检索结果-内蒙古大学图书馆

2024 IEEE International Conference on Future Machine Learning and Data science, FMLDS 2024

作者： Dey, Surio Sharma, Ankit Rai, Hritu Biswas, Susham Computer Science & Engineering Rajiv Gandhi Institute of Petroleum Technology Amethi India

ISBN: (纸本)9798350391213

Structural integrity is the foundation for both safety and durability and demands constant care and vigilance. In lieu of the traditionally adopted methods for defect detection in manufacturing and structural deformation, advanced techniques with automated methodology have been presented in this paper for identification and analysis with the help of Terrestrial Laser Scanning (TLS) data. This methodology will be flexible, able to treat different types of geometrical structures;thus, it can be found in real-life applications by increasing the scope. It involves capturing high-resolution TLS with fine surface details of the structure. Advanced algorithms fit idealized geometric models-cylinders or planes-such that it matches the data to those that have been scanned. Highly accurate virtual models quantify deviations between the actual structure and the virtual one to identify areas where defects in manufacturing or deformations exceed thresholds set in advance. The nature and extent of these defects are analyzed and visualized clearly across the structure's height. This reduces the actual time spent on structural analysis drastically, as automation increases the speed with great improvement in accuracy. Our results prove the efficiency of this approach in finding even slight deformations-a reliable tool for structural health monitoring. This methodology provides enormous opportunities for engineers and inspectors in charge of maintaining the safety and integrity of new and existing structures. © 2024 IEEE.

关键词： Laser applications

来源：评论

学校读者我要写书评

暂无评论

Multi-News Summarization Using Multi-Objective Differential Evolution Framework 15

Multi-News Summarization Using Multi-Objective Differential ...

引用

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

作者： Mishra, Santosh Kumar Rajiv Gandhi Institute of Petroleum Technology Department of Computer Science and Engineering Amethi Jais India

ISBN: (纸本)9798350370249

Summarization is a critical challenge in natural language processing, gaining prominence as individuals increasingly seek concise and accessible information. In the context of news articles, generating summaries from various sources on a given topic is particularly valuable. To address this, we frame the multi-news summarization task as a clustering-based optimization problem. Our approach employs a differential evolution-based multi-objective framework to solve it. News sentences are clustered using a multi-objective clustering technique, optimizing two cluster validity indices - the XB index and the PBM index - that evaluate the separation and compactness of the sentence clusters. This optimization simultaneously leverages the multi-objective differential evolution algorithm to automatically determine the optimal number of clusters. We conduct experiments using the multi-news dataset and evaluate the performance using the ROUGE-1, ROUGE-2, and ROUGE-SU metrics. The findings indicate that our proposed method surpasses existing approaches in generating high-quality summaries. © 2024 IEEE.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

A Web-Based Supervised Machine Learning Model for Air Quality Index and Respiratory Care Prediction 3

A Web-Based Supervised Machine Learning Model for Air Qualit...

引用

3rd International Conference on Machine Learning and Data engineering, ICMLDE 2024

作者： Singh, Mukund Pratap Bisht, Nikita Choudhary, Mandeep Goswami, Anurag Tagore, Nirbhay Kumar School of Computer Science Engineering and Technology Bennett University India Departmentl of Computer Science and Engineering Rajiv Gandhi Institute of Petroleum Technology Amethi India

