检索结果-内蒙古大学图书馆

2022 international conference on machine learning and data engineering, icmlde 2022

作者： Pati, Abhilash Panigrahi, Amrutanshu Nayak, Debashish Swapnesh Kumar Sahoo, Ghanashyam Singh, Debabrata Odisha Bhubaneswar India GITA Autonomous College Odisha Bhubaneswar India

Managing appendicitis in children is still lacking international consensus. This is due to the lack of defined international pediatric appendicitis management recommendations and the unavailability of data-driven studies. In clinical practice, heuristic scoring methods are frequently employed to determine patient urgency. The use of ensemble techniques may improve prediction responses, which is the major goal of this study. This study used an ensemble of classifiers to predict three target variables in 430 children and adolescents aged 0-18 years. The ensemble approaches used in this work are majority voting and weighted averaging. In the Jupyter Python environment, these strategies' results were confirmed in terms of accuracy, misclassification rate, sensitivity, specificity, precision, f1-score, false negative and positive rates, and Mathew's correlation coefficient. Combining machine learning and deep learning can help in diagnosing and managing pediatric appendicitis, allowing for more tailored medical decisions. © 2023 The Authors. Published by Elsevier B.V.

关键词： Pediatrics

来源：评论

学校读者我要写书评

暂无评论

Comparative Study of machine learning Models for the Detection of Abusive Messages: Case of Wolof-French Codes Mixing data 7th

Comparative Study of Machine Learning Models for the Detecti...

引用

7th EAI international conference on Innovations and Interdisciplinary Solutions for Underserved Areas, InterSol 2024

作者： Ndao, Ibrahima Dramé, Khadim Sambe, Gorgoumack Diallo, Gayo Laboratoire d’Informatique et d’Ingénierie pour l’Innovation Université Assane Seck de Ziguinchor Ziguinchor Diabir Senegal AHead Bordeaux Population Health - INSERM 1219 and LABRI University Bordeaux France

ISBN: (纸本)9783031864926

This paper presents a comparative study of machine learning models for detecting abusive messages, focusing on code-mixed data in Wolof and French languages. With the increasing use of digital platforms, there has been a surge in derogatory comments, necessitating effective detection strategies. The study introduces a meticulously annotated dataset of 2022 Twitter tweets, manually classified as abusive or not. Extensive experiments are conducted with various machine learning algorithms, including deep learning, with a focus on comparing their performance on the test dataset. © ICST Institute for Computer Sciences, Social Informatics and Telecommunications engineering 2025.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Enhancing Parkinson's Disease Diagnosis through Deep learning-Based Classification of 3D MRI Images 2

Enhancing Parkinson's Disease Diagnosis through Deep Learnin...

引用

2nd international conference on machine learning and data engineering, icmlde 2023

作者： Desai, Shivani Chhinkaniwala, Hitesh Shah, Smit Gajjar, Pranshav Gujarat Technological University Ahmedabad India Department of Computer Science and Engineering Institute of Technology Nirma University India India College of Engineering and Computing George Mason University United States

This paper presents a deep learning-based model developed to accurately classify Parkinson's disease patients using 3D MRI scans and data augmentation techniques. The study aimed to address the research question of whether this approach could effectively detect structural changes indicative of Parkinson's disease and enhance diagnostic accuracy. The model utilized 3D brain MRI scans from the midbrain region and leveraged the domain of data augmentation to expand the dataset and improve generalizability. The testing accuracy of the model was evaluated with and without data augmentation to further understand it's applicability. The paper demonstrated the effectiveness of the proposed model in classifying Parkinson's disease patients from healthy controls, achieving a testing accuracy of up to 90.13% with data augmentation. The incorporation of data augmentation led to a significant 15.53% increase in accuracy compared to the model without augmentation. The utilization of 3D MRI scans allowed for a more comprehensive assessment of structural changes associated with the disease, and it is intuitive to believe that shuch efficient predictions can facilitate earlier treatment and better patient outcomes. © 2024 Elsevier B.V.. All rights reserved.

关键词： Magnetic resonance

来源：评论

学校读者我要写书评

暂无评论

Research on the Development of New Energy Vehicles Based on Multiple machine learning Models and the ARIMA Algorithm 6

Research on the Development of New Energy Vehicles Based on ...

