Volumen 27 (2022): Edición 2 (December 2022)

A method is suggested to find all local minima and the global minimum of an unknown two-variable function bounded on a given rectangle regardless of the rectangle area. The method has eight inputs: five inputs defined straightforwardly and three inputs, which are adjustable. The endpoints of the initial intervals constituting the rectangle and a formula for evaluating the two-variable function at any point of this rectangle are the straightforward inputs. The three adjustable inputs are a tolerance with the minimal and maximal numbers of subintervals along each dimension. The tolerance is the secondary adjustable input. Having broken the initial rectangle into a set of subrectangles, the nine-point iterated rectangle dichotomy “gropes” around every local minimum by successively cutting off 75 % of the subrectangle area or dividing the subrectangle in four. A range of subrectangle sets defined by the minimal and maximal numbers of subintervals along each dimension is covered by running the nine-point rectangle dichotomy on every set of subrectangles. As a set of values of currently found local minima points changes no more than by the tolerance, the set of local minimum points and the respective set of minimum values of the surface are returned. The presented approach is applicable to whichever task of finding local extrema is. If primarily the purpose is to find all local maxima or the global maximum of the two-variable function, the presented approach is applied to the function taken with the negative sign. The presented approach is a significant and important contribution to the field of numerical estimation and approximate analysis. Although the method does not assure obtaining all local minima (or maxima) for any two-variable function, setting appropriate minimal and maximal numbers of subintervals makes missing some minima (or maxima) very unlikely.

There are considerable obstacles in the transport sector of developing countries, including poor road conditions, poor road maintenance and congestion. The dire impacts of these challenges could be extremely damaging to both human lives and the economies of the countries involved. Intelligent Transportation Systems (ITSs) integrate modern technologies into existing transportation systems to monitor traffic. Adopting Vehicular Adhoc Network (VANET) into the road transport system is one of the most ITS developments demonstrating its benefits in reducing incidents, traffic congestion, fuel consumption, waiting times and pollution. However, this type of network is vulnerable to many problems that can affect the availability of services. This article uses a Fuzzy Bayesian approach that combines Bayesian Networks (BN) and Fuzzy Logic (FL) for predicting the risks affecting the quality of service in VANET. The implementation of this model can be used for different types of predictions in the networking field and other research areas.

The Mekong Delta region of Vietnam has great potential for agricultural development thanks to natural incentives. Many livestock industries have developed for a long time and play an important role in the country with many agricultural export products. In the era of breakthrough technologies and advances in information technology, many techniques are used to support the development of smart agriculture. In particular, computer vision techniques are widely applied to help farmers save a lot of labour and cost. This study presents an approach for counting eels based on Mathematical Morphology Operations and Boundary Detection from images of breeding eels captured with the proposed photo box. The proposed method is evaluated using data collected directly from a breeding eel farm in Vietnam. The authors of the research evaluate and investigate the length distribution of eels to select the appropriate size for counting tasks. The experiments show positive results with an average Mean Absolute Error of 2.2 over a tray of more than 17 eels. The contribution of the research is to provide tools to support farmers in eel farms to save time and effort and improve efficiency.

The research examines the accuracy of current solution models for the Arabic text sentiment classification, including traditional machine learning and deep learning algorithms. The main aim is to detect the opinion and emotion expressed in Telecom companies’ customers tweets. Three supervised machine learning algorithms, Logistic Regression (LR), Support Vector Machine (SVM), and Random Forest (RF), and one deep learning algorithm, Convolutional Neural Network (CNN) were applied to classify the sentiment of 1098 unique Arabic textual tweets. The research results show that deep learning CNN using Word Embedding achieved higher performance in terms of accuracy with F1 score = 0.81. Furthermore, in the aspect classification task, the results reveal that applying Part of Speech (POS) features with deep learning CNN algorithm was efficient and reached 75 % accuracy using a dataset consisting of 1277 tweets. Additionally, in this study, we added an additional task of extracting the geographical location information from the tweet content. The location detection model achieved the following precision values: 0.6 and 0.89 for both Point of Interest (POI) and city (CIT).

Estimation of work efficiency is one of the important tasks in company management and analysis of workers’ activities. The environment for determining the efficiency of workers is the use of one or more IS of any kind, within the framework of which the worker’s duties are accomplished. This process can be performed both from home (isolated from the work environment and co-workers) and in the office on-site. Another aspect is related to the fact that a worker can work both with only one IS, or with multiple specialised systems in parallel, which requires the simultaneous integration of several data sources and the parallel reading and analysis of information relevant to worker activities. The task of work efficiency estimation is especially complicated if the company’s activity domain is narrowly specific. In this case, solving such a task of working hour accounting and efficiency estimation is not a trivial accumulation of statistical data, but requires a dedicated method. The work of an engineering system designer is one of the examples of such specific activities. Therefore, exactly this domain was chosen as an application case of the method and metrics proposed in the paper.

