检索结果-内蒙古大学图书馆

2nd IEEE International Conference on IoT, Communication and Automation technology, ICICAT 2024

作者： Srivastav, Shashank Gupta, Alok Singh, Laxman Singh, Rajesh Kumar Tripathi, Kanak Dwivedi, Anshu Kumar Buddha Institute of Technology Department of Computer Science Engineering Gorakhpur India Babu Banarasi das Engineering College Department of Computer Science Engineering Lucknow India Bennett University School of Computer Science Engineering and Technology Greater Noida India KIPM College of Engineering & Technology Dept of CSE Gorakhpur India Galgotia College of Engineering & Technology Dept of MCA Greater Noida India

ISBN: (纸本)9798350368109

In this electronically era, communication using email has become an part of our lives. However, with the convenience of email comes the nuisance of spam messages flooding our inboxes. Detecting and filtering out these spam emails is crucial to maintain productivity and security in our online interactions. In this research project, we explore the performance of using the firefly algorithm, a nature-inspired optimization technique, for spam detection. By leveraging the unique behavior of fireflies in search and optimization, we aim to develop a robust and efficient spam detection system. We start by gathering a dataset containing a mix of spam and non-spam (ham) emails. After preprocessing the text data and extracting relevant features using techniques like Count-Vectorizer, we train a logistic regression model, a commonly used classifier for binary classification tasks. To enhance the performance of our model, we employ the Firefly algorithm to optimize its hyperactive parameters. This algorithm impersonates the flashing behavior of fireflies to iteratively search for the foremost combination of model parameters, maximizing its ability to distinguish between spam and legitimate emails. Our experimental results demonstrate promising outcomes, with the optimized model achieving high accuracy and performance measures such as precision, recall, and F1-score on a held-out test set. These findings highlight the potential of nature-inspired algorithms like the firefly algorithm to improve spam detection techniques and effectively combat email spam in real-world scenarios. © 2024 IEEE.

关键词： Logistic regression

来源：评论

学校读者我要写书评

暂无评论

A novel transfer deep learning method for detection and classification of plant leaf disease

引用

Journal of Ambient Intelligence and Humanized Computing 2023年第9期14卷 12407-12424页

作者： Kaur, Prabhjot Harnal, Shilpi Gautam, Vinay Singh, Mukund Pratap Singh, Santar Pal Chitkara University Institute of Engineering and Technology Chitkara University Punjab India School of Computer Science Engineering and Technology Bennett University Greater Noida India Department of Computer Science and Engineering Rashtrakavi Ramdhari Singh Dinkar College of Engineering Begusarai India

The major cause of plant mortality and devastation, particularly among trees is plant diseases. This problem, however, may be handled and treated effectively through early detection. Crop/plant diseases must be identified and prevented as soon as possible to improve yield. Plant disease classification and identification by plant protection professionals through eye observation is a time-consuming and error-prone process. Previously, many researchers used hand-crafted techniques for the detection and classification of diseases. Also, due to a lack of knowledge experts and improper laboratory facilities, classification at an early stage is not possible. In terms of precision agriculture applications, developing effective, rapid, and highly successful computer-aided disease detection systems have become a necessity. A deep learning-based convolutional neural network (CNN) technique is used successfully in numerous computer vision tasks such as picture classification, object detection, segmentation, and image analysis for finding the best results. The existing models had been worked on a mixed crop approach and single class dataset with average accuracy. In this paper, the Modified InceptionResNet-V2 (MIR-V2) which is a form of the CNN model is used in conjunction with a transfer learning approach to recognize illnesses in images of tomato leaves. The proposed model is trained on a public dataset and self-collected dataset that includes seven different tomato leaf disease classifications with one healthy leaf. For the evaluation of model performance, different parameters such as dropout, learning rate, batch size, count of epochs, and accuracy are used. The disease classification accuracy rate for the applied models is 98.92% and the F1 score is 97.94%. The experimental results support the suggested approach’s validity and find it effective in detecting tomato leaf disease. © 2022, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

ConciseNet: A Robust Model for Enhancing Signal Reconstruction in Wireless Sensor Networks 4

ConciseNet: A Robust Model for Enhancing Signal Reconstructi...

