Piero Zappi

Activity recognition from on-body sensors: accuracy-power trade-off by dynamic sensor selection

Activity recognition from an on-body sensor network enables context-aware applications in wearable computing. A guaranteed classification accuracy is desirable while optimizing power consumption to ensure the systems wearability. In this paper, we investigate the benefits of dynamic sensor selection in order to use efficiently available energy while achieving a desired activity recognition accuracy. For this purpose we introduce and characterize an activity recognition method with an underlying run-time sensor selection scheme. The system relies on a meta-classifier that fuses the information of classifiers operating on individual sensors. Sensors are selected according to their contribution to classification accuracy as assessed during system training. We test this system by recognizing manipulative activities of assembly-line workers in a car production environment. Results show that the systems lifetime can be significantly extended while keeping high recognition accuracies. We discuss how this approach can be implemented in a dynamic sensor network by using the context-recognition framework Titan that we are developing for dynamic and heterogeneous sensor networks.

Tracking Motion Direction and Distance With Pyroelectric IR Sensors

Passive IR (PIR) sensors are excellent devices for wireless sensor networks (WSN), being low-cost, low-power, and presenting a small form factor. PIR sensors are widely used as a simple, but reliable, presence trigger for alarms, and automatic lighting systems. However, the output of a PIR sensor depends on several aspects beyond simple people presence, as, e.g., distance of the body from the sensor, direction of movement, and presence of multiple people. In this paper, we present a feature extraction and sensor fusion technique that exploits a set of wireless nodes equipped with PIR sensors to track people moving in a hallway. Our approach has reduced computational and memory requirements, thus it is well suited for digital systems with limited resources, such as those available in sensor nodes. Using the proposed techniques, we were able to achieve 100% correct detection of direction of movement and 83.49%-95.35% correct detection of distance intervals.

Activity recognition from on-body sensors by classifier fusion: sensor scalability and robustness

Activity recognition from on-body sensors is affected by sensor degradation, interconnections failures, and jitter in sensor placement and orientation. We investigate how this may be balanced by exploiting redundant sensors distributed on the body. We recognize activities by a meta-classifier that fuses the information of simple classifiers operating on individual sensors. We investigate the robustness to faults and sensor scalability which follows from classifier fusion. We compare a reference majority voting and a naive Bayesian fusion scheme. We validate this approach by recognizing a set of 10 activities carried out by workers in the quality assurance checkpoint of a car assembly line. Results show that classification accuracy greatly increases with additional sensors (50% with 1 sensor, 80% and 98% with 3 and 57 sensors), and that sensor fusion implicitly allows to compensate for typical faults up to high fault rates. These results highlight the benefit of large on- body sensor network rather than a minimum set of sensors for activity recognition and prompts further investigation.

An integrated multi-modal sensor network for video surveillance

To enhance video surveillance systems, multi-modal sensor integration can be a successful strategy. In this work, a computer vision system able to detect and track people from multiple cameras is integrated with a wireless sensor network mounting PIR (Passive InfraRed) sensors. The two subsystems are briefly described and possible cases in which computer vision algorithms are likely to fail are discussed. Then, simple but reliable outputs from the PIR sensor nodes are exploited to improve the accuracy of the vision system. In particular, two case studies are reported: the first uses the presence detection of PIR sensors to disambiguate between an opened door and a moving person, while the second handles motion direction changes during occlusions. Preliminary results are reported and demonstrate the usefulness of the integration of the two subsystems.

Enhancing the spatial resolution of presence detection in a PIR based wireless surveillance network

Pyroelectric sensors are low-cost, low-power small components commonly used only to trigger alarm in presence of humans or moving objects. However, the use of an array of pyroelectric sensors can lead to extraction of more features such as direction of movements, speed, number of people and other characteristics. In this work a low-cost pyroelectric infrared sensor based wireless network is set up to be used for tracking people motion. A novel technique is proposed to distinguish the direction of movement and the number of people passing. The approach has low computational requirements, therefore it is well-suited to limited-resources devices such as wireless nodes. Tests performed gave promising results.

