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

Analyzing Frauds in Banking Sector and Impact of Internet Banking on Its Customers: A Case Study of Bank of Maharashtra 1

Analyzing Frauds in Banking Sector and Impact of Internet Ba...

引用

1st International Conference on Computational Intelligence, Communication technology and Networking, CICTN 2023

作者： Bhatt, Sumit Kumar, Vijay Kumar, Sanjay Maharishi University of Information Technology Department of Master of Business Administration UP Lucknow India Shri Ram Murti Smarak College of Engineering & Technology Department of Computer Application UP Bareilly India

ISBN: (纸本)9798350338027

Banking fraud became an important issue in India as there were several examples of such misconduct within recent years. This research aims to identify frauds in Indian banking sector along with impact of internet banking on consumers with particular focus on bank of Maharashtra. In the introductory part of the paper, number of fraud activities in Indian banking sector along with its relevance are discussed including significance of internet banking in today's world. In the literature review part, two themes are selected and analysed which are fraud cases in Indian banking industry and evolution of internet banking in India. For both these themes, data collected from previous studies and presented with critical evaluation. The research methodology section has included research philosophy, research approach, research design as well as methods & sources. Pragmatist research philosophy, inductive research approach and descriptive research design are selected for this particular study. The sources mentioned in the methods & sources section from which the selected articles and publications are gathered. The results and discussion section has mentioned different fraud cases of Bank of Maharashtra (BoM) including details of those cases. Moreover, the evolution of internet banking and BoM's approach to implement internet banking are discussed in the next part of the results and discussion. Finally, the major reasons of frauds in Indian banking sector are concluded in the paper along with future scope of the research. At last, several strategic recommendations for government and banking institutions are presented, introducing which can help to deal with fraudulent activities through more appropriate way. © 2023 IEEE.

关键词： Crime

来源：评论

学校读者我要写书评

暂无评论

Assessment and Prediction of Urban Pollutants and its Influence on Human Health using Deep Learning Algorithm 9

Assessment and Prediction of Urban Pollutants and its Influe...

引用

9th IEEE International Conference for Convergence in technology, I2CT 2024

作者： Kavathekar, Vaishali Tripathy, Amiya Kumar Chettri, Sarat Kumar Bhanage, Vinayak Zaidansari, Mohammad Babu, Lavena Joshua, Allen Assam Don Bosco University Computer Science And Engineering Assam India Don Bosco Institute of Technology Mumbai India Don Bosco Institute of Technology Computer Engineering Mumbai India Assam Don Bosco University Computer Application Assam India Hiroshima University Advance Science And Engineering Hiroshima Japan Don Bosco Institute of Technology Information Technology Mumbai India

ISBN: (纸本)9798350394474

Mumbai, the financial center of India, is a thriving city where the urban environment is constantly changing. Degradation of the environment is a result of these changes. Recent research reveals a recurring problem, wherein pollutant levels regularly exceed advised thresholds, thus having an adverse effect on human health. The research makes use of meteorological data from four weather stations (Powai, Sion, Colaba and Borivali) that span the years 2000-2023. The chosen contaminants for study are PM2.5, PM10, and air temperature. All of the contaminants are growing exponentially, according to the study. For future prediction, deep learning techniques are used. In comparison to the other algorithms, the results show that Bi-LSTM is more accurate. Based on this model, it appears that regular places will soon become hotspots and maybe dangerous. With the use of this model, Mumbai metropolitan planners and authorities may make timely and well-informed decisions that would promote the city's sustainable growth and citizens well-being. © 2024 IEEE.

关键词： Data visualization

来源：评论

学校读者我要写书评

暂无评论

Enhanced Fine-Tuning of Lightweight Domain-Specific Q&A Model Based on Large Language Models 35

Enhanced Fine-Tuning of Lightweight Domain-Specific Q&A Mode...

引用

35th IEEE International Symposium on Software Reliability Engineering Workshops, ISSREW 2024

作者： Zhang, Shenglin Zhu, Pengtian Ma, Minghua Wang, Jiagang Sun, Yongqian Li, Dongwen Wang, Jingyu Guo, Qianying Hua, Xiaolei Zhu, Lin Pei, Dan Nankai University China Haihe Laboratory of Information Technology Application Innovation China Microsoft Tsinghua University China Tianjin Key Laboratory of Software Experience and Human Computer Interaction China China Mobile Research Institute China Beijing National Research Center for Information Science and Technology China