引用

6th IEEE international conference on Power, Intelligent Computing and Systems, ICPICS 2024

作者： Miao, Xinhua Li, Binhong School of Computer Science and Engineering South China University of Technology Guangzhou China School of Electronic and Information Engineering South China University of Technology Guangzhou China

ISBN: (纸本)9798350374315

This paper investigates the development of new energy vehicles in China using a combination of multi-model machine learning and the ARIMA algorithm. Initially, four indicators and six influencing factors representing the development of new energy-electric vehicles in China were identified. Through matrix forwarding and data standardization, normalized data was obtained. The entropy weight method was employed to calculate weights, resulting in development scores from 2011 to 2022. Subsequently, seven models including linear regression, polynomial regression, decision tree regression, random forest, gradient boosting, BP neural network, and support vector machine (SVR) were established. Different training and testing set proportions (70%, 75%, and 80%) were used to determine the best-fitting effect. The model with the best fitting effect was identified, and the influencing factors were ranked based on their impact on the development of new energy-electric vehicles in China. Additionally, utilizing the four indicators, the LSTM model and ARIMA algorithm were employed to forecast, evaluate, and score the development indicators. Subsequently, based on 12 years of data from 2011 to 2022, the paper describes and predicts the development of new energy electric vehicles in China for the next 10 years. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

DDoS Detection using Deep learning

DDoS Detection using Deep Learning

引用

2022 international conference on machine learning and data engineering, icmlde 2022

作者： Kumar, Deepak Pateriya, R.K. Gupta, Rajeev Kumar Dehalwar, Vasudev Sharma, Ashutosh Computer Science and Engineering Department Maulana Azad National Institute of Technology Bhopal462003 India Computer Science and Engineering Department Pandit Deendayal Energy University Gandhinagar382007 India Department of Computer Science and Engineering University of Petroleum and Energy Studies Dehradun248007 India

The network's infrastructure becomes more vulnerable to cyber-attacks as the number of services offered through the internet expands. The complexity of "Distributed Denial-of-Service (DDoS)" threats on the internet has recently increased, posing a challenge to typical protection systems. As a result, early identification and separation of network data is the most crucial part of protecting against DDoS threats. A "Long Short-Term Memory (LSTM)" based model is created in this study to identify DDoS threats on a sample of network traffic packets. LSTM is a deep learning technique that includes a feature selection and extraction algorithm. When trained, it updates itself;Even with a smaller number of data points, LSTM functions swiftly and correctly. Using the "CICDDoS2019 dataset" for training and testing, the suggested LSTM model can achieve an accuracy of up to 98 percent in the current work, and Deep learning exceeds machine learning on the CICDDoS2019 dataset. © 2022 Elsevier B.V.. All rights reserved.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Deep learning Forecasting: An LSTM Neural Architecture based Approach to Rainfall and Flood Impact Predictions in Bihar 2

Deep Learning Forecasting: An LSTM Neural Architecture based...

引用

2nd international conference on machine learning and data engineering, icmlde 2023

作者： Kumar, Guru Dayal Pradhan, Kalandi Charan Tyagi, Shekhar Indian Institute of Technology Indore School of Humanities and Social Sciences Indore452020 India Indian Institute of Technology Indore Discipline of Computer Science and Engineering Indore452020 India

The increasing prominence of natural disasters and the variability in climate change have underscored the significance of research in contemporary and prospective studies. This investigation zeroes in on floods, a ubiquitous natural calamity that plagues regions globally. Bihar stands out as a state exceptionally vulnerable to persistent and intense flooding, with a staggering 69.70 lakh hectares - equivalent to nearly 74 percent of its geographical expanse - enduring its detrimental consequences. The repercussions of such inundations are widespread, permeating multiple facets of life and erecting impediments to both the welfare and the developmental trajectory of local communities. Vital sectors, including infrastructure, agriculture, and livestock, bear the brunt of the damage, catalyzing the dislocation of innumerable households. In an agile response to these adversities, the state's administrative machinery has mobilized disaster response brigades, ensuring timely aid and succor to the distressed populace. To adeptly predict impending floods, this study harnesses data from 1991 to 2022, integrating pivotal metrics such as the 'Total Population affected (in lacs)', 'Mean Annual Rainfall', and 'Crop damage (in INR lakhs)'. By adopting an LSTM (Long Short-Term Memory) model, the research elucidates its findings via illustrative line plots, furnishing an accessible rendition of the flood trajectory predictions over the forthcoming five-year span. These predictive insights are instrumental for disaster management agencies, enhancing their strategic planning and readied responses to imminent flood events in Bihar. Capitalizing on these forecasts enables authorities to architect proactive interventions, ensuring reduced flood repercussions, bolstered community resilience, and an elevated state of disaster preparedness in the region. © 2024 Elsevier B.V.. All rights reserved.

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 comparison between geomembrane-sand tests and machine learning predictions

引用

GEOSYNTHETICS international 2025年第2期32卷 180-193页

作者： Tanga, A. T. Araujo, G. L. Silva Evangelista, F. Univ Brasilia Dept Civil & Environm Engn FT Brasilia DF Brazil

The interaction between soils and geosynthetics plays an important role in the applications of these materials for reinforcement in geotechnical engineering. The complexities of soil-geosynthetic interactions vary depending on the type and properties of both the geosynthetic and the soil. This paper introduces a machine learning approach, specifically a random forest algorithm, for predicting interface friction angles. The dataset comprises 495 interfaces involving geomembranes and sand, with fourteen influencing parameters recorded for each interface, influencing the shear strength outcome. In the analysis, Pearson's correlation coefficient is employed to measure the linear interdependence between each pair of input-input and input-output variables. Following the linear regression analysis, an optimized random forest is utilized to project the interface friction angle. The random forest algorithm divides the selected data into training and testing sets, and only 3% of the training set and 6% of the testing set exceed +/- 5 degrees from the actual records. The coefficient of determination (R-2) indicates strong agreement between the predicted and laboratory study friction angles, with R-2 = 0.93 for the training set and R-2 = 0.92 for the testing set. Consequently, the random forest algorithm demonstrates effectiveness in predicting interface friction angles.

