Vietnam Journal of Computer Science

In recent years, community detection in social network analysis has been a hot research topic that has attracted much more attention in the scientific community and a large number of articles have already been published in the literature. Community detection problems focus on determining the subgraphs of the network that have dense edges and whose nodes are expected to have similar features. Community detection has significant applications in different domains of social network analysis such as sociology, business, criminal detection and recommendation systems. The computational complexity is hampered by the huge size and the dynamic nature of social networks. This paper introduces a comprehensive survey of community detection methods in social networks based on mining attributes and interactions of users. We divide the community detection approaches into three basic categories, namely (1) node content-based approaches, (2) edge content-based approaches, and (3) node- and edge content-based approaches. We also discuss in detail the main idea of each method that is suitable for social network data. Furthermore, to promote the study of community detection, we introduce the benchmark datasets from available sources. Last, we present further research directions as well as some open challenges for the community detection problem in social networks.

Clustering methodologies are pivotal in enhancing the recommendation systems powered by collaborative filtering (CF). These systems commonly rely on CF approaches to generate recommendations based on similarities. While conventional user clustering methods are prevalent, there’s a growing necessity to delve into bio-inspired clustering techniques to elevate the recommendation generation process. This paper introduces a novel ensemble method termed Bio-Inspired Clustering Collaborative Filtering (BICCF) designed explicitly for recommendation systems. By harnessing swarm intelligence, this approach aims to refine the precision of recommendations within user-based CF frameworks. The study conducts experiments using real-world datasets sourced from MovieLens to assess the efficacy of this proposed method. The findings reveal marked enhancements in accuracy and efficiency, as evaluated through metrics such as Recall, Precision, MAE, and RMSE surpassing the performance of established baseline methods.

In the dynamic field of fog computing, there is a clear trend toward exploiting local, resource-rich nodes to bypass traditional cloud infrastructure limitations. This study introduces an innovative method for enhancing the reliability of Wi-Fi systems, crucial in fog computing, by integrating quality-focused user feedback. Our approach significantly enhances the assessment of Wi-Fi system trustworthiness by emphasizing user perspectives. While traditional metrics such as Availability, Performance, and Security Parameters are crucial for defining Quality of Service (QoS), our research also integrates user feedback as a key, albeit secondary, factor in assessing Wi-Fi node trustworthiness. Designed to improve the evaluation process, this method combines system-generated QoS metrics with user feedback to subtly increase trust assessment objectivity. This not only connects technical service quality with user experiences but also strengthens trust and reliability in fog computing. Utilizing sophisticated cloud theory techniques, our model employs both backward and forward cloud generators — the backward generator converts QoS data into qualitative insights, while the forward generator combines these insights with user feedback to thoroughly evaluate Wi-Fi node service quality. The integration of user feedback allows for a more dynamic and responsive system evaluation, addressing the limitations of previous models by providing a comprehensive assessment that aligns technical service quality with user experiences. This enhancement in trust evaluation is achieved by skillfully blending QoS metrics and user feedback to create a more objective trust value.

Internet of Things (IoT) refers to the network of interconnected physical devices, vehicles, home appliances, and other items embedded with sensors, software, and connectivity, enabling them to collect and exchange data. IoT forensics aim to investigate cybercrimes, security breaches, and other malicious activities that may have taken place on these connected devices. In particular, Electromagnetic Side-Channel Analysis (EM-SCA) has become an essential tool for IoT forensics due to its ability to reveal confidential information about the internal functions of IoT devices without interfering with these devices or wiretapping their networks. However, the accuracy and reliability of EM-SCA results can be limited by device variability, environmental factors, and data collection and processing methods. In fact, very few studies have explored potential solutions to address the significant impact of these limitations on the accuracy of EM-SCA approaches applied to crossed IoT devices. Therefore, this paper examines the impact of device variability on the accuracy and reliability of machine learning (ML)-based approaches for EM-SCA. We first present the background, basic concepts and techniques used to evaluate the limitations of current EM-SCA approaches and datasets. Our study then addresses one important limitation, which is caused by the multi-core architecture of the processors (aka. System-On-Chip). We present an approach to collect the EM-SCA datasets and demonstrate the feasibility of using transfer learning to obtain more meaningful and reliable results from EM-SCA in IoT forensics of crossed-IoT devices. Moreover, this study contributes a new dataset for using deep learning (DL) models in analyzing Electromagnetic Side-Channel data with regard to the cross-device portability matter.

Our investigation aims at pre-training clustering models to summarize Vietnamese texts. For this purpose, we create a large-scale dataset by collecting Vietnamese articles from newspaper websites and extracting the plain text to build the dataset, including 1,101,101 documents. We propose a new single-document extractive text summarization model based on clustering models. Our proposal clusters the documents with the hard clustering k-means algorithm and the soft clustering LDA (Latent Dirichlet Allocation) algorithm. Then, based on the pre-training clustering models, a summary model is used to select the salient sentence in the input text to construct the summary. The empirical results showed that our summary model achieved 51.22% ROUGE-1, 17.62% ROUGE-2 and 29.16% ROUGE-L on the testing set. Besides the traditional word representation such as BoW (Bag-of-Words), we also use the word meaning-based tools like FastText and BERT (Bidirectional Encoder Representations from Transformers) in our model. The additional benefit of our proposed extractive summary model is that the output summary is a long-text, readable document. Furthermore, the model’s architecture is straightforward, easy to understand and runs on cost-efficient resources like arm CPU and GPU too.

The implementation of parallel applications is always a challenge. It embraces many distinctive design decisions that are to be taken. The paper presents issues of parallel processing with use of .NET applications and popular Database Management Systems (DBMSes). In the paper, four design dilemmas are addressed: how efficient is the auto-parallelism implemented in the .NET TPL library, how do popular DBMSes differ in serving parallel requests, what is the optimal size of data chunks in the data parallelism scheme, and how the TPL auto-parallelism behaves in the public clouds. They are analyzed in the context of the typical and practical business case originated from IT solutions which are dedicated for the energy market participants. The paper presents the results of experiments conducted in a controlled, on-premises and cloud environments. The experiments allowed to compare the performance of the TPL auto-parallelism with a wide range of manually set numbers of worker threads. They also helped to evaluate four DBMSes: Oracle, MySQL, PostgreSQL, and MSSQL in the scenario of serving parallel queries. Finally, they showed the impact of data chunk sizes on the overall performance.