检索结果-内蒙古大学图书馆

2nd IEEE International Conference on Emerging Research in Computational science, ICERCS 2024

作者： Maragatham, T. Vinodhini, B. Abineshwar, M.K. Kongu Engineerning College Department of Computer Technology-PG Erode India SNS College of Technology Department of Computer Science and Engineering Coimbatore India

ISBN: (数字)9798331534967

ISBN: (纸本)9798331534950

The application of machine learning techniques for the classification of sleep stages based on electroencephalogram (EEG) data has experienced substantial advancements in recent years (SSC). Nonetheless, the efficacy of these models is largely contingent upon the availability of extensive labeled datasets for training, which limits their applicability in real-world scenarios. In such contexts, sleep research facilities can generate significant volumes of data;however, the process of labeling this data can be both resource-intensive and time-consuming. A prominent strategy to mitigate the challenge of insufficient labels is the adoption of the Reinforcement Learning (RIL) paradigm, which has seen a surge in interest recently. This research aims to evaluate the extent to which RIL can enhance the performance of existing SSC models within a limited-label environment. Conduct a comprehensive analysis across three SSC datasets and find that competitive results can be attained by optimizing pretrained SSC models with merely 5% of labeled data, in contrast to traditional supervised training utilizing complete labeling. Furthermore, self-supervised pretraining enhances the robustness of SSC models against challenges associated with domain shifts and data imbalance. In the context of limited labeled data, this study explores the potential of self-supervised pretraining to improve the performance of contemporary sleep stage classification models. © 2024 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

SMART AGRICULTURE: INTEGRATING AIR QUALITY MONITORING WITH DEEP LEARNING FOR PROCESS OPTIMIZATION*

引用

Scalable Computing 2025年第3期26卷 1005-1016页

作者： Shobana, J. Subramanian, A Venkata Balamurugan, P. Perumal, Sivakumar Sankari, V. Eldho, K.J. Nareshkumar, R. Department of Data Science and Business Systems School of Computing College of Engineering and Technology SRM Institute of Science and Technology Tamilnadu Kattankulathur India Department of Computer Science and Engineering GITAM University Bengaluru India Department of Computer Science and Engineering J N N Institute of Enginering India Saveetha university Chennai India Department of Computer Science and Engineering Sasi Institute of Technology and Engineering Andhra Pradesh Tadepalligudem India Department of Artificial Intelligence and Data Science K.Ramakrishnan College of Engineering Kariyamanickam Rd Tamil Nadu Samayapuram India PG and Research Department of Computer Science Mary Matha Arts and Science College Kerala Mananthavady India Department of Networking and Communications School of Computing College of Engineering and Technology SRM Institute of Science and Technology Tamilnadu Kattankulathur India

Modernization and intense industrialization have led to a substantial improvement in people’s quality of life. However, the aspiration for achieving an improved quality of life results in environmental contamination. A primary consequence of environmental degradation is air pollution, resulting from rising levels of poisonous chemicals in the atmosphere, which may induce detrimental health conditions in humans. It is harmful to both humans and agriculture. Given that the effects of air pollution on plants may not be readily apparent, it is important to analyse the necessary data and compute the outcomes. Farmers prioritise on pests and plant diseases, frequently neglecting the detrimental impacts of air pollution. Some plant species can withstand high amounts of pollution from suspended particulate matter and accumulated gases, while others are more susceptible to harm. Therefore, plants’ reaction to air pollution is influenced by the kind of harmful compounds, their levels, and the plant’s susceptibility to them. The LSTM +CNN Proposed Ensemble method may be used to analyse the impact of air pollution on agriculture by examining trends in crop production over time and predicting which crop is more resistant based on the pollution data. The initiative created for this aim may assist farmers in determining the most suitable crop to cultivate in their fields to minimize the impact of air pollution on agricultural yield. The findings show deep learning algorithms correctly predict hourly pollutant concentrations such as carbon monoxide, sulphur dioxide, nitrogen dioxide, ground-level ozone, and particulate matter 2.5, along with the hourly Air Quality Index (AQI) for California. A proposed model used test RMSE values as a measure to evaluate prediction performance, achieving the best possible results. © 2025 SCPE.

关键词： Nitrogen oxides

来源：评论

学校读者我要写书评

暂无评论

Hyperspectral Images for Crop Prediction using Machine and Deep Learning Models 3

Hyperspectral Images for Crop Prediction using Machine and D...

