检索结果-内蒙古大学图书馆

AI Sentries: Evaluating Machine Learning Models for Superior Phishing Email Detection 8

AI Sentries: Evaluating Machine Learning Models for Superior...

8th IEEE International Conference on Computational System and Information technology for Sustainable Solutions, CSITSS 2024

作者： Sahit, S. Vaishnavi, S. Vaibhav Reddy, A. Chaitra, M. Bnm Institute of Technology Affiliated to Vtu Dept. of Computer Science and Engineering Bengaluru India

ISBN: (数字)9798331505462

ISBN: (纸本)9798331505462

Email Phishing Detection focuses on studying how to process emails and spot threats using machine learning and advanced natural language processing. It aims to shield people and businesses from real email misuse. This study tries to fix some problems that earlier research had faced. It does this by making better machine learning detectors to spot fake emails. These detectors use different data sets and look at how to pull out key info. They also try to adapt to new tricks scammers use. The solutions put forward use new methods. These include tweaking features, combining different learning models, and using deep learning to boost accuracy while checking emails in real-time. The study also looks at how to use natural language processing (NLP) to understand what emails mean. This helps catch more fake emails. By looking at both how emails are written and what they mean, the system can spot scams more. This cuts down on false alarms and makes the system more reliable. This well-rounded approach not pushes the boundaries of spotting fake emails but also creates a strong system that can change as cyber threats do. This ensures protection that lasts and can bounce back from attacks. © 2024 IEEE.

关键词： Phishing

来源：评论

学校读者我要写书评

暂无评论

Advancement in EEG Signal Feature Extraction for Enhanced Seizure Detection and Prediction 8

Advancement in EEG Signal Feature Extraction for Enhanced Se...

引用

8th IEEE International Conference on Computational System and Information technology for Sustainable Solutions, CSITSS 2024

作者： Khattar, Sonam Kaur, Ravinder Chandigarh University Department of Computer Science Mohali India Thapar Institute of Engineering and Technology Department of Computer Science Punjab Patiala140413 India

ISBN: (纸本)9798331505462

Epileptic seizure is a highly severe neurological disorder that abruptly interrupts the daily life of those afflicted. In order to advance the technology utilized for managing epileptic seizures, new diagnostic procedures have concentrated on creating electroencephalogram (EEG) techniques that are based on machine learning and deep learning models. The main aim of this research is to focus on some of thecommonly used methods for feature extraction as mentioned in the literature. It will also delve into potential uses of these methods. There are many ways described in this article to process and extract features from EEG signals. Those include time, frequency, decomposing, time-frequency and spatial. Finally, we look at different areas where artificial intelligence is utilized including assistive technology, classification of brain related diseases brain-computer interface systems and integration of machine learning techniques. These applications contribute to a general architecture for analyzing EEG signals. Lastly, potential directions in EEG signal analysis involving feature extraction will be discussed. This study's findings will guide researchers find out which machine learning models that are most effective when it comes to deep learning as well as how feature extraction can be done so that it can enhance detection accuracy of epilepsy seizure based on EEG data. © 2024 IEEE.

关键词： Frequency domain analysis

来源：评论

学校读者我要写书评

暂无评论

Classification of diabetic macular edema severity using deep learning technique

引用

Research on Biomedical engineering 2022年第3期38卷 977-987页

作者： Kumar, Amit Tewari, Anand Shanker Singh, Jyoti Prakash Department of Computer Science & Engineering National Institute of Technology Patna Patna India

Purpose: Diabetic macular edema (DME) is a kind of hard exudates lesion seen near the diabetic macular region of the retina. DME causes visual loss and may result in complete blindness;early identification and treatment may be able to cure this. Identification of DME at an early stage is a challenging and error-prone task. To address this issue, the article presents a methodology that uses the notion of transfer learning to identify cases of DME from retinal fundus images. Methods: A pre-trained DenseNet121 is used in this technique to extract the useful set of feature vectors from the fundus images, which are then fed into a few additional fully connected layers and then into the classification layer to classify DME instances. A total of 577 fundus training images from 3 DME classes were used to train the proposed model, and 103 fundus testing images were used to verify the proposed model for classifying them into one of the three DME cases. Results: The suggested model is trained and tested on the Indian Diabetic Retinopathy Image Dataset (IDRiD). With the test images, the results demonstrate that the proposed model outperformed the state-of-the-art models presented in "Diabetic Retinopathy – Segmentation and Grading Challenge" held at ISBI-2018 with an accuracy of 86.4%. Conclusion: The proposed model diagnoses DME at an early stage for timely treatment and helps to reduce the workload of ophthalmologists. © 2022, The Author(s), under exclusive licence to The Brazilian Society of Biomedical engineering.

关键词： Grading

来源：评论

学校读者我要写书评

暂无评论

Multi-Trajectory Drone Surveillance: Amplifying Monitoring Capabilities in Disaster Management

Multi-Trajectory Drone Surveillance: Amplifying Monitoring C...

