检索结果-内蒙古大学图书馆

Intelligent and Innovative Technologies in Computing, Electrical and Electronics (IITCEE), International Conference

作者： Vedavyasa Kamath Ciji Pearl Kurian Shailesh K. R Suprabha Padiyar U Mangalam Sontakke Dept. of Electrical and Electronics Engg. Manipal Institute of Technology Manipal Academy of Higher Education Manipal Karnataka India Dept. of Data Science and Computer Applications Manipal Institute of Technology Manipal Academy of Higher Education Manipal Karnataka India

In recent years, photography-based photometry has gained popularity and is being implemented widely. Under this approach, a camera is used as a sensor to estimate photometric quantities like illuminance or luminance. The absolute distance between the target surface and the camera can be crucial for photometric analysis. The technique proposed in this article employs a fixed focal length lens mounted on a DSLR camera. The standardised classic ColorChecker chart is placed over the target surface, and the scene image with the chart is captured. The intuition is that the average pixel area of the swatches present on the chart decreases as the camera is moved away from the chart. OpenCV libraries are used to calculate the average pixel area of the chart color swatches. Distance is measured using an industry-standard laser-based distance measurement tool. Curve fitting is used to establish a mathematical relationship between camera-chart distance and the average pixel area of the swatches. Distance varies from 650 cm to 2 m during the data collection process. The influence of the tilt of the chart plane with respect to the camera sensor plane is also studied. During testing, the proposed power trendline-based mathematical model performed with an error percentage of less than 1. This approach for distance measurement enables finer tuning of the machine learning-based model and, as a result, more accurate illuminance estimation for the work plane.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SETA: Semantic-Aware Token Augmentation for Domain Generalization

arXiv

引用

arXiv 2024年

作者： Guo, Jintao Qi, Lei Shi, Yinghuan Gao, Yang The National Key Laboratory for Novel Software Technology The National Institute of Healthcare Data Science Nanjing University Nanjing210023 China The School of Computer Science and Engineering Southeast University Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications Ministry of Education Nanjing211189 China

Domain generalization (DG) aims to enhance the model robustness against domain shifts without accessing target domains. A prevalent category of methods for DG is data augmentation, which focuses on generating virtual samples to simulate domain shifts. However, existing augmentation techniques in DG are mainly tailored for convolutional neural networks (CNNs), with limited exploration in token-based architectures, i.e., vision transformer (ViT) and multi-layer perceptrons (MLP) models. In this paper, we study the impact of prior CNN-based augmentation methods on token-based models, revealing their performance is suboptimal due to the lack of incentivizing the model to learn holistic shape information. To tackle the issue, we propose the Semantic-aware Edge-guided Token Augmentation (SETA) method. SETA transforms token features by perturbing local edge cues while preserving global shape features, thereby enhancing the model learning of shape information. To further enhance the generalization ability of the model, we introduce two stylized variants of our method combined with two state-of-the-art (SOTA) style augmentation methods in DG. We provide a theoretical insight into our method, demonstrating its effectiveness in reducing the generalization risk bound. Comprehensive experiments on five benchmarks prove that our method achieves SOTA performances across various ViT and MLP architectures. Our code is available at https://***/lingeringlight/SETA. Copyright © 2024, The Authors. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

dataset Preprocessing Leveraging Vision Language Models: Storytelling for Accident Detection and Description

Dataset Preprocessing Leveraging Vision Language Models: Sto...

引用

Electrical Engineering (ICEENG), International Conference on

作者： Mohamed Yossri Elwaly Amgad Abdo Aly Ahmed Sewelam Sarah Elshamy Asmaa Zayed Mohamed Elsayed Mohamed Abdou Mohamed Saleh Faculty of Computers and Data Science Alexandria University Alexandria Egypt Dept. of Electrical Engineering Phaors Uniersity in Alexndria Alexandria Egypt Faculty of Computer Science and Engineering Alamein International University (AIU) Alamein Egypt Informatics Research Institute City of Scientific Research and Technological Applications (SRTA-City) Alexandria Egypt

ISBN: (数字)9798331519018

ISBN: (纸本)9798331519025

In recent years, the Vision-Language Models (VLMs) have significantly advanced the field of storytelling applications. Visual storytelling involves the use of Generative AI models to transform a sequence of video frames into a semantics-preserving story-like text. A critical aspect of developing these models lies in the preparation of datasets, which directly impacts their efficacy and robustness. This paper explores a comprehensive methodology for dataset preparation tailored to the detection and description of car accidents in video surveillance footage. This research explains the necessity of data collection, annotation, and preprocessing to transform a sequence of frames in a video into a semantics-preserving story-like text. We describe the steps, tools and challenges of this task.

