检索结果-内蒙古大学图书馆

2024 International Conference on Computing and Intelligent Reality Technologies, ICCIRT 2024

作者： Kowshik, S.B. Nair, Samhitha Kiruthika, S. Joshan Athanesious, J. Sch. of Electronics Engineering VIT Chennai India Sch. of Computer Science and Engineering VIT Chennai India

ISBN: (纸本)9798331510299

StockAI is a stock market analysis tool that integrates machine learning, traditional trading indicators, and intelligent agents to analyze live data and projections for stock investors. It does this by carrying out an analysis of the historical price trend of a stock and the ongoing stock markets from the use of mathematical indicators such as moving averages, relative strength index, and candlestick patterns. As a result, it aids in decision-making for both new and old traders. The system also leverages machine learning algorithms like random forests to generate price predictions with improved accuracy. StockAI's interactive interface allows users to engage with the tool through natural language queries. However, challenges remain in evaluating the outputs of large language models, as current methods rely heavily on human evaluation. The ultimate goal of StockAI is to help investors make informed decisions, optimize market opportunities and mitigate risks through a combination of AI-driven analysis and traditional financial indicators. © 2024 IEEE.

关键词： Marketplaces

来源：评论

学校读者我要写书评

暂无评论

Satellite Imagery Analysis Using Image Registration and Edge Detection 8

Satellite Imagery Analysis Using Image Registration and Edge...

引用

8th IEEE International Conference on Information and Communication Technology, CICT 2024

作者： Kiruthika, S. Athanesious, J. Joshan Kanna, Lakshmi Dathatreya Sch. of Computer Science and Engineering Vellore Institute of Technology Chennai India

ISBN: (纸本)9798331531539

In this research we evaluated multiple feature-based image registration techniques by leveraging keypoint detectors to extract robust and distinctive key points for matching across images. Various detectors and descriptors, including those used in the ratio test, FLANN parameters for approximate nearest neighbor searches, and the BF Matcher for brute-force matching, were employed to extract keypoints, which were then used to search for suitable matches. Various techniques, including warp Affine, estimateAffinePartial2D, and homography, were employed to estimate transformations. We have done a comparative analysis in which we used different combination of feature-based image registration algorithms and edge detection algorithms for the purpose of image alignment and boundary extraction. Subsequently, a performance assessment was performed by comparing the registered images with ground truth using Structural Similarity Index Measure (SSIM), Precision, Recall, Mean Square Error (MSE) and F1-Score metrics. Among the evaluated models, the BRISK model with the Canny edge detection algorithm consistently demonstrated superior performance, achieving the highest Precision (0.973), Recall (0.984), F1-Score (0.918), SSIM (0.0427), and the lowest MSE (0.0427) scores. These findings emphasize the efficacy of the BRISK model in image alignment tasks. © 2024 IEEE.

关键词： Satellite imagery

来源：评论

学校读者我要写书评

暂无评论

Hyperparameter Tunning in Simulation-based Optimization for Adaptive Digital-Twin Abstraction Control of Smart Manufacturing System 22

Hyperparameter Tunning in Simulation-based Optimization for ...

引用

2022 ACM SIGSIM International Conference on Principles of Advanced Discrete Simulation, SIGSIM PADS 2022

作者： Seok, Moon Gi Tan, Wen Jun Su, Boyi Cai, Wentong Nanyang Technological University Sch. of Computer Science and Engineering Singapore Singapore

ISBN: (纸本)9781450392617

Smart manufacturing utilizes digital twins (DTs) that are virtual forms of their production plants for optimizing decisions. Discrete-event models (DEMs) are frequently used to model the production dynamics of the plants. To accelerate the performance of the discrete-event simulations (DES), adaptive abstraction-level conversion (AAC) approaches were proposed to change specific subcomponents of the DEM with corresponding abstracted queuing models during the runtime based on the steady-state of the DEMs. However, the speedup and accuracy loss of the AAC-based simulations (ABS) are highly influenced by user-specified significance level α (degree of tolerance of statistical invariance between two samples) and the stability of the DEMs. In this paper, we proposed a simulation-based optimization (SBO) that optimizes the problem based on genetic algorithm (GA) while tuning the hyperparameter (α) during runtime to maximize the speedup of ABS under a specified accuracy constraint. For each population, the proposed method distributes the computing budget between the α exploration and fitness evaluation. A discrete-gradient-based method is proposed to estimate each individual's initial α (close to the final optimum) using previous exploration results of neighboring individuals so that the closeness can reduce the iterative α exploration as GA converges. We also proposed a clean-up method that removes inferior results to improve the α estimation. The proposed method was applied to optimize raw-material releases of a large-scale manufacturing system to prove the concept and evaluate the performance under various situations. © 2022 ACM.

关键词： Abstraction-level conversion hyperparameter tuning simulation-based optimization genetic algorithm discrete-event models manufacturing systems

来源：评论

学校读者我要写书评

暂无评论

Enhancing Energy Efficiency: Statistical Analysis of RRAM Operations using ZnO-based Approach

Enhancing Energy Efficiency: Statistical Analysis of RRAM Op...

