检索结果-内蒙古大学图书馆

Exploring outliers in global economic dataset having the impact of COVID-19 pandemic

International Journal of Business Intelligence and Data Mining 2023年第3期22卷 287-309页

作者： Desarkar, Anindita Das, Ajanta Chaudhuri, Chitrita Computer Science and Engineering Jadavpur University Kolkata700032 India Amity Institute of Information Technology Amity University Kolkata India

Outlier is a value that lies outside most of the other values in a dataset. Outlier exploration has a huge importance in almost all the industry applications like medical diagnosis, credit card fraudulence and intrusion detection systems. Similarly, in economic domain, it can be applied to analyse many unexpected events to harvest new knowledge like sudden crash of stock market, mismatch between country’s per capita incomes and overall development, abrupt change in unemployment rate and steep falling of bank interest. These situations can arise due to several reasons, out of which the present COVID-19 pandemic is a leading one. This motivates the present researchers to identify a few such vulnerable areas in the economic sphere and ferret out the most affected countries for each of them. Two well-known machine-learning techniques DBSCAN and Z-score are utilised to get these insights, which can serve as a guideline towards improving the overall scenario subsequently. Copyright © 2023 Inderscience Enterprises Ltd.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Robotics Process Automation Technologies for Data Collection and Analysis 15

Robotics Process Automation Technologies for Data Collection...

引用

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

作者： Usman, K. Hayath, T.M. Shafiulla, Mohammed Dadapeer Ballari Institute of Technology and Management Dept. of Computer Science and Engineering Karnataka Ballari India

ISBN: (纸本)9798350370249

Data collection and analysis are critical aspects of various business processes. However, these tasks can be time-consuming, prone to errors, and delays employee productivity when done manually, especially when we have to deal with huge data. Robotic Process Automation (RPA) technologies offer a promising solution in form of a BOT, by automating tedious tasks related with data handling. A survey by The Economist corporation believe that automation kick launches digital transformation, robotic process automation (RPA) has evolved from an emerging technology to a must-have digital transformation tool for enterprises to compete globally. An increasing number of companies are now using RPA to automate normal business processes in a non-intrusive and cost-effective way. On the other hand, decision-making, pattern recognition, and many other business-related tasks benefit greatly from the use of big data and analytics. This paper explores the application of RPA in data collection and analysis, examining its functionalities, benefits, and limitations. In practical, Bot produces error-free work and takes 94.44% less time for data collection compared to a manual process, which encourages all firms to adopt to RPA technologies. © 2024 IEEE.

关键词： Automation Data collection Process Robotics RPA

来源：评论

学校读者我要写书评

暂无评论

Predicting and Navigating Environmental Transformations using Machine Learning 2

Predicting and Navigating Environmental Transformations usin...

引用

2nd International Conference on Machine Learning and Data engineering, ICMLDE 2023

作者： Kumar, Lakshin Archana, A. Nath, Keshab Department of Computer Science and Engineering Indian Institute of Information Technology Kerala Kottayam686635 India

In today's world, as ecological challenges continue to rise, the importance of environmental monitoring and conservation cannot be overstated. These efforts play a vital role in countering the adverse impacts of human activities on our planet. The development of predictive models that can accurately predict the results of different conservation measures is essential for the success of these conservation efforts. This paper's objective is to create a Machine Learning (ML) model that predicts how environmental changes can unfold. This prediction helps in proactive monitoring and conservation planning, considering factors like deforestation, air pollution, sea level rise, temperature shifts, and forest preservation. The model relies on machine learning techniques, including AdaBoost, ETS, Prophet, SARIMA, LightGBM, and TL-BLSTM models, to analyze data, uncover trends, and inform decision-making. By offering a thorough assessment of the effects of conservation approaches, this model aids in shaping well-informed decisions regarding the distribution of resources. As a result, this process strengthens initiatives designed to protect biodiversity and the Earth's natural resources. Predicting changes in environmental variables is the main goal of this research, which will improve effective environmental management. In order to draw conclusions that are meaningful, this study compares several models for each of the four crucial factors. © 2024 Elsevier B.V.. All rights reserved.

关键词： Sea level

来源：评论

学校读者我要写书评

暂无评论

A Survey on Remote Sensing-Based Climate Change Prediction Using Artificial Intelligence Techniques 4

A Survey on Remote Sensing-Based Climate Change Prediction U...

