检索结果-内蒙古大学图书馆

2nd International Conference on Advances in Computation, Communication and Information Technology, ICAICCIT 2024

作者： Selvam, Thamizh D. Vinothkumar, J. Madhubala, S. Dept. of Computer Science Rajiv Gandhi Arts and Science College Puducherry India Dept. of Computer Applications Rajiv Gandhi Arts and Science College Puducherry India

ISBN: (纸本)9798331541217

The Internet of Things (IoT) embodies a revolutionary networking technology that links both living beings and inanimate objects. Its utilization is rapidly growing across diverse sectors, particularly in healthcare, where it is instrumental in enabling healthcare providers and individuals to monitor and diagnose diseases. It is crucial to ensure the security of healthcare data on IoT devices to prevent intermediary attacks and unauthorized access. This study explores the increasing security challenges associated with IoT in the healthcare field. To enhance the security and privacy of healthcare data, we propose a combination of the Two-Phase Deep Q Learning Network (TPDQN) and the Deep Learning Network (DLN). The DLN is primarily focused on authenticating certified IoT devices to prevent intermediate attacks, while the TPDQN is designed to detect and mitigate Distributed Denial of Service (DDoS) attacks and malware as they traverse multiple locations. The effectiveness of the proposed solution is measured using metrics such as mean square error (MSE), longevity, accuracy, throughput, and energy consumption, demonstrating improved performance relative to existing solutions. © 2024 IEEE.

关键词： Denial-of-service attack

来源：评论

学校读者我要写书评

暂无评论

Multi-Label Classification of CS Papers Using Natural Language Processing Models 22

Multi-Label Classification of CS Papers Using Natural Langua...

引用

22nd IEEE International Conference on Machine Learning and Applications, ICMLA 2023

作者： Zhang, Zheng Das, Amit Rahgouy, Mostafa Bao, Yida Baskiyar, Sanjeev Auburn University Dept. of Computer Science & Software Engineering Dept. of Mathematics & Statistics AuburnAL United States

ISBN: (纸本)9798350345346

computer science (CS) is a rapidly evolving field of knowledge with a significant volume and significance of scientific papers. Consequently, meticulous management and categorization of CS papers are crucial to ensure efficient access and retrieval of relevant information. This study aims to evaluate the effectiveness of eight traditional machine learning models, as well as Recurrent Neural Network (RNN) models, such as LSTM and BiLSTM, and state-of-the-art pre-trained self-attention-based natural language processing (NLP) models, including BERT, XLNet, RoBERTa, and DistilBERT, for the task of multi-label classification of arXiv CS paper classification. The results demonstrate that pre-trained self-attention-based models consistently outperform the other models regarding classification performance. Moreover, self-attention-based models exhibited superior performance and achieved a new state-of-the-art result. To the best of our knowledge, our paper represents the first endeavor to evaluate machine learning models, specifically on computer science-related documents, as part of a multi-label classification task. © 2023 IEEE.

关键词： BERT Deep Learning LSTM Machine learning multi-label classification

来源：评论

学校读者我要写书评

暂无评论

Leveraging ML to Detect Fraudulent Customs Declaration: A Case of Logistic Regression and LightGBM Algorithms 4

Leveraging ML to Detect Fraudulent Customs Declaration: A Ca...

引用

4th International Conference on Next Generation Computing Applications, NextComp 2024

作者： Chilomo, Innocent Kankuzi, Bennett Malawi University of Science and Technology Dept. of Computer Science and IT Thyolo Malawi

ISBN: (纸本)9798331517403

Harmonised System (HS) code fraud, also known as Customs tariff classification fraud, is common in developed and developing countries. It occurs when traders intentionally mis-classify goods during the time of clearance. Classification fraud results in tax revenue loss, restricted and prohibited goods entry, and unfair market competition. Current manual verification techniques to detect classification fraud are time-consuming and error-prone;thus, an effective and precise strategy is required. In this study, we developed and evaluated the performance of Logistic Regression and LightGBM machine learning models in detecting HS Code fraud using a dataset obtained from a government Revenue Authority in a developing country. Results show that the LightGBM model outperformed Logistic Regression. The LightGBM model demonstrated superior accuracy (0.961), precision (0.890), recall (0.901), and F1 score (0.896) as compared to the Logistic Regression model, which had accuracy (0.932), precision (0.772), recall (0.900), and F1 score (0.831). Our contribution is threefold: Firstly, the dataset used is from a developing country, unlike other studies that use datasets from developed countries. Secondly, we worked with Customs import data collected at an 8-digit HS code level, whereas most similar studies typically used HS codes at 2, 4, or 6-digit levels. Lastly, unlike comparable studies, we have compared the performance of Logistic Regression and LightGBM machine learning algorithms. © 2024 IEEE.

