检索结果-内蒙古大学图书馆

Multi-Scale Time Series Segmentation Network Based on Eddy Current Testing for Detecting Surface Metal Defects

IEEE/CAA Journal of Automatica Sinica 2025年第3期12卷 528-538页

作者： Xiaorui Li Xiaojuan Ban Haoran Qiao Zhaolin Yuan Hong-Ning Dai Chao Yao Yu Guo Mohammad S.Obaidat George Q.Huang the School of Intelligence Science and Technology University of Science and Technology Beijing the Beijing Advanced Innovation Center for Materials Genome Engineering the Key Laboratory of Intelligent Bionic Unmanned Systems and the Institute of Materials Intelligent Technology Liaoning Academy of Materials IEEE the Department of Computer Science Hong Kong Baptist University the School of Computer and Communication Engineering Key Laboratory of Advanced Materials and Devices for Post-Moore Chips Ministry of Education University of Science and Technology Beijing the Beijing Advanced Innovation Center for Materials Genome Engineering University of Science and Technology Beijing the School of Computer and Communication Engineering University of Science and Technology Beijing the King Abdullah Ⅱ School of Information Technology The University of Jordan the Department of Computational Intelligence the School of Computing SRM University the School of Engineering The Amity University The Hong Kong Polytechnic University

In high-risk industrial environments like nuclear power plants, precise defect identification and localization are essential for maintaining production stability and safety. However, the complexity of such a harsh environment leads to significant variations in the shape and size of the defects. To address this challenge, we propose the multivariate time series segmentation network(MSSN), which adopts a multiscale convolutional network with multi-stage and depth-separable convolutions for efficient feature extraction through variable-length templates. To tackle the classification difficulty caused by structural signal variance, MSSN employs logarithmic normalization to adjust instance distributions. Furthermore, it integrates classification with smoothing loss functions to accurately identify defect segments amid similar structural and defect signal subsequences. Our algorithm evaluated on both the Mackey-Glass dataset and industrial dataset achieves over 95% localization and demonstrates the capture capability on the synthetic dataset. In a nuclear plant's heat transfer tube dataset, it captures 90% of defect instances with75% middle localization F1 score.

关键词： Eddy current testing nondestructive testing semantic segmentation time series analysis

来源：评论

学校读者我要写书评

暂无评论

Exploring Data Mining Techniques for Early Autism Detection using Random Forest Algorithm 15

Exploring Data Mining Techniques for Early Autism Detection ...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Ayyadurai, M. Sujatha, K. Deeptha, R. Preethi, D. Dinesh, M. Department of Computer Science and Engineering Rajalakshmi Engineering College Chennai India Department of Computer Science and Engineering SRM Institute of Science and Technology Ramapuram Chennai India Department of Information Technology SRM Institute of Science and Technology Ramapuram Chennai India Saveetha University Chennai India

ISBN: (纸本)9798350370249

Autism, a neurological disorder, manifests uniquely in areas such as verbal and nonverbal communication, social interactions, behavioral adaptability, and specific interests. The results collected indicate that health professionals should receive more training in areas like psychology and developmental disorders and be able to detect Autism Spectrum Disorder (ASD) at a much earlier stage. They also provide pertinent information for reflection on the methods currently employed in evaluating children's development and diagnosing ASD. This study collects information from a specific set of children with autism spectrum disorder from kaggle and is based on real, up-to-date facts. The input and output dataset will have certain common characteristics that will determine whether or not a child currently has ASD or has any signs of the same shortly. Random Forests, also known as Random Decision Forests, is a widely used ensemble learning method for tasks like classification and regression. This technique operates by constructing numerous decision trees during the training process. This classification is used to classify the dataset collected, into categories and hence segregate the children examined as "with" and "without" ASD with high accuracy about 88%. ©2024 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Experimental investigation of performance, emissions, combustion characteristics, cyclic variations, and exergy efficiency of CI engine fueled with Karanja-camphor oil blends and diesel-camphor oil blends

引用

Environmental science and Pollution Research 2024年 1-19页

作者： Gurusamy, Manikandaraja Subramaniyan, Malarmannan Ponnusamy, Chandrasekaran Department of Mechanical Engineering Faculty of Engineering and Technology SRM Institute of Science and Technology Tamil Nadu Kattankulathur Chennai603203 India