引用

2023 IEEE International Conference on Sensors and Nanotechnology, SENNANO 2023

作者： Bature, Usman Isyaku Mohd Nawi, Illani Md Khir, Mohd Haris Ba Hashwan, Saeed S. Zahoor, Furqan Rahman, Mohammad Obaidur Universiti Teknologi Petronas Electrical and Electronic Engineering Seri Iskandar Malaysia Nanyang Technological University Sch. of Computer Science and Engineering 639798 Singapore

ISBN: (纸本)9798350333312

RRAM has garnered significant attention from various perspectives;however, certain barriers hinder its widespread adoption. These challenges revolve around reliability and power operation, making their resolution crucial. This work highlights the effects of operating at high voltages (>10V), which also affect other memory technologies, including Flash memory. The study introduces an insightful approach involving voltage flow analysis coupled with exploring the fundamental thermal energy flow in ZnO-based RRAM stacks operating within 1.2V. The model adopts a two-dimensional arrangement in COMSOL Multiphysics and further employs MATLAB (LiveLinkTM). The research delves into the dynamic resistance switching process, elucidating the role of joule heating effects, field-driven ion transport, and the temperature influence when the operating voltage exceeds 1.2V, as depicted in various plots. This investigation advances our comprehension of the complex dynamics involved in RRAM operation and demonstrates methods to enhance device performance, improve reliability, and ensure long-term functionality in practical applications. © 2023 IEEE.

关键词： Zinc oxide

来源：评论

学校读者我要写书评

暂无评论

StockAI - Stock Analysis Tool Agent

StockAI - Stock Analysis Tool Agent

引用

Computing and Intelligent Reality Technologies (ICCIRT), International Conference on

作者： S B Kowshik Samhitha Nair S Kiruthika J. Joshan Athanesious Sch. of Electronics Engineering VIT Chennai India Sch. of Computer Science and Engineering VIT Chennai India

ISBN: (数字)9798331510299

ISBN: (纸本)9798331510305

StockAI is a stock market analysis tool that integrates machine learning, traditional trading indicators, and intelligent agents to analyze live data and projections for stock investors. It does this by carrying out an analysis of the historical price trend of a stock and the ongoing stock markets from the use of mathematical indicators such as moving averages, relative strength index, and candlestick patterns. As a result, it aids in decision-making for both new and old traders. The system also leverages machine learning algorithms like random forests to generate price predictions with improved accuracy. StockAI’s interactive interface allows users to engage with the tool through natural language queries. However, challenges remain in evaluating the outputs of large language models, as current methods rely heavily on human evaluation. The ultimate goal of StockAI is to help investors make informed decisions, optimize market opportunities and mitigate risks through a combination of AI-driven analysis and traditional financial indicators.

关键词： Measurement Sentiment analysis Accuracy Large language models Natural languages Real-time systems Intelligent agents Stock markets Standards Random forests

来源：评论

学校读者我要写书评

暂无评论

Link Quality-Aware Geographic Predictive Routing for V2V Network Based on GPSR

Link Quality-Aware Geographic Predictive Routing for V2V Net...

引用

2023 International Technical Conference on Circuits/Systems, computers, and Communications, ITC-CSCC 2023

作者： Harayama, Michiko Mishioka, Masahiro Gifu University Faculty of Engineering Dept. Electrical Electronic and Computer Engineering Japan Grad. Sch. Natural Science and Technology Gifu University Dept. Intelligence Science and Engineering Japan

ISBN: (纸本)9798350326413

In recent years, advances in automotive IoT technology have not only improved automated driving and driving convenience but have also led to a diminishing number of traffic accidents. Vehicle Ad-hoc Networks (VANETs) have attracted much attention because automotive IoT is based on wireless communications. Ad-hoc routing protocols that apply the characteristics of vehicle-to-vehicle (V2V) networks are needed. One of them is Greedy Perimeter Stateless Forwarding (GPSR), a routing protocol using geographic information. It uses Global Positioning System (GPS) information for routing. However, GPSR may increase the packet drop rate due to radio attenuation and fading. Therefore, C. Li et al. proposed to select the next hop by evaluating the link quality. However, due to the large moving speed of the node, the next hop may be out of the radio propagation range at the communication timing. Therefore, in this study, we propose a new routing method that combines the future location prediction proposed by Z.S. Houssaini et al. The effectiveness of the method is demonstrated by simulations using ns-3 with traffic data acquired by SUMO. © 2023 IEEE.

关键词： Routing protocols

来源：评论

学校读者我要写书评

暂无评论

Satellite Imagery Analysis Using Image Registration and Edge Detection

Satellite Imagery Analysis Using Image Registration and Edge...