The quality of the air is crucial for people who suffer from respiratory conditions. The prediction of the air quality index (AQI) is essential for preventing health issues, particularly for those with respiratory diseases. Deteriorating air quality is often linked to increased residential, industrial, and transportation activity. Accurate AQI prediction can help in mitigating these health risks. Disseminating information about the air quality index among diverse populations is crucial. The motive of this study is to use several machine learning regression and classification approaches to develop quantitative and accurate air quality forecast models. Incorporating a preventive system that provides preventive measures to healthy people as well as those suffering from cancer and respiratory diseases is an additional component of this. This study evaluates multiple supervised machine learning algorithms, including Random Forest and XGBoost, for AQI prediction using real-time data from four Indian cities. To identify the most effective model, five different machine learning models were used, and hyperparameter tuning was performed to achieve better accuracy. After evaluating the R2 score, root mean squared error (RMSE), mean absolute error (MAE), and mean squared error (MSE) for five different regression algorithms, as well as precision, accuracy, recall, and F1 score for classification algorithms, it was found that the Random Forest and XGBoost (using the best hyperparameters) classifiers performed best among other models. The Random Forest model achieved an MAE of 0.97 and an R-squared of 0.998, while the XGBoost classifier reached a perfect accuracy of 1.0 after hyperparameter tuning, providing valuable insights for respiratory care and preventive measures. Other models that were looked at included k-nearest neighbors (KNN), decision trees, and support vector machines (SVM). When visiting locations with high air quality index (AQI) values, exercise carefulness since

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Metaverse: What, Why and Where? 9

Metaverse: What, Why and Where?

引用

9th IEEE Smart World Congress, SWC 2023

作者： Singh, Jasteg Srivastava, Gargi Agarwal, Sajal Rajiv Gandhi Institute of Petroleum Technology Computer Science and Engineering Jais India Rajiv Gandhi Institute of Petroleum Technology Electrical & Electronics Engineering Jais India

ISBN: (纸本)9798350319804

The metaverse, according to the computer industry, is the next iteration of the internet. It is a single, shared, immersive, lasting, 3D virtual realm where people may interact with one another and experience life in ways that are not possible in the real world. Artificial intelligence (AI), augmented reality (AR), and virtual reality (VR) are all firmly linked to the metaverse notion (VR). The metaverse has the power to alter our daily lives and how we view the future. Metaverse can be used in gaming, social interaction, media and entertainment, e-commerce, virtual tourism, and medical science. It will open up doors that have never been heard of or imagined before. Multinational companies are developing multiverses to interact with the digital world and the economy that will flow around these new technologies. These technologies have advantages and disadvantages and are affecting the economies of many countries, such as Europe, where it is estimated that the introduction of metaverse technologies will contribute $440 billion to the continent's *** review will give a detailed idea of the past, present, and future technologies used in the metaverse. It will cover the metaverse in many different sectors, such as gaming, tourism, medical research, social interaction, media and entertainment, and e-commerce. It will also show the limitations of these new technologies as well as how we can overcome them. Also an important aspect that will be covered is the new companies that are now focusing on the metaverse and how this will affect the economy of the whole world. © 2023 IEEE.

关键词： Artificial intelligence augmented reality metaverse virtual space vision

来源：评论

学校读者我要写书评

暂无评论

Blockchain-based Secure Storage and Management of Electronic Health Record using a Smart Card 5

Blockchain-based Secure Storage and Management of Electronic...

引用

5th International Conference on Recent Advances in Information technology, RAIT 2023

作者： Srivastava, Ishita Raj, Aryaman Gupta, Daya Sagar Rajiv Gandhi Institute of Petroleum Technology Computer Science and Engineering Amethi India

ISBN: (纸本)9798350335705

The use of Blockchain for consistent storage, management, and sharing of healthcare records has received a lot of recent attention as a more reliable and dependable alternative to cloud-based storage. With the potential of Blockchain technology in the health sector being explored, its practical applications in real-world healthcare scenarios on a large scale are facing challenges like scalability, the authenticity of records, and management of dynamic consent of the patients for data access and sharing of medical records. The paper describes the implementation of a secured and efficient system for the storage of medical records on the Blockchain. The proposed implementation focuses on scalability, the authenticity of medical records, data privacy, and controlled access and uses Proof-of-Authority as a consensus algorithm on a Permissioned-Blockchain and two-factor authentication through a smart card. The paper also introduces a constant-time searching algorithm for faster records retrieval of Electronic Health Records. While the Proof-of-Authority consensus mechanism resolves the scalability issues, the smart card acts as the access control token, that ensures data privacy and makes it convenient for the users to operate. © 2023 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Recent Advancements in Structural Health Monitoring using Optical Sensor

Recent Advancements in Structural Health Monitoring using Op...

