A facial expression recognition system that can provide quick assistance to the healthcare system and exceptional services to the patients is proposed in this article. The implementation of this work is divided into three components. In the first component, landmark points on the facial region are detected; a fixed-sized rectangular box is obtained by normalizing the detected face region, and then, down sampled to its varying sizes producing multiresolution images. Different convolution neural network architectures are proposed in the second component for analyzing the textual information within the multiresolution facial images. To extract more discriminating features and enhance the proposed system’s performance, some amalgamation of transfer learning, progressive image resizing, data augmentation, and fine tuning of parameters are employed in the third component. For experimental purposes, three benchmark databases, static facial expressions in the wild, Cohn-Kanade, and Karolinska directed emotional faces, are employed with some existing methods concerning these databases. The comparison with these databases shows the superiority of the proposed system.

Traffic accidents on highways are a leading cause of death despite the development of traffic safety measures. The burden of casualties and damage caused by road accidents is very high for developing countries. Many factors are associated with traffic accidents, some of which are more significant than others in determining the severity of accidents. Data mining techniques can help in predicting influential factors related to crash severity. In this study, significant factors that are strongly correlated with the accident severity on highways are identified by Random Forest. Top features affecting accidental severity include distance, temperature, wind_Chill, humidity, visibility, and wind direction. This study presents an ensemble of machine learning and deep learning models by combining Random Forest and Convolutional Neural Network called RFCNN for the prediction of road accident severity. The performance of the proposed approach is compared with several base learner classifiers. The data used in the analysis include accident records of the USA from February 2016 to June 2020. Obtained results demonstrate that the RFCNN enhanced the decision-making process and outperformed other models with 0.991 accuracy, 0.974 precision, 0.986 recall, and 0.980 F-score using the 20 most significant features in predicting the severity of accidents.

Head pose estimation is a sensitive topic in video surveillance/smart ambient scenarios since head rotations can hide/distort discriminative features of the face. Face recognition would often tackle the problem of video frames where subjects appear in poses making it quite impossible. In this respect, the selection of the frames with the best face orientation can allow triggering recognition only on these, therefore decreasing the possibility of errors. This paper proposes a novel approach to head pose estimation for smart cities and video surveillance scenarios, aiming at this goal. The method relies on a cascade of two models: the first one predicts the positions of 68 wellknown face landmarks; the second one applies a web-shaped model over the detected landmarks, to associate each of them to a specific face sector. The method can work on detected faces at a reasonable distance and with a resolution that is supported by several present devices. Results of experiments executed over some classical pose estimation benchmarks, namely Point ’04, Biwi, and AFLW datasets show good performance in terms of both pose estimation and computing time. Further results refer to noisy images that are typical of the addressed settings. Finally, examples demonstrate the selection of the best frames from videos captured in video surveillance conditions