关键词： Geosynthetics geomembrane interface friction angle machine learning random forest

来源：评论

学校读者我要写书评

暂无评论

Efficient Approach to Improve the Security of PDF Readers Using Transfer learning for Few Shots Sample Scenario 2

Efficient Approach to Improve the Security of PDF Readers Us...

引用

2nd international conference on machine learning and Autonomous Systems, ICMLAS 2025

作者： Bhardwaj, Sonam Dave, Mayank Dalal, Sumit School of Computer Science Engineering and Technology Bennett University Greater Noida India National Institute of Technology Department of Computer Engineering Kurukshetra India

ISBN: (纸本)9798331505745

PDF malware is a significant threat to computer security. The purpose of this study is to introduce a new approach for improving the security of PDF readers. The method utilizes transfer learning by leveraging existing models and a small number of labeled examples, even with limited training samples. The ResNet34 model has been modified for PDF malware detection by replacing the 2D and 3D channels with a 1D channel. Transfer learning is a technique that is employed to enhance the model by utilizing the labeled samples that are available in a scenario where only a few samples are provided. The evaluation of the PDFMal2022 dataset shows that our approach outperforms existing models. It achieves a detection accuracy of 91.6% on source data and 92.4% on target data. This approach effectively utilizes transfer learning and effectively mitigates the risks associated with PDF malware, thereby offering an improved security solution for PDF readers. © 2025 IEEE.

关键词： Computer viruses

来源：评论

学校读者我要写书评

暂无评论

Monitoring, classification and analysis of waste disposal sites using machine learning 2

Monitoring, classification and analysis of waste disposal si...

引用

2nd international conference on machine learning and data engineering, icmlde 2023

作者： Sharma, Kislaye Sood, Meenakshi National Institute of Technical Teachers Training and Research Chandigarh160019 India

Lack of planning and regulations around the landfills has resulted and continues to result in severe environmental damage to the immediate environment around the landfills. Our study systematically reviews the literature to understand different processes of monitoring and analysis of a waste disposal site. It further analyses a satellite footprint from Google Earth Engine, of the western part of India around the urban area of Bombay. For the satellite footprint, we compare different algorithms and satellites for detecting landfills using machine learning. We conduct a supervised classification for satellite images for Land Satellite Applied to Remote Sensing (LANDSAT) (2013 to 2023) and SENTINEL (2018 to 2023) using three different classification algorithms: CART (Classification and Regression Tree), Naive Bayes and SVM (Support Vector machine). The LANDSAT SVM model was generally the most stable and consistently performed well. The model consistently has one of the highest accuracy scores over the years, followed closely by SENTINEL SVM. The analysis can be replicated to other cities and other large-area studies, and can act as a pointer in doing further analysis of the landfill that can further be used to prevent the effects of the waste disposal site on its surrounding environment. © 2024 Elsevier B.V.. All rights reserved.

关键词： Land fill

来源：评论

学校读者我要写书评

暂无评论

Dzongkha Handwritten Digit Recognition using machine learning Techniques

Dzongkha Handwritten Digit Recognition using Machine Learnin...

引用

2022 international conference on machine learning and data engineering, icmlde 2022

作者： Adhikary, Prottay Kumar Dadure, Pankaj Saha, Pradipta Tawmo Pakray, Partha National Institute of Technology Assam Silchar India University of Petroleum and Energy Studies Dehradun India Chittagong University of Engineering and Technology Bangladesh

Handwritten digit recognition has recently gained importance, attracting many researchers due to its use in various machine learning and computer vision applications. As technology and science progressing, there is a need for a system to recognize the handwritten script in several real-time applications to reduce human effort. There a lot of work has been done on the recognition and generation of handwritten digits of high-resource languages such as English. However, insufficient work has been done on Dzongkha digits recognition, as Dzongkha digits are low-resource and more complex than English patterns. This paper aims to perform handwritten character recognition of Dzongkha digit using several machine learning techniques. The unavailability of the Dzongkha handwritten digit dataset is the prime motivation behind this work. To facilitates the recognition of Dzongkha handwritten digit, we have collected the data of Dzongkha handwritten digit from indigenous and non-indigenous people of Bhutan and provided the dataset for further research. Moreover, we have used several machine algorithms, including a support vector machine, K-nearest neighbor, and decision tree. Among these algorithms, the support vector machine classification algorithm has achieved a remarkable result with an accuracy of 98.29%. © 2023 The Authors. Published by Elsevier B.V.

关键词： Character recognition

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：