引用

4th International Conference on Sustainable Expert Systems, ICSES 2024

作者： Suhana, S. Karthiga, M. Bannari Amman Institute of Technology Erode India Bannari Amman Institute of Technology Department of Computer Science and Engineering Erode India

ISBN: (数字)9798331540364

ISBN: (纸本)9798331540364

Climate change prognosis is one of the most important fields of study that has attracted much interest in the last decade because of its implication for environmental and social development. The developments in remote sensing technologies that deliver data on various climatic factors have been integrated with Artificial Intelligence techniques to improve climate change prediction models. This paper aims to review the research done between the years 2014-2024 and how the AI methods were applied along with the remote sensing data for climate change prediction. The survey covers different AI techniques, including machine learning, deep learning, combined approaches, and their application to vast RS datasets. Major trends and issues in this rapidly developing multidisciplinary area are discussed, and the strengths and weaknesses of different AI methods are compared. Furthermore, recent AI techniques used in remote-sensing-based climate change prediction include Neural Networks, Support Vector Machines (SVMs), Random Forests and Decision trees with physical climate models. However, these models have limitations like difficulties in handling heterogeneous information from different sensors, high computational costs, limited labelled datasets, and issues interpreting complicated AI model results. It also points to the directions for future research, noting that there is a need for better, more powerful and easily understandable AI frameworks to handle the issue of climate change. This paper seeks to give the reader an insight into the current state of AI in climate change prediction and the use of remote sensing data in this area of research. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Descriptive Predictive Model for Parkinson’s Disease Analysis 1

引用

2nd International Conference on Information technology, InCITe 2022

作者： Ali, Akbar Rout, Ranjeet Kumar Umer, Saiyed Computer Science and Engineering Aliah University Kolkata India Computer Science and Engineering National Institute of Technology Jammu and Kashmir Srinagar India

ISBN: (数字)9789811973468

ISBN: (纸本)9789811973451

The popularity of machine learning applications is increasing day by day. Uses of prediction model are in so many fields, for example weather forecast, industry, medical, technology, and data science also. In this paper, we are going to analyze a very common disease in human known as Parkinson disease. It is mostly found in older people but some time also reflects its presence in younger people. Model objective is to predict according to the past information. It is better to have high accuracy of the proposed model. The goal of Parkinson disease predicting model is detecting Parkinson’s disease in humans according to the data we will provide. We have used two types of audio dataset in this model, namely dysphonia and dysarthria. We have used four machine learning algorithms namely support vector machine, logistic regression, K_nearest neighbor, and random forest. First dataset has 24 feature-set and other have 756 feature-set, so we have used PCA also to provide feature-set according to need. We divided the dataset into four modules in first module we have used only five feature-set, and then in second module, we have used ten feature-set and then 15 and 20 feature-set, respectively, and then all features at a time. We have feeded these module to all algorithms and noted which one is best for which case. So we have four algorithm and we have tested these module one by one to these algorithm carefully and noted down there result, and then we analyzed that for dysphonia if we use random forest, then it gives better result for ten feature-set while for dysarthria it is support vector machine that gives better performance for ten feature-set. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2023.

关键词： Weather forecasting

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning Based Approach for Detecting Mango Leaf Diseases 6

A Deep Learning Based Approach for Detecting Mango Leaf Dise...

引用

6th International Conference on Computational Intelligence and Networks, CINE 2024

作者： Pradhan, Astik Kumar Rout, Jitendra Kumar Ghosh, Debanjan Sinha, Shailendra Kumar Arka Jain University School of computer Science and IT Jamshedpur India National Institute of Technology School of computer Science and Engineering Raipur India

ISBN: (纸本)9798331516796

The mango industry faces substantial annual economic losses due to diseases and pests. Farmers encounter difficulties in differentiating between various mango diseases, as their symptoms can closely resemble each other and even occur simultaneously. By making it possible to quickly and accurately detect and identify mango leaf illnesses, this study aims to offer a remedy. To accomplish this, the research employs state-of-the-art Convolutional Neural Networks (CNNs), which are advanced learning algorithms capable of automatically extracting and understanding complex features from raw images. Specifically, the study utilizes EfficientNet, a model based on CNNs, to facilitate the early identification and classification of mango leaf diseases. Additionally, advanced data augmentation techniques such as rotation, reflection, translation, and scaling are applied to enhance the collected dataset. This enhanced data is then used to train the EfficientNet model, which achieves an amazing 98% accuracy rate in identifying and categorizing mango leaf diseases. These findings underscore the CNN method's effectiveness in detecting a wide range of mango leaf diseases, positioning it as an invaluable and practical tool for both farmers and agricultural experts. © 2024 IEEE.

关键词： Fruits

来源：评论

学校读者我要写书评

暂无评论

Enhancing Arecanut Farming Profits through Technological Advancements: A CNN-based Approach for Efficient Grading and Sorting 5

Enhancing Arecanut Farming Profits through Technological Adv...