引用

3rd International Conference on Electronics and Renewable Systems, ICEARS 2025

作者： Mahalakshmi, R. Kumutha, K. Sakthivanitha, M. Lakshmi, R. Bagavathi Sirajudeen, Mohamed Padmanabhan, Sankar Vels Institute of Science Technology & Advanced Studies Department of Computer Applications-PG Tamil Nadu Chennai India Vels Institute of Science Technology Advanced Studies Department of Computer Applications-PG Tamil Nadu Chennai India Vels Institute of Science Technology & Advanced Studies Department of Computer Application Tamil Nadu Chennai India Vels Institute of Science Technology & Advanced Studies Department of Information Technology Tamil Nadu Chennai India Nilgiri College of Arts and Science Pg and Research Department of Computer Science Tami Nadu The Nilgiris India Hindustan Institute of Technology and Science Department of Electronics and Communication Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798331509675

Crop classification is essential for local and national governments to make informed agricultural decisions. Remote sensing technology has made it possible to employ high-resolution hyperspectral images (HSIs) for land cover classification for decades. Machine Learning (ML) and Deep Learning (DL) are becoming more popular for HSI categorization due to advances in processing capacity and technology. HSIs can accurately identify crop types due to their narrow and continuous spectral band reflection. This study compares traditional machine learning (ML) models like Support Vector Machines (SVM) and Random Forest (RF) to deep learning (DL) models like Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN) for hyperspectral image classification (HSI). The HSI categorization was evaluated using performance criteria such as accuracy, precision, recall, and the F1-Score. CNN achieved the highest accuracy of 96%, demonstrating that it is the most reliable solution for complex HSI classification tasks because it successfully captures spatial and spectral data. © 2025 IEEE.

关键词： Classification Deep Learning(DL) Hyperspectral Images(HSI) Machine Learning(ML)

来源：评论

学校读者我要写书评

暂无评论

Epileptic Seizure Recognition using Machine Learning Algorithms 2

Epileptic Seizure Recognition using Machine Learning Algorit...

引用

2nd International Conference on Self Sustainable Artificial Intelligence Systems, ICSSAS 2024

作者： Jamunadevi, C. Arul, P. Dineshkumar, M.D. Pg Kongu Engineering College Department of Computer Technology Tamilnadu Erode India Department of Computer Science Tiruchirappalli620 022 India

ISBN: (纸本)9798350368413

The project entitled 'Epileptic Seizure Recognition Using Machine Learning Algorithms' is used to identify the epileptic seizure at the early stage. Epileptic seizure is a significant health concern affecting millions worldwide, necessitate precise and timely identification for effective medical intervention and management. The present system for epileptic seizure recognition often relies on traditional methods, including expert analysis of electroencephalogram (EEG) data and manual review. While these methods have proven effective, they are labor-intensive, prone to subjectivity and may not be suitable for real-time monitoring. This gap led to the proposed machine learning-based approach which offer potential seizure recognition, allowing for more timely and accurate intervention. This study propose a novel approach for epileptic seizure recognition by combining dimensionality reduction techniques, namely Principal Component Analysis (PCA) and t-Distributed Stochastic Neighbor Embedding (t-SNE), with the K-Means clustering algorithm, then integrate this unsupervised clustering approach with four popular machine learning algorithms: Support Vector Machine classifier, Logistic Regression, Naive Bayes classifier and Random Forest classifier to enhance the performance of seizure recognition. Each cluster is labeled as either seizure or non-seizure based on the majority class within it. The method involves the development and implementation of these algorithms within the context of epileptic seizure. The primary objective is to explore the feasibility and performance of these classifiers, aiming to enhance the efficiency of seizure recognition system. The work emphasizes the potential of machine learning in automating the identification of epileptic seizures, ultimately contributing to improved patient care and medical diagnosis. The improved accuracy of 95% is achieved by Random Forest model. © 2024 IEEE.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Detection of Acute Lymphoblastic Leukemia Using a Novel Bone Marrow Image Segmentation

引用

Tsinghua science and technology 2025年第2期30卷 610-623页

作者： M.Anline Rejula Ben M Jebin Ravi Selvakumar S.Amutha Eberlein George Department of Computer Applications-PG Scott Christian College(Autonomous)Nagercoil 629003India Department of Computer Science Malankara Catholic CollegeMariagiri 629153India School of Computer Science and Engineering Vellore Institute of TechnologyChennai 600127India Department of Pediatrics Government Medical College and HospitalGovernment of Tamil NaduNamakkal 637001India

