2 Mozos et al.Stress remains a significant social problem for individuals in modern societies. This paper presents a machine learning approach for the automatic detection of stress of people in a social situation by combining two sensor systems that capture physiological and social responses. We compare the performance using different classifiers including support vector machine, AdaBoost, and k-nearest neighbour. Our experimental results show that by combining the measurements from both sensor systems, we could accurately discriminate between stressful and neutral situations during a controlled Trier social stress test (TSST). Moreover, this paper assesses the discriminative ability of each sensor modality individually and considers their suitability for real time stress detection. Finally, we present an study of the most discriminative features for stress detection.
Objective measurements should be performed to improve risk assessment and therapeutic decisions in pancreatic cancer. Nuclear morphometry of the pancreatic nuclear features can provide important pre-operative information in resectability assessment. The fractal dimension of the nuclear shape and chromatin distribution may be considered a new promising adjunctive tool for conventional pathological analysis.
Intelligent collaborative environments, where heterogenous entities operate together in achieving common mission objectives have been increasingly adopted for monitoring and surveillance of interest areas and physical infrastructures. They can be assembled from multiple existing technologies ranging from wireless sensor networks (WSN), terrestrial remote operated vehicles (ROV) and unmanned aerial vehicles (UAV). In this context, we first introduce a multi-level system framework for multi-sensory robotic surveillance of critical infrastructure protection through communication, data acquisition and processing -MUROS. Leveraging a cognitive radio (CR) scheme is discussed as key point of the paper, arguing that by exploiting in an opportunistic fashion the time, frequency and spatial stream of the wireless environment, increased communication reliability can be achieved with positive impact on the availability and service level at each hierarchical level. The application of CR, given the heterogeneous nature of the application across multiple radio interfaces and protocols, stand outs as a novel and feasible research direction. We argument the advantages of this scheme within the constraints of a working scenario and define a simulation-based approach in order to validate our solution.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.