检索结果-内蒙古大学图书馆

IDSDeep-CCD: intelligent decision support system based on deep learning for concrete cracks detection

Multimedia Tools and Applications 2025年第12期84卷 10013-10026页

作者： Abualigah, Sayel M. Al-Naimi, Ahmad F. Sachdeva, Gagan AlAmri, Omran Abualigah, Laith Department of Computer Information Systems Jordan University of Science and Technology Irbid Jordan Gagan Sachdeva Dubai United Arab Emirates Hourani Center for Applied Scientific Research Al-Ahliyya Amman University Amman19328 Jordan Computer Science Department Al al-Bayt University Mafraq25113 Jordan Research Center University of Tabuk Tabuk71491 Saudi Arabia MEU Research Unit Middle East University Amman11831 Jordan Department of Electrical and Computer Engineering Lebanese American University Byblos13-5053 Lebanon School of Computer Sciences Universiti Sains Malaysia Pulau Pinang11800 Malaysia School of Engineering and Technology Sunway University Malaysia Petaling Jaya27500 Malaysia Applied Science Research Center Applied Science Private University Amman11931 Jordan College of Engineering Yuan Ze University Taoyuan32003 Taiwan

In an era where Intelligent Decision Support systems (IDSS) are integral to managing the vast data from Internet of Everything (IoE) systems, this study introduces IDSDeep-CCD, a novel IDSS approach for detecting concrete cracks, a critical issue in civil infrastructure maintenance. Traditional visual inspection methods for crack detection are time-consuming and error-prone. To address this, IDSDeep-CCD employs deep learning, utilizing an open-source dataset of concrete crack images for enhanced accuracy. The system's two-stage approach, featuring feature extraction via pre-trained models and a fully connected network for classification, significantly outperforms existing methods. Our results demonstrate a remarkable 99.9% accuracy rate in crack detection without data augmentation, marking a notable advancement in automatic detection technology. This breakthrough offers practical benefits for the industry by enabling more precise and efficient identification of concrete cracks, paving the way for timely and accurate remedial actions. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Exploiting the Potential of Self-Supervised Monocular Depth Estimation via Patch-Based Self-Distillation

引用

IEEE Internet of Things Journal 2025年第11期12卷 18042-18055页

作者： Yu, Ting Pan, Shan Chen, Wei Tian, Zijian Wang, Zehua Yu, F. Richard Leung, Victor C. M. Postdoctoral Research Station China RongTong Academy of Sciences Group Corporation Limited Beijing100022 China China RongTong Artificial Intelligence Research Center Beijing100022 China China University of Mining and Technology School of Artificial Intelligence Beijing100083 China China University of Mining and Technology School of Computer Science and Technology Xuzhou221116 China School of Artificial Intelligence Beijing100083 China The University of British Columbia Department of Electrical and Computer Engineering VancouverBCV6T 1Z4 Canada Carleton University Department of Systems and Computer Engineering OttawaONK1S 5B6 Canada Shenzhen University College of Computer Science and Software Engineering Shenzhen518060 China

Perceiving scene depth and 3D structure is one of the key tasks for Internet of Video Things (IoVT) devices to understand and interact with the environment. Self-supervised monocular depth estimation has demonstrated significant potential in leveraging large-scale unlabeled datasets to achieve competitive performance, thereby playing an increasingly important role in depth estimation. Despite recent methods providing additional supervisory signals through self-distillation strategies to improve depth estimation, an effective method for generating pseudo-depth labels suitable for addressing occlusion issues among elements far from the camera remains unexplored. To address this limitation, we propose a Patch-based Self-Distillation Learning Framework to exploit the potential of self-supervised monocular depth estimation in recovering fine-grained scene depth. In the proposed framework, elements far from the camera within the input image are enlarged by enlarging and cropping operations in the patch-based self-distillation branch. Guided by photometric consistency, the model learns the detailed occlusion relationships among elements from the enlarged patches, producing patch depth maps with fine structures. In the main branch, which takes full-scale images as input, patch depth maps serve as pseudo-depth labels through self-distillation loss to provide additional supervisory signals for regions where photometric consistency fails to offer effective supervision. This forces the depth estimation network to recover fine structures of elements far from the camera in full-scale input images. Regarding the architecture of the depth estimation network, we introduce a bin-center prediction. In this prediction, a global aggregator based on self-attention provides additional scene structure queries for adaptive scene depth discretization. Finally, to encourage the model to explore more general cues for depth inference beyond road plane cues, we propose a PatchMix data augmentati

