检索结果-内蒙古大学图书馆

International Artificial Intelligence and Data Processing Symposium (IDAP)

作者： Hüseyin Furkan Macan Özkan Bіngöl Salih Türk Murat Ekіncі Department of Management Information Systems Gumushane University Gümüşhane Turkey Department of Software Engineering Gumushane University Gümüşhane Turkey Department of Computer Engineering Karadeniz Technical University Trabzon Turkey

ISBN: (数字)9798331531492

ISBN: (纸本)9798331531508

The sizes of regions of interest (ROI) obtained from images captured by cameras in palmprint recognition may vary depending on the camera specifications and the position of the hand. The regions of interest that recognition systems can use are typically rescaled through interpolation techniques and then defined as inputs to the system. In such cases, there may be some loss of biometric data. This study aims to enhance the quality of the palmprint ROI images, which are critical for palmprint recognition systems. To achieve this, various super-resolution techniques were employed to reconstruct low-resolution ROI images to the target sizes while preserving the distinctiveness of their biometric features. This approach is designed to optimize recognition accuracy and improve data reliability in palmprint recognition processes.

关键词： Interpolation Image recognition Accuracy Palmprint recognition Superresolution Cameras Reliability engineering Data processing Artificial intelligence Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Impact of Extreme Class-Imbalance on Landslide-Risk Prediction and Mitigation Using Two-Stage Deep Neural Network 14

Impact of Extreme Class-Imbalance on Landslide-Risk Predicti...

引用

14th International Conference on Signal Processing Systems, ICSPS 2022

作者： Tengtrairat, N. Woo, W.L. Parathai, P. Sundaranaga, C. Na Ayutthaya, T. Kridakorn Rinchumphu, D. School of Software Engineering Payap University Chiang Mai Thailand Northumbria University Department of Computer and Information Sciences Newcastle upon Tyne United Kingdom Chiang Mai University City Research and Development Center Faculty of Engineering Chiang Mai Thailand Chiang Mai University Faculty of Engineering Department of Civil Engineering Chiang Mai Thailand

ISBN: (纸本)9798350336313

The classification of landslides is the one of the most challenging topics because of the complexity of the relationships of various dynamic and uncertain factors and the physical gaining data processes. Landslide incidents frequently occur in the upper northern region of Thailand due to its topography. The landslide classification method is proposed to capture the significant features from an extreme case of class-imbalance dataset. The imbalanced nature of some real-world data is one of the current challenges for machine learning researchers. A study area of this research covers an area of 25 square kilometers at Chiang Rai, in Thailand which contains 30,408 non-landslide data and 1,077 landslide data. The percentage of landslide data is 3.54% of the total data. This paper proposed the solution of landslide classification given by extreme class-imbalance dataset. The proposed method has two main steps i.e., firstly, mitigating class-imbalance dataset. and secondly two-stage learning. Performance of the proposed method benchmarks the baseline, the logistic regression (LR), the random forest classifier (RFC) methods given by enhanced dataset. In the case of imbalance dataset, the one-class method is assessed against the proposed method along with the LR and the RFC methods. Experimental results demonstrate that the proposed method has improved the landslide-risk prediction performance over the baseline, the LR, the RFC and the one-class SVM methods in terms of an average area under the curve scores by 0.48, 0.48, 0.03, and 0.06, respectively, in both enhanced dataset and imbalance dataset. © 2022 IEEE.

关键词： Landslides

来源：评论

学校读者我要写书评

暂无评论

Object Detection in Video by Detecting Vehicles Using Machine Learning and Deep Learning Approaches

Object Detection in Video by Detecting Vehicles Using Machin...

