检索结果-内蒙古大学图书馆

international conference on Intelligent Systems and Sustainable Computing, ICISSC 2022

作者： Ashwini, P. Suguna, N. Vadivelan, N. Research Scholar Department of Computer Science and Engineering Faculty of Engineering and Technology Annamalai University Chidambaram India Associate Professor Department of Computer Science and Engineering Faculty of Engineering and Technology Annamalai University Chidambaram India Professor Department of Computer Science and Engineering Teegala Krishna Reddy Engineering College Hyderabad India

ISBN: (纸本)9789819947164

Breast cancer is today’s deadly health issue which causes high mortality in woman worldwide. The preliminary detection and classification may help for proper treatment of the same. Understanding the causes of this cancer using traditional machine learning techniques misread feature extraction are leading to a complication. Traditional machine learning models are best suited for feature-based raw data. The novel deep learning techniques have been introduced for diagnosis of breast abnormalities using various imaging modalities like mammogram, magnetic resonance imaging (MRI) and ultrasound with high accuracy. This survey focuses on challenges of classical machine learning models and supervene efficient prediction models using novel deep learning techniques. This review presents comparison analysis of traditional machine learning and deep learning models. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

SRCPT: Spatial Reconstruction Contrastive Pretext Task for Improving Few-Shot Image Classification 24

SRCPT: Spatial Reconstruction Contrastive Pretext Task for I...

引用

16th international conference on machine learning and Computing (ICMLC)

作者： Wang, ZhenBang Duan, PengFei Rong, Yi Wuhan Univ Technol Sch Comp Sci & Artificial Intelligence Wuhan Hubei Peoples R China Wuhan Univ Technol Sanya Sci & Educ Innovat Pk Sanya Hainan Peoples R China

ISBN: (纸本)9798400709234

Self-supervised learning (SSL) has been widely applied in the pretraining phase of models. Among these SSL methods, the various data augmentation used in contrastive learning for constructing positive and negative sample pairs conveniently contribute to alleviating the issue of data scarcity in few-shot learning (FSL) tasks. Therefore, many approaches have introduced contrastive learning into FSL tasks. However, most of these methods only utilize the global embedding information of the entire image, making it challenging to capture and fully leverage the local visual information and structural details of image samples. To address this, we proposes a novel Spatial Reconstruction Contrastive Pretext Task (SRCPT) to enhance the FSL training objective. By constructing a two-branch network, the model can use local patches of the image for feature map reconstruction and employ spatial reconstruction weights to create a contrastive learning objective. The enhanced FSL objective of SRCPT encourages the model to capture more transferable spatial structures and local feature information, enabling the model to adapt well to new categories even with a few samples. Extensive experiments demonstrate that our proposed SRCPT method achieves state-of-the-art performance in three popular benchmark datasets across three types of few-shot image classification tasks.

关键词： few-shot learning local spatial feature reconstruction contrastive learning

来源：评论

学校读者我要写书评

暂无评论

Automatic Text Document Classification by Using Semantic Analysis and Lion Optimization Algorithm 2nd

Automatic Text Document Classification by Using Semantic Ana...

引用

2nd international conference on Computational Intelligence in machine learning, ICCIML 2022

作者： Ranjan, Nihar M. Prasad, Rajesh S. Mane, Deepak T. Information Technology JSPM RSCOE Pune India Computer Engineering MIT Art Design and Technology University Pune India Computer Engineering Vishwakarma Institute of Technology Pune India

ISBN: (纸本)9789819979530

Text mining is a popular research area in the field of computer science and engineering that enables the processing of natural language which has applications in the area of aerospace, biomedical, and so on. Text mining unsheathes the unknown information present in the data such that the extraction of the data seems to be effective. Text classification is a subdomain of the text mining that plays a major role in labelling the documents based on their semantic meaning and context. Different machine learning algorithms are available to classify the available text documents. The main contribution of this paper is use of semantic analysis with Lion Optimization Algorithm and Neural Network architecture. The semantic analysis technique is used for the text classification through semantic keywords rather than using independent features of keywords in the documents. Lion Optimization Algorithm is used to adjust the weight of the Neural Network to maximize the efficiency of the classifier. Two well-known open source dataset namely 20 Newsgroups and Reuters-21578 are used for the experimentation and evaluate the performance of the classification algorithms. Significant improvement in all three performance parameters in terms of accuracy, specificity, and sensitivity is observed. The maximum values observed with our proposed algorithm are 91.86, 95.54, and 84.96 for accuracy, sensitivity, and specificity, respectively. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： machine learning

来源：评论

学校读者我要写书评

暂无评论

machine learning Based Emotion Recognition in a Digital learning Environment 25th

Machine Learning Based Emotion Recognition in a Digital Lear...