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Improved chaotic fruit fly optimization with elman neural network based data-driven approach on product reviews classification

引用

Alexandria Engineering Journal 2025年 127卷 628-641页

作者： Alghamdi, Mohammed Al-shathry, Najla I. Said, Yahia Beyari, Hasan Sorour, Shaymaa Sattar, Khalid Nazim Abdul Alallah, Fouad Shoie Alshareef, Abdulrhman Department of Information Systems College of Computer Science King Khalid University Abha Saudi Arabia Department of Language Preparation Arabic Language Teaching Institute Princess Nourah bint Abdulrahman University P.O. Box 84428 Riyadh11671 Saudi Arabia Center for Scientific Research and Entrepreneurship Northern Border University Arar73213 Saudi Arabia Department of Administrative and Financial Sciences Applied College Umm Al-Qura University Makkah Saudi Arabia Department of Management Information Systems College of Business Administration King Faisal University Al-Ahsa31982 Saudi Arabia Department of Computer Science and Information College of Science Majmaah University Majmaah11952 Saudi Arabia Department of Information Systems Faculty of Computing and Information Technology King Abdulaziz University Jeddah Saudi Arabia

In the digital era, business platforms have considerably evolved towards online stores on the internet. Through the internet-based platform, customers can easily buy products through their smartphones and receive delivery at the place without going to the shopping mall. On the other hand, the disadvantage of these platforms is that customers need to learn about the product quality. Thus, these platform services frequently offer customer feedback to give feedback about the shipped items. Feedback is a valuable source for analyzing customer satisfaction. Customer satisfaction is effectively enhanced by performing a Sentiment Analysis (SA) of many customer ratings on E-commerce platforms. Yet, predicting the correct sentiment difference in customer feedback is challenging due to complicated logic, sequence length, and text pattern adjustments. This article focuses on designing and developing Enhanced NLP with Data-driven Product Reviews Classification using the improved chaotic fruit fly optimization (ENLPPR-ICFFO) method. The major goal of the ENLPPR-ICFFO method is to detect and classify the sentiments existing in product ratings. To accomplish this, the presented ENLPPR-ICFFO method employs data pre-processing to be consistent. Then, the Continuous Bag-of-Words (CBoW) method is utilized for the feature extraction. The extreme learning machine (ELM) method is used for the product review classification. The ENLPPR-ICFFO methodology includes an ICFFO-based hyperparameter selection technique for improving the overall product review classification technique. The empirical findings of the projected ENLPPR-ICFFO methodology are tested using a set of datasets. The performance validation of the ENLPPR-ICFFO technique portrayed superior accuracy values of 98.04 % and 96.57 % over existing methods under Amazon-Fine-Food-Reviews and Amazon-Products datasets. © 2025 The Authors

关键词： User experience

来源：评论

学校读者我要写书评

暂无评论

Traffic and Pollution Control Using IoT-Enabled Smart Routing Algorithm

Traffic and Pollution Control Using IoT-Enabled Smart Routin...

