检索结果-内蒙古大学图书馆

11th International Conference on Recent Trends in computing, ICRTC 2022

作者： Anand, Akshat Rajeswari, D. Department of Data Science and Business Systems School of Computing College of Engineering and Technology SRM Institute of Science and Technology Tamil Nadu Chennai603203 India

ISBN: (纸本)9789811988240

Communications have a crucial role in times of crisis, particularly in times of emergency. Whenever a region is affected by any disaster, social media sites such as Twitter, etc., are a great way to get information out to those who need it the most. Our paper suggests that in times of crisis, when people are worried about finding the right emergency contacts or are experiencing a transformation in their psychological response, they should manually enter their experience into an app to obtain contact information for the nearest SOS. Alternatively, the proposed application suggests scraping hashtags from around the world with web scraping scripts to retrieve geo-referenced tweets in real time. In order to gather accurate data, Twitter's API or some third-party application can be used in the development of this software. When there is a major crisis, social media user behavior plays a vital role, owing to its efficiency and high reliability with swift data dissemination. Anxiety over finding the right emergency team contact may cause people to lose their cool and become unclear about which authority they should call when an emergency occurs. Eventually, our application bridges the gap between clients in need of help and the approved agency that can really provide that support in different circumstances. In the case of, for example, a lost child or a flooded area, our application helps you get in touch with an organization that can assist you in dealing with the situation. We have used CNN-1-D + LSTM, CNN-1-D + Bi-LSTMs, and CNN-1-D + LSTM + Glove-100-D to get maximum accuracy for the classification model. It is possible to use the prototype solution in a novel way to organize immediate assistance with authorities in comprehensive administration, while integrating Twitter or other social platforms into the application can make it a feasible platform for preventive intervention and catastrophe management. © 2023, The Author(s), under exclusive license to Springer Nature

关键词： Emergency services

来源：评论

学校读者我要写书评

暂无评论

Device-Friendly Guava Fruit and Leaf Disease Detection Using Deep Learning 1st

Device-Friendly Guava Fruit and Leaf Disease Detection Using...

引用

1st International Conference on Machine Intelligence and Emerging Technologies, MIET 2022

作者： Nandi, Rabindra Nath Palash, Aminul Haque Siddique, Nazmul Zilani, Mohammed Golam BJIT Limited Dhaka Bangladesh School of Computing Engineering and Intelligent Systems Ulster University Coleraine United Kingdom Swinburne Online Australia Melbourne Australia

ISBN: (纸本)9783031346187

This research presents a machine learning model that detects plant disease from images of fruits and leaves. Five state-of-the-art machine learning models are used in this research, which achieved high accuracy in detecting plant disease. The problem with such models with high accuracy is that the models are of larger size which do not allow them to be applied to end-user devices. In this research, model quantization techniques such as float16 and dynamic range quantization are applied to the model architectures. The experimental results show that the GoogleNet model reached the size of 0.143 MB with an accuracy of 97% and the EfficientNet model reached the size of 4.2 MB with an accuracy of 99%. The source codes are available at https://***/CompostieAI/Guava-disease-detection. © 2023, ICST Institute for Computer Sciences, Social Informatics and Telecommunications engineering.

关键词： Fruits

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study of Hough Transform and PCA for Bolt Orientation Detection 22

A Comparative Study of Hough Transform and PCA for Bolt Orie...

引用

22nd IEEE International Conference on Industrial Informatics, INDIN 2024

作者： Gambale, Antonio Coleman, Sonya Kerr, Dermot Vance, Philip Kerr, Emmett Fermuller, Cornelia Aloimonos, Yiannis School of Computing Engineering & Intelligent Systems Ulster University Londonderry United Kingdom Dept. of Electronic & Mechanical Engineering Atlantic Technological University Letterkenny Ireland Institute for Advanced Computer Studies University of Maryland United States

ISBN: (纸本)9798331527471

In the fields of manufacturing and robotics, accurately determining the orientation of manufacturing components, such as bolts, is a critical yet challenging problem due to the limitations of existing detection methods. This study introduces a novel methodology for addressing this issue, leveraging traditional computer vision techniques, by proposing a streamlined approach that exploits the inherent geometric properties of bolts for orientation detection. Two methods are presented to ascertain the initial axis angle of the bolt: the Progressive Probabilistic Hough Transform (PPHT) and Principal Component Analysis (PCA). These methods are used in conjunction with a novel tip direction detection approach. The results of the study demonstrate consistent accuracy in angle determination, with PPHT and PCA both achieving angular deviations below ±0.5◦ in the simple dataset, and PCA showing enhanced robustness in the dataset degraded by shadows, with a maximum error under ±1.5◦. This research not only reaffirms the viability of fundamental computer vision techniques in modern robotic applications but also sets a precedent for simple, generalisable, and reliable orientation detection solutions. These methods effectively bridge the gap between highly specialised machine learning systems, which often require tailored, complex models and extensive training data, and more universally applicable, straightforward approaches. © 2024 IEEE.