This article compares the influence of blending the low-viscous oxygenated camphor oil with hydrocarbon diesel fuel and high-viscous oxygenated Karanja oil. The experiment is conducted in a four-stroke one-cylinder naturally aspirated Kirloskar compression ignition (CI) engine coupled with an eddy current dynamometer. The three types of fuel blends are prepared by blending the camphor oil with Karanja oil on the volume ratio of 30:70 (C30K70), 50:50 (C50K50), and 70:30 (C70K30), and the other three types of fuels are prepared by blending the camphor oil with diesel on the volume ratio of 30:70 (C30D70), 50:50 (C50D50), and 70:30 (C70D30). The experimental efficiency results show higher thermal efficiency of 31.86% and 30.84% for C70D30 and C70K30 at rated operating conditions. The brake-specific energy consumptions of C70D30 and C70K30 were found to be 11.29 and 11.67 MJ/kWh, respectively, at rated operating conditions. The lowest CO, CO2, HC, and smoke emissions are found for C70D30 at rated operating conditions, which are 96.58%, 6.15%, 34.20%, and 7.59% lower than diesel. However, the NO emissions were found to be 27.62% higher for C70D30 than diesel at full load. The rate of pressure rise, net heat release rate, and cyclic variations were found to increase with increase in proportion of the camphor oil. The P–v diagram also confirms the lower heat addition period for the C70D30 and C70K30 with an increase in brake thermal efficiency. The actual compression ratio and the actual cutoff ratio are found to have a reasonable correlation with the thermal efficiency of the engine. The exergy efficiency of C30K70 is found higher which is 2.11% higher than diesel fuel at rated power. Second-order polynomial equations were obtained for the engine characteristics using the curve fitting method, and the characteristic equations confirmed the confidence level of 95%. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Curve fitting

来源：评论

学校读者我要写书评

暂无评论

Tracking Individual in Kedarnath Trek Using LoRaWAN technology 3rd

Tracking Individual in Kedarnath Trek Using LoRaWAN Technolo...

引用

3rd International Conference on Emerging Trends in Expert Applications and Security, ICE-TEAS 2024

作者： Kumawat, Pushpak Newatia, Tanmay Tiwari, Sankalp Rai, Adarsh Parwekar, Pritee Department of Computer Science and Engineering SRM Institute of Science and Technology Delhi-Meerut Road Ghaziabad India

ISBN: (纸本)9789819739905

In remote trekking regions such as the Kedarnath trail, ensuring the safety and security of individuals remains a paramount concern due to the lack of reliable network connectivity and Internet services. Casualties and incidents of individuals losing connection with their groups often pose significant challenges for authorities in locating and providing assistance promptly. To address this issue, this research proposes the implementation of a Long-Range Wireless Local Area Network (LoRa WAN) system for tracking individuals during the Kedarnath trek (Mo et al., Proceedings of the 2020 15th IEEE conference on industrial electronics and applications (ICIEA), IEEE, 2020). By leveraging the long-range communication capabilities of LoRa technology, this system aims to establish a robust network infrastructure capable of tracking individuals and facilitating communication among trekking groups even in areas with minimal network coverage (Dragoni et al., Ad Hoc Netw, 56:122–140, 2016). Through the integration of GPS tracking devices and LoRa transceivers, real-time location data can be transmitted securely to a centralized monitoring system, enabling authorities to efficiently respond to emergencies and incidents. This paper outlines the technical design and implementation of the proposed LoRa WLAN system, discusses its potential benefits in enhancing safety and security during trekking expeditions, and presents a framework for future research and development in this domain (Abdelmaksoud et al., Proced Comput Sci 162:256–265, 2019). © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Industrial electronics

来源：评论

学校读者我要写书评

暂无评论

Detecting the symptoms of COVID-19 during pandemic environment using smart spectacle thermal images and deep capsule networks

引用

Multimedia Tools and Applications 2025年第8期84卷 4475-4501页

作者： Dwarakanath, B. Pandimurugan, V. Mohandas, R. Sambath, M. Baiju, B.V. Chinnasamy, A. SRM Institute of Science and Technology Ramapuram Chennai India Networking and Communications School of Computing SRMIST kattankulathur Chennai India Computational Intelligence School of Computing SRMIST kattankulathur Chennai India Computer Science and Engineering Hindustan Institute of Technology and Science Chennai India School of Computer Science and Engineering Vellore Institute of Technology Vellore India Department of Data Science and Business Systems School of Computing SRMIST kattankulathur Chennai India