引用

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

作者： S Shahul Hammed C. Preethi K Haripriya S. Pavalarajan M.R. Gowtham N. Akshaay Krithick Department of Computer Science and Business Systems PSNA College of Engineering and Technology Dindigul India

ISBN: (数字)9798331505745

ISBN: (纸本)9798331505752

Urbanization has led to increased traffic congestion and air pollution, primarily from vehicle emissions, posing risks to public health and the environment. Existing traffic management systems are inefficient in integrating real-time pollution data, leading to reactive control measures. This project proposes an IoT-based smart traffic management system that integrates real-time air quality monitoring with dynamic traffic control. IoT sensors collect pollution and vehicle data, which is processed using cloud computing and machine learning to optimize traffic flow and reduce emissions. AI techniques provide transparency, helping city authorities understand and trust the system's decisions. The system also offers predictive analytics for proactive pollution management and a user-friendly dashboard for real-time visualization. The solution aims to reduce urban emissions, and enhance traffic efficiency, offering a sustainable approach for modern cities.

关键词： Urban areas Pollution control Machine learning Traffic control Prediction algorithms Real-time systems Internet of Things Public healthcare Vehicle dynamics Monitoring

来源：评论

学校读者我要写书评

暂无评论

IoT Based Leakage Detection and Emergency Shutdown

IoT Based Leakage Detection and Emergency Shutdown

引用

Mobile Computing and Sustainable informatics (ICMCSI), International Conference on

作者： PS. Abarna S. Padma Priya S. Pavalarajan S. Sivatharani M. Manshi Department of Computer Science and Business Systems PSNA College of Engineering and Technology Dindigul India

ISBN: (数字)9798331522667

ISBN: (纸本)9798331522674

The risk of gas leaks has grown significantly as a life threatening issue in industrial activities, cooking, and heating. This system integrates automatic reaction mechanisms, real-time monitoring capabilities, and advanced detection technologies in a multifaceted manner to address various dangers. The comprehensive gas leak detection and automatic cut off system is intended to improve safety in a variety of situations, including industrial and residential ones. To precisely identify the existence of dangerous gases like methane and propane, the proposed system combines infrared, electrochemical, and semiconductor types of gas sensors integrated with a mobile application, users may remotely administer and monitor the system in real-time. The system initiates a multi-tiered response upon detecting a gas leak; it sounds an alarm, notifies user-specified The mobile devices about the leak, and turns on an exhaust fan to release concentrated gas. A solenoid valve is used by the system to quickly shut off the gas supply and electricity from any location. The need of user-friendly controls and prompt notifications in emergency situations is highlighted in this paper's discussion of software architecture, sensor integration, and user interface design. Experimental results show that the system is reliable and capable of responding quickly under different circumstances. In future the application of machine learning algorithms for predictive maintenance and the possibility of integrating IoT to further strengthen security protocols. The results emphasize importance to deploy these kinds of extensive safety systems widely in order to reduce the risks associated with gas exposure.

关键词： Gases Fans Machine learning algorithms Valves Real-time systems Mobile handsets Security Solenoids Leak detection Gas detectors

来源：评论

学校读者我要写书评

暂无评论

Smart Sanitation Management: Integrating IoT, AI-Driven Analytics, and Automated Sensing for Efficient Public Toilet Maintenance

Smart Sanitation Management: Integrating IoT, AI-Driven Anal...

引用

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

作者： K. Haripriya C. Preethi S.Shahul Hammed S. Pavalarajan S. Akhil Sharon S. Suryakumar Department of Computer Science and Business Systems PSNA College of Engineering and Technology Dindigul India

ISBN: (数字)9798331505745

ISBN: (纸本)9798331505752

An IoT-based self-sustained public toilet maintenance system aims to improve hygiene, efficiency, and resource management. It integrates smart sensors, microcontrollers, and cloud connectivity to monitor parameters such as water levels, air quality, and toilet usage in real-time. AI-driven predictive maintenance optimizes cleaning schedules, minimizes downtime, and ensures efficient resource use. Automated water control prevents wastage, while air quality sensors detect harmful gases and activate ventilation. A smart notification system alerts municipal authorities about supply shortages, enabling timely replenishment of water, soap, and tissues. By reducing manual intervention, the system lowers operational costs and improves service quality. Cloud connectivity allows seamless data processing, offering insights for better sanitation management. The integration of IoT and AI ensures proactive maintenance responses. A comparative analysis highlights the novelty of this system in automating and optimizing maintenance.

