Abstract. Our goal is to develop methods for non-experts to teach complex behaviors to autonomous agents (such as robots) by accommodating "natural" forms of human teaching. We built a prototype interface allowing humans to teach a simulated robot a complex task using several techniques and report the results of 44 human participants using this interface. We found that teaching styles varied considerably but can be roughly categorized based on the types of interaction, patterns of testing, and general organization of the lessons given by the teacher. Our study contributes to a better understanding of human teaching patterns and makes specific recommendations for future human-robot interaction systems.

No abstract

The motivation of the present work is to develop a simple grading scale (mild, moderate or severe) for estimation of an asymmetry level of breast thermograms. The scale should help to distribute test subjects into three groups. The first group, with mild asymmetry, will be supposed to have no thermographic abnormalities. Persons from the second group, moderate asymmetry, will be asked to receive a second thermography exam within 3 to 6 months. The third group, individuals with severe asymmetry, will be referred to oncology doctor and receive the second thermography exam within 2 to 3 months.

This research work seeks to improve the output of a data mining algorithm that supports diabetic patients' care. The model that is currently in operation uses three variables that are obtained from a general medical appointment database. This work aims to find other characteristics in the database to add them to those already considered to better describe patients to provide more accurate information. The article shows the process followed to improve the results of a k-means grouping algorithm for the follow-up process of diabetic patients. We present the process of defining the considered characteristics that were not part of the model, to analyze and eventually add them. A qualitative comparison between the algorithms is shown and the findings are explained during the analysis of the studied variables, in relation to sex and age of the patients.

!Breast cancer is the most common form of cancer in women worldwide; it represents 25% of all cancers in women. Infrared thermography of women breasts for early cancer detection is an approach that is not invasive and offers the opportunity to see for physiologic changes in the body years before other tools. An abnormal temperature distribution over a breast and usually its significant asymmetry could signal the existence of a malignancy. Another possible indicator of a tumor is a size and shape asymmetry between breasts. !It is a challenge to find the aforementioned asymmetry automatically in a thermal image, as a human body could be at a slight angle to the camera. !We approach this problem by differentiating both breasts' previously selected contours on a vector representation that allows to compare their size and shape using cosine similarity. Even though this is a Computer Vision problem, this framework requires low computing resources. !Our technique detects the small differences that appear in size and position of normal breasts, as there is no perfect symmetry in the human body, and it gives a measure of the difference between them that could be used in further applications using different criteria depending on the purpose. !