检索结果-内蒙古大学图书馆

Ensemble of deep learning models with Walrus Optimization Algorithm for accurate botnet recognition and classification

引用

Iran Journal of computer Science 2025年 1-18页

作者： Chacko, Ashwathy Anda Edwin, E. Bijolin Thanka, M. Roshni Ebenezer, V. Division of Computer Science and Engineering Karunya Institute of Technology and Sciences Coimbatore India Division of Data Science and Cyber Security Karunya Institute of Technology and Sciences Coimbatore India

The rapid growth of Internet of Things (IoT) networks has introduced significant security challenges, with botnet attacks being one of the most prevalent threats. These attacks exploit vulnerabilities in IoT devices, leading to severe disruptions and damage to critical infrastructures. Detecting botnet attacks in IoT environments is challenging due to the large volume of data, the dynamic nature of traffic, and the diverse attack patterns. To address these issues, we propose a novel approach called Walrus Optimized Ensemble Deep Learning for Anomaly-Based Recognition Classifier (WOAEDL-ABRC), which leverages a combination of advanced machine learning techniques for effective botnet detection. The methodology of this research involves four key components: (1) data preprocessing through min–max normalization to scale the features appropriately, (2) feature selection using the social cooperation search algorithm (SCSA) to identify the most informative attributes, (3) an ensemble deep learning model combining convolutional autoencoder (CAE), bidirectional gated recurrent unit (BiGRU), and deep belief network (DBN) for robust anomaly detection, and (4) hyperparameter optimization using the Walrus Optimization Algorithm (WAOA), which fine-tunes the model parameters for optimal performance. This ensemble approach ensures that the model benefits from the strengths of each individual technique while mitigating the weaknesses of others. The dataset used for this research includes network traffic data from IoT environments, consisting of various botnet attack scenarios and normal traffic patterns. The data undergoes extensive preprocessing and feature selection to reduce dimensionality and enhance the model’s performance. The implementation is carried out in Python using TensorFlow for deep learning, with the WAOA applied to optimize hyperparameters. The results demonstrate the effectiveness of the WOAEDL-ABRC in detecting botnet attacks, achieving superior accuracy, precision

关键词： Botnet recognition Deep learning Feature selection Internet of things Walrus Optimization Algorithm

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-based Immune Cell Classification for Enhanced Immunological Analysis 3

Machine Learning-based Immune Cell Classification for Enhanc...

引用

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

作者： Naveen Pranouv, S.S. Isravel, Deva Priya Dhas, Julia Punitha Malar Karunya Institute of Technology and Sciences Division of Computer Science and Engineering Coimbatore India

ISBN: (纸本)9798331509675

The automated classification of immune cells plays a vital role in advancing immunological research, diagnostics, and therapeutic monitoring. This paper leverages machine learning and image processing techniques to accurately classify various immune cell types from microscopic images by analyzing cellular features such as shape, size, and texture. The proposed Convolutional Neural Networks (CNN) based system integrates digital pathology workflows to provide a reliable and efficient tool for immune cell classification, reducing reliance on manual inspection. The model trained on a diverse dataset of labeled immune cell images to ensure high classification accuracy and adaptability across different cell types and imaging conditions. The proposed model provides a proactive solution to immunology research challenges, enhancing both the precision and efficiency of immune cell classification. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Intelligent Traffic Management System using Multi-Agent Reinforcement Learning 3

Intelligent Traffic Management System using Multi-Agent Rein...

