检索结果-内蒙古大学图书馆

Public Decision-Making Analysis in Urban Heat Islands Based on Socioeconomic Modelling by Deep Learning Techniques

Remote Sensing in Earth Systems sciences 2024年第1期8卷 108-117页

作者： Prakash, S. Wilson Kiruthigha, R. Yadav, Ajay Kumar Kanna, S. K. Rajesh Shaik, Khasimbee Krishna, B. Murali Department of Data Science and Business Systems SRM Institute of Science and Technology Chennai Kattankulathur India Department of Information Technology SRM Institute of Science and Technology Chennai Ramapuram India Department of Computer Application United Institute of Management UP Prayagraj 211010 India Department of Mechanical Engineering Rajalakshmi Institute of Technology Chennai India Department of Computer Science and Engineering Aditya University Andhra Pradesh Surampalem India Department of Computer Science and Engineering MLR Institute of Technology Hyderabad India

Urban heat island (UHI) effects, especially in highly urbanised areas, and greenhouse gas emissions from human activity are two elements that accelerate global climate change (GCC). Sustainable city planning and modification may benefit from the quantification of the surface UHI (SUHI) effect utilising land surface temperature (LST), local climate zones (LCZ), and deep learning methods like convolutional neural networks (CNN) and pix2pix. The findings show that socioeconomic variables account for 12–20% of variability in UHI intensity. In general, the contribution rate of urban economic scale is higher than that of population and industrial structure variables. The increase in urban economic expansion increased summertime heat discomfort. This research propose novel method in socioeconomic analysis based on urban heat pattern analysis with public healthcare system using decision-making with DL (deep learning) model. Input is collected as urban heat pattern dataset and processed for noise removal and normalisation. This data has been features are extracted and classified using convolutional fuzzy Q-Gaussian neural network and variational K-C-means regressive learning. The simulation analysis has been carried out based on training accuracy, average precision, recall, and F-measure. The proposed model attained average precision was 94%, recall was 90%, training accuracy was 97%, and F1-score was 92%. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.

关键词： Decision-making Deep learning model Public healthcare system Socioeconomic analysis Urban heat pattern

来源：评论

学校读者我要写书评

暂无评论

Multiple Disease Prediction from Retinal Images Using Deep Learning Algorithm

Multiple Disease Prediction from Retinal Images Using Deep L...

引用

2025 International Conference on Pervasive Computational Technologies, ICPCT 2025

作者： Rishikesh, B. Karthikayani, K. Srm Institute of Science and Technology Department of Computer Science and Engineering Vadapalani Campus Tamilnadu Chennai26 India

ISBN: (纸本)9798331508685

Retinal imaging serves as an essential tool for the early identification and diagnosis of numerous systemic diseases. This model framework is used for predicting multiple diseases simultaneously using retinal images. The implementation begins with the collection of annotated retinal images, enabling the identification of ailments as glaucoma, age-related macular degeneration, diabetic retinopathy, including hypertensive retinopathy. Preprocessing techniques are applied to enhance data quality and reduce noise. Feature extraction is conducted using the pretrained VGG16 convolutional neural network (CNNis essential for deep learning model training. Multi-label categorization and multi-task learning are employed to predict multiple diseases concurrently. Strict measures, including as accuracy, sensitivity, specificity, including the area under the receiver operating characteristic curve (AUC-ROC), are used to assess the system's performance. Clinical validation also evaluates its efficacy in practical settings. The incorporation of this predictive system into clinical workflows is facilitated by ensuring regulatory compliance and seamless communication with healthcare professionals. Experimental Results show that the suggested VGG16-based system accomplishes an impressive 98.7% accuracy in detecting multiple retinal diseases. The implementation underscores the transformative potential of leveraging advanced deep learning techniques in ophthalmology. Future efforts are focused on enhancing algorithm performance through larger datasets and refining models to further improve diagnostic precision, enabling timely and effective treatment strategies for retinal conditions. © 2025 IEEE.

关键词： Ophthalmology

来源：评论

学校读者我要写书评

暂无评论

Agri-Ontology: A Novel Ontology Framework for Agricultural Domain 3

Agri-Ontology: A Novel Ontology Framework for Agricultural D...

