检索结果-内蒙古大学图书馆

UPB Scientific Bulletin, Series C: Electrical Engineering and computer science 2024年第1期86卷 3-18页

作者： Mutasher Rashed, Baidaa Popescu, Nirvana Computer Science Dept. National University of Science and Technology POLITEHNICA of Bucharest Romania Computer Science Dept. University POLITEHNICA of Bucharest Romania

Medical imaging coupled with Artificial Intelligence (AI) applications, in particular Deep learning (DL) and Machine Learning (ML), can speed up the disease diagnostic process. The purpose of this work is to present a novel disease detection system by suggesting a new Convolutional Neural Network (CNN) model and combining the CNN features with three of ML classifiers and suggesting a new classifier using the stacking model. The proposed system was used in binary and multi-classification and applied to two different medical datasets. The proposed model was evaluated using accuracy, sensitivity, specificity, precision, recall, F1 score, and AUC, achieving robust results. © 2024, Politechnica University of Bucharest. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

ChatGPT Tweets Sentiment Analysis Using Machine Learning and Data Classification

引用

Informatica (Slovenia) 2024年第7期48卷 103-112页

作者： Sabir, Aliea Ali, Huda A. Aljabery, Maalim A. Faculty of Computer Science and Information Technology Computer Information System Dept. University of Basrah Basrah Iraq Faculty of Computer Science and Information Technology Computer Science Dept. University of Basrah Basrah Iraq

Many things, such as goods, products, and websites are evaluated based on user's notes and comments. One popular research project is sentiment analysis, which aims to extract information from notes and comments as a natural language processing (NLP) to understand and express emotions. In this study we analyzed the sentiment of ChatGPT labeled tweet datasets sourced from the Kaggle community using five Machine Learning (ML) algorithms;decision tree, KNN, Naïve Bayes, Logistic Regression, and SVM. We applied three feature extraction techniques: positive/negative frequency, a bag of words (count vector), and TF IDF. For each classification algorithm. The results were assessed using accuracy measures. Our experiments achieved an accuracy of 96.41% with the SVM classifier when using TF- IDF as a feature extraction technique. © 2024 Slovene Society Informatika. All rights reserved.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

AES-Based Steganography Using Blockchain: A Novel Approach for Secure Text Hiding in Encrypted Images

引用

Informatica (Slovenia) 2024年第21期48卷 67-78页

作者： Salim, Batool Arif Aljabery, Maalim A. Younis, Hameed Abdulkareem Faculty of Computer Science and Information Technology Computer Science Dept. University of Basrah Basrah Iraq

Steganography is a technique used to hide data within other data, emerging from the realization that information is valuable and must be concealed. By considering the potential of blockchain technology, which produces and stores data in an immutable chain, it is clear that steganography can be effectively applied alongside blockchain to hide information. This approach eliminates the need for traditional hiding methods. In this study, we aim to hide text messages within encrypted images using a new steganography-based blockchain, making them appear as ordinary encrypted images. The AES algorithm in CBC mode was used to encrypt both images and texts. Each image was split into 32-byte blocks, with a special block allocated for text, allowing for a text size of 32 characters. The robustness of the proposed technique against differential attacks was assessed using unified averaged changed intensity (UACI), number of pixels change rate (NPCR), entropy analysis, and correlation analysis. The outcomes are 99.6221% for NPCR, 33.5886 for UACI, and 7.9992 for the entropy value. Both statistical measures and differential metrics confirm the algorithm's effectiveness. This shows that the proposed encryption method generates random images and secure texts that are resistant to differential attacks and offer a prominent level of security. © 2024 Slovene Society Informatika. All rights reserved.

