检索结果-内蒙古大学图书馆

Streamlined Lung Abnormality Identification with Explainable AI: A Unified Framework for Chest CT and X-Ray Analysis

引用

Procedia computer science 2025年 258卷 467-475页

作者： R. Renugadevi Associate Professor Department of Computer Science and Engineering Saveetha Engineering College Saveetha Nagar Thandalam Chennai 602105 India

Based on CT and chest X-ray images, a new automatic classification method for lung anomaly identification is introduced. The issue of an unbalanced and limited available dataset is addressed by data augmentation. Various preprocessing methods are implemented to eliminate noise. Original CCT model serves as a foundation of this model and it is undergoing an ablation study with a 32 x 32 image CT scan dataset for best configuration determination. The model is then trained on an X-ray dataset for testing its performance in different modalities and performance is compared with six pre-trained models. Classic models showed mediocre outcomes with test accuracies between 40% and 78% for CT and 50% to 75% for X-ray with a large number of training cycles. On the other hand, the proposed model showed outstanding performance with test accuracies of 99.70% for CT and 95.30% for X-ray. By progressively shrinking the dataset of training images, the robustness of the model is assured, demonstrating that the model will still be able to perform well despite the reduction in data. The decisions of the model are explained through the explainable AI method Grad-CAM, which creates color visualizations to enable medical practitioners to make swift and certain judgments. This paper solves issues with training time and computational complexity by integrating deep learning methods with image preprocessing to identify lung abnormalities.

关键词： Lung Abnormality CT scan X ray CNN Artificial Intelligence

来源：评论

学校读者我要写书评

暂无评论

Twitter sentiment analysis using conditional generative adversarial network

引用

International Journal of Cognitive Computing in engineering 2024年第1期5卷 161-169页

作者： Mahalakshmi, V. Shenbagavalli, P. Raguvaran, S. Rajakumareswaran, V. Sivaraman, E. Department of Information Technology Sengunthar College of Engineering Tiruchengode Tiruchengode637205 India Assistant Professor Karunya Institute of Technology and Sciences Coimbatore India Assistant Professor Department of Computational Intelligence School of Computing SRM Institute of Science and Technology SRM Nagar Kattankulathur Kanchipuram Chennai Tamil Nadu 603203 India Assistant Professor Department of Computer Science and Design Erode Sengunthar Engineering College Tamil Nadu Thuduppathi India Department of Electrical and Computer Engineering Curtin University Miri Malaysia

Sentiment analysis, which aims to extract information from textual data indicating people's ideas or attitudes about a particular problem, has developed into one of the most exciting study issues in natural language processing (NLP) with the development of social media. Twitter is a social network with an extensive audience that expresses their thoughts and opinions clearly and readily. Due to the prevalence of slang phrases and incorrect spellings in short phrase styles, Twitter data analysis is more challenging than data analysis from other social networks. Automated feature selection still has several limitations, such as higher computing costs that rise with the number of characteristics. Deep learning, which is self-learned and more accurate at processing vast amounts of data, is utilized to overcome these challenges. This paper introduces a conditional generative adversarial network (GAN) for Twitter sentiment analysis, whereas a convolutional neural network (CNN) has been used to extract traits from Twitter data. Compared to existing works, the proposed work has outperformed in accuracy, recall, precision, and F1 score. The suggested method is the most accurate, with a classification accuracy of 93.33 %. © 2024

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

A Novel Ensemble Methodology to Validate Fuzzy Clusters of Big Data 4th

A Novel Ensemble Methodology to Validate Fuzzy Clusters of B...