引用

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

作者： Deepa, R. Jayaraman, Venkatesh Srinivasulu, Senduru Umamageswari, B. Surendran, R. Srm Institute of Science & Technology School of Computing Department of Computing Technologies Kattankulathur Tamilnadu Chennai603203 India Chennai Institute of Technology Department of Computer Science and Engineering Chennai600069 India Sathyabama Institute of Science and Technology School of Computing Department of Computer Science and Engineering Chennai600119 India Srm Institute of Science & Technology School of Computing Department of Computing Technologies Chennai600119 India Saveetha Institute of Medical and Technical Sciences Saveetha School of Engineering Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798331509675

The agricultural information system deals with massive amounts of data from heterogeneous sources. It helps the farmers gain accurate information by providing better insights. A significant issue in agricultural data is its unstructured form, which can be resolved through ontology - a novel framework known as AgriOntology is proposed to address this issue for the Agrovoc dataset. The data in the unstructured form is initially pre-processed through the Natural Language Processing approach to generate features for ontology construction. The BERT and Jaccard similarity are applied to establish a relationship between the features used to construct the Agri-Ontology. Post ontology construction, the BiGAN framework is used to analyze the performance. The performance of the constructed ontology is observed to have an accuracy of 94.64%, which is higher than the existing models. © 2025 IEEE.

关键词： Data assimilation

来源：评论

学校读者我要写书评

暂无评论

SMART AGRICULTURE: INTEGRATING AIR QUALITY MONITORING WITH DEEP LEARNING FOR PROCESS OPTIMIZATION*

引用

Scalable Computing 2025年第3期26卷 1005-1016页

作者： Shobana, J. Subramanian, A Venkata Balamurugan, P. Perumal, Sivakumar Sankari, V. Eldho, K.J. Nareshkumar, R. Department of Data Science and Business Systems School of Computing College of Engineering and Technology SRM Institute of Science and Technology Tamilnadu Kattankulathur India Department of Computer Science and Engineering GITAM University Bengaluru India Department of Computer Science and Engineering J N N Institute of Enginering India Saveetha university Chennai India Department of Computer Science and Engineering Sasi Institute of Technology and Engineering Andhra Pradesh Tadepalligudem India Department of Artificial Intelligence and Data Science K.Ramakrishnan College of Engineering Kariyamanickam Rd Tamil Nadu Samayapuram India PG and Research Department of Computer Science Mary Matha Arts and Science College Kerala Mananthavady India Department of Networking and Communications School of Computing College of Engineering and Technology SRM Institute of Science and Technology Tamilnadu Kattankulathur India

Modernization and intense industrialization have led to a substantial improvement in people’s quality of life. However, the aspiration for achieving an improved quality of life results in environmental contamination. A primary consequence of environmental degradation is air pollution, resulting from rising levels of poisonous chemicals in the atmosphere, which may induce detrimental health conditions in humans. It is harmful to both humans and agriculture. Given that the effects of air pollution on plants may not be readily apparent, it is important to analyse the necessary data and compute the outcomes. Farmers prioritise on pests and plant diseases, frequently neglecting the detrimental impacts of air pollution. Some plant species can withstand high amounts of pollution from suspended particulate matter and accumulated gases, while others are more susceptible to harm. Therefore, plants’ reaction to air pollution is influenced by the kind of harmful compounds, their levels, and the plant’s susceptibility to them. The LSTM +CNN Proposed Ensemble method may be used to analyse the impact of air pollution on agriculture by examining trends in crop production over time and predicting which crop is more resistant based on the pollution data. The initiative created for this aim may assist farmers in determining the most suitable crop to cultivate in their fields to minimize the impact of air pollution on agricultural yield. The findings show deep learning algorithms correctly predict hourly pollutant concentrations such as carbon monoxide, sulphur dioxide, nitrogen dioxide, ground-level ozone, and particulate matter 2.5, along with the hourly Air Quality Index (AQI) for California. A proposed model used test RMSE values as a measure to evaluate prediction performance, achieving the best possible results. © 2025 SCPE.

关键词： Nitrogen oxides

来源：评论

学校读者我要写书评

暂无评论

Autonomous Robot Navigation in Unknown Terrains using Generative Adversarial Networks 4

Autonomous Robot Navigation in Unknown Terrains using Genera...

引用

4th International Conference on Soft Computing for Security Applications, ICSCSA 2024

作者： Chitra, P. Sridar, K. Govindan, Sudha Britto Raj, S. Akshya, J. Choudhry, Mani Deepak Sundarrajan, M. St Joseph's Institute of Technology Department of Artificial Intelligence and Data Science Chennai India Veerammal Engineering College Department of Computer Science and Engineering Dindigul India Sona College of Technology Department of Computer Science and Engineering Salem India RRASE College of Engineering Department of Computer Science and Engineering Chennai India SRM Institute of Science and Technology Department of Computational Intelligence Chennai India SRM Institute of Science and Technology Department of Computing Technologies Chennai India SRM Institute of Science and Technology Department of Networking and Communications Chennai India