关键词： Bolts

来源：评论

学校读者我要写书评

暂无评论

Do we need watchful eyes on our workers? Ethics of using computer vision for workplace surveillance

AI and Ethics

引用

AI and Ethics 2025年 1-21页

作者： Sebastian, Rinu Ann Ehinger, Kris Miller, Tim School of Computing and Information Systems The University of Melbourne Carlton Australia School of Electrical Engineering and Computer Science The University of Queensland St Lucia Australia

In this paper, we critically examine the relevant ethical concerns of using computer vision-based surveillance in workplaces and propose an intent—and priority-based ethical framework for such systems. With the growing capabilities of computer vision technologies, its application in monitoring workplaces brings forth significant concerns. Organisations increasingly leverage computer vision for workplace surveillance to improve productivity, safety, and security. Unlike electronic surveillance techniques that monitor workers’ wire or electronic communication, computer vision-based workplace surveillance (CVWS) captures highly detailed visual and personal information about workers, including body language, emotional state, and actions. This makes CVWS potentially more intrusive than traditional electronic surveillance, raising a more comprehensive range of ethical considerations. However, this topic has received minimal attention in the current literature. Our proposed framework combines the intention for deploying surveillance with the moral notions of privacy, data security, fairness, transparency, explainability, autonomy, beneficence, nonmaleficence, dignity, and reliability to morally scrutinise CVWS systems. The paper proposes a second framework that aims to establish accountability among key stakeholders of the CVWS system. Further, we discuss two critical questions to consider when evaluating the necessity for CVWS systems in a work environment. In practice, this work will serve as a groundwork for stakeholders such as technical developers, employers, and regulatory and advocacy teams to make ethical design decisions during the developmental, operational, and maintenance stages of CVWS systems and devise proactive strategies to minimise potential harm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Autonomous novel class discovery for vision-based recognition in non-interactive environments

引用

Cognitive Robotics 2024年第1期4卷 191-203页

作者： Zhang, Xuelin Liu, Feng Cheng, Xuelian Yan, Siyuan Liao, Zhibin Ge, Zongyuan Faculty of Information Technology Monash University 20 Exhibition Walk MelbourneVIC3168 Australia The School of Computing and Information Systems The University of Melbourne Parkville MelbourneVIC3052 Australia Faculty of Sciences Engineering and Technology The University of Adelaide North Terrace Adelaide SA5001 Australia

Visual recognition with deep learning has recently been shown to be effective in robotic vision. However, these algorithms tend to be build under fixed and structured environment, which is rarely the case in real life. When facing unknown objects, avoidance or human interactions are required, which may miss critical objects or be prohibitively costly to obtain on robots in the real world. We consider a practical problem setting that aims to allow robots to automatically discover novel classes with only labelled known class samples in hand, defined as open-set clustering (OSC). To address the OSC problem, we propose a framework combining three approaches: 1) using selfsupervised vision transformers to mitigate the discard of information needed for clustering unknown classes;2) adaptive weighting for image patches to prioritize patches with richer textures;and 3) incorporating a temperature scaling strategy to generate more separable feature embeddings for clustering. We demonstrate the efficacy of our approach in six fine-grained image datasets. © 2024 The Authors

关键词： Machine vision

来源：评论

学校读者我要写书评

暂无评论

Impact of Bushfire Growth on the Optimal Power Flow of Distributed Generation systems: Australia Case Study 5

Impact of Bushfire Growth on the Optimal Power Flow of Distr...