引用

2021 International Conference on Forthcoming Networks and Sustainability in AIoT Era, FoNeS-AIoT 2021

作者： Abdullahi Madey, Ahmed Sheikh Yahyaoui, Amani Rasheed, Jawad Istanbul Sabahattin Zaim University Department of Computer Engineering Istanbul Turkey Istanbul Sabahattin Zaim University Department of Software Engineering Istanbul Turkey

ISBN: (纸本)9781665410915

In recent, the field of object vehicles detection in video is very interested and had became applicable with methods of deep learning and machine learning. The main objective for these applications is to display the targeted object from the videos. This field still facing low detection accuracy problems. The paper goal is to develop an approach able to classify vehicles in videos by using HOG features, Linear SVM classifier as machine learning method and YOLOv3 (You Only Look Once, Version 3) algorithm as deep learning method. In the present work, we used the two famous public datasets for vehicles detection from videos, which are KITTI and GTI datasets. The result of this study addresses the problems of vehicle detection and improved the accuracy of the training. © 2021 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Beyond Data, Towards Sustainability: A Sydney Case Study on Urban Digital Twins

arXiv

引用

arXiv 2024年

作者： Sohail, Ammar Shen, Bojie Cheema, Muhammad Aamir Ali, Mohammed Eunus Ulhaq, Anwaar Babar, Muhammad Ali Qureshi, Asama Faculty of Information Technology Monash University Australia Department of Computer Science and Engineering BUET Bangladesh School of Engineering and Technology Central Queensland University Australia Centre for Research on Engineering Software Technologies University of Adelaide Australia

As urban areas grapple with unprecedented challenges stemming from population growth and climate change, the emergence of urban digital twins offers a promising solution. This paper presents a case study focusing on Sydney's urban digital twin, a virtual replica integrating diverse real-time and historical data, including weather, crime, emissions, and traffic. Through advanced visualization and data analysis techniques, the study explores some applications of this digital twin in urban sustainability, such as spatial ranking of suburbs and automatic identification of correlations between variables. Additionally, the research delves into predictive modeling, employing machine learning to forecast traffic crash risks using environmental data, showcasing the potential for proactive interventions. The contributions of this work lie in the comprehensive exploration of a city-scale digital twin for sustainable urban planning, offering a multifaceted approach to data-driven decision-making. © 2024, CC BY.

关键词： Risk analysis

来源：评论

学校读者我要写书评

暂无评论

DAPoinTr: Domain Adaptive Point Transformer for Point Cloud Completion

arXiv

引用

arXiv 2024年

作者： Li, Yinghui Zhou, Qianyu Gong, Jingyu Zhu, Ye Dazeley, Richard Zhao, Xinkui Lu, Xuequan School of Information Technology Deakin University Australia Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China School of Computer Science and Technology East China Normal University Shanghai China School of Software Technology Zhejiang University Ningbo China Department of Computer Science and Software Engineering The University of Western Australia Australia

Point Transformers (PoinTr) have shown great potential in point cloud completion recently. Nevertheless, effective domain adaptation that improves transferability toward target domains remains unexplored. In this paper, we delve into this topic and empirically discover that direct feature alignment on point Transformer’s CNN backbone only brings limited improvements since it cannot guarantee sequence-wise domain-invariant features in the Transformer. To this end, we propose a pioneering Domain Adaptive Point Transformer (DAPoinTr) framework for point cloud completion. DAPoinTr consists of three key components: Domain Query-based Feature Alignment (DQFA), Point Token-wise Feature alignment (PTFA), and Voted Prediction Consistency (VPC). In particular, DQFA is presented to narrow the global domain gaps from the sequence via the presented domain proxy and domain query at the Transformer encoder and decoder, respectively. PTFA is proposed to close the local domain shifts by aligning the tokens, i.e., point proxy and dynamic query, at the Transformer encoder and decoder, respectively. VPC is designed to consider different Transformer decoders as multiple of experts (MoE) for ensembled prediction voting and pseudo-label generation. Extensive experiments with visualization on several domain adaptation benchmarks demonstrate the effectiveness and superiority of our DAPoinTr compared with state-of-the-art methods. Code will be publicly available at: https://***/Yinghui-Li-New/DAPoinTr Copyright © 2024, The Authors. All rights reserved.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

DNN-aided Low-complexity Physical-layer Network Coding Enabled Non-orthogonal Multiple Access 19

DNN-aided Low-complexity Physical-layer Network Coding Enabl...

