Vietnam Journal of Computer Science

Forecasting the domestic coffee consumption demand is important for policy planning and making the right decisions. Thus, in this study, we try to find out the most suitable model among three proposed models (GM (1,1), DGM (1,1) and Grey Verhulst model (GVM)) for predicting the amount of domestic coffee consumption in Vietnam in the future. Yearly data of coffee consumption from 2010–2020 are used in this research. The experimental results indicated that the GM (1,1) is the most accurate model selected in this study with the lowest average value of $\delta =2.93$%. So, the GM (1,1) model is strongly suggested in the analysis of coffee consumption demand in Vietnam. Finding the right tool will help managers make right decisions easily for sustainable development of the coffee industry in Vietnam in the future.

Software Fault Prediction (SFP) is the most persuasive research area of software engineering. Software Fault Prediction which is carried out within the same software project is known as With-In Fault Prediction. However, local data repositories are not enough to build the model of With-in software Fault prediction. The idea of cross-project fault prediction (CPFP) has been suggested in recent years, which aims to construct a prediction model on one project, and use that model to predict the other project. However, CPFP requires that both the training and testing datasets use the same set of metrics. As a consequence, traditional CPFP approaches are challenging to implement through projects with diverse metric sets. The specific case of CPFP is Heterogeneous Fault Prediction (HFP), which allows the program to predict faults among projects with diverse metrics. The proposed framework aims to achieve an HFP model by implementing Feature Selection on both the source and target datasets to build an efficient prediction model using supervised machine learning techniques. Our approach is applied on two open-source projects, Linux and MySQL, and prediction is evaluated based on Area Under Curve (AUC) performance measure. The key results of the proposed approach are as follows: It significantly gives better results of prediction performance for heterogeneous projects as compared with cross projects. Also, it demonstrates that feature selection with feature mapping has a significant effect on HFP models. Non-parametric statistical analyses, such as the Friedman and Nemenyi Post-hoc Tests, are applied, demonstrating that Logistic Regression performed significantly better than other supervised learning algorithms in HFP models.

In this paper, a production planning problem with inventory and backordering levels is discussed. It is assumed that cumulative demands in periods are uncertain and an interval uncertainty representation with continuous budget is used to model this uncertainty. The robust minmax criterion is applied to compute an optimal production plan. A row and column generation algorithm is constructed for solving the problem. Results of some computational tests are shown which demonstrate that the algorithm is efficient for the instances with up to 100 periods and returns solutions that are robust against the uncertainty in demands.

Legal ontologies play a key role in various legal applications and have been broadly used by many stakeholders. Innovative systems and ontologies in the law hold potential to conduct legal research. With the needs for legal information management in smart applications, especially for Vietnamese law, it is vitally important to construct core legal ontologies for knowledge representation. This study proposes a core ontology for Vietnamese legal documents which covers general legal domain called as ViLO. The ViLO ontology mainly consists of related institutions of Vietnamese political system, types and structures of legal documents. The method of the NeOn-based collaborations among domain experts and ontology engineers was conducted to build up the ViLO ontology. Through FOCA-based validation results, the proposed method was shown to be effective and efficient. The resulting ontology was demonstrated to be reliable and enriched. The ViLO ontology is supposed to be a basis for further constructions of domain ontologies and artificial intelligence applications in Vietnamese law.

Feature selection has become a powerful dimensional reduction strategy and an effective tool in handling high-dimensional data. Feature selection aims to reduce the dimension of the feature space, to speed up and reduce the cost of the learning model and that by selecting the most relevant feature subset to data mining and machine learning tasks. The selection of optimal feature subset is an optimization problem that proved to be NP-hard. Metaheuristics are traditionally used to deal with NP-hard problems since they are well known for solving complex and real-world problems in reasonable period of time. Genetic algorithm (GA) is one of the most popular metaheuristics algorithms, which proved to be effective for an accurate feature selection task. However, in the last few decades, data have become progressively larger in both numbers of instances and features. This paradigm is being popularly termed as Big Data. With the tremendous growth of dataset sizes, most current feature selection algorithms and exceptionally GA become unscalable. To improve the scalability of a feature selection algorithm on big data, the distributed computing strategy is always adopted such as MapReduce model and Hadoop system. In this paper, we first present a review for the most recent works which handle the use of Parallel Genetic algorithm in large datasets. Then, we will propose a new Parallel Genetic algorithm based on the Coarse-grained parallelization model (island model). The parallelization of the process and the distribution of the partitioning of data will be performed using Hadoop system with an Amazon cluster. The performance and the scalability of the proposed method were theoretically and empirically compared to the existing feature selection methods when handling large-scale datasets and results confirm the effectiveness of our proposed method.

Recently, it was shown that convolutional neural networks (CNNs) with suitably annotated training data and results produce the best traffic sign detection (TSD) and recognition (TSR). The whole system’s efficiency is determined by the data collecting process based on neural networks. As a result, the datasets for traffic signs in most nations throughout the globe are difficult to recognize because of their diversity. To address this problem, we must create a synthetic image to enhance our dataset. We apply deep convolutional generative adversarial networks (DCGAN) and Wasserstein generative adversarial networks (Wasserstein GAN, WGAN) to generate realistic and diverse additional training images to compensate for the original image distribution’s data shortage. This study focuses on the consistency of DCGAN and WGAN images created with varied settings. We utilize an actual picture with various numbers and scales for training. Additionally, the Structural Similarity Index (SSIM) and the Mean Square Error (MSE) were used to determine the image’s quality. In our study, we computed the SSIM values between pictures and their corresponding real images. When more training images are used, the images created have a significant degree of similarity to the original image. The results of our experiment reveal that the most leading SSIM values are achieved when 200 total images of $32\times 32$ pixels are utilized as input and the epoch is 2000.

The quest for customer intelligence to create value in marketing has highlighted the significance of the research focus of this paper. Customer intelligence, which is defined as understandings or insights resulting from the application of analytic techniques, plays a significant role in the survival and prosperity of enterprises in the knowledge-based economy. In this light, the paper has developed a framework of customer intelligence to support marketing decisions through the lens of knowledge-based theory. The proposed framework aims at supporting enterprises to identify the right customer data for the right customer intelligence corresponding with the right marketing decisions. In this light, four types of customer intelligence are clarified including product-aware intelligence, customer DNA intelligence, customer experience intelligence, and customer value intelligence. The applications of customer intelligence are also elucidated with relevant marketing decisions to maximize value creation. To illustrate the framework, an example is presented. The importance and originality of this study are that it responds to changes in customer intelligence in the age of massive data and covers multifaced aspects of marketing decisions.