引用

5th International Conference on System Reliability and Safety engineering, SRSE 2023

作者： Zielke, Jordan M. Wei, Bo Mo, Huadong University of New South Wales School of Engineering and Information Technology Canberra Australia University of Sydney School of Business Sydney Australia University of New South Wales School of Systems and Computing Canberra Australia

ISBN: (纸本)9798350305944

In recent years, the threat of bushfires in Australia has evolved at an unprecedented rate. With this comes increasing concerns from authorities and operators surrounding the impact of distributed generation systems (DGS) across the country. Though studies have been conducted into the impact of bushfires in Australia and the optimal power flow (OPF) of DGS, there is a lack of research integrating these two concepts. Therefore, this work will aim to analyse the impact of bushfires on the OPF of the Greater Sydney Region's DGS. Following extensive research into both concepts, a bushfire model and an OPF model have been integrated. The integration model outputs power flow data as the Greater Sydney region's DGS is impacted by the fire. When a transmission line is cut off by fire, the unsupplied power demand must be generated and re-distributed from another bus. Inevitably, a penalty cost will be associated with this which leads to an increase in the total operational cost of the system. The results indicate that the potential penalty cost and associated operational cost increase when a transmission line is cut off by fire. An optimal strategy that aims at protecting vulnerable buses and minimizing these costs was defined. This strategy outlines the requirement to further protect Eraring, Sydney West and Sydney North as these buses are the most critical within the network due to their fuel type and role. This work defines a new strategy to help combat the impact of bushfires on one of Australia's most essential DGS and to balance the trade-off between meeting consumer's demand and minimising operational costs. © 2023 IEEE.

关键词： Electric lines

来源：评论

学校读者我要写书评

暂无评论

Feature selection using modified chaotic satin bowerbird algorithm with deep transfer learning for Multispectral Image Classification

引用

International Journal of Information Technology (Singapore) 2024年 1-13页

作者： Rajakani, M. Kavitha, R.J. Rajesh, S. Department of Data Science and Business Systems School of Computing Faculty of Engineering and Technology SRM Institute of Science and Technology SRM Nagar Kattankulathur Chennai India Department of Electronics and Communication Engineering University College of Engineering Panruti Panruti 607106 India Department of Information Technology Mepco Schlenk Engineering College Sivakasi India

Multispectral image classification has received significant attention among research communities and academicians. Recently, several artificial intelligence (AI) models can be used for the extraction of prominent features. Besides, deep learning (DL) methods become more familiar and gained interest in the remote sensing community for the classification of multispectral and hyperspectral images. With this motivation, this paper presents an optimized feature learning with deep transfer learning enabled multispectral image classification (OFLDTL-MSIC) technique. The proposed OFLDTL-MSIC technique aims to categorize the different class labels of the multispectral images. Besides, the OFLDTL-MSIC technique applies multi-level discrete wavelet transform (DWT) based image decomposition technique. Moreover, the EfficientNet technique is applied as a feature extractor to generate a collection of features. Furthermore, selecting optimal features extracted by a EfficientNet involves identifying and retaining the most relevant and informative features The improved chaotic satin bowerbird optimization (CSBO) algorithm which uses dynamic population size is proposed for feature selection and kernel extreme learning machine (KELM) model is applied for the classification process. In order to ensure the enhanced performance of the OFLTDL-MSIC technique, a wide range of simulations take place using the Madurai LISS IV multispectral images and the results are examined under several aspects. The extensive comparative study highlighted the better performance of the OFLTDL-MSIC technique over the recent methods. © Bharati Vidyapeeth's Institute of Computer Applications and Management 2024.

关键词： Deep learning Image classification Multispectral images Parameter tuning Remote sensing

来源：评论

学校读者我要写书评

暂无评论

AdaptiveFL: Adaptive Heterogeneous Federated Learning for Resource-Constrained AIoT systems 24

AdaptiveFL: Adaptive Heterogeneous Federated Learning for Re...

引用

61st ACM/IEEE Design Automation Conference, DAC 2024

作者： Jia, Chentao Hu, Ming Chen, Zekai Yang, Yanxin Xie, Xiaofei Liu, Yang Chen, Mingsong MoE Engineering Research Center of SW/HW Co-Design Tech. and App. East China Normal University China School of Computer Science and Engineering Nanyang Technological University Singapore School of Computing and Information Systems Singapore Management University Singapore