In our study,we present a novel method for automating the segmentation and classification of bone marrow images to distinguish between normal and Acute Lymphoblastic Leukaemia(ALL).Built upon existing segmentation techniques,our approach enhances the dual threshold segmentation process,optimizing the isolation of nucleus and cytoplasm *** is achieved by adapting threshold values based on image characteristics,resulting in superior segmentation outcomes compared to previous *** address challenges,such as noise and incomplete white blood cells,we employ mathematical morphology and median filtering *** methods effectively denoise the images and remove incomplete cells,leading to cleaner and more precise ***,we propose a unique feature extraction method using a hybrid discrete wavelet transform,capturing both spatial and frequency *** allows for the extraction of highly discriminative features from segmented images,enhancing the reliability of *** classification purposes,we utilize an improved Adaptive Neuro-Fuzzy Inference System(ANFIS)that leverages the extracted *** enhanced classification algorithm surpasses traditional methods,ensuring accurate identification of acute lymphoblastic *** innovation lies in the comprehensive integration of segmentation techniques,advanced denoising methods,novel feature extraction,and improved *** extensive evaluation on bone marrow samples from the Acute Lymphoblastic Leukemia Image DataBase(ALL-IDB)for Image Processing database using MATLAB 10.0,our method demonstrates outstanding classification *** segmentation accuracy for various cell types,including Band cells(96%),Metamyelocyte(99%),Myeloblast(96%),***(97%),***(97%),and Neutrophil cells(98%),further underscores the potential of our approach as a high-quality tool for ALL diagnosis.

关键词： Adaptive Neuro-Fuzzy Inference System(ANFIS) blood cells segmentation leukemia classification

来源：评论

学校读者我要写书评

暂无评论

Backpropagation Shuffled Leaping Neural Network Implementation in Classification of DDoS Packet Flow Traffic in Data Mining

引用

SN computer science 2024年第8期5卷 1131页

作者： Umamaheswari, N. Kumutha, K. Kalaivani, M.S. Ramya, R. Tagore College of Arts and Science Tamilnadu Chennai India Department of Computer Application- PG Vels Institute of Science Technology and Advanced Studies Tamilnadu Chennai India Department of Computer science and Engineering Bannari Amman Institute of Technology Tamil Nadu Erode India

All web applications remember the ultimate goal of storage services, Distributed Denial of Service (DDoS), to achieve high security from various attacks. The client-server application reduces fees and runs the elite registration gadget, while the notable part assumes that it is manufactured using a grant application. Analysis of the traceback data is difficult in the previous system, and then it containsa common DDoS attack *** DDoS attacks involving different network layers such as (SIDDoS (SQL (Structured Query Language) injection), HTTP (HyperText Transfer Protocol) flood, TCP (Transmission Control Protocol) are recommended here as there are signs that new datasets of common datasets are not being collected in the proposed system. The DDoS attack classification consists of three main steps: preprocessing, trace out the source IP address, Backpropagation Shuffled Leaping Neural Network (BSLNN) based on maintaining the specifications’ integrity. The preprocessing is the first step based on the Gabor Filter used to remove the data’s noise and the second Adaboost Random Optimal Selection method to analyzethe packet flow’s relative frequency. The third step is the Backpropagation Shuffled Leaping Neural Network (BSLNN) classification of traceback data maintaining the specifications analysis’s integrity. The proposed system achieves good periodic study of packet flow accuracy and time complexity. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Adaboost random optimal selection Backpropagation Shuffled Leaping Neural Network (BSLNN) Gabor filter Preprocessing Trace out the source IP address

来源：评论

学校读者我要写书评

暂无评论

Early Prediction of Chronic Obstructive Pulmonary Disease: A Deep Transfer Learning Approach 2

Early Prediction of Chronic Obstructive Pulmonary Disease: A...

引用

2nd International Conference on Self Sustainable Artificial Intelligence Systems, ICSSAS 2024

作者： Rukumani Khandhan, C. Gothai, E. Arun, G. Bharathi Priya, R. Kongu Engineering College Department of Computer Science & Engineering Perundurai Erode638060 India Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Computer Science & Pg Chennai600062 India Kongu Engineering College Department of Computer Technology -PG Tamil Nadu Perundurai638060 India

ISBN: (数字)9798350368413

ISBN: (纸本)9798350368413

Chronic Obstructive Pulmonary Disease (COPD) is a prevalent, crippling lung ailment that often progresses undetected until its advanced stages, leading to significant morbidity and mortality. Early prediction and interference are crucial to improving patient outcomes. Here, a novel approach for the early prediction of COPD using deep transfer learning is proposed. Three cutting edge models from deep transfer learning, namely Inception, ResNet, and VGGNet, are trained to extract and classify features from audio recordings of breathing sounds. These models are fine-tuned on a dataset consisting of sounds from both healthy individuals and those with COPD, along with six other lung disorders. The extracted features are used to predict the presence of COPD, enabling early detection and intervention. The outcome of the proposed methodology demonstrates the efficiency of the model's capability to predict COPD, with the deep transfer learning models achieving high precision in distinguishing COPD patients from non-COPD individuals. This approach shows the potential for cost-effective and early prediction of COPD, facilitating timely interventions and improved management of the disease. © 2024 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

Embedded Deep NN with Convolution NN-ID to Binominal Sentiment Prediction 9

Embedded Deep NN with Convolution NN-ID to Binominal Sentime...

