检索结果-内蒙古大学图书馆

2023 International Conference on Next-Generation Computing, IoT and Machine Learning, NCIM 2023

作者： Jony, Asaduzzaman Miah, Abu Saleh Musa Islam, Muhammad Nazrul Dept. of Computer Science and Engineering Dhaka Bangladesh The University of Aizu Dept. of Computer Science and Engineering Aizuwakamatsu Japan Dept. of Computer Science and Engineering Dhaka Bangladesh

ISBN: (纸本)9798350316001

Nowadays, the DHCP starvation attack is a crucial attack that denied the services for the legitimate network user where the attacker mainly occupies all the IP addresses in the DHCP server pool. Most of the existing studies proposed ICMP (Internet Control Message Protocol) and the ARP (Address Resolution Protocol) based techniques to detect the DHCP starvation attack. However, the ICMP-based detection is ineffective if the client has an active host-based firewall that blocks the ICMP ECHO REQUEST, while the ARP-based detection does not work for DHCP networks separated by a DHCP relay agent and works only within the same or local network. Therefore, the objective of this research is to propose an effective technique to detect DHCP starvation attack detection through port scanning to address the limitations of ICMP and ARP-based detection methods. To attain this objective, this study first highlights the limitations of existing detection methods demonstrating insightful facts. Secondly, the study proposed a port scan-based DHCP starvation attack detection method for local and remote (relay) DHCP networks. Finally, the effectiveness and validation of the proposed techniques were demonstrated using the Multivendor Network Emulation software (EVE-NG). The study showed that the proposed port scanning-based technique could accurately detect the DHCP starvation attack while overcoming the limitations of the ICMP and ARP techniques. © 2023 IEEE.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

Chatbot Based on Emotions Using Deep Learning 1

Chatbot Based on Emotions Using Deep Learning

引用

1st International Conference on Optimization Techniques for Learning, ICOTL 2023

作者： Nirupa, V. Renuka, G.B. Naga Lakshmi, B. Sumanth Kumar, C.P. Rudra Sekhar Reddy, A. Paramesh, J. Dept. of Computer Science & Engineering Madanapalle India Dept. of Computer Science & Engineering Anantapur India

ISBN: (纸本)9798350328042

Human emotions are unpredictable as they change very frequently. Human emotions areinvoluntary mental states of feelings and are accompanied by physiological changes. Emotions which can be detected through the facial expressions play a major role and are very much important for non-verbal communication as they reflect on their faces. In the process of developing computer modeling of human's emotions, a lot researches have been made. Therefore, a chatbot detecting the emotions can be a better approach for detecting emotions. In this study, it demonstrate that Convolutional Neural Networks (CNNs) offer a superior method for detecting human emotions and develop a deep learning model that can accurately classify the facial expressions. The FER 2013 dataset was used in this study's training. The evaluation of the suggested approach produces pretty accurate findings, which could inspire academics to develop a Chabot model based on emotions in the future. © 2023 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Classifying white blood cells using combining different convolutional neural networks

引用

Multimedia Tools and Applications 2025年 1-24页

作者： Toptaş, Murat Toptaş, Buket Hanbay, Davut Software Eng. Dept. Engineering and Natural Science Faculty Bandırma Onyedi Eylül University Balıkesir Turkey Computer Eng. Dept. Engineering Faculty Inonu University Malatya44280 Turkey

White blood cells are warrior cells that protect the human body against external factors. Each of these warrior cells performs a distinct task, making every piece of information about them highly valuable in the medical field. In this article, a classification framework for the four known types of white blood cells is proposed. It is hoped that the classification of these types will contribute to the prediction of diseases such as AIDS, malaria, leukemia, and many others. In the proposed method, images of white blood cells from the Blood Cell Classification and Detection dataset were used as input to Convolutional Neural Networks. The feature vectors extracted using these Convolutional Neural Network architectures were combined into a single vector. A Minimum Redundancy Maximum Relevance algorithm was then employed to identify the most effective features within the feature vector. Experiments were conducted using these selected features, and the analysis of each experiment was reported in detail. The Support Vector Machines classifier achieved an accuracy of 98.63% in classifying white blood cell types by combining features from multiple deep learning architectures. The experimental results demonstrated that the features obtained from different layers of the Convolutional Neural Networks had varying impacts on the classification performance. © The Author(s) 2025.

关键词： Convolutional neural networks

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

TCCL: Discovering Better Communication Paths for PCIe GPU Clusters 24

TCCL: Discovering Better Communication Paths for PCIe GPU Cl...

