Learning Actions From Natural Language Instructions Using an ON-World Embodied Cognitive Architecture.

Endowing robots with the ability to view the world the way humans do, to understand natural language and to learn novel semantic meanings when they are deployed in the physical world, is a compelling problem. Another significant aspect is linking language to action, in particular, utterances involving abstract words, in artificial agents. In this work, we propose a novel methodology, using a brain-inspired architecture, to model an appropriate mapping of language with the percept and internal motor representation in humanoid robots. This research presents the first robotic instantiation of a complex architecture based on the Baddeley's Working Memory (WM) model. Our proposed method grants a scalable knowledge representation of verbal and non-verbal signals in the cognitive architecture, which supports incremental open-ended learning. Human spoken utterances about the workspace and the task are combined with the internal knowledge map of the robot to achieve task accomplishment goals. We train the robot to understand instructions involving higher-order (abstract) linguistic concepts of developmental complexity, which cannot be directly hooked in the physical world and are not pre-defined in the robot's static self-representation. Our proposed interactive learning method grants flexible run-time acquisition of novel linguistic forms and real-world information, without training the cognitive model anew. Hence, the robot can adapt to new workspaces that include novel objects and task outcomes. We assess the potential of the proposed methodology in verification experiments with a humanoid robot. The obtained results suggest robust capabilities of the model to link language bi-directionally with the physical environment and solve a variety of manipulation tasks, starting with limited knowledge and gradually learning from the run-time interaction with the tutor, past the pre-trained stage.

HRV Features as Viable Physiological Markers for Stress Detection Using Wearable Devices.

Stress has been identified as one of the major causes of automobile crashes which then lead to high rates of fatalities and injuries each year. Stress can be measured via physiological measurements and in this study the focus will be based on the features that can be extracted by common wearable devices. Hence, the study will be mainly focusing on heart rate variability (HRV). This study is aimed at investigating the role of HRV-derived features as stress markers. This is achieved by developing a good predictive model that can accurately classify stress levels from ECG-derived HRV features, obtained from automobile drivers, by testing different machine learning methodologies such as K-Nearest Neighbor (KNN), Support Vector Machines (SVM), Multilayer Perceptron (MLP), Random Forest (RF) and Gradient Boosting (GB). Moreover, the models obtained with highest predictive power will be used as reference for the development of a machine learning model that would be used to classify stress from HRV features derived from heart rate measurements obtained from wearable devices. We demonstrate that HRV features constitute good markers for stress detection as the best machine learning model developed achieved a Recall of 80%. Furthermore, this study indicates that HRV metrics such as the Average of normal-to-normal (NN) intervals (AVNN), Standard deviation of the average NN intervals (SDNN) and the Root mean square differences of successive NN intervals (RMSSD) were important features for stress detection. The proposed method can be also used on all applications in which is important to monitor the stress levels in a non-invasive manner, e.g., in physical rehabilitation, anxiety relief or mental wellbeing.

A Cognitive Neural Architecture Able to Learn and Communicate through Natural Language.

Communicative interactions involve a kind of procedural knowledge that is used by the human brain for processing verbal and nonverbal inputs and for language production. Although considerable work has been done on modeling human language abilities, it has been difficult to bring them together to a comprehensive tabula rasa system compatible with current knowledge of how verbal information is processed in the brain. This work presents a cognitive system, entirely based on a large-scale neural architecture, which was developed to shed light on the procedural knowledge involved in language elaboration. The main component of this system is the central executive, which is a supervising system that coordinates the other components of the working memory. In our model, the central executive is a neural network that takes as input the neural activation states of the short-term memory and yields as output mental actions, which control the flow of information among the working memory components through neural gating mechanisms. The proposed system is capable of learning to communicate through natural language starting from tabula rasa, without any a priori knowledge of the structure of phrases, meaning of words, role of the different classes of words, only by interacting with a human through a text-based interface, using an open-ended incremental learning process. It is able to learn nouns, verbs, adjectives, pronouns and other word classes, and to use them in expressive language. The model was validated on a corpus of 1587 input sentences, based on literature on early language assessment, at the level of about 4-years old child, and produced 521 output sentences, expressing a broad range of language processing functionalities.