关键词： Electrical engineering Generative AI Visual analytics Scalability Semantics Transforms Video surveillance Robustness Automobiles Accidents

来源：评论

学校读者我要写书评

暂无评论

Quantitative Analysis of IITs’ Research Growth and SDG Contributions

arXiv

引用

arXiv 2024年

作者： Sharma, Kiran Nagori, Akshat Manya Dubey, Mehul Khurana, Parul School of Engineering & Technology BML Munjal University Haryana Gurugram122413 India Center for Advanced Data and Computational Science BML Munjal University Haryana Gurugram122413 India School of Computer Applications Lovely Professional University Punjab Phagwara144411 India

The Indian Institutes of Technology (IITs) are vital to India’s research ecosystem, advancing technology and engineering for industrial and societal benefits. This study reviews the research performance of top IITs—Bombay, Delhi, Madras, Kharagpur, and Kanpur based on Scopus-indexed publications (1952–2024). Research output has grown exponentially, supported by increased funding and collaborations. IIT-Kanpur excels in research impact, while IIT-Bombay and IIT-Madras are highly productive but show slightly lower per-paper impact. Internationally, IITs collaborate robustly with the USA, Germany, and the UK, alongside Asian nations like Japan and South Korea, with IIT-Madras leading inter-IIT partnerships. Research priorities align with SDG 3 (Health), SDG 7 (Clean Energy), and SDG 11 (Sustainable Cities). Despite strengths in fields like energy, fluid dynamics, and materials science, challenges persist, including limited collaboration with newer IITs and gaps in emerging fields. Strengthening specialization and partnerships is crucial for addressing global challenges and advancing sustainable development. © 2024, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optimizing Blockchain Mining Decisions Using Deep Reinforcement Learning Algorithms

Optimizing Blockchain Mining Decisions Using Deep Reinforcem...

引用

Machine Learning and Autonomous Systems (ICMLAS), International Conference on

作者： Anne Sreyas Venkatesam Karnati Shainy Reddy Shanmugasundaram Hariharan Bibhuti Bhsan Dash Subrata Chowdhury Sudhansu Shekhar Patra Department of Artificial Intelligence and Data Science Vardhaman College of Engineering Hyderabad India School of Computer Applications Kalinga Institute of Industrial Technology (KIIT) Deemed to be University Bhubaneswar Odisha India Department of CSE Sreenivasa Institute of Technology and Management Studies Chittoor Anthra Pradesh India

ISBN: (数字)9798331505745

ISBN: (纸本)9798331505752

Blockchain technology is a distributed database that records the transactions across a network of computers. Blockchain technology ensures security and transparency of the data. Blockchain mining refers to the process of verifying the transactions in a blockchain network. However, blockchain mining consumes high energy and solving complex mathematical problems and puzzles. We this study addressed these challenges of blockchain mining using Reinforcement Learning (RL). We have developed a custom environment, BlockchainMiningEnv using openAIGym framework. This environment specifies key factors of blockchain mining like difficulty level and energy cost. These are used to create a realistic model for training an intelligent agent. The agent is trained with algorithms like proximal policy optimizing (PPO) Soft Actor-Critic (SAC) and Advantage Actor-Critic(A2C) to learn how to deal with these computational resources. The main aim of the agent is to maximize rewards by increasing mining efficiency and minimizing the energy consumption. In this paper we have combined blockchain technology with Reinforcement Learning (RL) to improve efficiency and sustainability of blockchain mining by maintaining the security and transparency of the data.

关键词： Training Scalability Reinforcement learning Robustness Mathematical models Blockchains data mining Security Sustainable development Tuning

来源：评论

学校读者我要写书评

暂无评论

A comparative Analysis of ensemble methods and their efficiency in the classification of ‘HIT AND RUN’ cases in an imbalanced dataset (Traffic Crashes) with and without using "Synthetic minority oversampling technique"

A comparative Analysis of ensemble methods and their efficie...

