Unsupervised Active Visual Search With Monte Carlo Planning Under Uncertain Detections.

We propose a solution for Active Visual Search of objects in an environment, whose 2D floor map is the only known information. Our solution has three key features that make it more plausible and robust to detector failures compared to state-of-the-art methods: i) it is unsupervised as it does not need any training sessions. ii) During the exploration, a probability distribution on the 2D floor map is updated according to an intuitive mechanism, while an improved belief update increases the effectiveness of the agent's exploration.

Forensic value of soft tissue detachments from the hyoid bone in death due to strangulation asphyxia.

Background: There are no unequivocal histopathological findings for the diagnosis of fatal asphyxia due to neck compression. From the observation of a series of asphyxiation cases, we noted, during microscopic analysis, a high frequency of "detachment" of soft tissues from the hyoid bone. This specifically refers to the presence of an optical space between the surface of the hyoid bone and soft tissues.

Liquorice Toxicity: A Comprehensive Narrative Review.

Background: Renowned since ancient times for its medical properties, liquorice is nowadays mainly used for flavoring candies or soft drinks. Continuous intake of large amounts of liquorice is a widely known cause of pseudo-hyperaldosteronism leading to hypertension and hypokalemia. These manifestations are usually mild, although in some cases may generate life-threatening complications, i.

Adversarial Data Augmentation for HMM-Based Anomaly Detection.

In this work, we concentrate on the detection of anomalous behaviors in systems operating in the physical world and for which it is usually not possible to have a complete set of all possible anomalies in advance. We present a data augmentation and retraining approach based on adversarial learning for improving anomaly detection. In particular, we first define a method for generating adversarial examples for anomaly detectors based on Hidden Markov Models (HMMs).

Learning State-Variable Relationships in POMCP: A Framework for Mobile Robots.

We address the problem of learning relationships on state variables in Partially Observable Markov Decision Processes (POMDPs) to improve planning performance. Specifically, we focus on Partially Observable Monte Carlo Planning (POMCP) and represent the acquired knowledge with a Markov Random Field (MRF). We propose, in particular, a method for learning these relationships on a robot as POMCP is used to plan future actions.