ISBN: (纸本)9798400706011

Although Federated Learning (FL) is promising to enable collaborative learning among Artificial Intelligence of Things (AIoT) devices, it suffers from the problem of low classification performance due to various heterogeneity factors (e.g., computing capacity, memory size) of devices and uncertain operating environments. To address these issues, this paper introduces an effective FL approach named AdaptiveFL based on a novel fine-grained width-wise model pruning mechanism, which can generate various heterogeneous local models for heterogeneous AIoT devices. By using our proposed reinforcement learning-based device selection strategy, AdaptiveFL can adaptively dispatch suitable heterogeneous models to corresponding AIoT devices based on their available resources for local training. Experimental results show that, compared to state-of-the-art methods, AdaptiveFL can achieve up to 8.94% inference improvements for both IID and non-IID scenarios. © 2024 Copyright is held by the owner/author(s). Publication rights licensed to ACM.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

LLM4RSR: Large Language Models as Data Correctors for Robust Sequential Recommendation 39

LLM4RSR: Large Language Models as Data Correctors for Robust...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Sun, Yatong Yang, Xiaochun Sun, Zhu Wang, Yan Wang, Bin Qu, Xinghua School of Computer Science and Engineering Northeastern University China School of Computing Macquarie University Australia Singapore University of Technology and Design Singapore National Frontiers Science Center for Industrial Intelligence and Systems Optimization China Ministry of Education China Singapore

ISBN: (纸本)157735897X

Sequential Recommenders (SRs) are trained to predict the next item as the target given its preceding items as the input, assuming every input-target pair is matched and is reliable for training. However, users can be induced by external distractions to click on items inconsistent with their true preferences, resulting in unreliable training instances with mismatched input-target pairs. To resist unreliable data, researchers attempt to develop Robust SRs (RSRs). However, our data analysis unveils that existing RSRs are data-driven. That is, for most instances formed by infrequently co-occurred items, existing RSRs are uncertain about their reliability. To fill this gap, we propose a generic framework - LLM4RSR (Large Language Models for Robust Sequential Recommendation) to semantically complement data-driven RSRs by correcting uncertain instances into reliable ones based on LLMs' semantic comprehension of items beyond co-occurrence. In this way, RSRs can be re-trained with the corrected data for better accuracy. This is a selective knowledge distillation procedure, where the LLM acts as a teacher guiding student RSRs via uncertain instances. To align LLMs with the data correction task and mitigate inherent hallucinations, we equip the LLM with profile, plan, and memory modules, which are automatically optimized via textual gradient descent, eliminating the need for human effort and expertise. Experiments on four real-world datasets spanning eight backbones verify the generality, effectiveness, and efficiency of LLM4RSR. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

State of Health Estimation of Lithium Batteries through Vision Transformer Analysis of Electrochemical Impedance Spectroscopy 51

State of Health Estimation of Lithium Batteries through Visi...

引用

51st International Conference on Computers and Industrial engineering, CIE 2024

作者： Selim, Alaa Mo, Huadong Pota, Hemanshu Li, Chaojie Liu, Xiaoyu Zhou, Jingxuan Dong, Daoyi School of Engineering and Technology University of New South Wales CanberraACT Australia School of Systems and Computing University of New South Wales CanberraACT Australia School of Electrical Engineering and Telecommunication UNSW SydneyNSW Australia Guanghua School of Management Peking university Beijing China School of Computer and Information Engineering Chuzhou university Chuzhou China CIICADA Lab School of Engineering Australian National University CanberraACT Australia

The rapid advancement and widespread deployment of energy storage systems, particularly lithium-ion batteries, underscore the necessity for precise and reliable state of health (SOH) estimation techniques. This paper develops a novel approach to battery SOH estimation by leveraging Vision Transformers (ViTs), a class of transformer models excelling in handling visual data, to analyze Electrochemical Impedance Spectroscopy (EIS) data. Unlike traditional methods that rely heavily on handcrafted features or classical impedance models, our methodology treats EIS Nyquist plots as images and utilizes ViTs for direct SOH classification. We use a comprehensive real dataset comprising thousands of Nyquist plots, labeled with their corresponding SOH and augmented through various colormap transformations to enhance ViT robustness. Our experiments demonstrate that ViTs can capture subtle, yet critical, impedance characteristics indicative of battery health, achieving superior classification accuracy compared to conventional machine learning techniques. The broader impact of this research lies in its potential to enhance the reliability and longevity of battery systems across various applications, from consumer electronics to electric vehicles and grid storage, ultimately contributing to more sustainable and efficient energy management. © 2024 Computers and Industrial engineering. All rights reserved.

关键词： Diagnosis

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：