Mankind using AI Programs 3

Genetic Testing of Huntington's Disease by Facial Examinatio...

引用

3rd International Conference on Innovations in computer science and Software engineering, ICONICS 2022

作者： Atruba Feroze, S. Faiza Nasim, S. NED University of Engineering and Technology Dept.of Computer and Information System Engineering Karachi Pakistan NED University of Engineering and Technology Dept. of Computer Science and I.T NEDUET Karachi Pakistan

ISBN: (纸本)9781665461412

This Genetic disorder is considered as one of the major challenges faced by Medical sciences as it is inherited by humans from one generation to another. With an increasing number of natives of the World at a higher rate, it causes a major impact on information society socially and economically during their lifetime. The citizens of Pakistan and Indian sub continents are facing genomic disease in probably high frequency as compared to other continents. Occurrence of congenital diseases in Pakistan results in higher percentages of unusual genetic diseases especially in children. After analyzing all the current scenarios, some goals and objectives were settled in order to facilitate and give general awareness to people. The objectives of systematic review are evaluation of diagnostic accuracy of AI for the identification of genome contributions to the pathogenesis of Huntington's disease through facial probe AI to accurately identify genetic disorders. The narrative review is performed in Ned University. In this proceeding sequence, 30 cases of both Normal and Genetically affected Patients were documented in which some certain sorts of tests were performed by using facial recognition. For this FR test, at first a combo list of information of all six emotions of a human being i.e. (Happy, Sorrow, Amazed, Fear, Anger, Revulsion) is gathered in the form of mutated images, which was then later be arranged into a pseudo-random order. Now with the help of Vision Technology we have applied some CV Techniques for the extraction of large pattern sets of features. Lastly the purpose of ML and DL techniques is to receive and compare those morphed image data from the Facial Database in order to identify each of six different emotions of HDNormal Person. This whole procedure is conducted in real time. Hence in this way we may recognize the HD genetic disorder among the people in an efficient way. The detailed procedure is explained in the Methodology section of this narrative revi

关键词： Genome

来源：评论

学校读者我要写书评

暂无评论

Multi-Access Edge Computing Using Intelligent Mobile User Resource Allocation In 6G 4

Multi-Access Edge Computing Using Intelligent Mobile User Re...

引用

4th IEEE International Maghreb Meeting of the Conference on sciences and Techniques of Automatic Control and computer engineering, MI-STA 2024

作者： Saeed, Mamoon M. Saeed, Rashid A. Mokhtar, Rania A. Gaid, AbdulGuddoos S. A. Ahmed, Zeinab E. Elbasheir, Mohammed S. Faculty of Engineering Department of Communications and Electronics Engineering Yemen Taif University Faculty of Engineering Department of Electrical and Electronic Engineering Altaif Saudi Arabia College of Computers and Information Technology Taif University Department of Computer Engineering Taif21944 Saudi Arabia Taiz University Faculty of Engineering & Information Technology Dept. of Communication & Computer Engineering Taiz Yemen International Islamic University Malaysia Department of Electrical and Computer Malaysia School of Electronic Engineering Sudan University of Science and Technology Khartoum Sudan

ISBN: (纸本)9798350372632

Edge computing plays a crucial role in the advancement of Beyond 5G (B5G) and 6G networks. The substantial growth in network traffic and computational requirements necessitates the implementation of multi-access edge computing (MEC) as a viable solution. MEC aims to bring the capabilities of cloud computing closer to end-users by integrating them into the radio access network (RAN). This research introduces an optimal approach to connect mobile users with MEC hosts and access points, effectively distributing radio and computing resources to individual mobile users. The objective is achieved by lowering the total user transmit power while abiding by latency constraints in both the communication and computation phases, using the Grey Wolf Optimization technique (GWO). A comparison to alternative smart techniques demonstrates the effectiveness of the suggested approach © 2024 IEEE.

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

Skyline Algorithm Based on QoS to Improve Web Services: A Review

Skyline Algorithm Based on QoS to Improve Web Services: A Re...