引用

25th international conference on Interactive Collaborative learning (ICL) / 51st IGIP international conference on engineering Pedagogy

作者： Ivleva, Natalja Pentel, Avar Dunajeva, Olga Justsenko, Valeria Virumaa Coll Tallinn Univ Technol Jarvekula Tee 75 EE-30322 Kohtla Jarve Estonia

ISBN: (纸本)9783031268755;9783031268762

In this paper, we develop a method to monitor the emotional state of students and teachers during the study process based on facial expressions using machine learning and deep learning techniques. We describe the implementation of the created emotion detection model into the learning process as a web application to determine the emotional state of students and teachers in a digital learning environment in near real-time. Several training methods and models were examined using Python and Keras Tensorflow library and the results were compared against the classifiers SupportVector machine, Random Forest, and Convolutional Neural Networks (CNN). The average recognition rate of the best model is about 96% and the proposed system is able to recognize emotions in near real-time.

关键词： Facial emotion recognition Monitoring system learning environment

来源：评论

学校读者我要写书评

暂无评论

Farmer's Assistant in Agricultural Sector by using machine learning and Deep learning

Farmer's Assistant in Agricultural Sector by using Machine L...

引用

2022 OPJU international Technology conference on Emerging Technologies for Sustainable Development, OTCON 2022

作者： Jadhav, Rohini Bhaladhare, Pawan Sandip University School of Computer Science and Engineering Nashik India

ISBN: (纸本)9781665492942

When raising crops, farmers encounter several difficulties, including erratic irrigation, subpar soil, etc. A significant portion of farmers, particularly in India, lack the knowledge necessary to choose the right crops and fertilizers. Additionally, both farmers and consumers suffer large losses when crops fail due to illness. Testing the soil is important since it enables the measurement of soil fertility and, consequently, the forecast of crops. The pH of a soil is a gauge of its acidity and alkalinity. pH scales run from 0 to 14, with 7 considered neutral, acidic below that, and alkaline beyond that. We have suggested a system that will have a pH-reading device, and based on the soil's pH, we will estimate the amount of nitrogen (N), phosphorus (P), and potassium (K) in the soil. Despite recent advancements in the automated identification of certain diseases using machine learning strategies, the use of Deep learning has not been adequately investigated. Due to the high quality of the training data, a lack of processing power, and the models' limited generalizability, these models are also difficult to use. In order to solve some of these problems and perhaps enhance crop productivity, we develop an open-source, user-friendly online application. We support recommendations for crops, fertilizers, and plant disease prevention in particular. We think that by doing this, farmers will be able to produce more crops with a given amount of land, and crop damage will be less likely to occur. © 2023 IEEE.

关键词： Fertilizers

来源：评论

学校读者我要写书评

暂无评论

Environmental Analysis using Remote Sensing data

Environmental Analysis using Remote Sensing Data

引用

2023 international conference on Recent Advances in Science and engineering Technology, ICRASET 2023

作者： Aakash, D. Jaraline Kirubavathy, K. Bai V, Thulasi Kcg College of Technology Department of Electronics and Communication Chennai India

ISBN: (纸本)9798350306927

To predict various environmental determinants using the remote sensing data becomes mandate research in the current trend. Two decades of remote sensing data (2000-2022) LANDSAT 7 images are downloaded and estimated various environmental parameters using QGIS with the help of standard formula. The extracted parameters are collected and analyzed using various machine learning algorithm. The missing data dealt by using Gradient Boost algorithm and created a cleaned datasheet. These datasets are trained and tested using nine various machine learning algorithms and predicted the future environmental determinants like NDVI, NDWI, NDMI, NDBI, and LST until 2030. SARIMAX algorithm produced 95.73% of accuracy in predicting future environmental determinants. These analysis help to have a better understand of environmental trends and changes, which could help with environmental planning and making real-time decision-making that can be shared globally via the Internet. © 2023 IEEE.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Barriers and Challenges in Clinical Application of machine learning Algorithms

Barriers and Challenges in Clinical Application of Machine L...

引用

2024 international conference on Information and Communication Technology for Development for Africa, ICT4DA 2024

作者： Abdurahman, Hamza Shukri Yimer, Amare Kassaw Bahir Dar University Bahir Dar Institute of Technology Bahir Dar Ethiopia

ISBN: (纸本)9798331527792

According to the World Health Organization's 2022 report, pneumonia is the primary cause of death for children, with over five million under-five deaths, while Nigeria, India, Pakistan, the Democratic Republic of the Congo, and Ethiopia account for half of these deaths. Currently, this disease is diagnosed manually by a radiologist using a chest x-ray image. However, through this method, the identification of pneumonia is difficult due to the overlapping features of various conditions of the lower respiratory tract. Recently, there have been plenty of machine learning models developed to diagnose pneumonia. Nevertheless, none of these models were used for support in the diagnosis of pneumonia in a healthcare setting. By collecting chest CXR images from local healthcare facilities as well as global sources and creating a CNN model, the main barriers and challenges associated with machine learning algorithms in clinical applications were identified in this work. The key barriers and challenges were identified as data, algorithms and clinical utilities, strategy and financing, and technology. The association between clinical diagnosis and machine learning algorithms was also investigated, including the radiologist's attitude toward machine learning, performance analysis on pneumonia detection, limitations of clinical diagnosis, limitations of machine learning diagnosis, and machine learning-aided diagnosis. Finally, a clinical diagnosis of pneumonia supported by machine learning algorithms is recommended as the only viable option for accurate treatment. © 2024 IEEE.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Deep Residual SVM: A Hybrid learning Approach to obtain High Discriminative Feature for Land Use and Land Cover Classification

Deep Residual SVM: A Hybrid Learning Approach to obtain High...