引用

4th International Conference on Advances in Electrical, Computing, Communication and Sustainable Technologies, ICAECT 2024

作者： Kumari, P. Meena Sekar, K. Jagadeesh, P. Dheepa, T. Avn Institute of Engineering and Technology Department of Computer Science and Engineering Telangana Hyderabad India National Institute of Technology Silchar Department of Computer Science and Engineering Assam Silchar India Barath University Department of Computer Science and Engineering Tamilnadu India Kongunadu College of Engineering and Technology Department of Computer Science and Engineering Tiruchirappalli India

ISBN: (纸本)9798350343670

This paper introduces a novel data collection model called ConciseNet that leverages a cutting-edge data reconstruction method to significantly enhance signal reconstruction accuracy in wireless sensor networks (WSNs). In traditional WSNs, data collection is prone to errors and losses, especially in long-range scenarios. The proposed model addresses this challenge by employing ConciseNet, an attentive sequential model that effectively compresses sensor signals without compromising information fidelity. The unique strength of ConciseNet lies in its ability to capture essential features from raw sensor data, allowing for efficient and precise reconstruction over extended periods. The result is a more robust and accurate representation of collected data, thereby improving the quality of information gathered by the WSN and maximizing the lifetime of sensors and WSNs. © 2024 IEEE.

关键词： Compressive sensing Data Reconstruction Time dependency Transformer Neural Network Wireless Sensor Network

来源：评论

学校读者我要写书评

暂无评论

An Efficient Investigation of Cloud Computing Security with Machine Learning Algorithm 7

An Efficient Investigation of Cloud Computing Security with ...

引用

7th International Conference on Inventive Computation Technologies, ICICT 2024

作者： Senthilkumar, R. Yasotha, S. Manochithra, P.M. Senthil, J. Sivakumar, G. Shree Venkateswara Hi Tech Engineering College Computer Science And Engineering Tamilnadu Erode India Sri Eshwar College of Engineering Computer Science And Engineering Tamilnadu Coimbatore India Sri Krishna College of Engineering And Technology M.Tech Computer Science And Engineering Tamilnadu Coimbatore India Erode Sengunthar Engineering College Computer Science And Engineering Tamilnadu Erode India

ISBN: (纸本)9798350359299

Due to developments in technologies like Cloud Computing (CC), the Internet of Things (IoT), etc., the data volume transmitted across communication infrastructures has skyrocketed recently. In order to make network systems susceptible, attackers have increased their determinations. Improving the security of such network systems is very crucial. Using Deep Learning (DL) methods with an Intrusion Detection System (IDS) framework is put into action in this research. The Gated Recurrent Unit (GRU) as well as Support Vector Machine (SVM) are used in this study for attack detection. Therefore, the implementation of SoftMax in the GRU model's last output layer, this study introduces a linear SVM. The NSL-KDD dataset is taken into account to evaluate the proposed IDS framework's performance. In addition, when the number of features increases, current IDSs have poor test accuracy ratings when it comes to identifying new attacks. Each dataset's feature space was reduced using an XGBoost (XGB)-based feature selection approach in this research. After that, 22 detailed characteristics were selected from the NSL-KDD dataset using XGB. The results show that, the proposed IDS paradigm outperformed other approaches. © 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

A Comprehensive Analysis on Severity Estimation of Plant Diseases by Deep Learning Models

A Comprehensive Analysis on Severity Estimation of Plant Dis...