引用

engineering and Technology (PICET), Parul International Conference on

作者： Yamini Barge Tanvi Patel Lalit Purohit Dept. of Computer Science Engineering Parul University Vadodara India Dept. of Information Technology SGSITS Indore India

ISBN: (数字)9798350369748

ISBN: (纸本)9798350369755

The popularity of Web Service-based systems is due to the advantage of flexibility, reusability and support for rapid system development. Web Service selection is a very important step for these web service-based systems. The skyline technique is widely used in the past for the selection of web services. In this work, an exhaustive study of Skyline-based web service selection techniques is presented. A review of the existing state-of-the-art is presented based on the approach followed for selection of web services, the advantages of using the proposed approach, the limitations of the approach and the problem addressed.

关键词： Web services Reviews Quality of service Linear programming User experience Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

In-Field Fault Detection Framework for Edge Accelerator Using Autoencoder

In-Field Fault Detection Framework for Edge Accelerator Usin...

引用

IEEE International Test Conference on India (ITC India)

作者： R S Haripriya Jaynarayan T Tudu Dept. of Electrical Engineering Indian Institute of Technology Tirupati India Dept. of Computer Science & Engineering Indian Institute of Technology Tirupati India

ISBN: (数字)9798350352597

ISBN: (纸本)9798350352603

AI accelerators are ubiquitous across all computational domains, including safety-critical systems such as autonomous driving. However, they are also susceptible to dynamic faults due to aging-related and missed permanent manufacturing defects manifesting during in-field operation. Detecting such faults early during in-field operations is essential, particularly for the processing elements with fewer resources. The fault detection framework should operate at the level of predictions rather than individual neurons to achieve fault detection with minimal resource overhead. The output of the classifier network could have captured the fault effects as they propagate through both hardware and software architecture. In this work, we propose a methodology that uses the input image and the logits (output of the classifier network without softmax function) to predict the correctness of the prediction. The method detects the faults that significantly reduce the topl accuracy by more than 50%. This methodology necessitates one-time training of the decoder and additional computation of 1904 neurons using a 3-layer lightweight detection network during in-field operation for fault detection. However, traditional redundancy-based methods such as Dual Modular Redundancy require an additional 4950 neuron computation, equivalent to the classifier network. The proposed method results in around 61 % lesser neuron computation compared to traditional methods and a 99.99 % critical fault detection rate.

关键词： Training Software architecture Fault detection Image edge detection Neurons AI accelerators Decoding

来源：评论

学校读者我要写书评

暂无评论

Accelerating Real-Time Imaging for Radiotherapy: Leveraging Multi-GPU Training with PyTorch 22

Accelerating Real-Time Imaging for Radiotherapy: Leveraging ...

引用

22nd IEEE International Conference on Machine Learning and Applications, ICMLA 2023

作者： Obe, Ruth Kaufmann, Brandt Baird, Kaelen Kadel, Sam Soltani, Yasmin Cham, Mostafa Gobbert, Matthias K. Barajas, Carlos A. Jiang, Zhuoran Sharma, Vijay R. Ren, Lei Peterson, Stephen W. Poif, Jerimy C. U. of Houston-Clear Lake Dept. of Computer Science and of Software Engineering United States U. of San Francisco Dept. of Mathematics and Statistics United States Skidmore College Dept. of Computer Science and of Mathematics United States Mount Holyoke College Dept. of Computer Science and of Psychology United States U. of Houston Dept. of Biomedical Engineering United States U. of Maryland Dept. of Information Systems Baltimore County United States U. of Maryland Dept. of Mathematics and Statistics Baltimore County United States Medical Physics Graduate Program Duke University United States U. of Maryland School of Medicine Dept. of Radiation Oncology United States U. of Maryland School of Medicine Department of Radiation Oncology United States U. of Cape Town Dept. of Physics South Africa H3D Inc. United States