引用

International Conference on computer Theory and applications (ICCTA)

作者： Manjula Shenoy K R Srinivas Prabhu Information and Communication Technology Department Manipal Institute of Technology Manipal Academy of Higher Education Manipal India Data Science and Computer Applications Department Manipal Institute of Technology Manipal Academy of Higher Education Manipal India

ISBN: (数字)9798350309584

ISBN: (纸本)9798350309591

In some cases of developing a predictive model for a classification problem, the distribution of classes is skewed, meaning a majority of the training samples belong to a single class and a very small number of samples belong to a minority class. If Machine Learning techniques are applied directly to such data sets, it may result in a model which either ignores the minority class as a whole or gives less importance to the samples belonging to the minority class. Such datasets are often called imbalanced datasets. There are multiple ways to deal with these problems some include Random Over Sampling, Random Under Sampling, Threshold value tuning, one class classification to find the outlier, etc. One such technique is called the "Synthetic minority oversampling technique (SMOTE)". In this paper we are going to analyze the efficiency of ensemble methods for the classification of imbalanced datasets with and without using SMOTE. The dataset used for this purpose is an open-source Traffic crashes dataset available on the Chicago data portal. The target variable for our study is the "HIT_AND_RUN_I" column available in the dataset. This is a dichotomous variable that has 2 valid values. "Y" for the cases that are of positive outcomes as in "HIT_AND_RUN_I" = yes. "N" for the cases that are of negative outcomes as in "HIT_AND_RUN_I" = No.

关键词： Training Predictive models computer crashes data models Ensemble learning Tuning Portals

来源：评论

学校读者我要写书评

暂无评论

ECG signals-based security and steganography approaches in WBANs: A comprehensive survey and taxonomy

引用

Sustainable Computing: Informatics and Systems 2024年 41卷

作者： Masdari, Mohammad Band, Shahab S. Qasem, Sultan Noman Sayed, Biju Theruvil Pai, Hao-Ting Department of Computer Engineering Urmia Branch Islamic Azad University Urmia Iran Future Technology Research Center National Yunlin University of Science and Technology Douliu Taiwan Department of Information Management International Graduate School of Artificial Intelligence National Yunlin University of Science and Technology Taiwan Riyadh11432 Saudi Arabia Computer Science Department Faculty of Applied Science Taiz University Taiz6803 Yemen Department of Computer Science Dhofar University PO Box 2509 SalalahPCode 211 Oman Bachelor Program of Big Data Applications in Business National Pingtung University Pingtung Taiwan

Wireless Body Area Networks (WBANs) are integral components of e-healthcare systems, responsible for monitoring patients' physiological states through intelligent implantable or wearable sensor nodes. These nodes collect medical data, which is then transmitted to remote healthcare facilities for thorough evaluation. Securing medical data within WBANs is paramount due to its central role in preserving patient privacy and confidentiality. Notably, Electrocardiogram (ECG) signals have recently gained prominence as pivotal elements within diverse security frameworks. Incorporating ECG signals strategically enhances the security and reliability of WBANs and broader e-healthcare systems, instilling greater trustworthiness. This survey article provides an in-depth exploration of contemporary ECG-based security schemes, adding to the scholarly discourse. The imperative to categorize these security paradigms revolves around their use of ECG signals. This categorization identifies three key domains: the first involves schemes that utilize ECG signals for cryptographic operations, encompassing key generation, agreement, management, and authentication. The second category employs steganography-based techniques, using ECG signals to conceal patients' sensitive medical data. The third category focuses on enhancing ECG signal security during data transmission. Each category is meticulously elaborated, detailing architectural foundations, notable contributions, and intrinsic security services. Furthermore, each section presents a comprehensive overview of the attributes characterizing ECG-based security frameworks. This includes insights into employed datasets, simulation environments, evaluation metrics, and inherent advantages and limitations. Expanding on this, a thorough analysis of distinctive attributes underpinning these security frameworks concludes by shedding light on potential directions for future research. © 2023 Elsevier Inc.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Accessible Authentication Using Keyword Search through Homomorphic Encryption 1

Accessible Authentication Using Keyword Search through Homom...