ISBN: (纸本)9798331515720

Autonomous Robot Navigation in unknown and dynamic environments is considered one of the grand challenges in robotics. These motions that guide it span from rescue operations to planetary exploration. Classical methods for path planning, including A*, Dijkstra, and RRT, were unable to balance the efficiency and adaptability of motion planning over complex terrain. This may have a powerful solution using Generative Adversarial Networks (GANs) with advanced machine learning techniques to improve the ability of robotic navigation. This study proposes a GAN-based approach for designing an effective self-adaptive path planning and obstacle avoidance system for autonomous robots. Despite performing well in structured environments, traditional techniques normally fail in analysing the unstructured terrains with real-time adjustments and dynamic changes due to the high computational costs and lack of flexibility involved. In this regard, the proposed GAN-based system resolves these issues by rating navigation paths concerning safety and efficiency. Quantitative analysis demonstrates that within a forest, desert, urban, or off-road environment, the computational times by using the developed strategy turn out to be 0.12 seconds, 0.10 seconds, 0.14 seconds, and 0.13 seconds, respectively, behaving much lower than what can be achieved with other algorithms. This approach proves much superior in terms of computational efficiency path smoothness and adaptability under different environmental conditions in applications related to autonomous robot navigation systems. © 2024 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Enhancing Cyber-Physical Systems Security: A Review of Deep Learning and Blockchain Integration 5

Enhancing Cyber-Physical Systems Security: A Review of Deep ...

引用

5th International Conference on Image Processing and Capsule Networks, ICIPCN 2024

作者： Selvi, K. Dilip, Golda SRM Institute of Science and Technology Faculty of Engineering and Technology Department of Computer Science and Engineering Vadapalani Campus Chennai India

ISBN: (纸本)9798350367171

Cyber-Physical Systems (CPS) combine physical and computational elements to produce intelligent systems communicating with their surroundings. By integrating digital and physical processes, CPS provides increased functionality in various industries, including industry, transportation, and healthcare. However, there are security, data integrity, and privacy issues brought on by the extensive integration of CPS across several domains. Therefore, addressing these issues is significant for an effective and reliable CPS model. This study presents a comprehensive review exploring the synergistic relationship between two cutting-edge technologies, Deep Learning (DL) and Blockchain, deployed to resolve these issues in CPS. This study explores the efficiency of leveraging DL and blockchain to enhance the reliability and effectiveness of the CPS models. Also, this study examines the challenges and limitations faced by those DL and blockchain approaches during their implementation across different CPS domains. This comprehensive review provides promising directions for future research in this dynamic and interdisciplinary field for mitigating the challenges in CPS models. It also aids researchers, practitioners, and policymakers by providing a deeper understanding of the possible effects, difficulties, and opportunities related to utilizing DL and Blockchain technologies to improve the security and functionality of CPS. © 2024 IEEE.

关键词： Blockchain technologies Cyber-Physical Systems Deep Learning Internet of Things

来源：评论

学校读者我要写书评

暂无评论

Parallel Deep Convolution Neural Network (P-DCNN) Prediction of Paddy Crop Disease 7th

Parallel Deep Convolution Neural Network (P-DCNN) Prediction...

引用

7th International Conference on Soft Computing: Theories and Applications, SoCTA 2023

作者： Gangadevi, G. Raja Ratna, S. Jospin Jeya, J. Priya, M. Department of Computer Science and Engineering SRM Institute of Science and Technology Chennai Ramapuram India Velammal Engineering College Chennai India

ISBN: (纸本)9789819720309

Agriculture is one of the major sources for gross regional product among the developing nations. The nature and amount of crop cultivated along with its yield in each region varies with soil and climate. Additionally, the crop yield is affected due to the event of disease. Paddy is one of the chief food crops cultivated in numerous parts, and it succumbs to several diseases. The framers often find it hard to predict the nature of disease over the paddy crop. For supporting the farmer, a novel Parallel Deep Convolution Aggregation Neural Network (P-DCNN) classifier is proposed to predict and localize the disease in paddy crop using raw images. The novel parallel classifier which has hybrid tanh and sigmoid function is developed for the proposed work. The input images considered for processing are given into equally divided and sent to two smaller networks works independent to each other simultaneously, and then outcome is merged into a final output layer. Parallelization reduces the computational time for processing the images through the network. The performance of the proposed framework is evaluated on various performance metrics. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Precision agriculture

来源：评论

学校读者我要写书评

暂无评论

Event analysis of functional near infrared spectroscopy brain signal using Conditional Generative Adversarial Network 1

Event analysis of functional near infrared spectroscopy brai...