引用

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

作者： Shaheen, Dalaali Paulraj, Getzi Jeba Leelipushpam Jebadurai, Immanuel Johnraja Kirubakaran, Stewart Karunya Institute of Technology and Sciences Division of Computer Science and Engineering Coimbatore India Karunya Institute of Technology and Sciences Division of Cse Coimbatore India

ISBN: (纸本)9798331509675

This paper presents a decentralized multi-agent system for intelligent traffic management in urban environments, where each agent represents a traffic light controller at an intersection. The proposed system leverages a combination of Distributed W-Learning and Deep Q-Networks (DQN) to optimize traffic flow. Distributed W-Learning enables agents to prioritize decisions based on multiple performance policies, while DQN enhances their ability to handle complex state-action mappings through neural network approximations. By utilizing locally available traffic data, each agent adapts dynamically to diverse traffic conditions. The integration of these machine learning techniques ensures a fully decentralized and self-organizing approach, minimizing congestion, improving traffic efficiency, and addressing multiple objectives simultaneously. Simulation experiments are conducted using SUMO (Simulation of Urban MObility) to evaluate the system's performance in realistic traffic scenarios. This study highlights the potential of combining Distributed W-Learning and DQN in multi-agent reinforcement learning to revolutionize traffic management systems and achieve scalable, adaptive, and efficient urban traffic control. © 2025 IEEE.

关键词： Traffic congestion

来源：评论

学校读者我要写书评

暂无评论

Neuroimaging-based Machine Learning for Early Alzheimer's Disease Prediction 3

Neuroimaging-based Machine Learning for Early Alzheimer's Di...

引用

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

作者： Jerome, Jim Isravel, Deva Priya Dhas, Julia Punitha Malar Karunya Institute of Technology and Sciences Division of Computer Science and Engineering Coimbatore India

ISBN: (纸本)9798331509675

Early detection of Alzheimer's disease (AD) is crucial for timely intervention and slowing its progression. This research leverages neuroimaging-based machine learning to classify cognitive impairment levels using MRI images. The proposed approach involves preprocessing MRI images, converting them into a numerical format, and training a BEiT (BERT for Image Transformation) model to classify individuals into one of four categories: No Impairment, Very Mild, Mild, or Moderate Impairment. A web interface, developed using Streamlit, enables user-friendly access, allowing real-time predictions by uploading MRI images. This system demonstrates the potential of integrating advanced machine learning techniques and neuroimaging for early Alzheimer's diagnosis, paving the way for personalized interventions and improved outcomes. © 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

From light sensing to adaptive learning:hafnium diselenide reconfigurable memcapacitive devices in neuromorphic computing

引用

Light(Science & Applications) 2025年第1期14卷 215-226页

作者： Bashayr Alqahtani Hanrui Li Abdul Momin Syed Nazek El-Atab Electrical and Computer Engineering Program Computer Electrical Mathematical Science and Engineering DivisionKing Abdullah University of Science and Technology(KAUST)ThuwalSaudi Arabia Electrical Engineering Department College of EngineeringPrincess Nourah Bint Abdulrahman University(PNU)RiyadhSaudi Arabia

Advancements in neuromorphic computing have given an impetus to the development of systems with adaptive behavior,dynamic responses,and energy efficiency *** charge-based or emerging memory technologies such as memristors have been developed to emulate synaptic plasticity,replicating the key functionality of neurons—integrating diverse presynaptic inputs to fire electrical impulses—has remained *** this study,we developed reconfigurable metal-oxide-semiconductor capacitors(MOSCaps)based on hafnium diselenide(HfSe2).The proposed devices exhibit(1)optoelectronic synaptic features and perform separate stimulus-associated learning,indicating considerable adaptive neuron emulation,(2)dual light-enabled charge-trapping and memcapacitive behavior within the same MOSCap device,whose threshold voltage and capacitance vary based on the light intensity across the visible spectrum,(3)memcapacitor volatility tuning based on the biasing conditions,enabling the transition from volatile light sensing to non-volatile optical data *** reconfigurability and multifunctionality of MOSCap were used to integrate the device into a leaky integrate-and-fire neuron model within a spiking neural network to dynamically adjust firing patterns based on light stimuli and detect exoplanets through variations in light intensity.