引用

2023 IEEE International Conference on Device Intelligence, Computing and Communication Technologies, DICCT 2023

作者： Agarwal, Sajal Srivastava, Gargi Rajiv Gandhi Institute of Petroleum Technology Deaprtment of Electronics Engineering Jais India Rajiv Gandhi Institute of Petroleum Technology Deaprtment of Computer Science and Engineering Jais India

ISBN: (纸本)9781665474924

Civil structure monitoring is a mandatory field of research now a days due to the adverse effects of environmental change on the civil structures for various industries. Optical sensing is a well-established field in structural monitoring, however recent advancements in fiber sensing technique are marvelous and open new possibilities of better monitoring. In this study these advancements are reviewed based on the materials used in optical sensors. © 2023 IEEE.

关键词： Optical sensors

来源：评论

学校读者我要写书评

暂无评论

AI-Enabled Road Health Monitoring System for Smart Cities 4th

AI-Enabled Road Health Monitoring System for Smart Cities

引用

4th International Conference on Data, engineering, and Applications, IDEA 2022

作者： Bhatt, Arpit Kumar Biswas, Susham Department of Computer Science and Engineering Rajiv Gandhi Institute of Petroleum Technology Jais Uttar Pradesh Amethi India

ISBN: (纸本)9789819700363

Automatic crack identification is a difficult issue that has been explored for decades, due to the complexity of roadway networks. Any pavement that has cracks in its beginning to lose its surface integrity. Therefore, fracture identification and management are essential duties because cracks that spread severely damage structures. Manual inspection is limited to places that can be accessed by people and is based on the expert's prior knowledge. This paper describes the methods used for evaluation of roads on pothole and crack detection in the highway pavement. The objective of this research work is to create a precise pavement health smart monitoring system that requires a phone camera-based monitoring and with the help of profiling of whole cross section of the road. A 1 km stretch area in RGIPT campus is considered for this study. In this research work, road pavement is converted into 3D point cloud with the help of mobile camera. Large pavement area is divided into several grids to study the nature of terrain and various features of roads. With the help of point cloud, every grid is studied for their coordinate axes as well RGB values to identify the variation of z-coordinates as we proceed forward. We have tried to bring automation in road health monitoring using AI-ML. Identification and feature extraction is performed using classification in depth variation as well as corresponding change in RGB value of generated point cloud. Obtained results are very accurate with the help of image processing, and results are also verified with actual pavement surface. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Smart city

来源：评论

学校读者我要写书评

暂无评论

AdaFedProx: A Heterogeneity-Aware Federated Deep Reinforcement Learning for Medical Image Classification

引用

IEEE Transactions on Consumer Electronics 2024年第1期71卷 1432-1441页

作者： Sahoo, Pranab Tripathi, Ashutosh Saha, Sriparna Mondal, Samrat Singh, Jyoti Prakash Sharma, Bhisham Computer Science and Engineering Department Indian Institute of Technology Patna India Electrical and Electronics Engineering Department The Rajiv Gandhi Institute of Petroleum Technology India Indian Institute of Technology Computer Science and Engineering Department Patna India National Institute of Technology Computer Science and Engineering Department Patna India Chitkara University Centre of Research Impact and Outcome Punjab Rajpura140401 India

In the realm of smart healthcare, vast amounts of valuable patient data are generated worldwide. However, healthcare providers face challenges in data sharing due to privacy concerns. Federated learning (FL) offers a privacy-preserving solution by enabling collaborative model training without direct access to patient data. This decentralized approach utilizes data from diverse sources, resulting in a globally learned model with satisfactory performance across individual sites. However, federated training encounters challenges such as "system heterogeneity"in client specifications and "data heterogeneity"in imbalanced data distribution. Standard FL methods become unstable and require extensive hyperparameter tuning for optimal performance when facing heterogeneous clients, posing challenges in real-world applications. This research introduces a novel heterogeneity-aware federated learning approach named AdaFedProx to address the performance degradation resulting from heterogeneity. AdaFedProx utilizes a reinforcement learning-driven strategy, introducing a tailored proximal term into the objective function to incorporate partial client information in heterogeneous settings. Dynamically determining the proximal term based on individual client states, including critical characteristics like data distribution, system specification, and performance feedback, empowers AdaFedProx to make regularized decisions throughout the federated training. AdaFedProx consistently outperforms four state-of-the-art methods on three medical datasets across diverse heterogeneity settings (0%, 50%, and 75% straggler). The code can be found at https://***/Pranabiitp/AdaFedProx. © 1975-2011 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Know How Much Sensitive Precision and Recall Validity Measures Are? 27th