引用

1st International Conference on Innovations in Communications, Electrical and computer engineering, ICICEC 2024

作者： Akila, V. Shirly Edward, A. Sathiya, R. Vasuki, A. Rishi, Priti Anju, M.I. Anita Christaline, J. SRM Institute of Science and Technology Department of Ece Vadapalani Chennai India Vellore Institute of Science and Technology School of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350376517

The brain's intricate processes have been the subject of an extraordinary amount of detailed study by researchers, who have access to vast quantities of brain signal data. Event-related brain signals are necessary for comprehending cognitive activities such as memory, attention, and decision-making. The brain mechanisms of cognitive processes are revealed by these signals. Deep learning and machine learning are technologies that are promising for the analysis of brain signals related to events. These sophisticated methodologies are capable of detecting intricate data patterns that suggest cognitive activities. This investigation employs deep learning and machine learning to analyze brain signals associated with events. Event-related signal pre-processing, feature extraction, and categorization comprise the primary procedures. Data preparation eliminates noise and anomalies in order to prepare signals for analysis. The objective of feature extraction is to identify the brain signals that most accurately represent cognitive activity. Categorization is the process of classifying these characteristics in order to comprehend their cognitive processes. A comparison is made between deep learning and machine learning in the context of event-related neural signal processing. The comparison is made between support vector machines and decision trees and deep learning methods such as convolutional neural networks and neural networks. Both methodologies are effective in identifying neural correlates of cognitive processes. This method has the potential to enhance our comprehension of the brain's operation and potential treatments, thereby facilitating the development of diagnostic and therapeutic instruments for neurological and psychiatric illnesses. © 2024 IEEE.

关键词： Near infrared spectroscopy

来源：评论

学校读者我要写书评

暂无评论

An effective object detection via BS2ResNet and LTK-Bi-LSTM

引用

Multimedia Tools and Applications 2025年 1-20页

作者： V, Arulalan V, Premanand Kumar, Dhananjay Department of Computing Technologies SRM Institute of Science and Technology Chengalpattu District Tamil Nadu Kattankulathur603203 India Department of Computer Science and Engineering Vellore Institute Technology Chennai Campus Tamil Nadu Chennai India Department of Information Technology Anna University MIT Campus Tamil Nadu Chennai India

Video analytics faces complex challenges in object detection and classification. Deep learning based approaches have achieved remarkable success in past decade. However, existing object identification models that utilize backbone’s core features still present challenges due to their lack of semantic information. To address these issues, a novel object detection and classification framework utilizing Batch normalization and Softswish activation adapted ResNet (BS2ResNet) and Logistic Tanh Kaiming Bi-directional Long Short Term Memory (LTK-Bi-LSTM) techniques was proposed. The framework employs frame conversion, noise removal, and contrast elevation during frame pre-processing, followed by background subtraction using the Supreme Distance-centered Fuzzy C-Means (SD-FCM) clustering algorithm, and edge detection using the Hyperbolic Tangent Kernel Canny Edge Detector (HTKCED). BS2ResNet is then used for object detection, and features are extracted and passed to the LTK-Bi-LSTM neural network for object classification. The proposed system was found to improve object detection and classification accuracy, outperforming existing techniques. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Survey on Enhancing Digital Twin Security Systems with Explainable AI Techniques 3

A Comprehensive Survey on Enhancing Digital Twin Security Sy...

引用

3rd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2025

作者： Lalithadevi, B. Krishnaveni, S. Department of Computer Science and Engineering Sathyabama Institute of Science and Technology Chennai India Department of Computational Intelligence SRM Institute of Science and Technology Kattankulathur India

ISBN: (纸本)9798331527549

Digital Twin (DT) technology has emerged as a cornerstone in modern engineering, enabling real-time digital replication of physical assets for monitoring, diagnostics, and optimization. However, as DTs become increasingly integrated into critical infrastructure, their security has become a paramount concern. This paper presents a comprehensive survey on the integration of Explainable Artificial Intelligence (XAI) into Digital Twin security, highlighting the potential of XAI in enhancing the transparency, interpretability, and trustworthiness of AI - driven security mechanisms in DTs. We explore various XAI techniques, including model- agnostic approaches, interpretable neural networks, and rule-based systems, detailing their potential applications in bolstering the security of Digital Twins. Furthermore, we identify several key challenges in implementing XAI for DT security, such as the need for standardized metrics for interpretability, the trade-offs between model complexity and explainability, and the potential for adversarial attacks on explainable models. Through our analysis, we highlight the critical research gaps, including the security of Digital Twin (DT) systems and explores the integration of Explainable AI (XAI) to enhance transparency, interpretability, and trustworthiness. Outcomes include detailed XAI applications for DT security, identification of limitations, and a roadmap for future research. We discuss various XAI techniques, their applications, and the current challenges in implementing XAI for DT security. Our survey identifies key research gaps and offers a roadmap for future research in this emerging field. © 2025 IEEE.

关键词： Artificial intelligence

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：