关键词： Technological innovation Costs Water conservation Air quality Ventilation Real-time systems Maintenance Sustainable development Water resources Intelligent sensors

来源：评论

学校读者我要写书评

暂无评论

Blockchain Integration for Robust Intellectual Property Protection in New Product Development (NPD) 3

Blockchain Integration for Robust Intellectual Property Prot...

引用

3rd International Conference on Electronics and Renewable systems, ICEARS 2025

作者： Chinnasamy, P. Subashini, B. Nijanthan, Nijanthan Madasamy Raja, G. Swetha, Devulapally Sreenivasulu Reddy, L. School of Computing Kalasalingam Academy of Research and Education Department of Computer Science and Engineering Tamilnadu India School of Computing Srmist Department of Data Science and Business Systems Kattankulathur India Paavai Engineering College Tamilnadu Namakkal India Paavai Engineering College Tamilnadu Namakkal India Vaagdevi Engineering College Dept. of Computer Science and Engineering Warangal Dist. Telangana Bolli Kunta506005 India School of Advanced Sciences Kalasalingam Academy of Research and Education Department of Mathematics Tamilnadu Krishnankoil India

ISBN: (纸本)9798331509675

The rapid advancement of Blockchain technology has led to its widespread application in several domains of digital activities, such as e-government concerns and monetary security. This article presents a smart contract-based Blockchain solution for protecting intellectual property rights in new product development. The proposed solution effectively tackles the challenges associated with the confidentiality of personally identifiable information, efficiency in storing transaction-related information, as well as cooperation and monitoring in IPR. Initially, we create a mathematical model based on smart contract enabled Blockchain and intelligent contracts. Subsequently, we develop algorithms for Blockchain generation, and intelligent contracts. The system is suitable for protecting IPR in a blockchain network, by implementation of distributed identity authentication and real-time extensible storage. These features enhance the security and expandability of circuit copyright protection based on blockchain technology. The experimental results demonstrate that the suggested algorithm has decreased the cost for communication and enhanced the effectiveness of storing information and administration. Furthermore, it demonstrates resilience against many common attacks such as double-spending assaults, while maintaining low cost and overhead. Additionally, it exhibits a superior level of security in comparison to three other competing algorithms. © 2025 IEEE.

关键词： Smart contract

来源：评论

学校读者我要写书评

暂无评论

Rice Leaf Disease Detection Using Deep Learning Models: A Comprehensive Approach

Rice Leaf Disease Detection Using Deep Learning Models: A Co...

引用

Disruptive Technologies (ICDT), International Conference on

作者： Gorli Ramya Valli Kumari Vatsavayi Department Of Computer Science And Systems Engineering Andhra University College of engineering Visakhapatnam India

ISBN: (数字)9798331519582

ISBN: (纸本)9798331519599

Rice serves as a primary food source for more than half of the global population. However, a range of diseases brought on by pathogens, including as bacteria, viruses and fungus are posing a growing threat to rice agriculture. These diseases have the potential to seriously reduce crop productivity and threaten food security. Conventional disease detection techniques mostly depend on the labor-intensive, time consuming and frequently prone to human error manual inspection performed by qualified agronomists. We concentrate on two cutting edge architectures: Vision Transformers (ViT) and DenseNet169, which is well-known for its high accuracy in image classification applications and efficiency in feature reuse which make use of self-attention mechanisms to identify complex patterns in images. We developed these models to precisely categorize various rice leaf diseases, including Bacterial Leaf Blight, Brown Spot, Leaf Blast, Leaf Scald, Narrow Brown Spot, Neck Blast, Rice Hispa, Sheath Blight, Tungro, and healthy leaves. This was achieved using a comprehensive dataset containing 15,910 annotated images of rice leaves. Our proposed systems improve crop management practices by enabling prompt interventions based on precise predictions but it helps to guarantee ensuring global food security and maximizing overall crop yield. This study highlights the revolutionary potential of artificial intelligence in agriculture, paving the way for further advancements that can enhance sustainability and productivity.

