This paper proposes a novel supervised learning algorithm for spiking neural networks. The algorithm combines Hebbian learning and least mean squares method and it works well for small training datasets and short training cycles. The proposed method is applied in human-robot interaction for recognizing musical hand gestures based on the work of Zoltán Kodaly. The MNIST dataset is also used as a benchmark test to´ verify the proposed algorithm’s capability to outperform shallow ANN architectures. Experiments with the robot also provided promising results by recognizing the human hand signs correctly.

As a new kind of robots, called cooperative robots, are more commonly used in industry, a new way of communication is becoming more important due to the increasing number of closer cooperation between human and robots. This paper proposes the idea behind a novel method of using visual communication between cobots and humans focusing mainly on the field of industrial robotics. This device can decrease the mental stress experienced by the coworker and can increase the trust resulting in a closer to ergonomic workspace from the coworker viewpoint. Other possible usage is also discussed.

The main objective of the present study is to highlight the role of technological (soft sensor) methodologies in the assessment of the neurocognitive dysfunctions specific to neurodevelopmental disorders (for example, autism spectrum disorder (ASD), attention deficit hyperactivity disorder (ADHD), and specific learning disorder). In many cases neurocognitive dysfunctions can be detected in neurodevelopmental disorders, some of them having a well-defined syndrome-specific clinical pattern. A number of evidence-based neuropsychological batteries are available for identifying these domain-specific functions. Atypical patterns of cognitive functions such as executive functions are present in almost all developmental disorders. In this paper, we present a novel adaptation of the Tower of London Test, a widely used neuropsychological test for assessing executive functions (in particular planning and problem-solving). Our version, the Tower of London Adaptive Test, is based on computer adaptive test theory (CAT). Adaptive testing using novel algorithms and parameterized task banks allows the immediate evaluation of the participant’s response which in turn determines the next task’s difficulty level. In this manner, the subsequent item is adjusted to the participant’s estimated capability. The adaptive procedure enhances the original test’s diagnostic power and sensitivity. By measuring the targeted cognitive capacity and its limitations more precisely, it leads to more accurate diagnoses. In some developmental disorders (e.g., ADHD, ASD) it could be very useful in improving the diagnosis, planning the right interventions, and choosing the most suitable assistive digital technological service.

As cobots become more popular in manufacturing, the close cooperation between the robot and the human operator becomes more complex. This paper proposes a method for optimizing the robot's work pace by interactive bacterial evolutionary algorithm. One of the main contributions is the interactivity of the optimization via the operator's feedback. Beside the operator's subjective evaluation, heart rate signals are also measured. The paper focuses mainly on the concept of this method tested with the help of some volunteers. Preliminary tests show that the algorithm is able to find comfortable configurations with less then 1% of them evaluated.