ISBN: (纸本)9798350367041

Large language models (LLMs) excel at general question-answering (Q&A) but often fall short in specialized domains due to a lack of domain-specific knowledge. Commercial companies face the dual challenges of privacy protection and resource constraints when involving LLMs for fine-tuning. This paper propose a novel framework, Self-Evolution, designed to address these issues by leveraging lightweight open-source LLMs through multiple iterative fine-tuning rounds. To enhance the efficiency of iterative fine-tuning, Self-Evolution employ a strategy that filters and reinforces the knowledge with higher value during the iterative process. We employed Self-Evolution on Qwen1.5-7B-Chat using 4,000 documents containing rich domain knowledge from China Mobile, achieving a performance score 174% higher on domain-specific question-answering evaluations than Qwen1.5-7B-Chat and even 22% higher than Qwen1.5-72B-Chat. Self-Evolution has been deployed in China Mobile's daily operation and maintenance for 117 days, and it improves the efficiency of locating alarms, fixing problems, and finding related reports, with an average efficiency improvement of over 18.6%. In addition, we release Self-Evolution framework code in https://***/Zero-Pointer/Self-Evolution. © 2024 IEEE.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Research on Mining Association Rules for Classroom Concentration Based on Apriori Algorithm 7

Research on Mining Association Rules for Classroom Concentra...

引用

7th IEEE information technology and Mechatronics Engineering Conference, ITOEC 2023

作者： Bai, Jingqiu Kong, Huafeng Hu, Wenhan Wuhan Business University Department of Information Engineering Hubei China Major in Data Science and Big Data Technology China The Main Research Direction Is the Computer Application China

ISBN: (纸本)9798350334197

This paper studies the correlation between students' concentration in class and learning interest, emotional state and other influencing factors. By collecting students' classroom status data, a data set suitable for data mining is constructed. Based on the idea of Apriori algorithm, the Anaconda Navigator programming tool is used to mine the association rules of students' classroom concentration. Through data mining based on Apriori algorithm, and the association rules between students' emotional state, learning interest and other factors and in-class test scores are output. The results of strong association rules show that the better students' emotional state, learning interest and other states are, the better their classroom concentration performance is. Mining the potential influencing factors of students' classroom concentration provides valuable reference theory for students to improve classroom concentration and teachers to improve classroom teaching effect, which is helpful for teachers and students to build a more efficient classroom together in the future. © 2023 IEEE.

关键词： Association rules

来源：评论

学校读者我要写书评

暂无评论

Implementation of e-Healthcare Data Acquisition System Using IoT (Internet of Things) 1

引用

Virtual International Conference on Futuristic Communication and Network Technologies, VICFCNT 2021

作者： Mishra, Adarsh Ravi Shukla, Ragini Mishra, Ravi Department of Computer Application and Information Technology Dr. C. V. Raman University Bilaspur India Department of Electronics and Telecommunication GHRIET Nagpur India

ISBN: (数字)9789811983382

ISBN: (纸本)9789811983375

A smart healthcare system monitors the vital parameter of patient and continuously displaying the information regarding patient. Smart healthcare system is built by some important sensors and microprocessor. The main objective of the paper is to introduce smart healthcare device that supports doctors as well as guardian of patients to monitor patient’s condition. Sensors are integrated and attached to device to monitor patient in a very effective manner. This device prevents patient to reach in its chronic condition because one alarm has been attached to it;if the condition is reaching up or down as per the set normal value, it will be alarming to indicate the patient's condition. Device is providing Zigbee wireless connection to prompt monitoring convenience to doctor in system, so that it helps to diagnose sick patient easily. It is a device that supports doctor for better treatment and frequent observation of the patient. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Zigbee

来源：评论

学校读者我要写书评

暂无评论

An Automated System for Bone Invasion Detection Occurring at Stage T4 in Oral Squamous Carcinoma using Machine Learning Algorithms 2

An Automated System for Bone Invasion Detection Occurring at...

引用

2nd IEEE International Conference on Intelligent Technologies, CONIT 2022

作者： Agarwal, Pinky Yadav, Anju Mathur, Pratistha Manipal University Jaipur Computer Application Jaipur India Manipal University Jaipur Information Technology Jaipur India

ISBN: (数字)9781665484077

ISBN: (纸本)9781665484077

Bone invasion is the condition where a cancer tumor invades nearby bones. Detection of bone invasion in oral squamous carcinoma is important for treatment planning and surgery of patients. This bone invasion can be a subtle erosion or deep erosion. It is challenging for radiologists to identify the subtle erosion in ct-scan images of oral cancer patients. This paper presents three machine learning (ML) classifiers: Support Vector Machine (SVM), Random Forest (RF), and XG Boost classifiers for automatic detection of bone invasion in CT images of oral cancer patients. The proposed framework classifies CT images as images without invasion and images with invasion. Due to the unavailability of the public dataset for this work, a dataset of 37 patients is collected from S.M.S. hospital, Jaipur. All the three classifiers SVM, RF, and XG Boost have given outstanding results with 0.94, 0.93, and 0.95 accuracies respectively. For this, both time and spatial domain features are extracted using Grey Level Co-occurrence Matrix (GLCM), Gray Level Difference Method (GLDM), Wavelet Transform (WT), and Fast Fourier Transform (FFT) methods, and extracted features are concatenated and a feature pool is created. Among all XG Boost has outperformed others. © 2022 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Analyzing the Effects of Coding and Compression on Network Performance 5th

Analyzing the Effects of Coding and Compression on Network P...