关键词： Productivity computer vision Pathogens Accuracy Food security Transformers Feature extraction Agriculture Sustainable development Diseases

来源：评论

学校读者我要写书评

暂无评论

Optimizing Load and Routes in Supply Chain Management with Travelling Salesman Problem and CapsNet Attention 3

Optimizing Load and Routes in Supply Chain Management with T...

引用

3rd International Conference on Integrated Circuits and Communication systems, ICICACS 2025

作者： Rajasekar, P. Begam, M. Shabeena Chattopadhyay, Shouvik Basha, S. Chand Chandre, Shanker Dwivedi, Vijay Kumar Srm Institute of Science and Technology Department of Data Science and Business Systems Kattankulathur India Sns College of Technology Department of Mba Coimbatore India Institute of Engineering & Management Department of Mba Kolkata India University of Engineering & Management Kolkata India St Ann's College of Engineering and Technology Department of Business Administration Chirala India School of Computer Science & Artificial Intelligence Sr University Department of Computer Science & Artificial Intelligence Warangal India Vishwavidyalaya Engineering College Department of Mathematics Ambikapur India

ISBN: (纸本)9798331508456

Ever since the industrial revolution, industries have partnered to solve marketing problems and create new channels. Because they don't understand their clients' needs, sales centers often pursue conflicting aims. Lack of information has extended delivery times. Due to supply time, quality, or bulk freight depreciation agreements, facility expenses rise to satisfy demand, resulting in excess inventory. Supply chain management, particularly regional inventory management, has considerably impacted beer manufacturing profitability. The recommended method involves training the model and extracting features. Dynamic and PCA feature extraction are different. While PCA's main purpose is to dissociate correlated from uncorrelated data, dynamic PCA considers auto- and cross-correlation in time-series observations. A revised CapsNet approach trained the models. The Improved CapsNet model outperformed the Attention and baseline models in every test. The model solved brewing supply chain issues with 94.68% accuracy. The most successful advanced machine learning approaches for improving SCM include augmented CapsNet, PCA, and dynamic PCA, according to research. These techniques boost industrial profitability when applied to major issues like excess stock and supply unpredictability. The suggested strategy is more reliable and superior than present solutions, according to results. © 2025 IEEE.

关键词： Supply chain management

来源：评论

学校读者我要写书评

暂无评论

Towards Understanding the Critical Role of Human Behavior in Smart and Cognitive City Cybersecurity 16

Towards Understanding the Critical Role of Human Behavior in...

引用

16th International Conference on Ambient systems, Networks and Technologies Networks, ANT 2025 / 8th International Conference on Emerging Data and Industry 4.0, EDI40 2025

作者： Alraddadi, Rawan Alshayeb, Mohammad Mahmood, Sajjad Niazi, Mahmood Information and Computer Science Department King Fahd University of Petroleum and Minerals Dhahran Saudi Arabia College of Computer Science and Engineering Taibah University Yanbu Saudi Arabia Interdisciplinary Research Center for Intelligent Secure Systems Dhahran Saudi Arabia

The rapid development of cognitive cities, driven by IoT and AI technologies, introduces unique cybersecurity challenges aggravated by human-centric vulnerabilities. The objective of this paper is to examine the role of human factors in the cybersecurity landscape of both smart and cognitive cities. Through a literature review, we investigate how human interactions with digital infrastructures impact security and privacy. We highlight the need to address human errors, social engineering attacks, and insider threats while distinguishing how differences in infrastructure, intelligence, and citizen roles between smart and cognitive cities shape the management of human-centric vulnerabilities. Our review of existing research on integrating human behavioral data into AI systems suggests significant threat detection and response improvements. The findings suggest that human-centric AI detection tools not only mitigate risks of human errors and latent failures but also significantly improve protection for vulnerable populations, thereby promoting stronger human-AI collaboration. Ultimately, this paper advocates for advancing these tools to bolster urban cybersecurity frameworks. © 2025 The Author(s).

关键词： Cyber attacks

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：