引用

19th IEEE Annual Consumer Communications and Networking Conference, CCNC 2022

作者： Chen, Guanyu Chan, Tse-Tin Pan, Haoyuan Liang, Jiaxin Shenzhen University College of Computer Science and Software Engineering Shenzhen China Hang Seng University of Hong Kong Department of Computing Hong Kong Hong Kong Chinese University of Hong Kong Department of Information Engineering Hong Kong Hong Kong

ISBN: (纸本)9781665431620

This paper presents a low-complexity physical-layer network coding (PNC) enabled non-orthogonal multiple access (NOMA) system with the help of deep neural networks (DNN). NOMA allows multiple users to send packets simultaneously to a common access point (AP) using the same frequency band. In PNC-enabled NOMA systems, the AP decodes not only individual packets of different users by conventional multiuser decoding (MUD) techniques, but also different linear combinations of individual packets by PNC decoding, referred to as PNC packets. Prior works showed that the decoded PNC packets could significantly improve the system throughput. However, when the number of simultaneously transmitting users increases, the number of possible PNC packets also increases exponentially, leading to high decoding complexity if the AP tries to blindly decode all possibilities. Therefore, this paper exploits DNNs to reduce the decoding complexity. Specifically, we find that the decoding results of different linear combinations are mainly affected by the relative phase offsets among the wireless signals of different users. Hence, we can use a DNN to learn the relationships between the relative phase offsets and the decoding results. Since our DNN can learn the decoding patterns, i.e., which linear combinations are more likely to be decoded given the same relative phase offsets, the AP can attempt to decode only a subset of all the linear combinations, thus reducing the decoding complexity. Experimental results show that our DNN-assisted decoding scheme reduces the decoding complexity by more than 30% compared with the traditional brute-force approach, while maintaining almost the same throughput performance. © 2022 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Effectiveness of Deep Learning Technologies to Assist Educational Inclusion for Children with Down Syndrome

Effectiveness of Deep Learning Technologies to Assist Educat...

引用

Advancements in Computing (ICAC), International Conference on

作者： Shehan Silva Anjula Jayasinghe Rishitha Dilshan Chandur Dissanayake Samitha Vidhanaarachchi Dilshan De Silva Department of Computer Science and Software Engineering Sri Lanka Institute of Information Technology Malabe Sri Lanka

Down Syndrome (DS) is a genetic disorder causing intellectual disability and developmental delays. Despite instances of discrimination, several individuals with DS have achieved success through proper education and community support. This research addresses the challenges faced by children with DS in terms of motor skill development, cognitive impairments, and speech difficulties with the use of Deep Learning Technologies such as LSTM, CNN machine learning models. To bridge the educational gap and improve speech intelligibility, this study focuses on oral motor exercises that enhance articulation skills. Cognitive development in individuals with DS is also a concern, prompting the proposal of a self-learning system to foster cognitive growth. Fine motor skills improvement is explored through yoga exercises, and interventions like interactive technologies are considered to enhance learning experiences. This paper discusses the development of a user-friendly mobile application for early intervention in DS, integrating interactive activities using advanced technologies and a parent therapy dashboard. The system's potential for improving developmental skills and future expansion is emphasized.

关键词：

来源：评论

学校读者我要写书评

暂无评论

BeSafe: Air Quality Monitoring and Control with IoT

BeSafe: Air Quality Monitoring and Control with IoT

引用

2023 International Conference on Evolutionary Algorithms and Soft Computing Techniques, EASCT 2023

作者： Arun, K.C. Azam, Sadia Siddique, Ayesha Ali, Mubashir Hussain, Aamir Asia Pacific University School of Computing Kuala Lumpur Malaysia Universita di Verona Dipartimento di Informatica San Francesco Italy University of Agriculture Department of Computer Science Faisalabad Pakistan Lahore Garrison University Department of Software Engineering Lahore Pakistan Muhammad Nawaz Shareef University of Agriculture Department of Computer Science Multan Pakistan

