No abstract

No abstract

No abstract

Purpose of research. Emotions play one of the key roles in the regulation of human behaviour. Solving the problem of automatic recognition of emotions makes it possible to increase the effectiveness of operation of a whole range of digital systems such as security systems, human-machine interfaces, e-commerce systems, etc. At the same time, the low efficiency of modern approaches to recognizing emotions in speech can be noted. This work studies automatic recognition of emotions in speech applying machine learning methods.Methods. The article describes and tests an approach to automatic recognition of emotions in speech based on multitask learning of deep convolution neural networks of AlexNet and VGG architectures using automatic selection of the weight coefficients for each task when calculating the final loss value during learning. All the models were trained on a sample of the IEMOCAP dataset with four emotional categories of ‘anger’, ‘happiness’, ‘neutral emotion’, ‘sadness’. The log-mel spectrograms of statements processed by a specialized algorithm are used as input data.Results. The considered models were tested on the basis of numerical metrics: the share of correctly recognized instances, accuracy, completeness, f-measure. For all of the above metrics, an improvement in the quality of emotion recognition by the proposed model was obtained in comparison with the two basic single-task models as well as with known solutions. This result is achieved through the use of automatic weighting of the values of the loss functions from individual tasks when forming the final value of the error in the learning process.Conclusion. The resulting improvement in the quality of emotion recognition in comparison with the known solutions confirms the feasibility of applying multitask learning to increase the accuracy of emotion recognition models. The developed approach makes it possible to achieve a uniform and simultaneous reduction of errors of individual tasks, and is used in the field of emotions recognition in speech for the first time.

Corona discharges that occur on the conductive elements of power lines are serious problems that can lead to failures in the power system. Corona discharge produces ultraviolet (UV) radiation, which can be detected using special UV sensors. One way to automate inspection of the corona discharge is using of autonomous unmanned aerial vehicles (UAVs) equipped with UV sensor. At the same time, the trajectory of the autonomous UAV flight should be built taking into account the spatial and geometric features of the inspected power lines, as well as the requirements for the gathered data. This work describes a new method for autonomous UAV trajectory planning. The trajectory is planned in accordance with the spatial and geometric characteristics of the inspected powerline, peculiarities of the powerline damage type and in accordance with the quality requirements for the gathered data (representativeness, sample size, unification of the gathering procedure). The trajectory planning method and UV image gathering were simulated in Blender software. As a result, by the fully automated data gathering process, we collected a representative dataset of 200 images in UV spectrum for one lattice tower and two simulated discharges with 326 manually segmented corona discharge areas.