引用

29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, ASPLOS 2024

作者： Kim, Heehoon Ryu, Junyeol Lee, Jaejin Dept. of Computer Science and Engineering Seoul National University Seoul Korea Republic of Dept. of Data Science Dept. of Computer Science and Engineering Seoul National University Seoul Korea Republic of

ISBN: (纸本)9798400703867

Exploiting parallelism to train deep learning models requires GPUs to cooperate through collective communication primitives. While systems like DGX, equipped with proprietary interconnects, have been extensively studied, the systems where GPUs mainly communicate through PCIe have received limited attention. This paper introduces TCCL, a collective communication library designed explicitly for such systems. TCCL has three components: a profiler for multitransfer performance measurement, a pathfinder to discover optimal communication paths, and a modified runtime of NCCL to utilize the identified paths. The focus is on ring-based collective communication algorithms that apply to popular communication operations in deep learning, such as AllReduce and AllGather. The evaluation results of TCCL on three different PCIe-dependent GPU clusters show that TCCL outperforms (up to ×2.07) the state-of-the-art communication libraries, NCCL and MSCCL. We also evaluate TCCL with DL training workloads with various combinations of parallelism types. © 2024 Copyright held by the owner/author(s).

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Exploring Advanced Approaches: A Comprehensive Analysis of Machine Learning and Deep Neural Networks in Spectrum Sensing Applications 4

Exploring Advanced Approaches: A Comprehensive Analysis of M...

引用

4th International Conference on Ubiquitous Computing and Intelligent Information Systems, ICUIS 2024

作者： Karthiga, G. Saravanan, K. Amc Engineering College Dept. of Computer Science and Engineering Karnataka Bengaluru India New Horizon College of Engineering Dept. of Computer Science and Engineering Karnataka Bengaluru India

ISBN: (数字)9798331529635

ISBN: (纸本)9798331529635

The increasing demand for wireless communication resources has intensified the need for effective spectrum sensing techniques to alleviate the scarcity of available spectral bands. This survey paper presents an indept. exploration and comparative analysis of various spectrum sensing methodologies, focusing on Machine Learning (ML) and Deep Neural Network (DNN) approaches. The study delineates the landscape of traditional spectrum sensing techniques, encompassing energy detection, matched filtering, cyclo-stationary feature detection, and cooperative spectrum sensing. This paper explains sensing using machine learning-based such as Support Vector Machines (SVM), Random Forest, Neural Networks, and Hidden Markov Models (HMM) are systematically elucidated. Moreover, the paper meticulously scrutinizes the advancements in deep learning-based spectrum sensing, encapsulating the utilization of Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and Deep Reinforcement Learning (DRL) methodologies. The discussion encompasses their applications, advantages, and limitations in the context of spectrum sensing. © 2024 IEEE.

关键词： Hidden Markov models

来源：评论

学校读者我要写书评

暂无评论

Personalized Movie Recommendation Based on User Preferences Using Optimized Sequential Transformer Model

Personalized Movie Recommendation Based on User Preferences ...

引用

2024 International Conference on Artificial Intelligence and Emerging Technology, Global AI Summit 2024

作者： Ravikumar, R.N. Jain, Sanjay Sarkar, Manash Amity University Rajasthan Dept. of Computer Science and Engineering Jaipur India Atria Institute of Technology Dept. of Computer Science and Engineering Banglore India

ISBN: (纸本)9798350379716

This study explores the application of a Transformer based model to the 'MovieLens 1M' and 'MovieLens 10M' datasets provided by GroupLens, which includes one million and ten movie ratings. The Transformer model, known for its proficiency in handling sequence-to-sequence tasks, employs multi-head self-attention mechanisms and position-wise feed-forward networks. Our implementation, developed in PyTorch, benefits from its capacity for automatic differentiation and GPU acceleration, which significantly enhances the training efficiency. The model underwent rigorous hyperparameter tuning and optimization to adapt optimally to the characteristics of the dataset. Performance evaluation using the Normalized Discounted Cumulative Gain (NDCG) metric demonstrates that the Transformer model substantially outperforms a conventional popular recommendation system across various top-K rankings. Specifically, for the MovieLens 1M dataset, the Transformer model achieved NDCG scores of 0.0455, 0.0805, 0.0995, and 0.1273 at top 1, 3, 5, and 10, respectively. Comparatively, the popular recommendation system scored 0.0023, 0.0044, 0.0061, and 0.0091 at these same rankings. This trend of superior performance by the Transformer model is also consistent across the MovieLens 10M dataset, further confirming its effectiveness in ranking highly relevant items at the top of the list. Also, to address quality and utility of recommendations, MAP, Precision, Recall, F1 Score, Coverage and Serendipity metrics evaluated. These results underscore the effectiveness of Transformer models in extracting and leveraging complex patterns in sequence data, demonstrating a clear superiority over traditional methods in recommendation systems. This study highlights the potential of deep learning architectures to revolutionize fields reliant on understanding user preferences and sequential data interactions. © 2024 IEEE.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Predictive Modeling and Dynamic Analysis of Price Trends in eCommerce using ML Technique 3

Predictive Modeling and Dynamic Analysis of Price Trends in ...