引用

2025 IEEE International Conference on Computational, Communication and Information technology, ICCCIT 2025

作者： Sonu Varghese, K. Kumar, R. Satheesh Sahrdaya College of Engineering and Technology APJ Abdul Kalam Technological University Kerala Department of Computer Science and Engineering India Jawaharlal College of Engineering and Technology APJ Abdul Kalam Technological University Department of Computer Science and Engineering Kerala India

ISBN: (纸本)9798331512965

The rapid spread of diseases and pest infestations has a detrimental effect on plant health. Methods for disease classification and detection have gained new insights from the developments in computer vision and deep learning approaches. However, there has been relatively limited work in the area of severity estimation and disease progression rate since it requires more detailed information such as the percentage of affected leaf area, symptoms intensity, and environmental factors that lead to the disease progression over time. Thus the modern agricultural sector faces a significant difficulty in the assessment of plant disease severity and tracking of disease development. The purpose of this study is to perform a thorough review of various deep learning methods for plant disease severity assessment, taking into account factors like accuracy, severity level measurement, and dataset employed. The article also suggests ways to address the shortcomings of the current approach. © 2025 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Adaptation of Federated Explainable Artificial Intelligence for Efficient and Secure E-Healthcare Systems

引用

computers, Materials & Continua 2024年第3期78卷 3413-3429页

作者： Rabia Abid Muhammad Rizwan Abdulatif Alabdulatif Abdullah Alnajim Meznah Alamro Mourade Azrour Department of Computer Science Kinnaird College for WomenLahorePakistan College of Science and Engineering University of DerbyDerbyDE221GBUK Department of Computer Science College of ComputerQassim UniversityBuraydah51452Saudi Arabia Department of Information Technology College of ComputerQassim UniversityBuraydah51452Saudi Arabia Department of Information Technology College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityRiyadh84428Saudi Arabia STI Laboratory IDMS TeamFaculty of Sciences and TechniquesMoulay Ismail University of MeknèsMeknesMorocco

Explainable Artificial Intelligence(XAI)has an advanced feature to enhance the decision-making feature and improve the rule-based technique by using more advanced Machine Learning(ML)and Deep Learning(DL)based *** this paper,we chose e-healthcare systems for efficient decision-making and data classification,especially in data security,data handling,diagnostics,laboratories,and *** Machine Learning(FML)is a new and advanced technology that helps to maintain privacy for Personal Health Records(PHR)and handle a large amount of medical data *** this context,XAI,along with FML,increases efficiency and improves the security of e-healthcare *** experiments show efficient system performance by implementing a federated averaging algorithm on an open-source Federated Learning(FL)*** experimental evaluation demonstrates the accuracy rate by taking epochs size 5,batch size 16,and the number of clients 5,which shows a higher accuracy rate(19,104).We conclude the paper by discussing the existing gaps and future work in an e-healthcare system.

关键词： Artificial intelligence data privacy federated machine learning healthcare system security

来源：评论

学校读者我要写书评

暂无评论

Enhancing COVID-19 Detection with YOLOv5 Object Detection Algorithm in Chest X-ray Images 3

Enhancing COVID-19 Detection with YOLOv5 Object Detection Al...

引用

3rd International Conference for Innovation in technology, INOCON 2024

作者： Duraisamy, Premkumar Arunkumar, D. Niranjani, V. Kpr Institute of Engineering and Technology Department of Computer Science and Engineering Coimbatore India Sri Eshwar College of Engineering Department of Computer Science and Engineering Coimbatore India

ISBN: (纸本)9798350381931

In the ongoing fight against COVID-19, accurate diagnostic tools are crucial. This study focuses on the detection of COVID-19, primarily by analyzing Chest X-ray images to identify and understand the disease. We introduce a new approach that utilizes the YOLOv5 (You Only Look Once) object detection algorithm. YOLOv5 is known for its ability to quickly identify objects, and we have fine-tuned it to perform effectively with X-ray images. The result is a model that excels at identifying intricate COVID-19-related patterns in X-ray images, achieving a high accuracy score of 98%. By carefully adjusting and training the model with specific data, our method achieves even higher accuracy. This modification makes YOLOv5 a powerful tool for automating the detection of COVID-19, offering hope for early detection and timely action in the ongoing global fight against the pandemic. © 2024 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Predicting Alzheimer's Onset through Neuroimaging 2

Predicting Alzheimer's Onset through Neuroimaging

引用

2nd International Conference on Advancements in Smart, Secure and Intelligent Computing, ASSIC 2024