关键词： AES algorithm blockchain CBC mode correlation analysis entropy analysis NPCR secure texts steganography UACI

来源：评论

学校读者我要写书评

暂无评论

Hybrid Book Recommendation System Using Collaborative Filtering and Embedding Based Deep Learning

Informatica (Slovenia)

引用

Informatica (Slovenia) 2025年第8期49卷 189-204页

作者： Remadnia, Ouahiba Maazouzi, Faiz Chefrour, Djalel Dept. of Computer Science University of Souk Ahras Algeria

We propose a hybrid e-book recommendation mechanism that leverages collaborative filtering and content-based recommendation paradigms to address inherent challenges in e-learning systems. For collaborative filtering, we present an innovative deep learning framework that utilizes embeddings to enhance accuracy and manage large datasets efficiently. This framework effectively addresses the cold start problem, thereby improving recommendation precision. In content-based recommendation, we introduce a regression-based technique to elevate system capabilities by incorporating content attributes. The integration of these techniques into our deep learning model creates a comprehensive and adaptable solution with scalability and effectiveness. Experiments on the Book Recommendation dataset demonstrate that our solution provides better suggestions and outperforms existing works in terms of Root Mean Square Error (RMSE) and Mean Absolute Error (MAE), achieving values of 0.69 and 0.51, respectively. © 2025 Slovene Society Informatika. All rights reserved.

关键词： Collaborative learning

来源：评论

学校读者我要写书评

暂无评论

Differential Privacy-Based Data Collection for Improving Data Utility and Reducing Computational Overhead

引用

Transactions of the Korean Institute of Electrical Engineers 2025年第1期74卷 102-108页

作者： Kim, Jong Wook Dept. of Computer Science Sangmyung University Korea Republic of

With the rise of real-time data collection through mobile devices such as smartphones, user-driven decision-making systems in various fields such as transportation and healthcare have advanced significantly. However, increasing concerns about the privacy of sensitive information have emerged, leading to the widespread use of differential privacy (DP) to mitigate these risks. Among DP-based data collection methods, local differential privacy (LDP) and distributed differential privacy (DDP) are prominent. While LDP provides low computational overhead, it compromises data utility, while DDP provides better utility at the cost of higher computational overhead. To address these limitations, this paper introduces a DP-compliant (θ,λ) data collection method. The proposed approach collects a fraction of θ of the total items and a fraction of λ of the total user data, achieving improved data utility compared to LDP while significantly reducing computational overhead compared to DDP, resulting in more efficient data collection. Experimental results on real-world datasets show that the proposed method not only improves data utility over LDP, but also effectively reduces computational overhead over DDP. Copyright © The Korean Institute of Electrical Engineers.

关键词： Data collection

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 Flower Images Based on Deep Learning and Machine Learning 8

Classification Flower Images Based on Deep Learning and Mach...

引用

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

作者： Mustfa, Asia Kamal Abdulateef, Salwa Khalid Hameed, Qabas Amer Ahmed, Mohamed Aktham Al-Qaysi, Zaydoon Computer Science and Mathematics College Tikrit University Dept. Computer Science Tikrit Iraq

ISBN: (纸本)9798350354423

Image classification has grown increasingly popular due to the growing significance of machine learning and deep learning. Flower images may sometimes exhibit resemblances in terms of hue, form, and visual characteristics. The problem lies in the classification of flowers. This work employs a hybrid approach that integrates deep learning and machine learning techniques to classify 17 discrete flower species. In order to do this, we utilised the ResNet_50, PCA, and SVM architecture to classify several species from the 'Oxford-17' dataset. With this goal in mind, we have made efforts to improve our model in order to get more accuracy compared to similar methods. Prior to inputting our images into our pretrained model, we resized them, and subsequently fine-tuned the model. The dataset was partitioned into two distinct sets: a training set and a testing set. We attained a precision rate of 95.58% while utilising the 'Oxford-17' dataset. Our approach outperformed previous machine learning and deep learning-based methods on this dataset. © 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

Hybrid CNN-ViT architecture to exploit spatio-temporal feature for fire recognition trained through transfer learning

