Hector Jasso

Real-time nondestructive structural health monitoring using support vector machines and wavelets

We present an alternative to visual inspection for detecting damage to civil infrastructure. We describe a real-time decision support system for nondestructive health monitoring. The system is instrumented by an integrated network of wireless sensors mounted on civil infrastructures such as bridges, highways, and commercial and industrial facilities. To address scalability and power consumption issues related to sensor networks, we propose a three-tier system that uses wavelets to adaptively reduce the streaming data spatially and temporally. At the sensor level, measurement data is temporally compressed before being sent upstream to intermediate communication nodes. There, correlated data from multiple sensors is combined and sent to the operation center for further reduction and interpretation. At each level, the compression ratio can be adaptively changed via wavelets. This multi-resolution approach is useful in optimizing total resources in the system. At the operation center, Support Vector Machines (SVMs) are used to detect the location of potential damage from the reduced data. We demonstrate that the SVM is a robust classifier in the presence of noise and that wavelet-based compression gracefully degrades its classification accuracy. We validate the effectiveness of our approach using a finite element model of the Humboldt Bay Bridge. We envision that our approach will prove novel and useful in the design of scalable nondestructive health monitoring systems.

A robotic model of the development of gaze following

For humanoid robots, the skill of gaze following is a foundational component in social interaction and imitation learning.We present a robotic system capable of learning the gaze following behavior in a real-world environment. First, the system learns to detect salient objects and to distinguish a caregiverpsilas head poses in a semi-autonomous manner. Then we present multiple scenes containing different combinations of objects and head poses to the robot head. The system learns to associate the detected head pose with correct spatial location of where potentially ldquorewardingrdquo objects would be using a biologically plausible reinforcement learning mechanism.

A Unified Account of Gaze Following

Gaze following, the ability to redirect ones visual attention to look at what another person is seeing, is foundational for imitation, word learning, and theory-of-mind. Previous theories have suggested that the development of gaze following in human infants is the product of a basic gaze following mechanism, plus the gradual incorporation of several distinct new mechanisms that improve the skill, such as spatial inference, and the ability to use eye direction information as well as head direction. In this paper, we offer an alternative explanation based on a single learning mechanism. From a starting state with no knowledge of the implications of another organisms gaze direction, our model learns to follow gaze by being placed in a simulated environment where an adult caregiver looks around at objects. Our infant model matches the development of gaze following in human infants as measured in key experiments that we replicate and analyze in detail.

Using 9-1-1 call data and the space–time permutation scan statistic for emergency event detection

The space-time permutation scan statistic has been previously used to detect disease outbreaks, without need for uniform population at risk, control group data, or information about the distribution of population-at-risk in order to establish the statistical significance of found clusters of cases. This paper shows results from using the space-time permutation scan statistic to detect clusters of 9-1-1 emergency calls. These clusters are then correlated with wide-scale emergency events as reported on the news. Using several examples, it is shown that these clusters are useful for estimating the location, temporal extent, and human impact of such emergency events.

A virtual reality platform for modeling cognitive development

We present a virtual reality platform for developing and evaluating embodied models of cognitive development. The platform facilitates structuring of the learning agent, of its visual environment, and of other virtual characters that interact with the learning agent. It allows us to systematically study the role of the visual and social environment for the development of particular cognitive skills in a controlled fashion. We describe how it is currently being used for constructing an embodied model of the emergence of gaze following in infant-caregiver interactions and discuss the relative benefits of virtual vs. robotic modeling approaches.

Spatiotemporal analysis of 9-1-1 call stream data

Currently, archival 9-1-1 call stream data is used mainly for administrative purposes. We present spatiotemporal analysis of thirteen months worth of call stream data for the purpose of illustrating how this data might be used for enhancing emergency response in the State of California. An analysis of the data shows regularity in the 9-1-1 call volume which can facilitate the automatic detection of abnormally high call volumes that are associated with environmental, medical emergency, and law enforcement events. Thus, this is a first step towards the detection of unusual trends that could indicate widely spread events that require response beyond that of isolated incidents.

Learning to Attend -- From Bottom-Up to Top-Down

The control of overt visual attention relies on an interplay of bottom-up and top-down mechanisms. Purely bottom-up models may provide a reasonable account of the looking behaviors of young infants, but they cannot accurately account for attention orienting of adults in many natural behaviors. But how do humans learn to incorporate top-down mechanisms into their control of attention? The phenomenon of gaze following, i.e. the ability to infer where someone else is looking and to orient to the same location, offers an interesting window into this question. We review findings on the emergence of gaze following in human infants and present a computational model of the underlying learning processes. The model exhibits a gradual incorporation of top-down cues in the infants attention control. It explains this process in terms of generic reinforcement learning mechanisms. We conclude that reinforcement learning may be a major driving force behind the incorporation of top-down cues into the control of visual attention.

A reinforcement learning model of social referencing

We present a novel computational model of social referencing. The model replicates a classic social referencing experiment where an infant is presented with a novel object and has the choice of consulting an adultpsilas informative facial expression before reacting to the object. The infant model learns the value of consulting the adultpsilas facial expression using the temporal difference learning algorithm. The model is used to make hypotheses about the reason for a lack of social referencing found in autistic individuals, based on an aversion to faces. Comparisons are made between this reinforcement learning model and a previous model based on mood contagion.