引用

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

作者： Kumari, Neha Minz, Sonajharia School of Computer and Systems Sciences JNU New Delhi India

Classification of multispectral images is impacted by challenges such as inadequate training samples, limited ground truth, and complex spatiotemporal dependencies. The accuracy of classifiers due to the lack of training samples is also compounded by the class imbalance problem in spatial analytics. This paper proposes a novel idea of exploiting the deep residual networks trained on millions of images for high discriminative feature representations. These derived representations are classified using bias-corrected Adam optimizer-based Support Vector machine classifiers. The intuition behind this approach is the significance of representations in the last layers of the pre-trained network that contributes to the classification accuracy. These encapsulated representations from the pre-trained network can outperform traditional feature representations. Residual networks solved the vanishing gradients problem in deep learning and improved classification accuracy. Hence, this work explores the combined potential of the representation power of deep residual pre-trained networks and the classification ability of Support Vector machines. The model implementation experiments have been conducted using two publicly available benchmark datasets, Eurosat and UC Merced for Land Use and Land Cover Classification. The proposed model DRSVM (Deep Residual Support Vector machines) demonstrated higher efficiency in terms of computational parameters and time complexity than conventional convolutional neural networks, pre-trained networks, and Support Vector machines with comparable accuracy. data augmentation techniques are used further for enhancing the performance of the model. Conventional supervised deep learning algorithms like CNN overfit in dense layers in case of inadequate training data. This hybrid approach alleviates overfitting issues by eliminating dense layers and replacing the Softmax function with Support Vector machines for classification. © 2022 Elsevier B.V.. All righ

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Noninvasive prediction of metastasis in esophageal cancer using ensemble-based feature selection

引用

international JOURNAL OF SYSTEM ASSURANCE engineering AND MANAGEMENT 2024年 1-11页

作者： Aalam, Syed Wajid Ahanger, Ab Basit Assad, Assif Macha, Muzafar A. Bhat, Muzafar Rasool Islamic Univ Sci & Technol Dept Comp Sci 1 Univ Ave Pulwama 192122 Jammu & Kashmir India Islamic Univ Sci & Technol Dept Comp Sci & Engn 1 Univ Ave Pulwama 192122 Jammu & Kashmir India Islamic Univ Sci & Technol IUST Watson Crick Ctr Mol Med 1 Univ Ave Awantipora 192122 Jammu & Kashmir India

Esophageal cancer (EC) is a significant health concern worldwide, and predicting its metastatic progression is essential for planning effective treatments. Histopathological intervention is the gold standard for diagnosing Esophageal Cancer Metastasis (ECM). However, we introduced a noninvasive, data-driven approach utilizing different machine learning (ML) algorithms on clinical data from TCGA to predict the risk of ECM. Among these algorithms, CatBoost stands out, achieving a 73% accuracy and a 75% area under the curve (AUC) using 5-fold cross-validation with a standard deviation of 4% among 5-folds. We visualized feature importance graphs and feature correlations to explain the decision-making of ML models. Our findings highlight associations between height, weight, age, alcohol consumption, the number of packs smoked, tumor location, and the risk of metastasis in EC patients. This approach offers a promising way to enhance EC metastasis prediction while minimizing invasive procedures.

关键词： Metastasis TCGA machine learning Feature importance Esophageal cancer

来源：评论

学校读者我要写书评

暂无评论

Classification of Phishing Website Using machine learning Based Proposed Ensemble Model

Classification of Phishing Website Using Machine Learning Ba...

引用

2022 OPJU international Technology conference on Emerging Technologies for Sustainable Development, OTCON 2022

作者： Pathak, Prakash Shrivas, Akhilesh Kumar Bilaspur India

ISBN: (纸本)9781665492942

Phishing is the process of trying to get sensitive data from unauthorized persons, such as usernames, passwords, credit card numbers, and debit card information. Since there is no one method to properly reduce every vulnerability due to the problem of phishing. There are many techniques are frequently utilized to reduce specific attacks. The main aim of this research work is to develop a robust machine learning based model that can detect and classify URL based phishing data. This paper proposed a new ensemble model that is a combination of Decision Tree (DT), Support Vector machine (SVM), and Logistic Regression (LR) using the voting scheme ensemble technique. The proposed ensemble model compared with other individual classifiers like Decision Tree (DT), K-Nearest Neighbors (KNN), Support Vector machine (SVM), Gaussian Naive Bayes (GNB), Logistic Regression (LR) techniques, and ensemble classifiers like Extreme Gradient Boosting (XGBoost), Adaptive Boosting (AdaBoost) where our proposed ensemble model achieved remarkable performance of 99.02% accuracy with 10-fold cross validation technique. Finally, machine learning based classification techniques are suitable and robust methods that handle the dynamic nature of phishing techniques and provide an accurate method of classification. © 2023 IEEE.

关键词： Decision trees

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：