ISBN: (纸本)9798350345346

Proton beam therapy is an advanced form of cancer radiotherapy that uses high-energy proton beams to deliver precise and targeted radiation to tumors. This helps to mit-igate unnecessary radiation exposure in healthy tissues. Real-time imaging of prompt gamma rays with Compton cameras has been suggested to improve therapy efficacy. However, the camera's non-zero time resolution leads to incorrect interaction classifications and noisy images that are insufficient for accurately assessing proton delivery in patients. To address the challenges posed by the Compton camera's image quality, machine learning techniques are employed to classify and refine the generated data. These machine-learning techniques include recurrent and feedforward neural networks. A PyTorch model was designed to improve the data captured by the Compton camera. This decision was driven by PyTorch's flexibility, powerful capabilities in handling sequential data, and enhanced G PU usage. This accelerates the model's computations on large-scale radiotherapy data. Through hyperparameter tuning, the validation accuracy of our PyTorch model has been improved from an initial 7 % to over 60 %. Moreover, the PyTorch Distributed Data Parallelism strategy was used to train the RNN models on multiple G PU s, which significantly reduced the training time with a minor impact on model accuracy. © 2023 IEEE.

关键词： Clas-sification Compton camera Distributed Data Parallelism Proton beam therapy PyTorch Recurrent neural network

来源：评论

学校读者我要写书评

暂无评论

Efficient Parallel Algorithm for Detecting Longest Flow Paths in Flow Direction Grids

Efficient Parallel Algorithm for Detecting Longest Flow Path...

引用

International Symposium on Advanced Computing and Communication (ISACC)

作者： Karunamuni Jayarukshi Shivali Agarwal Girish K K Santosh Goudar Biswajit Bhowmik Dept. of Computer Science and Engineering Maharshi Sushrut CAS Lab BRICS Laboratory National Institute of Technology Karnataka Mangalore Bharat Dept. of Computer Science and Engineering Ishwarchandra Vidyasagar AIT Lab BRICS Laboratory National Institute of Technology Karnataka Mangalore Bharat Dept. of Computer Science and Engineering BRICS Laboratory National Institute of Technology Karnataka Mangalore Bharat

ISBN: (数字)9798331523893

ISBN: (纸本)9798331523909

High-performance computing (HPC) has transformed the capacity to address complex computational tasks across various scientific fields by enabling the efficient processing of large datasets and intricate simulations. In hydrological modeling, a critical task is identifying the longest flow channel within a catchment, which is essential for understanding water flow patterns and managing resources. However, existing geographic information system (GIS) algorithms for flow path identification often suffer from inefficiencies and inaccuracies. To address these challenges, this paper introduces innovative parallel methods utilizing Open Multi-Processing (OpenMP), a widely-used API that supports multi-platform shared-memory parallel programming. This approach optimizes the analysis of flow direction data, resulting in faster and more accurate identification of flow channels. The results demonstrate that the proposed method outperforms current approaches, offering substantial improvements in both performance and precision. These advancements have the potential to significantly enhance hydrological modeling practices and water resource management.

关键词： Accuracy Parallel programming Computational modeling Scalability Redundancy Computational efficiency Reliability Parallel algorithms Water resources Geographic information systems

来源：评论

学校读者我要写书评

暂无评论

Electricity Generation From Food Waste Using IOT

Electricity Generation From Food Waste Using IOT

引用

Artificial Intelligence For Internet of Things (AIIoT), International Conference on

作者： M Arunkumar S. Agalya M Bhuvanaeshwari Dept. of Information Technology IFET College of Engineering Villupuram India Dept. of Computer Science and Engineering Surya Group of Institutions Villupuram India

ISBN: (数字)9798350372120

ISBN: (纸本)9798350372137

One inventive solution is to turn food waste into power using the Internet of Things (IoT) to meet the growing need for sustainable energy sources. It turns thermal energy from trash into electricity by utilizing thermoelectric devices and the Seebeck effect. Real-time monitoring and control are made possible with IoT integration. By improving the extraction of energy from liquid or semi-solid waste, this technique reduces waste and promotes a circular energy economy. The system makes use of hardware components such as transformers and voltage regulators. The outcomes of experiments demonstrate its efficacy and possible role in renewable energy. This creative idea, which provides a sustainable route ahead for the production of power from food waste, highlights the importance of IoT in improving waste-to-energy systems.