CitiSense: improving geospatial environmental assessment of air quality using a wireless personal exposure monitoring system

Environmental exposures are a critical component in the development of chronic conditions such as asthma and cancer. Yet, medical and public health practitioners typically must depend on sparse regional measurements of the environment that provide macro-scale summaries. Recent projects have begun to measure an individuals exposure to these factors, often utilizing body-worn sensors and mobile phones to visualize the data. Such data, collected from many individuals and analyzed across an entire geographic region, holds the potential to revolutionize the practice of public health. We present CitiSense, a participatory air quality sensing system that bridges the gap between personal sensing and regional measurement to provide micro-level detail at a regional scale. In a user study of 16 commuters using CitiSense, measurements were found to vary significantly from those provided by official regional pollution monitoring stations. Moreover, applying geostatistical kriging techniques to our data allows CitiSense to infer a regional map that contains considerably greater detail than official regional summaries. These results suggest that the cumulative impact of many individuals using personal sensing devices may have an important role to play in the future of environmental measurement for public health.

A Solar-powered Video Sensor Node for Energy Efficient Multimodal Surveillance

Building an energy efficient wireless vision network for monitoring and surveillance is one of the major efforts in the sensor network community. We present a multi-modal video sensor node designed for low-power and low-cost video surveillance, traffic control and people detection based on wireless sensor networks. It is equipped with a solar energy harvesting unit, which extends the autonomy ofthe nodes considerably using a solar cell of 70 cm2 and exploits CMOS video camera and Pyroelectric InfraRed (PIR) sensors to reduce remarkably the power consumption of the system in absence of events. The on-board microprocessor enables image classification using algorithms basedon support vector machines (SVM). We describe hardware-software architecture of the video sensor node and characterization in terms of power consumption and accuracy. Finally simulation results demonstrate the effectiveness of multimodal video sensors powered by harvesting circuits.

Pyroelectric InfraRed sensors based distance estimation

Pyroelectric infrared (PIR) sensors are low-power, low-cost devices commonly used in ambient monitoring systems in order to provide a simple, but reliable, trigger signal in presence of people. In this work we show how we are able to estimate the position of a person using PIR detectors. Our sensor node locally extracts basic features (passage duration and PIRpsilas output amplitude) and fuses them from pairs of nodes in order to classify the passages into three classes according to person position. We tested three classifiers: naive Bayes, support vector machines (SVM) and k-nearest neighbor (k-NN). All of them can be implemented on low power, low cost devices while achieving a correct classification ratio ranging from 80% up to 93%.

Network-Level Power-Performance Trade-Off in Wearable Activity Recognition: A Dynamic Sensor Selection Approach

Wearable gesture recognition enables context aware applications and unobtrusive HCI. It is realized by applying machine learning techniques to data from on-body sensor nodes. We present an gesture recognition system minimizing power while maintaining a run-time application defined performance target through dynamic sensor selection. Compared to the non managed approach optimized for recognition accuracy (95% accuracy), our technique can extend network lifetime by 4 times with accuracy >90% and by 9 times with accuracy >70%. We characterize the approach and outline its applicability to other scenarios.

Hidden Markov Model based gesture recognition on low-cost, low-power Tangible User Interfaces

The development of new human–computer interaction technologies that go beyond traditional mouse and keyboard is gaining momentum as smart interactive spaces and virtual reality are becoming part of our everyday life. Tangible User Interfaces (TUIs) introduce physical objects that people can manipulate to interact with smart spaces. Smart objects used as TUIs can further improve the user experiences by recognizing and coupling natural gesture to command issued to the computing system. Hidden Markov Models (HMM) are a typical approach to recognize gestures. In this paper, we show how the HMM forward algorithm can be adapted for its use on low-power, low-cost microcontrollers without floating point unit that can be embedded into several TUI. The proposed solution is validated on a set of gestures performed with the Smart Micrel Cube (SMCube), a TUI developed within the TANGerINE framework. Through the paper we evaluate the complexity of the algorithm and the performance of the recognition algorithm as a function of the number of bits used to represent data. Furthermore, we explore a multiuser scenario where up to four people share the same cube. Results show that the proposed solution performs comparably to the standard forward algorithm run on a PC with double-precision floating point calculations.