关键词： Logistic regression

来源：评论

学校读者我要写书评

暂无评论

Acoustic data acquisition and integration for semantic organization of sentimental data and analysis in a PWSN

引用

Multimedia Tools and Applications 2024年 1-23页

作者： Das, Sushovan Mondal, Uttam Kr. Dept. of CSE College of Engineering and Mgmt WB Kolaghat721171 India Dept. of Computer Science Vidyasagar University WB Midnapur721102 India

In an acoustic pervasive wireless sensor network (PWSN), the BASE station plays a vital role in gathering and integrating acoustic sensor data from various nodes, including end and router devices tracking time-driven events. The semantic BASE station is crucial in the IoT landscape as it consolidates data from these networks, enabling thorough sentiment analysis of acoustic signals and yielding insights across domains. A semantic processor at the BASE station is essential for an energy-efficient and intelligent PWSN, managing data collection, integration, signal feature extraction, and publication for model training and sentiment analysis. This paper introduces a novel approach to designing a semantic BASE station, focusing on ontology generation, evaluation, and updates to bolster pervasive wireless sensors in capturing and depicting events and time through an ontological framework. The study addresses challenges in efficiently gathering, integrating, and processing acoustic data from pervasive nodes, proposing a semantic processor at the BASE station to enhance feature extraction and metadata publication. The semantic organization of feature-extracted labeled metadata enables the analysis of comprehensive machine learning (ML) applications such as sentiment analysis, type detection, and environment detection by generating confusion matrix. Evaluation includes performance metrics (NEEN, LSNS, BDAS) as well as accuracy, precision, sensitivity, and specificity for sentimental data analysis to validate the proposed technique’s efficacy. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Sensor nodes

来源：评论

学校读者我要写书评

暂无评论

Towards the Diagnosis of Heart Disease Using an Ensemble Learning Approach 22

Towards the Diagnosis of Heart Disease Using an Ensemble Lea...

引用

22nd IEEE International Conference on Machine Learning and Applications, ICMLA 2023

作者： Zhang, Zheng Xu, Liangliang Bao, Yida Baskiyar, Sanjeev Auburn University Dept. of Computer Science & Software Engineering Dept. of Mathematics & Statistics AuburnAL United States

ISBN: (纸本)9798350345346

Heart disease is one of the leading causes of death worldwide. Understanding the presence of heart disease is crucial for timely intervention and effective management. However, it is still a challenging task to accurately diagnose and treat heart disease. In this paper, we propose an ensemble machine learning model that combines the predictive power of three state-of-the-art machine learning algorithms: BERT (Bidirectional Encoder Representations from Transformers), FT-transformer, and XG-Boost. Through extensive training and evaluation, we assess the performance of our model using established metrics such as accuracy, precision, recall, F1-score, and receiver operating char-acteristic (ROC) curve analysis. The results obtained demonstrate the effectiveness and validity of our machine learning system in predicting heart disease accurately. This paper presents a promising approach that can assist healthcare professionals in making informed decisions and improving patient outcomes, enhances our understanding of heart disease patterns, and contributes to the development of effective diagnostic and treatment approaches. © 2023 IEEE.

关键词： Autoencoder BERT Heart Disease Machine Learning Transformer XG-Boost

来源：评论

学校读者我要写书评

暂无评论

A Motor Activity Analysis as a Depression Indicator: Predictive Approach Using A Hybrid CNN and LSTM Network 6

A Motor Activity Analysis as a Depression Indicator: Predict...

引用

6th International Conference on Cybernetics and Intelligent System, ICORIS 2024

作者： Sutedja, Vinsensius Odilo Andreas, Frans Nabiilah, Ghinaa Zain Moniaga, Jurike V. Dept. Computer Science School of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (纸本)9798331539603

Depression is a prevalent mental disorder affecting behavior, cognition, and physical activity. Early detection and intervention are crucial to mitigating its severe impacts, including suicidal ideation or suicide attempts. This study proposes a novel predictive model using a hybrid Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) network to analyze motor activity data as an indicator of depression. Utilizing the "Depresjon" dataset, which comprises activity levels from both depressed and non-depressed individuals, the model extracts features through CNN and processes these with LSTM to identify depression patterns. To address class imbalance in the dataset, Synthetic Minority Over-sampling Technique (SMOTE) was employed, enhancing the model's predictive accuracy. The final model achieved a high accuracy rate of 97.89%, significantly outperforming the other model created. This research demonstrates the potential of combining CNN and LSTM for effective depression prediction, providing a valuable tool for early diagnosis and intervention. © 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

Enhancing Human computer Interaction (HCI) Through Machine Learning Application 8

Enhancing Human Computer Interaction (HCI) Through Machine L...