引用

Conference on Information and Communication Technology (CICT)

作者： S Kiruthika. J. Joshan Athanesious Lakshmi Dathatreya Kanna Sch. of Computer Science and Engineering Vellore Institute of Technology Chennai India

ISBN: (数字)9798331531539

ISBN: (纸本)9798331531546

关键词： Image registration Image edge detection Measurement uncertainty Detectors Mean square error methods Nearest neighbor methods Feature extraction Satellite images Sensors Information and communication technology

来源：评论

学校读者我要写书评

暂无评论

Differentiate Music Genre from an Audio File Using CNN

Differentiate Music Genre from an Audio File Using CNN

引用

2023 International Conference on System, Computation, Automation and Networking, ICSCAN 2023

作者： Raja Rajeswari, S. Dhanalakshmi, R. School of Computer Science and Engineering Vellore Institute of Technology Chennai600127 India Ctr. for Cyber Phys. Syst. Sch. of Comp. Science and Engineering Vellore Institute of Technology Chennai600127 India

ISBN: (纸本)9798350315127

The complexity of music production has gradually decreased recently, causing a big number of individuals to produce music as a result and submitting it to streaming media. Because there are so many music streaming services, people are putting in a lot of effort looking for certain songs. The result says, it's critical to be able to swiftly classify musical genres in today's culture. As deep learning and machine learning technologies progress, Convolutional Neural Networks (CNN) are indeed being applied in a number of disciplines, and new CNN-based versions have appeared one after the other. Manually extracting features from time-series data is required for traditional music genre classification. Applying deep learning to time-series data has proven to be useful and efficient. To save time for the user when looking for different styles of genres. Librosa is used to convert into a corresponding Mel spectrum. Converted Mel send to a CNN model for training. © 2023 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

InvMetrics: Measuring Privacy Risks for Split Model-Based Customer Behavior Analysis

引用

IEEE Transactions on Consumer Electronics 2024年第1期70卷 4168-4177页

作者： Deng, Ruijun Hu, Shijing Lin, Junxiong Yang, Jirui Lu, Zhihui Wu, Jie Huang, Shih-Chia Duan, Qiang Fudan University Sch. of Comp. Science and the Engineering Research Center of Cyber Security Auditing and Monitoring Ministry of Education Shanghai200433 China Fudan University School of Computer Science Shanghai200433 China Shanghai Blockchain Engineering Research Center Shanghai200433 China National Taipei University of Technology Department of Electronic Engineering Taipei City10608 Taiwan Pennsylvania State University Information Sciences and Technology Department AbingtonPA19001 United States

Mobile Edge Computing (MEC) has great potential to facilitate cheap and fast customer behavior analysis (CBA). Model splitting, widely adopted in collaborative learning of MEC, partitions the CBA models between the customer device and the edge server in a layer-wise manner to support efficient distributed learning. However, the split-model architecture (SMA) is vulnerable to data reconstruction attacks for privacy leakage in intermediate data, of which the risk measurements remain unexplored. In this paper, we propose a privacy risk measurement framework, called InvMetrics, for split model-based CBA systems, which assess the degree of privacy leakage from both the CBA owners' and the regulators' perspectives. For CBA owners, we propose a privacy metric, Distance Loss (DLoss), based on distance correlation, which is computationally efficient, and thus eligible for being deployed on the customers' devices. For third-party evaluators, we propose Uncertainty Loss (ULoss) based on entropy, which can measure privacy risk without accessing raw data. Evaluation results on three CBA datasets and one image dataset demonstrate that InvMetrics framework with DLoss and ULoss can accurately measure privacy risk and is more efficient than the state-of-the-art. © 1975-2011 IEEE.

关键词： Data privacy

来源：评论

学校读者我要写书评

暂无评论

Performance Assessment of an Extremely Energy-Efficient Binary Neural Network Using Adiabatic Superconductor Devices 5

Performance Assessment of an Extremely Energy-Efficient Bina...

引用

5th IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2023

作者： Chen, Olivia Li, Zhengang Yamauchi, Tomoharu Wang, Yanzhi Yoshikawa, Nobuyuki Tokyo City University Dept. Computer Science Tokyo Japan Northeasetern University Dept. Electrical and Computer Engineering Boston United States Tokyo City University Grad. Sch. Informative Engineering Tokyo Japan Yokohama National University Dept. Electrical and Computer Engineering Yokohama Japan

ISBN: (纸本)9798350332674

Binary Neural Networks (BNNs) are gaining popularity for solving real-world problems using Deep Neural Networks (DNNs), such as image recognition and natural language processing. BNNs use binary precision for weights and activations, reducing memory usage by 32 times compared to conventional networks using 32-bit floating-point precision. Among various types of BNNs, AQFP-based BNNs utilizing superconducting logic families are promising for energy-efficient computing, using magnetic flux quantization and quantum interference in Josephson-junction-based superconductor loops. This paper presents a performance assessment of a novel AQFP-based BNN architecture, highlighting scalability issues caused by increased inductance in the analog accumulation circuit. We also discuss potential optimization approaches to address these issues and improve scalability. © 2023 IEEE.

关键词： Image recognition

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：