引用

2024 IEEE International Students' Conference on Electrical, Electronics and computer science, SCEECS 2024

作者： Mourya, Gojja Sree Jami, Abhinav Ajith, Abhinav Seikh, Ayan Habib Kumar, J. Sathish Motilal Nehru National Institute of Technology Dept. of Computer Science and Engineering Allahabad India

ISBN: (纸本)9798350348460

In the disaster-affected area, whether it's a search and rescue operation, mock drill, managing food distribution, issuing warnings or anything else, the key to successfully carrying out these activities is preparation. To ensure that plans are accurate, one needs to know what actually happened in the disaster-affected area and for this purpose thoroughly and quickly the entire area need to be studied. To address this issue, we use UAV or drone navigation autonomously in required trajectories. By using UAVs you can cover surveillance across the vast acres of land quickly and know what happened and plan rescue operations accordingly. In this paper, we presented our work on moving the drones in multiple trajectories and swarm, thus amplifying surveillance capabilities. Each trajectory is maneuvered autonomously and a corresponding trajectory-algorithm running at the back end is presented along with the simulation results. © 2024 IEEE.

关键词： Disaster management Drones Multi-Agent Systems Surveillance Swarm Trajectories Unmanned Aerial Vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Classification of Mental Workload Using 1D-CNN with Transfer Learning 1

Classification of Mental Workload Using 1D-CNN with Transfer...

引用

1st International Conference on Pioneering Developments in computer science and Digital Technologies, IC2SDT 2024

作者： Chaturvedi, Sushil Ahirwal, Mitul Kumar Maulana Azad National Institute of Technology Dept. of Computer Science and Engineering Bhopal India

ISBN: (纸本)9798350365016

Mental workload (MWL) can be explained as the ratio of a participant's mental effort to their brain capability when performing activities. A significant challenge in the field of MWL classification for brain-computer interfaces (BCIs) based on electroencephalograms (EEGs) is the variability among individuals. It commonly takes unnecessary time to retrain the classification model from starting for a new subject. To address the individual variations among different subjects, a one-dimensional convolutional neural network along with transfer learning (1D CNN-TL) is proposed in this work. The end-to-end 1D-CNN learns the common features of EEG signals and, to tackle the problem of difference in EEG for individuals, a transfer learning technique is used that does fine-tuning on fully connected (FC) layers for a new participant having less training data. The average test accuracy (mean±stdv) of 65.18± 8.37 is achieved over the Cross-session mental workload dataset. The suggested method can achieve satisfying results for new unknown data with less time and fewer training data. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Hyperspectral Image Classification based on Cycle GAN and EfficientNet 4

Hyperspectral Image Classification based on Cycle GAN and Ef...

引用

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

作者： Reddy, Tatireddy Subba Anusha, Sheguri Reddy, Enugu Vishnu Vardhan Shivamani, Vuppala Venkata Mrudula, V. B v Raju Institute of Technology Department of Computer Science and Engineering Telangana Medak India

ISBN: (纸本)9798350343670

Because of the existence of narrow contiguous bands, Hyperspectral Remote Sensing is a sophisticated remote sensing technique that improves the capacity of precise categorization. Given the availability of duplicate information, the massive quantity of continuous bands observed in hyperspectral photos raises the processing complexity. The primary data sets have a limited number of labeled pixels;however, we need additional pixels for improved hyperspectral picture categorization. As a result, the main hurdles are dimensionality reduction and a restricted number of labelled samples. To address these issues, we introduced the Kernel PCA approach for dimensionality reduction, the Cycle GAN technique for increasing labelled samples, and the EfficientNet technique for classification. These strategies will be more accurate than existing techniques for hyperspectral picture categorization. © 2024 IEEE.

关键词： Cycle GAN Hyperspectral image Indian Pines Kernal Principal Component Analysis (KPCA) Salinas scene semi-supervised classification University of Pavia

来源：评论

学校读者我要写书评

暂无评论

Population Diversity-Aided Adaptive Cuckoo Search 1

引用

International Conference on Modeling, Simulation and Optimization, CoMSO 2022

作者： Sarkar, Debojyoti Biswas, Anupam Department of Computer Science and Engineering National Institute of Technology Silchar Assam Silchar788010 India

ISBN: (数字)9789819968664

ISBN: (纸本)9789819968657

Cuckoo search (CS) is an evolutionary algorithm based on Levy flight distribution (LFD). The exploration and exploitation of CS are largely dependent on a probabilistic parameter Pa, the value of which ranges between 0 and 1. A lesser Pa value promises higher exploration, while a higher value leads to higher exploitation. The original CS algorithm has a Pa value fixed to 0.25. A controlled varying Pa suggests a richer exploration-exploitation balance. In this article, we have presented a version of the algorithm with a dynamic Pa value guided by real-time population diversity and have cited the results pertaining to improved efficiency and accuracy when tested upon fifteen CEC-15 benchmark functions. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

A Transfer Learning Based Approach for Alzheimer's Disease Classification 13

A Transfer Learning Based Approach for Alzheimer's Disease C...

