Comparing Social Robot Embodiment for Child Musical Education.

The present research focuses in the comparison of two social robot models running the same Human-Robot Interaction (HRI) applications targeting the context of music education for children aged 9-11, with the objective of underlying the design choices favored by the target audience on the running tasks. The Guitar Tuner consists of two main functionalities: tuning process and performance evaluation, which we implemented using the NAO and Zenbo robots. User evaluation included 20 children and assessed their perceived robot embodiment preferences (e.g., shape, robot motion, displays, and emotional expressivity) and perceived usability aspects. The evaluation used an experimental remote protocol supporting collecting online feedback with users during the COVID-19 pandemic. Empirical results supported performing quantitative and qualitative evaluations of the HRI application and highlighting the perceived differences of robot embodiment features. The discussions center on improving a future version of the HRI application, plus children's considerations about their preferred robot embodiment features during the observation sessions. Finally, we propose recommendations for robot embodiment design for children and learning based on this case study and discuss protocol limitations during the social distancing context, that we believe as a valid alternative to move forward with experimental designs, particularly in robotics, becoming a great contribution to other researchers facing similar hurdles.

Using a Support Vector Machine Based Decision Stage to Improve the Fault Diagnosis on Gearboxes.

Gearboxes are mechanical devices that play an essential role in several applications, e.g., the transmission of automotive vehicles. Their malfunctioning may result in economic losses and accidents, among others. The rise of powerful graphical processing units spreads the use of deep learning-based solutions to many problems, which includes the fault diagnosis on gearboxes. Those solutions usually require a significant amount of data, high computational power, and a long training process. The training of deep learning-based systems may not be feasible when GPUs are not available. This paper proposes a solution to reduce the training time of deep learning-based fault diagnosis systems without compromising their accuracy. The solution is based on the use of a decision stage to interpret all the probability outputs of a classifier whose output layer has the softmax activation function. Two classification algorithms were applied to perform the decision. We have reduced the training time by almost 80% without compromising the average accuracy of the fault diagnosis system.

Structured Pyramidal Neural Networks.

The Pyramidal Neural Networks (PNN) are an example of a successful recently proposed model inspired by the human visual system and deep learning theory. PNNs are applied to computer vision and based on the concept of receptive fields. This paper proposes a variation of PNN, named here as Structured Pyramidal Neural Network (SPNN). SPNN has self-adaptive variable receptive fields, while the original PNNs rely on the same size for the fields of all neurons, which limits the model since it is not possible to put more computing resources in a particular region of the image. Another limitation of the original approach is the need to define values for a reasonable number of parameters, which can turn difficult the application of PNNs in contexts in which the user does not have experience. On the other hand, SPNN has a fewer number of parameters. Its structure is determined using a novel method with Delaunay Triangulation and k-means clustering. SPNN achieved better results than PNNs and similar performance when compared to Convolutional Neural Network (CNN) and Support Vector Machine (SVM), but using lower memory capacity and processing time.