In software development, defects influence the quality and cost in an undesirable way. Software defect prediction (SDP) is one of the techniques which improves the software quality and testing efficiency by early identification of defects(bug/fault/error). Thus, several experiments have been suggested for defect prediction (DP) techniques. Mainly DP method utilises historical project data for constructing prediction models. SDP performs well within projects until there is an adequate amount of data accessible to train the models. However, if the data are inadequate or limited for the same project, the researchers mainly use Cross-Project Defect Prediction (CPDP). CPDP is a possible alternative option that refers to anticipating defects using prediction models built on historical data from other projects. CPDP is challenging due to its data distribution and domain difference problem. The proposed framework is an effective two-stage approach for CPDP, i.e., model generation and prediction process. In model generation phase, the conglomeration of different pre-processing, including feature selection and class reweights technique, is used to improve the initial data quality. Finally, a fine-tuned efficient bagging and boosting based hybrid ensemble model is developed, which avoids model over -fitting/under-fitting and helps enhance the prediction performance. In the prediction process phase, the generated model predicts the historical data from other projects, which has defects or clean. The framework is evaluated using25 software projects obtained from public repositories. The result analysis shows that the proposed model has achieved a 0.71±0.03 f1-score, which significantly improves the state-of-the-art approaches by 23 % to 60 %.

In order to increase sales, companies try their best to develop relevant offers that anticipate customer needs. One way to achieve this is by leveraging artificial intelligence algorithms that process data collected based on customer transactions, extract insights and patterns from them, and then present them in a user-friendly way to human or artificial intelligence decision makers. This study is based on a hybrid approach, it starts with an online marketplace dataset that contains many customers’ purchases and ends up with global personalized offers based on three different datasets. The first one, generated by a recommendation system, identifies for each customer a list of products they are most likely to buy. The second is generated with an Apriori algorithm. Apriori is used as an associate rule mining technique to identify and map frequent patterns based on support, confidence, and lift factors, and also to pull important rules between products. The third and last one describes, for each customer, their purchase probability in the next few weeks, based on the BG/NBD model and the average of transactions using the Gamma-Gamma model, as well as the satisfaction based on the CLV and RFMTS models. By combining all three datasets, specific and targeted promotion strategies can be developed. Thus, the company is able to anticipate customer needs and generate the most appropriate offers for them while respecting their budget, with minimum operational costs and a high probability of purchase transformation.

Nowadays, vehicular networks attract car manufacturers, network researchers, and governments as well. They represent one of the building blocks, for the intelligent transportation systems. Our task is to study the employment of SDN advantages to facilitate and improve the performance of vehicular ad-hoc networks. The goal of the research is to evaluate AODV routing protocol performance improved with SDN technology applied on VANET network in specified environment of a city. We have evaluated three parameters: packet delivery ratio, end-to-end delay and throughput using SUMO and NS3 simulators. The implemented evaluation protocol shows the importance of the adopted approach.

The Content Based Image Retrieval (CBIR) system is a framework for finding images from huge datasets that are similar to a given image. The main component of CBIR system is the strategy for retrieval of images. There are many strategies available and most of these rely on single feature extraction. The single feature-based strategy may not be efficient for all types of images. Similarly, due to a larger set of data, image retrieval may become inefficient. Hence, this article proposes a system that comprises of two-stage retrieval with different features at every stage where the first stage will be coarse retrieval and the second will be fine retrieval. The proposed framework is validated on standard benchmark images and compared with existing frameworks. The results are recorded in graphical and numerical form, thus supporting the efficiency of the proposed system.

The paper proposes a framework to record meeting to avoid hassle of writing points of meeting. Key components of framework are “Model Trainer” and “Meeting Recorder”. In model trainer, we first clean the noise in audio, then oversample the data size and extract features from audio, in the end we train the classification model. Meeting recorder is a post-processor used for sound recognition using the trained model and converting the audio into text. Experimental results show the high accuracy and effectiveness of the proposed implementation.

The increasing use of multimedia applications in wireless ad-hoc networks makes the support of quality of service (QoS) an overriding necessity. In this article, we present a new extension of the IEEE 802.11e EDCA scheme called NCA-EDCA, which uses the lifetime and the number of retransmissions attempts of a packet to assess the aggressiveness of the environment in order to adjust the channel access parameters to work in the best possible way and improve service quality accordingly. This new extension aims to (1) improve the performance of real-time applications; (2) increase the overall throughput by reducing the collision rate and (3) achieve an acceptable level of fairness. The simulation results show that our extension significantly improves EDCA for better QoS support of multimedia applications. More specifically, it increases throughput of the different flows by no negligible factors and significantly reduces the collision rate while maintaining a high degree of fairness between flows of equal priority.

Due to the rapid growth of the Internet of Things (IoT), researchers have demonstrated various IoT solutions, which are used to interconnect a wide range of IoT devices through the Internet. However, IoT stumbled into vertical silos; the available solutions provide specific IoT infrastructure, devices, protocols, data formats and models. This diversity and heterogeneity lead to interoperability issues. Heterogeneity happens at all IoT layers, especially at the application layer; devices often adopt mutually incompatible application-layer communication protocols to connect devices to IoT services. Furthermore, in order to integrate semantics to raw data, each system uses its one domain-specific ontology to make data more understandable and interpretable by adding semantic annotations. Working in isolation reduces the interoperability among IoT devices and systems, things across domains need to internetwork and collaborate to provide high level IoT services. Therefore, to alleviate the problem of both communication protocol interoperability and semantic interoperability across vertical silos of systems at the application layer, this paper proposes a semantic gateway (SGIoT) that acts as a bridge between heterogeneous sink nodes at the physical level and IoT services. SGIoT enables interconnectivity between communication protocols such as CoAP and MQTT regardless of their communication model, meanwhile it enables semantics integration throu gh cross-domain ontology (CDOnto) for semantic annotation, in order to provide interpretation of messages among IoT applications across domains. Our approach focuses on modularity and extensibility.