引用

Multimedia Tools and Applications 2025年第8期84卷 4703-4732页

作者： Shahid, Mohammad Wang, Hong-Cyuan Chen, Yung-Yao Hua, Kai-Lung Dept. of Computer Science and Information Engineering National Taiwan University of Science and Technology Taipei Taiwan Dept. of Electronic and Computer Engineering National Taiwan University of Science and Technology Taipei Taiwan

Fires are becoming one of the major natural hazards that threaten the ecology, economy, human life and even more worldwide. Therefore, early fire detection systems are crucial to prevent fires from spreading out of control and causing destruction. Based on vision sensors, many fire detection techniques have evolved with the recent surge of curiosity in deep learning, which exploits the spatial features of individual images. However, fire can take different forms, scales, and combustion materials can produce different colors, making accurate fire detection from an image challenging. Small fires captured from long-distance cameras lack salient features, further complicating detection. This paper proposes a hybrid structure that uses attention-enhanced convolutional neural networks and vision transformers (CNN-ViT) to detect fire. The proposed CNN-ViT first pays spatial attention to every frame and then aggregates temporal contextual information from neighboring frames to improve detection performance. Due to the limited availability of training fire datasets, the study employs deep transfer learning for feature extraction using pre-trained CNN. We used various metrics to examine the efficacy of the proposed approach. The results showed that the CNN-ViT method outperformed previous models based on spatial-temporal characteristics by achieving a relative improvement in accuracy and F1 score. The satisfactory results on images contaminated with different intensities of noise confirm the robustness of the approach. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Fires

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Based Intrusion Detection for Cybersecurity in Unmanned Aerial Vehicles Network 4

Deep Learning Based Intrusion Detection for Cybersecurity in...

引用

4th IEEE International Conference on Electrical, computer, and Energy Technologies, ICECET 2024

作者： Niyonsaba, Simon Konate, Karim Soidridine, Moussa Moindze Dept. Mathematics and Computer Science Dakar Senegal

ISBN: (纸本)9798350395914

In this article, we have proposed Deep Learning techniques for cybersecurity in Unmanned Aerial Vehicles (UAVs). UAVs, also known as drones, have become versatile tools used in many applications. However, UA V cybersecurity remains a major concern due to the evolution of cyberattacks. Faced with this issue, it is important to give a contribution on intrusion detection systems (IDS) to be applied in UAVs, given that existing cybersecurity solutions still present limitations. It is in this context that we have proposed Deep Learning-based intrusion detection models such as Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM) and the combination of Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) models (CNN+LSTM) and these are evaluated using the CICIDS2017 dataset. Based on their performance, the proposed models are compared with Machine Learning models to decide on the best model for intrusion detection in UAVs. Thus, the results obtained during the experiment indicate that the hybrid CNN-LSTM model obtained a high accuracy of 99.063% compared to the other models. © 2024 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

Tail Optimality of the Nudge-M Scheduling Algorithm

引用

Performance Evaluation Review 2024年第2期52卷 21-23页

作者： Charlet, Nils Van Houdt, Benny Dept. Computer Science University of Antwerp Antwerp Belgium

Recently it was shown that the response time of First-Come- First-Served (FCFS) scheduling can be stochastically and asymptotically improved upon by the Nudge scheduling algorithm in case of light-tailed job size distributions. Such improvements are feasible even when the jobs are partitioned into two types and the scheduler only has information about the type of incoming jobs (but not their size). In this paper we introduce Nudge-M scheduling, where basically any incoming type-1 job is allowed to pass any type-2 job that is still waiting in the queue given that it arrived as one of the last M jobs. We prove that Nudge- M has an asymptotically optimal response time within a large family of Nudge scheduling algorithms when job sizes are light-tailed. Simple explicit results for the the prefactor of Nudge-M are derived as well as explicit results for the optimal parameter M. An expression for the prefactor that only depends on the type-1 and type-2 mean job sizes and the fraction of type-1 jobs is presented in the heavy traffic setting. © 2024 Copyright is held by the owner/author(s).

关键词： Scheduling algorithms

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：