No association between educational level and pancreatic cancer incidence in the European Prospective Investigation into Cancer and Nutrition.

INTRODUCTION: Until now, studies examining the relationship between socioeconomic status and pancreatic cancer incidence have been inconclusive. AIM: To prospectively investigate to what extent pancreatic cancer incidence varies according to educational level within the European Prospective Investigation into Cancer and Nutrition (EPIC) study. METHODS: In the EPIC study, socioeconomic status at baseline was measured using the highest level of education attained. Hazard ratios by educational level and a summary index, the relative indices of inequality (RII), were estimated using Cox regression models stratified by age, gender, and center and adjusted for known risk factors. In addition, we conducted separate analyses by age, gender and geographical region. RESULTS: Within the source population of 407, 944 individuals at baseline, 490 first incident primary pancreatic adenocarcinoma cases were identified in 9 European countries. The crude difference in risk of pancreatic cancer according to level of education was small and not statistically significant (RII=1.14, 95% CI 0.80-1.62). Adjustment for known risk factors reduced the inequality estimates to only a small extent. In addition, no statistically significant associations were observed for age groups (adjusted RII(≤ 60 years)=0.85, 95% CI 0.44-1.64, adjusted RII(>60 years)=1.18, 95% CI 0.73-1.90), gender (adjusted RII(male)=1.20, 95% CI 0.68-2.10, adjusted RII(female)=0.96, 95% CI 0.56-1.62) or geographical region (adjusted RII(Northern Europe)=1.14, 95% CI 0.81-1.61, adjusted RII(Middle Europe)=1.72, 95% CI 0.93-3.19, adjusted RII(Southern Europe)=0.75, 95% CI 0.32-1.80). CONCLUSION: Despite large educational inequalities in many risk factors within the EPIC study, we found no evidence for an association between educational level and the risk of developing pancreatic cancer in this European cohort.

A novel multithreshold method for nodule detection in lung CT.

Multislice computed tomography (MSCT) is a valuable tool for lung cancer detection, thanks to its ability to identify noncalcified nodules of small size (from about 3 mm). Due to the large number of images generated by MSCT, there is much interest in developing computer-aided detection (CAD) systems that could assist radiologists in the lung nodule detection task. A complete multistage CAD system, including lung boundary segmentation, regions of interest (ROIs) selection, feature extraction, and false positive reduction is presented. The selection of ROIs is based on a multithreshold surface-triangulation approach. Surface triangulation is performed at different threshold values, varying from a minimum to a maximum value in a wide range. At a given threshold value, a ROI is defined as the volume inside a connected component of the triangulated isosurface. The evolution of a ROI as a function of the threshold can be represented by a treelike structure. A multithreshold ROI is defined as a path on this tree, which starts from a terminal ROI and ends on the root ROI. For each ROI, the volume, surface area, roundness, density, and moments of inertia are computed as functions of the threshold and used as input to a classification system based on artificial neural networks. The method is suitable to detect different types of nodules, including juxta-pleural nodules and nodules connected to blood vessels. A training set of 109 low-dose MSCT scans made available by the Pisa center of the Italung-CT trial and annotated by expert radiologists was used for the algorithm design and optimization. The system performance was tested on an independent set of 23 low-dose MSCT scans coming from the Pisa Italung-CT center and on 83 scans made available by the Lung Image Database Consortium (LIDC) annotated by four expert radiologists. On the Italung-CT test set, for nodules having a diameter greater than or equal to 3 mm, the system achieved 84% and 71% sensitivity at false positive/scan rates of 10 and 4, respectively. For nodules having a diameter greater than or equal to 4 mm, the sensitivities were 97% and 80% at false positive/scan rates of 10 and 4, respectively. On the LIDC data set, the system achieved a 79% sensitivity at a false positive/scan rate of 4 in the detection of nodules with a diameter greater than or equal to 3 mm that have been annotated by all four radiologists.