检索结果-内蒙古大学图书馆

Practical cloud storage auditing using serverless computing

science China(Information sciences) 2024年第3期67卷 33-47页

作者： Fei CHEN Jianquan CAI Tao XIANG Xiaofeng LIAO College of Computer Science and Software Engineering Shenzhen University College of Computer Science Chongqing University

Cloud storage auditing research is dedicated to solving the data integrity problem of outsourced storage on the cloud. In recent years, researchers have proposed various cloud storage auditing schemes using different techniques. While these studies are elegant in theory, they assume an ideal cloud storage model;that is, they assume that the cloud provides the storage and compute interfaces as required by the proposed schemes. However, this does not hold for mainstream cloud storage systems because these systems only provide read and write interfaces but not the compute interface. To bridge this gap, this work proposes a serverless computing-based cloud storage auditing system for existing mainstream cloud object storage. The proposed system leverages existing cloud storage auditing schemes as a basic building block and makes two adaptations. One is that we use the read interface of cloud object storage to support block data requests in a traditional cloud storage auditing scheme. Another is that we employ the serverless computing paradigm to support block data computation as traditionally required. Leveraging the characteristics of serverless computing, the proposed system realizes economical, pay-as-you-go cloud storage auditing. The proposed system also supports mainstream cloud storage upper layer applications(e.g., file preview) by not modifying the data formats when embedding authentication tags for later auditing. We prototyped and open-sourced the proposed system to a mainstream cloud service, i.e., Tencent Cloud. Experimental results show that the proposed system is efficient and promising for practical use. For 40 GB of data, auditing takes approximately 98 s using serverless computation. The economic cost is 120.48 CNY per year, of which serverless computing only accounts for 46%. In contrast, no existing studies reported cloud storage auditing results for real-world cloud services.

关键词： cloud storage auditing serverless computing object storage usability

来源：评论

学校读者我要写书评

暂无评论

CLASSIFICATION BY A STACKING MODEL USING CNN FEATURES FOR MEDICAL IMAGE DIAGNOSIS

UPB Scientific Bulletin, Series C: Electrical Engineering an...

引用

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

Heuristic Algorithms for Software Modules Clustering 3

Heuristic Algorithms for Software Modules Clustering

引用

3rd International Conference on Machine Learning and Data Engineering, ICMLDE 2024

作者： Ali, Ali H. Taha, Dujan B. Software Dept. College of Computer Science and Mathematics Mosul University Iraq Computer Science Dept. College of Computer Science and Mathematics Mosul University Mosul Iraq

In the fields of software engineering, the maintenance phase takes the most effort. Software Module Clustering (SMC), as a part of reverse engineering, is used for the purpose of creating structural models from the source code enhancing its comprehensibility. Finding the best clusters is an NP-hard problem. The method of software module clustering aims to extract the best clusters, which involves Increase cohesion and reduce coupling. This re-search addresses a set of problems with the aim of solving them, which are drawback found in most previous studies. This paper adopts three main methods to solve Software Modules Clustering problem (SMCP), a Teaching-Learning-Based-optimization (TLBO) algorithm, a Black Widow optimization (BWO) algorithm, and the third is a hybrid algorithm combining the previous two methods. These algorithms were used to cluster software modules and were evaluated based on MQ (Modularity Quality), cohesion, coupling, and stability. To determine the optimal number of clusters for each reference program, the Louvain algorithm is used, which works on detecting communities in networks. The study also experintly examined the impact of the chaos, random, Lorenzo methods in the initial generation of solutions on the quality of the results and stability. Considering the results of the experiments conducted on eight standard applications, the hybrid algorithm performs better in SMC problems than the TLBO and BWO. The performance of these algorithms also improves significantly, when their initial populations are generated using the logistic Lorenz and Chaos method rather than a random one. 6.644548537, 6.318318013, and 4.375766992 are the average MQ of the clusters that were formed for the selected casses set using the Hybrid method, BWO, and TLBO, respectively. © 2025 The Author(s).

关键词： Reverse engineering

来源：评论

学校读者我要写书评

暂无评论

A Novel Music Recommendation System Using Filtering Techniques

Informatica (Slovenia)

引用

Informatica (Slovenia) 2024年第4期48卷 595-610页

作者： Vashishtha, Srishti Varshney, Deepika Sarin, Eva Kaur, Simran Computer Science and Engineering Dept. Bharati Vidyapeeth’s College of Engineering GGSIPU New Delhi India Computer Science and Engineering Dept. Jaypee Institute of Information Technology Noida India

With the growth of the World Wide Web, a large amount of music data is available on the Internet. A large number of people listen to music online rather than downloading and listening offline. But only some sites provide personalized and accurately recommended songs while they listen to an auto-playing playlist. Hence the need for recommendation systems arises. Two approaches can be applied to the recommendation system: content based filtering and collaborative filtering. While in content-based filtering approach, analysis on the songs’ content which has been preferred by the user in history is done and the songs with relative similarity are recommended. While latter suggests songs that certain users of similar listening pattern have preferred. But collaborative filtering-based recommendation systems not only requires time to attain stability but also might recommend unsuitable music because it is not personalized to each user’s preference. Also, the latter requires the songs to be listened by a few users already to recommend it any other user. Hence for overall analysis, answers to few questions need to be implemented in recommendation systems: the very first one is how the properties should be analyzed, next one is how the analysis should be done and last is how the songs related to the user’s preference should be chosen. So, for suggesting the better system which solves these three questions as well as provides better and personalized recommendations, In this paper we build a collaborative filtering as well as content based filtering recommendation system, where various factors determine the essence of the songs, i.e. liveliness, keys used, loudness, pitch, valence, etc., are analyzed for comparison. From the experimental analysis in has been identified that content-based filtering technique performed best on KNN machine learning classifier with accuracy of 85%. © 2024 Slovene Society Informatika. All rights reserved.

关键词： Collaborative filtering

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

Informatica (Slovenia)

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

Programming Language Identification via Selection of Target Categories and Machine Learning for Unknown Category

引用

Transactions of the Korean Institute of Electrical Engineers 2025年第5期74卷 950-956页

作者： Yoo, Heejeong Lee, Eunsu Yoo, Hoon Dept. of Computer Science Sangmyung University Korea Republic of

This paper presents a method for an efficient programming language identification technique which consists of selection of target categories and machine learning for unknown category. As software development scales are complicated, the source codes in use are getting huge and diverse. A programming language identification technique is essential to manage source codes effectively. However, existing research lacks a clear rationale for target categories selection criteria and does not address the issue of unknown categories. In this paper, we propose a method for selecting target categories based on frequency of use and importance, and machine learning techniques to handle unknown categories. We present three methods for classifying the unknown categories. Experimental results demonstrate that the proposed methods effectively classify the unknown categories. Copyright © The Korean Institute of Electrical Engineers.

关键词： Software design

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

ChatGPT Tweets Sentiment Analysis Using Machine Learning and Data Classification

Informatica (Slovenia)

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

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

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：