引用

5th International Conference on Data Science, Machine Learning and applications, ICDSMLA 2023

作者： Agarwal, Ankita Kumar, Deepak Singh, Alka Preethi, D. Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh Lucknow India Department of Mathematics Vivekananda Global University Jaipur India Department of Master of Computer Application Noida Institute of Engineering and Technology Uttar Pradesh Greater Noida India Karnataka Bengaluru India

ISBN: (纸本)9789819780426

This paper objectives to research the consequences of coding and compression on network performance. Network coding is the technique of encoding information before it is despatched over a network and has become an outstanding method to enhance community overall performance. Compression then again is used to reduce the size of the data before transmission, ensuing in quicker transmission time. This observe evaluates the effect those techniques have on network overall performance by measuring the bandwidth utilization, throughput, latency, and packet losses. A test becomes conducted to have a look at how the strategies have an effect on one of kind mixtures of information speeds, packet sizes, and facts loading. Results display that both strategies had a fine impact at the community overall performance, with network coding and compression having an extra effect on networks with higher facts hundreds. Moreover, the effects show that community coding had a greater impact on networks with larger packets, while compression had a more effect on networks with smaller packets. This studies gives insight into how community coding and compression can be used to enhance network overall performance. Coding and compression are important components of network performance that have been studied and tested to have a full-size influence on network pace, scalability, and reliability. Coding is used to reduce the amount of data that is sent over a community, by way of reducing the quantity of records frames that need to be sent and growing the performance of the records transfer technique. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Network coding

来源：评论

学校读者我要写书评

暂无评论

A Novel Approach with Fusion Edge Prediction Strategy for Table Structure Recognition 11

A Novel Approach with Fusion Edge Prediction Strategy for Ta...

引用

11th International Conference on information Systems and Computing technology, ISCTech 2023

作者： Liu, Yingli Zhang, Guangtao Shen, Tao Kunming University of Science and Technology Faculty of Information Engineering and Automation Kunming650093 China Kunming University of Science and Technology Yunnan Key Laboratory of Computer Technologies Application Kunming650500 China

ISBN: (纸本)9798350342406

Table, as an information carrier with high information density and direct display form, are widely used in scientific literature and social production documents. Accurately identifying tables from various documents will significantly promote the intelligent application of documents. The table's structural information is crucial for comprehending how the text content in the table relates to one another, but teaching a computer to fully understand a table's structure is still a very difficult undertaking. In this research work, we provided a unique edge-based method to recognize table structures. Specifically, we define the inter-cell relationships as an edge prediction problem and leverage graph convolutional networks to learn representations of the cells. These learned representations are then utilized to directly predict the connections between the cells. The experimental results conducted on three publicly available datasets for table structure recognition provide compelling evidence supporting the feasibility and usefulness of our presented methodology. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Multi-objective performance prediction based on a self-constructed Al-Si alloy dataset 11

Multi-objective performance prediction based on a self-const...

引用

11th International Conference on information Systems and Computing technology, ISCTech 2023

作者： Hu, Dan Liu, Yingli Shen, Tao Kunming University of Science and Technology Faculty of Information Engineering and Automation Kunming650093 China Kunming University of Science and Technology Yunnan Key Laboratory of Computer Technologies Application Kunming650500 China

ISBN: (纸本)9798350342406

The combination of data-driven approaches and machine learning techniques has changed the design approach for new materials, propelling materials science research into the realm of the fourth paradigm. Researchers in the field of materials science have increasingly focused on utilizing machine learning methods to uncover the underlying nonlinear relationships within material data. However, there is currently limited research in the field of aluminum-silicon alloys regarding the prediction of alloy performance based on the composition-process-structure relationship. Additionally, there is a lack of data sharing in the aluminum-silicon alloy domain. Therefore, this study proposes a methodology. Firstly, an aluminum-silicon alloy dataset is constructed by mining relevant information from materials literature. Then, high-dimensional features in the dataset are subjected to feature selection techniques for dimensionality reduction. Subsequently, a multilayer perceptron model is applied to investigate the relationship between input features such as alloy composition, preparation process, and microstructural parameters, and output features such as yield strength, ultimate tensile strength, and elongation, enabling performance prediction. © 2023 IEEE.

关键词： Feature Selection

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：