关键词： integrate volatile integrating

来源：评论

学校读者我要写书评

暂无评论

MedFILIP: Medical Fine-grained Language-Image Pre-training

引用

IEEE Journal of Biomedical and Health Informatics 2025年第5期29卷 3587-3597页

作者： Liang, Xinjie Li, Xiangyu Li, Fanding Jiang, Jie Dong, Qing Wang, Wei Wang, Kuanquan Dong, Suyu Luo, Gongning Li, Shuo The School of Computer Science and Technology Harbin Institute of Technology Harbin China The Department of Thoracic Surgery at No. 4 Affiliated Hospital Harbin Medical University Harbin China The School of Computer Science and Technology Harbin Institute of Technology Shenzhen China The College of computer and control engineering Northeast Forestry University Harbin China The Computer Electrical and Mathematical Sciences & Engineering Division King Abdullah University of Science and Technology Thuwal Saudi Arabia The Department of Biomedical Engineering Department of Computer Data Science Case Western Reserve University ClevelandOH United States

Medical vision-language pretraining (VLP) that leverages naturally-paired medical image-report data is crucial for medical image analysis. However, existing methods struggle to accurately characterize associations between images and diseases, leading to inaccurate or incomplete diagnostic results. In this work, we propose MedFILIP, a fine-grained VLP model, introduces medical image-specific knowledge through contrastive learning, specifically: 1) An information extractor based on a large language model is proposed to decouple comprehensive disease details from reports, which excels in extracting disease deals through flexible prompt engineering, thereby effectively reducing text complexity while retaining rich information at a tiny cost. 2) A knowledge injector is proposed to construct relationships between categories and visual attributes, which help the model to make judgments based on image features, and fosters knowledge extrapolation to unfamiliar disease categories. 3) A semantic similarity matrix based on fine-grained annotations is proposed, providing smoother, information-richer labels, thus allowing fine-grained image-text alignment. 4) We validate MedFILIP on numerous datasets, e.g., RSNA-Pneumonia, NIH ChestXray14, VinBigData, and COVID-19. For single-label, multi-label, and fine-grained classification, our model achieves state-of-the-art performance, the classification accuracy has increased by a maximum of 6.69%. © 2013 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

An Optimal Real-Time Routing and Clustering Protocol for UAV Networks Based on Security 4

An Optimal Real-Time Routing and Clustering Protocol for UAV...

引用

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Sophia, S. Leelipushpam Paulraj, Getzi Jeba Yuvarajan, D. Karunya Institute of Technology and Sciences Division of Artificial Intelligence and Machine Learning Coimbatore India Karunya Institute of Technology and Sciences Division of Computer Science and Engineering Coimbatore India

ISBN: (纸本)9798331523923

Unmanned Aerial Vehicle (UAV) networks play an important role in different application areas such as military surveillance, emergency services, and infrastructure. However, these networks face significant challenges such as data leakage, unauthorized access, limited processing capacity, and energy constraints. Available techniques such as Elliptic Curve Cryptography (ECC), hash-based techniques, and dynamic clustering algorithms have been proposed to enhance security and operational performance;however, they often encounter challenges concerning scalability, adaptability to real-time changes within the network, and resource-related constraints. This research presents a streamlined authentication framework with the intent to facilitate secure and effective functionalities in turbulent and fluctuating settings. The proposed protocol uses Dijkstra's algorithm for optimal real-time routing, Adaptive Optimization Clustering (AOC) for dynamic resource distribution, and K-means clustering for noise classification. The proposed methodology achieves substantial improvements in power efficiency, latency, and Packet Delivery Rate (PDR) due to reduced computational overhead as well as risks such as data interception and replay attacks. Simulation results conclude that the system suggested here would be secure, scalable, and energy-efficient to be used for applications in demanding scenarios, such as mission-critical scenarios. © 2025 IEEE.

关键词： Emergency services

来源：评论

学校读者我要写书评

暂无评论

Early-Stage Detection of Colorectal Cancer Using Image Classification 4

Early-Stage Detection of Colorectal Cancer Using Image Class...

