7 July 2021 in IEEE Latin America Transactions
The Internet of Things (IoT) brings new applications and challenges related to cloud computing. The service distribution challenge is becoming more evident and a need for better service options is emerging. The focus of the work is to optimize issues related to the allocation of resources in Edge Computing, improving the quality of service (QoS) with new methodologies. An algorithm based on a bio-inspired model was developed. This algorithm is based on the behavior of gray wolves and it is called Algorithm for 5G Resource Management Optmization in Edge Computing (GROMEC). The algorithm uses the meta-heuristic technique applied to Edge Computing, to result in a better allocation resources through user equipment (UE). The resources considered for allocation in that work are processing, memory, time and storage. Two genetic algorithms were used to define the fitness of an Edge in relation to the resource. Two other algorithms that use traditional techniques in the literature, the Best-First and AHP methods, were considered in the evaluation and comparison with the GROMEC. In the function used to calculate fitness during the simulation made with the GROMEC, the proposed algorithm had a lower number of denied services, presented a low number of blocks and was able to meet the largest number of UEs allocating on average up to 50% more in relation to the Best and 5.25% in relation to Nancy.
23 December 2021 in IEEE Latin America Transactions
JEJacinto Diassala Monteiro Ernesto
Jacinto Diassala Monteiro Ernesto
The internet and web applications have been growing steadily and together with the increasing number of cyber attacks. These attacks are carried out through requests that are considered normal or abnormal (attack requests). Therefore, an intrusion attack can be considered as a classification problem. Machine learning algorithms are used as a way to train models to classify these requests in order to increase the security of web systems. The data used to carry out the training and tests in this work come from the CSIC 2010 dataset. The J48, Naive Bayes, OneR, Random Forest and IBM Watson LGBM algorithms were tested. The metrics used were t-rate, precision, recall and f measure. The results showed that the algorithm used by the Watson tool (LGBM) was the one that did the best in all metrics when compared to the other algorithms in the literature.
23 December 2021 in IEEE Latin America Transactions
The high growth of urban centers brings several problems for the population, such as socioeconomic and health problems due to toxins, polluting gases, delay in emergency care, and the stress to which citizens are exposed to traffic. Generally, for predicting the impact of a given action in the city, simulations are used to take into account the mobility of its inhabitants. These simulations must correspond with the environment that you want to be represented. Therefore, datasets with real data, make the simulations more reliable so that the results obtained are more satisfactory. The project aims to build a dataset with real data of user locations and traffic interventions for network simulations, optimize services for intelligent transport systems, and improve urban mobility in the city of Catanduva - SP. The results were performed on the mobile application (TIMELESS) and show that it consumes few smartphone resources (data, memory, and battery) to collect and generate the data set, compared to the use of other applications in the same segment (traffic monitoring and route suggestion).