ISBN: (纸本)9798350313413

Air pollution is a common matter nowadays. It's defined as contamination of physical, biological, or chemical alteration in the air which results in harmful effects on living objects and makes it difficult for them to survive. The prominent cause of air pollution is the discharge of injurious gases from industrial waste and the use of fossil fuels. The effects of air pollution are very severe climate change, soil erosion, different diseases, and many more thus it's very important to take proper note of air superiority as long-term effects of air pollution can result in heart diseases, lung cancer, etc. We have devised a system to measure the contamination level of air through sensors base hardware which sends the data directly to the associated server making it easier to read even on mobile 'through a software application. The sensors would be plotted in different routes and locations i.e., industrial region, traffic zone, etc.' to investigate the pollution stages of the air making it easier for the user to take a safer route. One of the important usages of the system is to give information about the low contaminated areas near roads and industrial areas so that they can be safeguarded through certain measures. © 2023 IEEE.

关键词： Air Quality Environmental Pollution Internet of Things Quality Monitoring Sensors

来源：评论

学校读者我要写书评

暂无评论

Automated Feedback in software engineering: Enhancing Computational Thinking Process

Automated Feedback in Software Engineering: Enhancing Comput...

引用

IEEE Southeastcon

作者： Faraz Parsa Amir Ali Amiri Moghadam Turaj Ashuri Department of Computer and Software Engineering Faculty of Artificial Inteligence Karaj Azad University Karaj Iran Department of Robotics and Mechatronics Engineering Southern Polytechnic College of Engineering and Engineering Technology Kennesaw State University Marietta GA USA Southern Polytechnic College of Engineering and Engineering Technology Kennesaw State University Marietta GA USA

Computational thinking is the systematic approach of defining a problem and crafting its solution. It employs computer programming algorithms to address scientific, engineering, and mathematical challenges using programming languages. Feedback plays a pivotal role in the learning journey of computational thinking. It is widely recognized that offering timely feedback to students on their computational endeavors significantly contributes to their achievement and overall satisfaction with the course. This research explores the implementation of an automated feedback system designed to evaluate and offer early feedback on computer engineering projects. The aim is to integrate best practices and software tools related to computational thinking into the thinking and learning processes within an engineering curriculum. Preliminary findings suggest that the automated feedback system enhances students' computational skills and improves their performance in the course. We anticipate that the insights gained from this research will inform the enhancement of curricula and course evaluations across different computational thinking tasks, disciplines, and courses.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Model X-Ray: Detection of Hidden Malware in AI Model Weights using Few Shot Learning

arXiv

引用

arXiv 2024年

作者： Gilkarov, Daniel Dubin, Ran The Department of Computer Science Ariel Cyber Innovation Center Ariel University Ariel Israel The Department of Computer and Software Engineering Ariel Cyber Innovation Center Ariel University Ariel Israel

The potential for exploitation of AI models has increased due to the rapid advancement of Artificial Intelligence (AI) and the widespread use of platforms like Model Zoo for sharing AI models. Attackers can embed malware within AI models through steganographic techniques, taking advantage of the substantial size of these models to conceal malicious data and use it for nefarious purposes, e.g. Remote Code Execution. Ensuring the security of AI models is a burgeoning area of research essential for safeguarding the multitude of organizations and users relying on AI technologies. This study leverages well-studied image few-shot learning techniques by transferring the AI models to the image field using a novel image representation. Applying few-shot learning in this field enables us to create practical models, a feat that previous works lack. Our method addresses critical limitations in state-of-the-art detection techniques that hinder their practicality. This approach reduces the required training dataset size from 40000 models to just 6. Furthermore, our methods consistently detect delicate attacks of up to 25% embedding rate and even up to 6% in some cases, while previous works were only shown to be effective for a 100%-50% embedding rate. We employ a strict evaluation strategy to ensure the trained models are generic concerning various factors. In addition, we show that our trained models successfully detect novel spread-spectrum steganography attacks, demonstrating the models' impressive robustness just by learning one type of attack. We open-source our code to support reproducibility and enhance the research in this new field. © 2024, CC BY-NC-ND.

关键词： Zero-shot learning

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：