Know How Much Sensitive Precision and Recall Validity Measu...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Mishra, Sumit Swain, Srinibas Prakash, Ved Department of Computer Science and Engineering Rajiv Gandhi Institute of Petroleum Technology Amethi Jais India Department of Computer Science and Engineering Indian Institute of Information Technology Guwahati Guwahati India

ISBN: (纸本)9783031781650

For the performance evaluation of the clustering algorithm, evaluation metrics are used. For this purpose, the obtained set of clusters are compared with the actual set of clusters (or gold standard). Various evaluation metrics have been proposed in the past. One important question regarding these evaluation metrics is – how good are these metrics for evaluating the performance of the clustering algorithm? Wagner et al. have proposed some of the properties of these evaluation metrics. The evaluation metric should also have a high sensitivity value to capture the change in the clustering result/gold standard along with these properties. In this paper, we compute the sensitivity of two commonly used evaluation metrics – Precision and Recall. We also show that the sensitivity of Precision and Recall is polynomial with respect to the number of data-points. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

An Autoencoder-BiLSTM framework for classifying multiple types of lung diseases from CXR images

引用

Multimedia Tools and Applications 2024年第38期83卷 86091-86120页

作者： Ankayarkanni, B. Sangeetha, P. Department of Computer Science and Engineering Sathyabama Institute of Science and Technology Jeppiaar Nagar Chennai600 119 India Rajiv Gandhi College of Engineering Research and Technology Maharashtra Chandrapur442403 India

Millions of people die from lung illness each year as a result of its rise in recent years. CXR imaging is one of the most widely used and reasonably priced diagnostic techniques for the diagnosis of many illnesses. Unfortunately, even for seasoned radiologists, accurately diagnosing sickness from Chest X-Rays (CXR) samples is challenging. To combat the pandemic, a reliable, affordable, and efficient way to diagnose lung disease has become essential. Consequently, a unique optimized Auto Encod-BI Long-Short Term Memory (Bi-LSTM) model is proposed in this research work. Pre-processing, segmentation, feature extraction, and multiple types of lung illness diagnosis are the four main stages of the suggested model. First, Laplacian filtering and Contrast Limited Adaptive Histogram Equalization (CLAHE) are used to pre-process the gathered CXR pictures. Next, the Region of Interest (ROI) from the previously processed images are recognized by means of the newly enhanced MobileNetV2. The new Self-Improved Slime Mould Algorithm (SI-SMA) is used to fine-tune the hyper-parameters of MobileNetV2 in order to precisely identify the afflicted locations. Based on the phenomenon of slime mould oscillation, the conventional Slime Mould Algorithm (SMA) model has been modified with the creation of the SI-SMA model. Next, characteristics like the Local Binary Pattern (LBP) and Histogram of Oriented Gradient (HOG) are taken out. Finally, a unique AutoEncod-BiLSTM Framework—which is divided into three categories—is shown to automate the process of identifying illnesses in CXR pictures: pneumonia, COVID-19, and normal. The autoencoder and Bi-LSTM are combined to create the suggested AutoEncod-BiLSTM model. The retrieved features are used to train the AutoEncod-BiLSTM Framework. Moreover, the proposed model enhanced the disease detection efficiency than the existing models and the disease detection accuracy of the proposed model is about 99.1%. Furthermore, the suggested model attains better

关键词： Equalizers

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：