引用

3rd IEEE North Karnataka Subsection Flagship International Conference, NKCon 2024

作者： Banerjee, Pallab Prasad, Vishal Thakur, Kanika Mitra, Dipra Gaurav, Kumar Kanrar, Soumen Amity University Dept. of Computer Science Engineering Jharkhand Ranchi India Galgotias University Dept. of Computer Science Engineering Greater Noida India

ISBN: (纸本)9798350364569

In the ever-evolving landscape of eCommerce, staying ahead of pricing trends is paramount for both consumers and sellers. This project presents an advanced Ecommerce Product Price Tracker with Price Prediction capabilities, aimed at empowering users with foresight into future pricing dynamics. Supervised Machine Learning algorithms, encompassing regression and time series analysis, form the backbone of predictive modeling, enabling accurate forecasts of forthcoming price movements. The resultant tool not only provides real-time tracking of current product prices but also furnishes predictive analytics, empowering users with actionable insights. By bridging the gap between data-driven insights and eCommerce dynamics, this project contributes to fostering efficiency and efficacy in the vibrant eCommerce ecosystem. © 2024 IEEE.

关键词： Predictive analytics

来源：评论

学校读者我要写书评

暂无评论

Breast Cancer Classification via the Use of ML and DL: A Comprehensive Review 3

Breast Cancer Classification via the Use of ML and DL: A Com...

引用

3rd International Conference on Automation, Computing and Renewable Systems, ICACRS 2024

作者： Sarang, Ruvanshi Dabhi, Vipul Shah, Arpit Dept. of Computer Science Engineering Parul University Vadodara India Dept. of Computer Engineering Parul University Vadodara India

ISBN: (纸本)9798331532420

New and improved methods of diagnosis are needed because breast cancer is still the leading cancer-related killer worldwide. Updates to the methods used to categorize breast cancer have emerged because of recent advances in DL and ML. This review paper’s goal in conducting this research is to bring together existing breast cancer diagnostic and classification methods that make use of deep learning and machine learning techniques. We examine the many approaches, datasets, and performance indicators used in the industry and point out the pros and cons of each as part of the review paper. This review aims to thoroughly examine all the methods that are now in use, spot any trends, and propose new areas for research. This review helps researchers and practitioners understand the current state of breast cancer categorization by combining the findings of past research. Discuss recent advances in ML/DL techniques for improving classification, such as ensemble methods, transfer learning, or hybrid models. Additionally, propose the use of fine-tuning of hyperparameters or novel architectures to enhance classification. © 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

From Image to Emotion: Exploring CNN Architectures for Facial Emotion Recognition

From Image to Emotion: Exploring CNN Architectures for Facia...

引用

2024 IEEE International Conference on Computing, Applications and Systems, COMPAS 2024

作者： Mahmud Rafi, M Shahriar Alam, Tazrian Chowdhury, Linkon Roy Chowdhury, Bristy East Delta University Dept. of Computer Science and Engineering Chattogram Bangladesh Bgc Trust University Dept. of Computer Science and Engineering Chattogram Bangladesh

ISBN: (纸本)9798331529765

Facial Emotion Recognition (FER) has made significant accomplishments over the past few years while the implications of it are quite extensive and are found in different domains. In this paper, a deep learning-based architecture is proposed for FER where we mainly focus on the main components, including dataset preparation;preprocessing methods;feature extraction techniques;classification algorithm;and XAI approaches. The proposed model based on convolutional neural networks (CNNs) operates with feature extraction from facial images. Preprocessing techniques such as resizing, normalization, and augmentation are used to elevate the quality and variety of the dataset. Due to the architecture of VGG16 and ResNet50, we implement three CNN models to extract discriminant features from facial expressions. Meanwhile, each model works as a classifier so that it can make accurate classifications. On the other hand, we use saliency maps to give the model the computation process in a more interpretable manner. Through multiple experimentation and evaluation, the established model shown the high accuracy of the regional analysis of facial emotions, and, as a result, FE R systems can be updated by the improved performance and explainability. © 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

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：