引用

1st IEEE International Interdisciplinary Humanitarian Conference for Sustainability, IIHC 2022

作者： Vekariya, Vipul Manjunath, R. Gill, Jasmeen Gopianand, M. Kumar, Avneesh Jha, Amaresh Parul University Department of CSE PIET Gujarat Vadodara India Department of Data Science & Mathamatics Bangalore India RIMT University Department of CSE Godindgarh Mandi India PSNA College of Engineering and Technology Department of Computer Applications Dindigul India Galgotias University Department of Computer Application Uttar Pradesh Greater Noida India School of Modern Media UPES Dehradun India

ISBN: (纸本)9781665456876

data storage presents substantial issues due to concerns about data security and privacy. In this study, we provide a search-based, interoperable, verified public key cryptography system. The searchability is significantly improved by our recommended method, which allows the cloud servers to create invert crypto indexes while needing a query trap and leveraging asymmetric cryptography developed by van Vries, Miller, Showing different, and Vaikuntanathan. Contrarily, the recommended method offers a brand-new permitted dataset built on the inversion decryption scheme and shows how it may be used to evaluate the thoroughness and correctness of serps. Additionally, using the provided method, many users may do encrypted searches on cryptography. Finally, it is shown that the offered technique is secure utilizing the approximate-GCD problem. The experiment's results showed that the proposed technique had less computational complexity than the methods currently in use. © 2022 IEEE.

关键词： Public key cryptography

来源：评论

学校读者我要写书评

暂无评论

Corrigendum to "Early Parkinson's disease diagnosis using Transition Propagation Graph Neutral Network with Dynamic Hunting Leadership Optimization" [Biomed. Signal Proc. Contr. 101(25):107196/ 10.1016/***.2024.107196](S1746809424012540)(10.1016/***.2024.107196)

引用

Biomedical Signal Processing and Control 2025年 106卷

作者： Subasree, S. Priya, S. Brindha, S. Sakthivel, N.K. Sri Shakthi Institute of Engineering and Technology Tamil Nadu Coimbatore India Department of Computer Science and Engineering Nehru Institute of Engineering and Technology Tamil Nadu Coimbatore India Department of Computer Science and Applications St.Peter's Institute of Higher Education and Research Avadi Tamil Nadu Chennai India Department of Artificial Intelligence and Data Science Sri Shakthi Institute of Engineering and Technology Tamil Nadu Coimbatore India

I hope this message finds you well. I am writing to request an urgent correction to the affiliation and email ID associated with my article published in your journal on November 23, 2024. This update is crucial for the accurate representation of my contact information and for the acceptance of the paper by my university. If my affiliation is not updated, they won't allow me to sit for the exam. Kindly consider my situation and help me. Please update the Affiliation and Mail Id as follows: First Author: Dr. S. Subasree Dean (Academics), Department of computer science and Engineering (Cyber Security), Sri Shakthi Institute of Engineering and Technology, Coimbatore, Tamil Nadu, India 4th & Corresponding Author: Dr. N. K. Sakthivel Principal Department of Artificial Intelligence and data science, Sri Shakthi Institute of Engineering and Technology, Coimbatore, Tamil Nadu, India nksakthivel@*** I kindly request that the necessary changes be made as soon as possible. Thank you very much for your prompt attention to this matter. © 2025

关键词：

来源：评论

学校读者我要写书评

暂无评论

Simulating Physical Climate Models Using Temporal Transformers and Spatial data as Computational Shortcuts

Simulating Physical Climate Models Using Temporal Transforme...

引用

International Conference on Distance Learning and Education (ICDLE)

作者： Zhijing Wu Jingbo He Jingtong Zhang Wenyi Pan Jinan University-University of Birmingham Joint Institute Jinan University Guangzhou Guangdong China Data Science and Applications Institute Inner Mongolia University of Technology Hohhot Inner Mongolia China NUIST Waterford Institute Nanjing University of Information Science and Technology Nanjing Jiangsu China School of Computer Science and Technology Huazhong University of Science and Technology Wuhan Hubei China

ISBN: (数字)9798350391121

ISBN: (纸本)9798350391138

This paper presents a transformer-based deep learning model to simulate physical climate models. To address its complexity and statical, we propose a novel approach which combines spatial features extracted from satellite remote sensing images and climate time series data as a more accurate reflection of real-world dynamics. Our model extracts spatial features for each timestamp, generates embedding layers for each spatial feature vector, and consolidates these embedding vectors into the encoding layer of the Transformer. The self-attention mechanism is also applied to the decoding layer with the mask attention removed, which aims to reduce the model complexity. Compared to other time series models, our work achieves better performance in simulating physical climate models. This model features an image input to image output design, aiming to assist non-expert researchers in climate rapidly predicting future climate conditions. Our work shows the potential of applying deep learning to simplify physical models in the field of climate, thereby opening up new possibilities for satellite remote sensing image research and forecasting related climate conditions.

关键词： Deep learning Satellites Computational modeling Time series analysis Transformers Feature extraction data models Complexity theory Remote sensing Meteorology

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：