The pandemic creates a more complicated providence of medical assistance and diagnosis procedures. In the world, Covid-19, Severe Acute Respiratory Syndrome Coronavirus-2 (SARS Cov-2), and plague are widely known pandemic disease desperations. Due to the recent COVID-19 pandemic tragedies, various medical diagnosis models and intelligent computing solutions are proposed for medical applications. In this era of computer-based medical environment, conventional clinical solutions are surpassed by many Machine Learning and Deep Learning-based COVID-19 diagnosis models. Anyhow, many existing models are developing lab-based diagnosis environments. Notably, the Gated Recurrent Unit-based Respiratory Data Analysis (GRU-RE), Intelligent Unmanned Aerial Vehicle-based Covid Data Analysis (Thermal Images) (I-UVAC), and Convolutional Neural Network-based computer Tomography Image Analysis (CNN-CT) are enriched with lightweight image data analysis techniques for obtaining mass pandemic data at real-time conditions. However, the existing models directly deal with bulk images (thermal data and respiratory data) to diagnose the symptoms of COVID-19. Against these works, the proposed spectacle thermal image data analysis model creates an easy and effective way of disease diagnosis deployment strategies. Particularly, the mass detection of disease symptoms needs a more lightweight equipment setup. In this proposed model, each patient's thermal data is collected via the spectacles of medical staff, and the data are analyzed with the help of a complex set of capsule network functions. Comparatively, the conventional capsule network functions are enriched in this proposed model using adequate sampling and data reduction solutions. In this way, the proposed model works effectively for mass thermal data diagnosis applications. In the experimental platform, the proposed and existing models are analyzed in various dimensions (metrics). The comparative results obtained in the experiments just

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Approaches for Disease Detection Based on Plant Leaf Image: A Review 23th

Deep Learning Approaches for Disease Detection Based on Plan...

引用

23rd International Conference on Intelligent Systems Design and Applications, ISDA 2023

作者： Saraswathi, E. Banu, J. Faritha Department of Computer Science and Engineering SRM Institute of Science and Technology Ramapuram Bharathi Salai Tamilnadu Chennai India Faculty of Engineering and Technology SRM Institute of Science and Technology Ramapuram Bharathi Salai Tamilnadu Chennai India

ISBN: (纸本)9783031648359

The demand for rapid and precise plant disease diagnostics has increased with interest in environmentally friendly farming techniques. Deep learning algorithms are employed in image analysis has shown significant promise for the quick and precise detection of plant diseases. Early detection of diseases in plant is crucial. Yet conventional approaches have their limits, as is discussed at the article’s outset. This review article of the relevant literature sums up the state of the art in identifying plant disease and different deep learning methods, such as convolutional neural networks, recurrent neural networks, and generative adversarial networks, which have been applied to the problem of plant disease identification. Several datasets that have been used to train and evaluate deep learning models for identifying plant diseases are also discussed in the paper. Finally, this study wraps up with a discussion of the problems and future possibilities in this subject, including the need to create more reliable and interpretable models depend on deep learning and the integration of several detection paradigms for more precise disease identification. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Hybrid Xception-ResNext BiLSTM Model with Attention and Visual Synchronization for Robust Deepfake Detection

Hybrid Xception-ResNext BiLSTM Model with Attention and Visu...

引用

2024 International Conference on System, Computation, Automation and Networking, ICSCAN 2024

作者： Suresh, M. Raghavan, J.Vijaya Roy, Abhisek Das, Swet Snigdha Srm Institute of Science and Technology Department of Computing Technologies Chennai India Manakula Vinayagar Institute of Technology Department of Electrical and Electronics Engineering Pondicherry India Computer Science Engineering Srm Institute of Science and Technology Chennai India

ISBN: (纸本)9798331510022

Deepfake technology has become a significant problem since it allows for the creationof compelling manipulated videos. This research presents a novel hybrid deepfake detection system that combines the Xception and ResNext networks with a Bidirectional Long Short-Term Memory (BiLSTM) model and Convolutional Block Attention Module (CBAM). Apart from focusing on the temporal and spatial anomalies of deepfakes, our model also includes visual synchronization analysis and physiological signal detection. Extensive experiments are conducted across several datasets, exhibiting cutting-edge performance across various manipulation scenarios. The proposed method achieves good generalization, as they are in real-world circumstances. © 2024 IEEE.

关键词： Gallium nitride

来源：评论

学校读者我要写书评

暂无评论

Work-Integrated Learning: Elevating Educational Outcomes and Career Prospects in Higher Education 13

Work-Integrated Learning: Elevating Educational Outcomes and...

