ABSTRACT Understanding financial behaviour, particularly in the stock market, has attracted significant interest in recent years due to advancements in artificial intelligence and its impact on the global economy. The field of stock market prediction, which explores the interaction between finance and computer science to create predictive models, aims to forecast the behaviour of various securities in the financial market. One of the most well‐known and widely used techniques is Deep Learning, which employs different deep neural network structures for learning nonlinear models. In this study, we used open data from some of the largest companies in Brazil—Petrobras (PETR4), Itaúsa (ITSA4), and Vale (VALE3)—provided by BovDB, a historical dataset containing the stock prices of all companies listed on the Brazilian stock exchange (B3) from 2000 to 2020. As part of the preprocessing, a price correction factor was applied to neutralise the effects of market events on stock behaviour, enabling the recurrent neural network (RNN) model to process this information better. The results showed that using this correction factor significantly improves predictions, reducing abrupt behaviours in stock prices and decreasing the model's prediction error. For instance, the prediction error in VALE3 stock was reduced by < 10% compared with uncorrected data. These findings highlight the potential of using an event correction factor in stock data processed by an RNN, facilitating its training and providing more reliable forecasts.

In this work, a 3D vision system has been developed using a frontal Kinect v2 sensor to monitor the driver, enabling to recognize the use of a cell phone while driving, avoiding driving risks. In fact, when cars are driven by people on phone calls, it increases between 4 and 6 times the risk of crash. The Naturalistic Driver Behavior Dataset (NDBD) was created specifically for this work and it was used to test the proposed system. The proposed solution uses two analysis of the driver's hands positions, the Short-Term (ST) and Long-Term (LT) pattern recognition subsystems, thus it could detect the cell phone usage by the driver in hand-held situations. The system has 3 levels of alarm: no alarm, lowest alarm, and highest alarm. ST detects between no alarm or some level alarm. LT is responsible for determining the risk alarm level, low or high. The classifiers are based on Machine Learning and Artificial Neural Nets (ANN), furthermore, the values set to adjust input features, neuron activation functions, and network topology/training parameters were optimized and selected using a Genetic Algorithm. The best system performance results obtained in the experiments achieved 95% of accuracy in NDBD frames. For the ST classifier, it was used length periods of 5 frames and a window of 80 or 210 frames for LT. The best results achieved obtained only 1% of “no risk” situation having a wrong prediction (false positives with alarm activation), contributing to the driver comfort when he/she is using the system.

In this work, a vision system has been developed using a frontal camera to monitor the driver, enabling to recognize the use of a cell phone while driving. It is estimated that 80% of car crashes and 65% of near collisions involved drivers who were inattentive in traffic for three seconds before the event. Five videos in real environments were generated to test the proposed system. The solution is a hybrid system and that uses a pattern recognition system (PR) for classification and a movement detection system (MD) for choosing the PR parameters at the end of each period of 3 seconds. The PR parameters are the threshold (frames identified as a cell phone use) and classifier selection. The classifiers are based on ANN, furthermore, the value of constants in neuron activation function and network training parameters were adopted with a genetic algorithm. Experimentally, it was established that when the movement indicates a possible use of the cell phone, the threshold 60% and an MLP/Gaussian classifier with seven neurons in intermediate layer are suitable; otherwise, a threshold of 85%, and MLP/Gaussian with two neurons in intermediate layer for classification are used. The average accuracy achieved was 91.68% in real environment scenes.