引用

9th International Conference on science, technology, Engineering and Mathematics, ICONSTEM 2024

作者： Gokila, S. Rajeswari, S. Helen, D. Lakshna, A. Hindustan Institute of Technology And Science Department of Computer Applications Chennai India Shrimathi Devkunvar Nanalal Bhatt Vaishnav College For Women Pg Department of Computer Science Chennai India Srm Institute of Science And Technology Department of Computer Applications Chennai Kattankulathur India Jeppiaar Engineering Collge Department of Computer Science Engineering Chennai India

ISBN: (纸本)9798350365092

Objective: The objective is to develop a generalized deep learning system for sentiment analysis in a feedback system. This implies an intention to create a model that can effectively analyze sentiment across different domains or datasets. Methodology: It is proven that the deep learning systems are playing a major role in NLP, but still there is a need of enhancement to make the prediction system a perfect one. The Convolution Neural Network (CNN) could emphasize its ability to capture spatial dependencies in textual data and the Deep Neural Network(DNN) fetches the feature in text with varying semantics. In this context the proposed work Embed the Deep Neural Network with Convolution Neural Network in a three-layered ID architecture(EDNN with CNN-ID.) The model is enhanced in generalizing input-shape, kernel, channel, and filter parameters of the convolution layer. It produces remarkable results in sentimental analysis. The work is experimented with a feedback system from three different domains like Movie Review, Doctor Treatment Review, Product Review. Result: The EDNN with CNN-ID produces accuracy 93%, 91% and 91% for the three datasets © 2024 IEEE.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Based Intrusion Detection for IoT Networks 4

Deep Learning Based Intrusion Detection for IoT Networks

引用

4th International Conference on Ubiquitous Computing and Intelligent Information Systems, ICUIS 2024

作者： Ananthi, P. Nirmaladevi, K. Mothika, G. Kongu Engineering College Department of Computer Technology-PG Tamilnadu Erode638060 India Madanapalle Institute of Technology & Science Department of Computer Applications India Kongu Engineering College Erode India

ISBN: (纸本)9798331529635

Intrusion detection is crucial for securing IoT networks amid the rapid proliferation of devices, posing significant security challenges. This study offers a unique intrusion detection model for IoT deep learning methods used in networks include Convolutional Neural Networks (CNN), TabNet, and the Transient Search Optimization (TSO) method. The project starts by developing and evaluating distinct intrusion detection components. CNN, specializing in feature extraction, analyzes network traffic for potential intrusions. TabNet, known for interpretability and effectiveness with structured data, captures intricate relationships. The novel TSO algorithm improves the system's ability to detect temporary anomalies. Each component's performance is assessed individually, highlighting unique strengths. TabNet excels in structured IoT data pattern identification, surpassing CNN. The TSO algorithm strengthens temporary anomaly recognition, enhancing IoT network security. An ensemble technique combines CNN and TabNet predictions, reducing false positives and negatives to elevate overall detection accuracy. The ensemble, using both CNN and TabNet, achieves an impressive accuracy rate exceeding 99%, demonstrating significant gains in intrusion detection performance. © 2024 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

Detection of Conjunctive Eyes Outbreak using Deep Learning Approaches: A Literature Review 1

Detection of Conjunctive Eyes Outbreak using Deep Learning A...

引用

1st IEEE International Conference on Advances in Computing, Communication and Networking, ICAC2N 2024

作者： Pahwa, Seema Kaur, Amandeep Dhiman, Poonam Chitkara University Institute of Engineering and Technology Chitkara University Punjab India Government PG College Department of Computer Science India

ISBN: (纸本)9798350356816

Eye illness is a common medical ailment that affects the pupil, iris, and sclera, as well as other critical organs. Well-known disorders that fall under this category include cataract and conjunctivitis. Conjunctivitis is an inflammatory response in the conjunctival tissue, the most common eye condition globally and a significant contributor to global health and economic issues. It is caused by various bacterial, viral, allergic substances, and self-inflammatory sensitivities, resulting in acute or persistent symptoms. In this study, several Deep Learning (DL) models that have previously been trained to recognize the conjunctivitis virus are compared. Four metrics - Precision, Recall, F1-score, and Accuracy - for assessing the results of deep learning models are compared in this literature review. The most effective models are selected based on achievable outcomes, improving overall performance in subsequent studies. Along with different CNN technologies, other technologies like VGGNet, ResNet, Inception-V3, InceptionResNet, Xception, EfficientNet, deep convolution neural network (DCNN), and support vector machine (SVM) are also analyzed. Data from hospital, Kaggle, shutter stock, and publicly available case reports are also included in the analysis. While a thorough examination was conducted d using a limited dataset, this review aims to inform researchers on the application of deep learning models for early identification of conjunctivitis eyes. It emphasizes the need for a larger dataset with more images from various locations worldwide for more accurate diagnosis. © 2024 IEEE.

关键词： Support vector machines

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：