引用

13th IEEE International Conference on Teaching, Assessment and Learning for engineering, TALE 2024

作者： Kiruthika, Usha Kanaga Suba, Raja S. Valusa, Bhavani National Institute of Technology Tiruchirappalli Department of Computer Science and Engineering Tamil Nadu India Srm Institute of Science and Technology Tiruchirappalli Department of Computer Science and Engineering Tamil Nadu India

ISBN: (纸本)9798350376234

Work-integrated learning (WIL) combines academic learning with practical work experiences, helping students transition smoothly from theory to real-world application. This paper explores the effectiveness of WIL programs in enhancing employability, fostering industry-ready skills, and promoting a holistic educational experience. This paper focuses on analyzing the statistical outcomes of WIL and how it can be improved in universities. It highlights the challenges, such as misalignment between academic curricula and industry needs, while proposing strategies for overcoming these barriers. Some of the case studies of WIL implementations show how various methodologies can guide universities in effectively incorporating work-integrated learning into their curricula. Through the analysis of prior studies and statistical data, this research aims to identify the best practices and key factors that contribute to the successful implementation of WIL. Ultimately, this study aims to contribute to the development of more effective, responsive, and impactful educational frameworks that better prepare students for their professional futures. © 2024 IEEE.

关键词： apprenticeships co-ops curriculum externships virtual internships work integrated learning

来源：评论

学校读者我要写书评

暂无评论

Demand Forecasting in Supply Chain Management using CNN-LSTM Hybrid Model 14

Demand Forecasting in Supply Chain Management using CNN-LSTM...

引用

14th International Conference on Computing Communication and Networking Technologies, ICCCNT 2023

作者： Naveen Parthasarathy, M.K. Rastogi, Shrey Alice, K. SRM Institute of Science and Technology Computer Science & Engineering Chennai India SRM Institute of Science and Technology Computing Technologies Chennai India

ISBN: (纸本)9798350335095

Efficient supply chain management is necessary to meet customer demands. Demand forecasting is a predictive analysis that estimates how much of a product or service a customer will need in the future. Accurate demand forecasting relies on past sales data and statistical estimates from test markets. Deep neural networks have gained popularity as a demand forecasting technique in supply chain management because of their high level of accuracy. The objective of this study is to use Long Short-Term Memory (LSTM) neural networks with hyperparameter tuning, as well as a hybrid model comprising Long Short-Term Memory and 1D Convolutional Neural Networks (CNNs), to predict the demand for eight medicinal drugs. The results obtained from the hybrid model will be compared with the LSTM models to select the best model for long-term forecasting. Demand forecasting has several applications, including inventory control, production planning, and market entry decisions © 2023 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Cyber-Attack Defense System Enhanced by Artificial Intelligence

Cyber-Attack Defense System Enhanced by Artificial Intellige...

引用

2024 International Conference on Intelligent Systems for Cybersecurity, ISCS 2024

作者： Rangrez, Usman Showkat Qadri, Syed Absar Ashok Kumar, C. Jothi Kumar, C. SRM Institute of Science and Technology Kattankulathur Computer Science and Engineering Tamil Nadu Chennai India SRM Institute of Science and Technology Kattankulathur Computing Technologies Tamil Nadu Chennai India

ISBN: (纸本)9798350375237

In today's rapidly evolving digital landscape, ensuring the security of computer systems and networks is of utmost importance. With the widespread use of internet access, the escalation of cyberattacks and infiltration attempts poses significant threats to both data integrity and user privacy. Addressing these challenges, the integration of AI-Powered Cyber Security Defender Systems has become an essential component within contemporary cybersecurity frameworks. This research delves into the realm of these advanced systems, exploring their development, classification, methodologies, challenges, and future prospects. The study commences by examining key milestones that have shaped the modern architectures of AI-Powered Cyber Security Defender Systems throughout their historical evolution. It provides a comprehensive classification of these systems, elucidating their operations and advantages. Leveraging artificial intelligence and machine learning, these systems have the capability to analyze large datasets, identify patterns, and respond to malicious activities within networks, significantly enhancing overall security. The research paper underscores the pivotal role played by AI-Powered Cyber Security Defender Systems in safeguarding digital assets and user information. In conclusion, the study offers valuable insights for cybersecurity experts, researchers, and policymakers, thoroughly addressing the development, methodologies, challenges, and future trends of these systems, advocating for a proactive approach to securing the digital sphere. © 2024 IEEE.

关键词： Cybersecurity

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：