关键词： Food waste Renewable energy sources Regulators Production Transformers Thermoelectric devices Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Enhancing Interpretability, Reliability and Trustworthiness: Applications of Explainable Artificial Intelligence in Medical Imaging, Financial Markets, and Sentiment Analysis

Enhancing Interpretability, Reliability and Trustworthiness:...

引用

International Conference on Electronics, computers and Artificial Intelligence (ECAI)

作者： Kriti Srivastava Afreen Sorathiya Jinal Mehta Vineet Chotaliya Dept. of Computer Science & Engineering (Data Science) SVKM’S Dwarkadas J Sanghvi College of Engineering Mumbai India

ISBN: (数字)9798350371154

ISBN: (纸本)9798350371161

In today’s technological era, as AI systems become more integral to critical decision-making, the importance of Explainable Artificial Intelligence (XAI) has become more pronounced. It addresses the challenge of understanding complex machine learning and deep learning models, ensuring transparency, interpretability, and accountability. This research paper provides a comprehensive analysis of XAI, focusing on its significance, methodologies, challenges, and future prospects. Theoretical foundations of XAI are elucidated, clarifying key concepts such as interpretability, transparency, and accountability. We differentiate between model-agnostic and model-specific XAI methods, outlining their strengths and limitations. A range of recent XAI techniques, including Local Interpretable Model-agnostic Explanations (LIME), SHapley Additive exPlanations (SHAP), and Gradient-weighted Class Activation Mapping (Grad-CAM), are scrutinized. Through case studies in Healthcare (Pneumonia Classification), Finance (Stock Price Prediction), and Entertainment (Sentiment Analysis), we demonstrate how XAI enhances the understandability and trustworthiness of AI systems. Additionally, a comparative study of all three methods on all three case studies has been conducted, and the results are compared. Challenges such as scalability issues and ethical considerations, including biases and fairness, are discussed. Looking ahead, we offer insights into future XAI research trajectories, aiming to foster public trust and shape a future where AI systems are both intelligent and comprehensible.

关键词： Sentiment analysis Ethics Pneumonia Explainable AI Decision making Finance Entertainment industry

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Machine-Learned Price Prediction Models for Block-Chain Technology 1

Evaluation of Machine-Learned Price Prediction Models for Bl...

引用

1st IEEE International Conference on Innovations in High Speed Communication and Signal Processing, IHCSP 2023

作者： Goel, Vikas Sharma, Ashutosh Ranjan, Raju Sharma, Amit Kumar KIET Group of Institutions Dept. of IT Ghaziabad India IMSUC-Ghaziabad Dept. of Computer Application Ghaziabad India School of Computing Science & Engineering Galgotia University Greater Noida India Dept. of CS&E Ch. Charan Singh University Campus Meerut India

ISBN: (纸本)9798350345957

As a new form of technology, blockchain has much to offer. The technology has a wide range of potential uses and advancements, depending on the field of application. However, further study is required to realise the potential of advanced technologies like Blockchain and smart contracts. There is a lot of potential for investigation because the technology is so new. This research looked at the origins of the Blockchain and analysed several different blockchain solutions. Ethereum was discovered to be the most often used platform for constructing distributed apps after being compared to other platforms. Therefore, a distributed smart energy microgrid application will be built on the Ethereum platform. There is a coin, or token, exclusive to each blockchain platform. Bitcoin's relationship to other cryptocurrencies was measured using the Karl Pearson correlation coefficient. The research concludes that ether's price is most sensitive to changes in the price of bitcoin. On a preferred Ethereum network, a distributed application for managing smart microgrids has been built. The smart contract constitutes the heart of this programme. As a result, we also take care of the smart contract's layout, coding, and optimization. In comparison to the original, less GAS is consumed by this smart contract. The entire distributed app has been built and thoroughly tested. Smart Energy Microgrid Distributed Application framework results demonstrate that the application functioned as expected. © 2023 IEEE.

关键词： Blockchain

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：