引用

13th IEEE International Conference on Communication Systems and Network Technologies, CSNT 2024

作者： Patel, Ruchi Verma, Ashok Kumar Jain, Juhi Rai, Preeti Gyan Ganga Institute of Technology and Sciences Department of Computer Science & Engineering MP Jabalpur India

ISBN: (纸本)9798350305463

Alzheimer's disease (AD) is a degenerative neurological condition that impairs cognitive function and awareness in humans. It has a direct impact on the development of cognitive capacity and brain function. The incidence of Alzheimer's disease is progressively increasing, especially among persons aged 60 and older, finally resulting in mortality. It disrupts nearly all cognitive processes that the brain can perform. Over time, this leads to a reduction in brain size and volume. At now, there is no known therapy capable of reversing the neurological deterioration caused by Alzheimer's disease. Prompt recognition of symptoms is essential for enabling early detection and therapy. Over the years, extensive study has been carried out on the utilization of machine learning for the diagnosis and categorization of Alzheimer's disease. This research proposes a transfer learning-based approach that utilizes the VGG-16 deep learning architecture. The proposed framework offers a method for categorizing AD, consisting of the following steps: For data input, import the pre-trained VGG-16 model and exclude the fully linked layers. Revise the current fully connected layers or introduce new ones to align with the objective of classifying Alzheimer's disease. Implement weight freezing on the initial layers and do fine-tuning on the model using the OASIS dataset to tailor it for the specific characteristics of brain MRI scans. Divide the dataset into training, validation, and test sets. Continue the training process of the updated model using the training dataset. Monitor the model's performance on the validation set and adjust hyperparameters accordingly. The model's performance is assessed using accuracy, precision, recall, and F1 score as metrics on the OASIS datasets. The proposed method has achieved an accuracy of 94.4%, a precision of 90%, a recall of 99.9%, and an F1 score of 95%. © 2024 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Sleep Disorder Detection Using Deep Learning

Sleep Disorder Detection Using Deep Learning

引用

2025 International Conference on computer, Electrical and Communication engineering, ICCECE 2025

作者： Reddy, K. Rakesh Kumar Abinaya, K. Ram, G.L.V. Satya Sai Sathyabama Institute of Science and Technology Semmancheri Tamil Nadu Chennai600119 India Sathyabama Institute of Science and Technology Department of Computer Science and Engineering Semmancheri Tamil Nadu Chennai600119 India

ISBN: (纸本)9798331513894

Since sleep disorders can have a major impact on general well-being, classifying them is crucial to enhancing human health. Experts have historically categorized the stages of sleep, but this is a challenging and error-prone process. By more efficiently assessing, tracking, and diagnosing sleep disturbances, accurate machine learning algorithms (MLAs) can be beneficial. This study uses the publicly accessible Sleep Health and Lifestyle Dataset to evaluate deep learning algorithms and traditional MLAs for the categorization of sleep disorders. Thirteen characteristics pertaining to sleep and everyday activities are included in the 400row dataset. A genetic algorithm was employed to adjust the parameters of the machine learning models in order to maximize their performance. The Artificial Neural Network (ANN) method was evaluated in the study. Significant performance differences were found in the results, with the ANN obtaining the best classification accuracy of 92.92%. In addition, it outperformed the other algorithms tested with high precision (92.01%), recall (93.80%), and F1-score (91.93%). © 2025 IEEE.

关键词： Sleep research

来源：评论

学校读者我要写书评

暂无评论

A Noval Text To Speech Conversion Using Hierarchical Neural Network

A Noval Text To Speech Conversion Using Hierarchical Neural ...

引用

2024 International Conference on Advances in Data engineering and Intelligent Computing Systems, ADICS 2024

作者： Yuvega, S. Rajendran, P. Selvi Hindustan Institute Of Technology And Sciences Department Of Computer Science And Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350364828

The creation of a realistic voice from written text is revolutionized by the state-of-the-art paradigm in text-to-speech (TTS) systems, the Hierarchical Neural Network Architecture (HNNA). An extensive analysis of the important role the HNNA plays in identifying hierarchical patterns in textual input a function that enables the generation of expressive and contextually relevant speech is done in this abstract. The HNNA captures language hierarchies via hierarchical representations. It starts with word embedding analysis of textual inputs and moves on to sentence and document abstractions. Modern models like RNN are used in this architecture to generate high-quality speech signals, and transformer-based encoders decode hierarchical text representations. The integration of linguistic patterns and emphasis on context-aware processing make the HNNA noteworthy. Because of this, speech produced by contemporary TTS systems can sound more intonated, realistic, and understandable. © 2024 IEEE.

关键词： Network architecture

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：