作者： Kandula, Niravange Chakravarty, Sujata Kandula, Aksha Mohapatra, Sunil Kumar Centurion University of Technology & Management Computer Science & Engineering Vizianagaram India Centurion University of Technology & Management Computer Science & Engineering Bhubaneswar India Andhra University College of Engineering Computer Science & Engineering Andhra Pradesh Visakhapatnam India

ISBN: (纸本)9798350370188

Alzheimer's disease is a progressive and lethal neurological condition epitomized by the accumulation of protein aggregates in the brain cells that are responsible for cognitive functions. It stands as the most prevalent cause of death, especially among the elderly. The resemblance between the neuropathology of various dementia types and the disease's irreversible nature presents a significant global healthcare challenge in terms of diagnosing and identifying it in its early stages. Traditional methods rely on cognitive assessments and subjective examination by clinicians which can be time-consuming and are prone to human errors. In contrast, a well-trained Deep Learning model can identify subtle structural and functional brain changes in Magnetic Resonance Imaging, that can serve as early indicators of neurodegenerative diseases, facilitating prompt and accurate therapies. The work examines image classification using Convolutional Neural Networks (CNN), Residual Networks (ResNet), VGG networks (VGGNET's), and Alex Net. The result shows that CNN and VGGNET outperformed in accuracy across non-demented, mildly demented, very mildly demented, and moderately demented stages with 98% and 99% accuracy, respectively. © 2024 IEEE.

关键词： Neurodegenerative diseases

来源：评论

学校读者我要写书评

暂无评论

Multi-Stage Progressive Generative Adversarial Network for Low-Dose CT Denoising 6

Multi-Stage Progressive Generative Adversarial Network for L...

引用

6th International Conference on Communications, Information System and computer engineering, CISCE 2024

作者： Wang, Lifang Li, Jinjin Zhang, Rongguo Guo, Xiaodong College of Computer Science and Technology Taiyuan University of Science and Technology Taiyuan China College of Electronic Information Engineering Taiyuan University of Science and Technology Taiyuan China

ISBN: (纸本)9798350353174

To address the balance between spatial details and high-level contextual information in low-dose CT image denoising tasks, a multi-stage progressive generative adversarial network is introduced. This network learns features from CT images in three phases, transitioning from coarse to fine. Wavelet transforms are employed in the initial two phases to expand the perceptual domain of the image. Subsequently, a dense residual network enhances the expression of image details in the third phase. This integration of information across stages facilitates the capture of multi-scale information and abstract features. Additionally, a discriminator equipped with multi-scale re-sidual modules is designed to improve noise artifact discrimination. Experimental results demonstrate significant outperformance of our proposed network over existing algorithms in denoising performance, both quantitatively and qualitatively. © 2024 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

LLDif: Diffusion Models for Low-Light Facial Expression Recognition 27th

LLDif: Diffusion Models for Low-Light Facial Expression Rec...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Wang, Zhifeng Zhang, Kaihao Sankaranarayana, Ramesh College of Engineering and Computer Science Australian National University CanberraACT Australia School of Computer Science and Technology Harbin Institute of Technology Shenzhen China

ISBN: (纸本)9783031782008

This paper introduces LLDif, a novel diffusion-based facial expression recognition (FER) framework tailored for extremely low-light (LL) environments. Images captured under such conditions often suffer from low brightness and significantly reduced contrast, presenting challenges to conventional methods. These challenges include poor image quality that can significantly reduce the accuracy of emotion recognition. LLDif addresses these issues with a novel two-stage training process that combines a Label-aware CLIP (LA-CLIP), an embedding prior network (PNET), and a transformer-based network adept at handling the noise of low-light images. The first stage involves LA-CLIP generating a joint embedding prior distribution (EPD) to guide the LLformer in label recovery. In the second stage, the diffusion model (DM) refines the EPD inference, ultilising the compactness of EPD for precise predictions. Experimental evaluations on various LL-FER datasets have shown that LLDif achieves competitive performance, underscoring its potential to enhance FER applications in challenging lighting conditions. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Emotion 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：