引用

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Santhosh, Ashlin Anusha Bamini, A.M. Rajeswari, M. Brindha, D. Chitra, R. Stewart Kirubakaran, S. Karunya Institute of Technology and Sciences Division of Computer Science and Engineering Tamil Nadu Coimbatore India

ISBN: (纸本)9798331523923

Early detection of colorectal cancer is important as it is one of the most common and deadliest types of cancer worldwide. This project proposes an image classification model based on deep learning architecture that could detect colorectal cancer in its preliminary stages by using an EfficientNetB0. By using the Colorectal Cancer Whole Slide Images (WSI) dataset, a classification model using the WSI dataset to classify tissue samples into six distinct categories of varying grades of cancerous growths and normal. In this model, transfer learning is included to maintain computational efficiency while enhancing accuracy. A user interface with Streamlit, which has real-time image upload, analysis, and prediction display, was also developed. The predictions come with confidence scores, and the Interface also provides educational content for each cancer stage to help raise awareness and prevent the disease. Applications with potential for medical diagnosis and as an educational tool for early detection of colorectal cancer are possible for this system. © 2025 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

R-LIME: Rectangular Constraints and Optimization for Local Interpretable Model-agnostic Explanation Methods 27th

R-LIME: Rectangular Constraints and Optimization for Local I...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Ohara, Genji Kimura, Keigo Kudo, Mineichi Division of Computer Science and Information Technology Graduate School of Information Science and Technology Hokkaido University Sapporo060–0814 Japan

ISBN: (纸本)9783031783531

In recent years, complex machine learning models have been widely introduced in various industrial fields due to their high accuracy. However, their increasing complexity has been a major obstacle to their implementation in sensitive decision-making situations. In order to address this problem, various post-hoc explanation methods have been proposed, but they have not been able to achieve interpretability of both the explanation and its scope. We propose R-LIME, a novel method that interprets complex classifiers within an interpretable scope. R-LIME locally and linearly approximates the complex decision boundary of a black-box classifier within a rectangular region and maximizes the region as long as the approximation accuracy exceeds a given threshold. The resulting rectangular region is interpretable for users because it is expressed as a conjunction of feature predicates. Through qualitative and quantitative comparisons on a real-world dataset, we demonstrate that R-LIME provides more reliable and interpretable explanations than existing methods. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Decentralized MIMO Systems With Imperfect CSI Using LMMSE Receivers

引用

IEEE Journal on Selected Topics in Signal Processing 2025年第2期19卷 331-348页

作者： Zhuang, Zeyan Zhang, Xin Xu, Dongfang Song, Shenghui Eldar, Yonina C. The Hong Kong University of Science and Technology Department of Electronic and Computer Engineering Hong Kong Hong Kong The Hong Kong University of Science and Technology Division of Integrative Systems and Design Hong Kong Hong Kong The Weizmann Institute of Science Department of Mathematics and Computer Science Rehovot7610001 Israel

Centralized baseband processing (CBP) is required to achieve the full potential of massive multiple-input multiple-output (MIMO) systems. However, due to the large number of antennas, CBP suffers from two major issues: 1) Extensive data interconnection between radio frequency (RF) circuitry and the central processing unit;and 2) high-dimensional computation. To this end, decentralized baseband processing (DBP) has been proposed, where the antennas at the base station are partitioned into clusters connected to separate RF circuits and equipped with separate computing units. However, the optimal fusion scheme that maximizes signal-to-interference-and-noise ratio (SINR) and the related performance analysis for DBP with general spatial correlation and imperfect channel state information (CSI) have not been studied. In this paper, we consider a decentralized MIMO system where all clusters adopt linear minimum mean-square error (LMMSE) receivers. We first establish an optimal linear fusion scheme that has high computational and data input/output costs. To reduce the cost, we then propose two suboptimal fusion schemes with reduced complexity. For all three schemes, we study the SINR performance by leveraging random matrix theory and demonstrate conditions under which the suboptimal schemes are optimal. Furthermore, we determine the optimal regularization parameter for the LMMSE receiver, identify the best antenna partitioning strategy, and prove that the SINR will decrease as the number of clusters increases. Numerical simulations validate the accuracy of the theoretical results. © 2025 IEEE.

关键词： Mean square error

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：