引用

4th International Conference on Trends in Cognitive Computation engineering, TCCE 2022

作者： Sardar, Tanvir Habib Sarkar, Rashel Ahmed, Sheik Jamil Bandyopadhyay, Anjan Assistant Professor Department of CSE GITAM School of Technology GITAM University Bangalore India Associate Professor Department of Computer Science University of Science and Technology Meghalaya Ri-Bhoi India Assistant Professor School of Computer Science and Engineering & Information Science Presidency University Bangalore India Assistant Professor Kalinga Institute of Industrial Technology Odisha Bhubaneswar India

ISBN: (纸本)9789811994821

The clustering of datasets is a widely used technique in unsupervised machine learning. The cluster quality evaluation is a tricky problem because external validation is usually not possible for clustering. This happens due to the unavailability of external proof. Although there are many methods developed and experimented with to validate the results obtained from clustering, it is always preferred to use more than a few cluster validity measures. The big data usually contain a high percentage of noise in it, making it necessary to use some additional techniques to incorporate while clustering big data. In this work, we have clustered document big data using fuzzy logic-based enhancement of traditional K-Means and K-Medoids. This work has suggested the Ensembling of seven different cluster quality validity measures to determine the best quality of fuzzy clusters. The Reuters standard document dataset is clustered using different cluster numbers, and the proposed ensemble methodology is proven to determine optimal numbers of clusters. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

A novel enhanced lemurs optimization-based hybrid attention network for classifying arrthymia from ECG signal using optimal weighted feature

引用

Australian Journal of Electrical and Electronics engineering 2024年第3期21卷 311-335页

作者： Wajgi, Rakhi Brammya, G. Ramesh, Gopisetty Deotare, Vilas Vasudeo Govindasamy, Chinnaraj Preetha, N.S. Ninu Department of Computer Technology Yeshwantrao Chavan College of Engineering Nagpur India Department of Electronics and Communication Engineering Resbee Info Technologies Private Limited Chennai India Department of EIE CVR College of Engineering Mangalpalli India Professor in E&TC Savitribai Phule Pune University Pune India Department of Computer Science and Engineering Saveetha School of Engineering Kuthambakkam India

An arrhythmia is just a disease associated with irregular heart rhythm. Any kind of arrhythmia can be determined with an ECG test. However, this requires long and excellent-quality of ECG samples. This makes an affordable, reliable, and automated system for recognizing and diagnosing arrhythmias. To meet the aforementioned criteria, a new technique with the aid of an attention-aided deep learning approach is proposed to classify arrhythmia in this paper. "Higher-order statistical (HOS)" features are extracted from the original EEG signal and the deep features are obtained from the analyzed QRS complex signals and RR interval by means of a "One-Dimensional Convolution Neural Network (1DCNN)". The Risk Rate Enhanced Lemurs Optimization Algorithm (RRE-LOA) is utilized to modify the weight, and the extracted features are selected optimally before carrying out the feature selection followed by feature concatenation with weight fusion in order to generate the Weighted Fused Features (WFF). A range of indicators is used to compare the performance of the executed classification model with the traditional models. The results demonstrate that the proposed methodology for classifying arrhythmias offers an enhanced performance while classifying the arrhythmia thus aiding in faster treatment of the arrhythmia disease. ©, Engineers Australia.

关键词： Electrocardiograms

来源：评论

学校读者我要写书评

暂无评论

Levy Flight Adopted Particle Swarm Optimization-based Resource Allocation Strategy in Fog Computing

引用

Chinese Journal of Electronics 2023年

作者： Sharmila Patil(Karpe) Brahmananda S H Research Scholar Department of Computer Science and Engineering GITAM School of Technology GITAM Deemed University Professor Department of Computer Science and Engineering GITAM Bengaluru

The prevalence of the Internet of Things(Io T) is unsteady in the context of cloud computing, it is difficult to identify fog and cloud resource scheduling policies that will satisfy users’ Qo S need. As a result, it increases the efficiency of resource usage and boosts user and resource supplier profit. This research intends to introduce a novel strategy for computing fog via emergencyoriented resource allotment, which aims and determines the effective process under different parameters. The modeling of a non-linear functionality that is subjected to an objective function and incorporates needs or factors like Service response rate, Execution efficiency, and Reboot rate allows for the resource allocation of cloud to fog computing in this work. Apart from this, the proposed system considers the resource allocation in emergency priority situations that must cope-up with the immediate resource allocation as well. Security in resource allocation is also taken into consideration with this strategy. Thus the multi-objective function considers 3 objectives such as Service response rate, Execution efficiency, and Reboot rate. All these strategies in resource allocation are fulfilled by Levy Flight adopted Particle Swarm Optimization(LF-PSO). The evaluation is performed to determine whether the developed strategy is superior to numerous traditional schemes. The cost function attained by the adopted technique is 120, which is 19.17%, 5%, and 2.5%greater than the conventional schemes like GWSO, EHO,and PSO, when the number of iterations is 50.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Crop Yield Prediction Based on Weather and Soil Parameters Using Regression Tree Model 1