引用

5th International Conference on Mobile Computing and Sustainable Informatics, ICMCSI 2024

作者： Dhanush Ghate, D. Pallavi, K.N. Poojari, Asmita NMAM Institute of Technology Dept. of Computer Science and Engineering Karnataka Nitte574110 India

ISBN: (纸本)9798350395235

Technological advancements can have powerful impact on the economic growth of agriculture in India. Areca nut farming is one such terrain of agriculture where investment in technology and automation can elevate the profit from farming by bringing down production cost. Areca nut is the major crop of Karnataka having roots in fifteen different districts. The grading and sorting of areca nuts is an important step in the production of areca nuts and is traditionally done by man power. People are trained to identify good and bad areca nuts, but the time taken for sorting areca nuts is more and it is not feasible for a large quantity of areca nuts. In order to minimize the time consumed, this method is introduced which classify the areca nuts into four different grades based on their quality. © 2024 IEEE.

关键词： Sorting

来源：评论

学校读者我要写书评

暂无评论

Optimal Key Generation using Support Vector Machine for Health Records

Optimal Key Generation using Support Vector Machine for Heal...

引用

2024 International Conference on Emerging Innovations and Advanced Computing, INNOCOMP 2024

作者： Himanshu Punhani, Akash SRM Institute of Science and Technology Department of Computer Science and Engineering Delhi-NCR Campus Ghaziabad201204 India

ISBN: (纸本)9798350376470

As the digital age continues to progress, the demand for advanced data privacy techniques has become increasingly vital. With the rise of large-scale collection of data and the proliferation of machine learning algorithms, ensuring privacy while extracting valuable insights has become a challenging situation. This research paper proposes an approach that leverages machine learning-based techniques to achieve scalable privacy preservation, while also providing an optimal key generation mechanism for data encryption and decryption. The proposed approach is evaluated on a real-world healthcare dataset, and the experimental results demonstrate that the proposed approach provides a significant improvement in privacy preservation, while maintaining the performance and accuracy of the system. Healthcare data is among most sensitive one for this scenario as this data encompasses a vast array of information related to patient health, medical conditions, treatments, outcomes, and more. Leveraging this data in a responsible and privacy-preserving manner holds tremendous potential for improving healthcare outcomes, advancing medical research, and enhancing the overall quality of patient care. © 2024 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Enhanced Heart Disease Diagnosis in MRI Images Using Swan Adapt Optimized Thresholding Segmentation with U-Net Model 5

Enhanced Heart Disease Diagnosis in MRI Images Using Swan Ad...

引用

5th International Conference on Electronics and Sustainable Communication Systems, ICESC 2024

作者： Steephan Amalraj, J. Kumaresan, T. Pravin Savaridass, M. Vaanathi, S. Bannari Amman Institute of Technology Computer Science and Engineering Sathyamangalam India Bannari Amman Institute of Technology Electronics and Instrumentation Engineering Sathyamangalam India Bannari Amman Institute of Technology Atrificial Intelligence and Data Science Sathyamangalam India

ISBN: (数字)9798350379945

ISBN: (纸本)9798350379945

The diagnosis of heart disease in MRI images is a critical application within the area of medical imaging. Conventional segmentation algorithms have difficulty in the accurate delineation of normal and sick heart tissues due to problems such as noise sensitivity, inaccuracy in boundaries, and sensitivity to parameters. In this work, we propose a novel strategy of thresholding based on image clusters, which we term SwanAdaptOpti thresholding for the segmentation of MRI images. The proposed system also utilizes Watershed segmentation with markers refined to enhance the segmentation of diseased heart tissues. Indeed, our approach is capable of achieving satisfactory performance in delineating normal and sick heart images, avoiding issues like overfitting, underfitting, and local optima. The overall robustness of our approach is demonstrated by extensive experimentation, which reveals the potential of our approach for the accurate and reliable diagnosis of heart disease from MRI images with an accuracy of 96%. © 2024 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

IoT-based Food Quality Monitoring System Using Machine Learning 2

IoT-based Food Quality Monitoring System Using Machine Learn...

引用

2nd IEEE International Conference on Networking and Communications, ICNWC 2024

作者： Vasanthi, R. Ashika, K. Archana, D. St.Joseph's Institute of Technology Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350365269

One of the main considerations in preventing food waste is food safety and cleanliness. Foods should not be allowed to deteriorate or rot due to environmental elements including humidity, temperature, and darkness. The quality of the food should also be regularly checked. Deploying quality monitoring systems is beneficial due to the following reasons:. These food quality monitoring systems keep an eye on the external elements influencing food quality. Factors such as vacuum storage, refrigeration, and others later kept the items from spoiling. More specifically, the sensors in this system - which measure temperature, pH, humidity, gas, and DHT - provide the vital data required to assess the condition of the product that is being packed or kept. Leveraging Internet of Things (IoT) technology involves transmitting data to a computer system. Subsequently, this system displays a user interface that tracks the product's evolution over time. The goal of the project is to enhance food quality assessment by employing machine learning algorithms. © 2024 IEEE.

关键词： Internet of things

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：