引用

8th International Symposium on Multidisciplinary Studies and Innovative Technologies, ISMSIT 2024

作者： Yaseen, Fahad Abdulateef Ahmed, Mohammad Shihab Khudhur, Mokhalad Eesee College Tikrit University Dept. Computer Science Computer Science and Mathematics Tikrit Iraq

ISBN: (纸本)9798350354423

Integrating human-computer interaction with machine learning is an important development that contributes and opens the way for many experiences that serve the user. This research presents the scientific benefits and effects resulting from integrating human-computer interaction and machine learning, and on the other hand, discusses the common applications between them and what challenges will arise from data privacy and ethical considerations. Thus, this interaction will contribute to enhancing and encouraging user participation and to a greater increase in intelligence and responsiveness. This research aims to present and propose innovative solutions that address the challenges that will face this interaction, in addition to presenting a concept and a methodological model that increases the power of human-computer interaction in a more intelligent and smooth way. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Classification and Prediction of Alzheimer's Disease using Deep Learning 7

Classification and Prediction of Alzheimer's Disease using D...

引用

7th International Conference on Intelligent Computing and Control Systems, ICICCS 2023

作者： Brindha, D. Ebenezer, V. Selvaraj, E. Jackson Bevin Geoff, D.M. Dileep, B. Bethina Nambi, M. Thirumalai Dept. of Computer Science and Engineering Coimbatore India Dept. of Computer Science and Engineering Coimbatore India

ISBN: (纸本)9798350397253

This study has proposed a novel technique for performing object detection and image classification with a Convolutional Neural Network (CNN) architecture. Nevertheless, employing a 2D CNN architecture to identify a lot of patients as AD or MCI based on 3D MR Images becomes challenging when dealing with hundreds of MRI images that are highly similar in nature. It provides a solution to this problem that streamlines the concept of classification of patients based on 3D MRI by exploiting 2D data produced by the CNN structure. In this method, 2D characteristics from MRI are extracted and then converted by using an appropriate Machine Learning (ML) algorithm for categorization. © 2023 IEEE.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Detection Systems for Distributed Denial-of-Service (DDoS) Attack Based on Time Series: A Review 21

Detection Systems for Distributed Denial-of-Service (DDoS) A...

引用

21st International Multi-Conference on Systems, Signals and Devices, SSD 2024

作者： Adil Nafea, Ahmed Maad Hamdi, Mustafa Abdulhakeem, Baraa Saad Shakir, Ahmed Thair Alsumaidaie, Mustafa S. Ibrahim Shaban, Ali Muwafaq College of Computer Science and Information Technology University of Anbar Ramadi Dept. Artificail Inteligence Iraq College of Computer Science and IT University of Anbar Ramadi Dept. of Computer Science Iraq College of Computer Science and IT University of Anbar Ramadi Dept. of Information System Iraq College of Applied Sciences University of Anbar Ramadi Dept. of Biophysics Iraq College of Computer Science and Information Technology University of Anbar Ramadi Dept. Information System Iraq

ISBN: (纸本)9798350374131

The Distributed Denial-of-Service (DDoS) attacks are one of the most critical threats to the stability and security of the Internet. With the increasing number of devices connected to the Internet, the frequency and severity of DDoS attacks are also increasing. To mitigate the impact of DDoS attacks, intelligent detection systems are becoming increasingly important. This paper reviews the recent literature on intelligent techniques, including machine learning (ML), Deep Learning (DL), and artificial intelligence (AI), for detecting DDoS attacks. We will provide an overview of the existing research in the field and analyse the trends in using time series data analysis for DDoS attack detection. A taxonomy and conceptual framework for DDoS mitigation are presented. This study highlights the use of several intelligent techniques for detecting DDoS attacks and evaluates the performance utilizing real datasets and also discusses future research directions in this field. © 2024 IEEE.

关键词： Time series analysis

来源：评论

学校读者我要写书评

暂无评论

Gauging Deep Learning Archetypal Effectiveness in Haematological Reclamation

引用

SN computer science 2024年第7期5卷 963页

作者： Pradeep kumar, B.P. Ravikumar, J. Dept. of Computer Science and Design Atria Institute of Technology VTU Karnataka Bangalore India Dept. of Computer Science and Engineering Atria Institute of Technology VTU Karnataka Bangalore India

This paper project an system for reclamation of medical images in an effective way for the extraction and retrieving of data from large archives is critical. This study aims to improve haematological image reclamation by combining visual-based image reclamation (VBIR) approaches with the GLCM algorithm, specifically for characteristics related to the prostate gland. While previous research has focused on computer-aided methods for Gleason grading, our technique focuses on early-stage feature reclamation across 14 paired glands. The experimental findings, including Bicubic Interpolation The resolution Enrichment with a standard deviation of 12.37, kurtosis of 122.83, and skewness of 2.92, demonstrate improved reclamation performance. Our suggested methodology uses a handmade learning approach that includes critical components such as GLCM contrast and correlation. This extensive feature extraction step includes descriptors for morphology, texture, fractals, and contextual information, which are then subjected to in-dept. statistical analysis to identify significant features. Using an RNN, our technique improves performance somewhat but significantly when compared to alternatives, with time required for execution offering insights into the intricate interaction of stages and the effect of sample variability. These findings not only encourage more research, but also help to advance standard reviews in haematological analysis of images. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Gland reclamation Gray-level co-occurrence matrix (GLCM) Haematological Haematological image Prostate gland

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：