引用

4th International Conference on Communication, Devices and Computing (ICCDC 2023)

作者： Narasimha Reddy, Kandi Venkata Brahma Reddy, Evuri Assistant Professor Department of Computer Science and Engineering Narasaraopeta Engineering College Narasaraopeta Guntur India Department of Computer Science and Engineering Narasaraopeta Engineering College Narasaraopeta Guntur India

ISBN: (数字)9789819927104

ISBN: (纸本)9789819927098

The development of artificial intelligence and advances in computer science have provided a significant impetus for progress in the field of machine learning. In recent years, machine learning algorithms have been used effectively in the sector of agriculture with the purpose of accurately estimating the amount of crop output. The process of estimating the yield of crops using accessible historical data, such as characteristics relating to the weather and soil, as well as previous crop yields, is known as crop yield prediction. A function of machine learning known as regression makes predictions about a number. The use of regression methods may be highly beneficial when attempting to forecast the yield of crops. The development of regression methods applicable to the agricultural industry is the primary emphasis of this research. When attempting to estimate the amount of wheat, maize, and cotton that will be harvested, many types of regression analysis, including quadratic, pure-quadratic, interactions, and polynomial, are used. Finally, a regression tree model has been suggested that is capable of reliably predicting the yields of cotton, maize, and wheat. The metrics of Root Mean Squared Error (RMSE), R’, and Mean Percentage Prediction Error (MPPE) are used in the decision-making process to predict the yield in an effective way. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Crops

来源：评论

学校读者我要写书评

暂无评论

An Extensive Overview of anamoly Detection Analysis in FL-Based IDS

引用

Procedia computer science 2025年 259卷 326-335页

作者： Himani Tyagi Abhilasha Singh Research Scholar Department of Computer Science and Engineering SRM Institute of Science and Technology Delhi- NCR Campus Ghaziabad Associate Professor Department of Computer Science and Engineering SRM Institute of Science and Technology Delhi- NCR Campus Ghaziabad

In this paper, we present a Federated Learning-based Intrusion Detection System (FL-IDS) aimed at enhancing security in Connected Autonomous Vehicles (CAVs) within IoT environments. The novelty lies in the dual utilization of Support Vector Machine (SVM) and Convolutional Neural Networks (CNN) for anomaly detection, leveraging the Flower framework for privacy-preserving, decentralized model training. Unlike traditional centralized approaches, FL-IDS ensures data confidentiality by sharing only model updates. Using the NSL-KDD dataset, our evaluation highlights superior accuracy and loss metrics, validating the efficiency of both machine learning and deep learning methods for detecting DDoS, Probe, and U2R attacks. This work contributes to the advancement of secure and efficient vehicular communication systems, providing scalable solutions for real-world IoT deployments.

关键词： Federated Learning Deep Learning Machine learning CAV IDS Edge Computing

来源：评论

学校读者我要写书评

暂无评论

Predictive Model for Accident Severity

IAENG International Journal of Computer Science

引用

IAENG International Journal of computer science 2022年第1期49卷 110-124页

作者： Mostafa, Solwan M. Salem, Sameh A. Habashyis, Shahira M. Teaching Assistant and a Master Student of Computer and Systems Department Faculty of Engineering Helwan University Cairo11792 Egypt Professor of Computer and Systems Department Faculty of Engineering Helwan University Cairo11792 Egypt Associate Professor of Computer and Systems Department Faculty of Engineering Helwan University Cairo11792 Egypt

In the development of sustainable transportation, traffic safety is a significant matter, and predicting the severity of traffic accidents is still a critical problem in the traffic safety field. However, the utilized road traffic accidents (RTAs) datasets suffer from imbalance distribution. This problem leads to a decrease in classification performance, specifically in predicting the minority classes. This paper aims to treat the class imbalance problem through Synthetic Minority Over-sampling Technique (SMOTE), Support Vector Machine-SMOTE (SVM-SMOTE), Borderline-SMOTE(BL-SMOTE), and Adaptive Synthetic (ADASYN), along with proposing an accurate predictive model for accident severity. Different accident severity models are employed, namely Random Forest (RF), K-Nearest Neighbor (KNN), Naïve Bayes (NB) classifiers, Decision Tree (DT), and Extra Trees (ET). These models are tested using real-world datasets. Several evaluation metrics are used to evaluate the proposed model. Experimental results show that the proposed model significantly improves predicting both the minority and majority classes. These results indicate the robustness and reliability of the proposed predictive model in enhancing road traffic safety and management. © 2022. All Rights Reserved.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

FLBlock: A Sustainable Food Supply Chain Approach Through Federated Learning and Blockchain

引用

Procedia computer science 2024年 235卷 3065-3074页

作者： N Nasurudeen Ahamed P Karthikeyan Assistant Professor School of Computer Science & Engineering Presidency University Bangalore-560064 India Associate Professor School of Computer Science & Engineering RV University Bangalore-560059 India

Blockchain technology has become a pivotal asset in many industries, particularly Food Supply Chain Management. This technology, renowned for its capacity to preserve data immutably and expedite tracking across the intricate stages of the food supply chain, plays a pivotal role in enhancing transparency across the food industry. We proposed a Blockchain-based Federated Learning model. This model amalgamates the strengths of Blockchain and federated learning within the food supply chain, focusing on sustainable and high-quality food production. Our primary objective is to fortify data security within various facets of the food supply chain, encompassing raw material suppliers, producers, distributors, and consumers. Simultaneously, we strive to enhance the precision of our model, aiming to outperform existing Blockchain-based solutions in terms of accuracy. The proposed model demonstrates superior accuracy compared to existing methods.

关键词： Blockchain Federated Learning Supply Chain Food Supply Chain

来源：评论

学校读者我要写书评

暂无评论

Plastic Waste Management Strategies: A Sustainable Approach

Plastic Waste Management Strategies: A Sustainable Approach

引用

National Conference on Technological Advancements in Waste Management: Challenges and Opportunities, TAWMCO 2023

作者： Pandey, Srijan Singh, Sudheer Kumar Singh, Ranjana Scholar Department of Economics National P. G. College UP Lucknow India Associate Professor Department of Computer Science and Engineering Galgotias University UP Greater Noida India Assistant Professor Department of Economics National P. G. College UP Lucknow India

ISBN: (纸本)9789819760237

Plastic pollution has become a global environmental crisis, with detrimental impacts on ecosystems, economy, and human health. To address this challenge, effective plastic waste management strategies are essential. This research paper focuses on the issue of plastic waste and the management strategies to be adopted in India. The paper emphasizes the necessity of innovative waste management techniques to tackle this problem on a larger scale. Despite notable efforts to tackle the problem in India, an alarming plastic waste approximately 3.8 million tons remains uncollected or improperly disposed of each year, which contributes to pollution. Drawing on existing literature and case studies, the paper examines the environmental, economic, and social dimensions of plastic waste management. The findings underscore the importance of holistic and collaborative efforts involving government policies, industry initiatives, public awareness campaigns, and technological innovations to achieve a circular economy and mitigate the adverse effects of plastic pollution. Key strategies include the implementation of extended producer responsibility (EPR) laws, the promotion of circular economy principles, investment in recycling infrastructure, public awareness campaigns, and international cooperation. The paper offers a set of recommendations that are based on solid evidence and propose a more sustainable and environmentally friendly approach. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Circular economy

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：