Miika Valtonen

TileTrack: Capacitive human tracking using floor tiles

Accurate, simple and affordable methods for passive indoor tracking of human beings are still missing. In this article, we describe the development of an unobtrusive two-dimensional human positioning system based on low-frequency electric fields. The systems operation is based on measuring the capacitance between multiple floor tiles and a receiving electrode. The presented system is invisible to the user and uses a single-chip solution to measure the capacitances. The implemented system is evaluated with two different types of receiving electrodes and the results are presented. With the used tiles, the system can locate a standing human with at least 15 cm accuracy and track a walking person with at least 41 cm accuracy. The update rate of the system is 10 Hz.

Learning and adaptive fuzzy control system for smart home

Automated smart homes have widely established their position as a research field during the last decade. More and more context sensitive concepts are being studied and at the same time proactivity has broken through in ambient intelligence research. Technology has advanced towards an adaptive and autonomous home, which can take care of the inhabitants’ well-being in numerous ways.

Unobtrusive human height and posture recognition with a capacitive sensor

In pervasive context recognition and user identification applications, unobtrusive recognition of user height and posture is difficult. With the current state of technology, this becomes even harder in environments where cameras are not desired or allowed. This paper answers this problem by presenting a simple, unobtrusive, and low-cost system for measuring height and posture of the user. The measurement method is based on capacitive coupling of low-frequency signals and conductivity of the human body. The designed system was simulated, implemented, and tested with 14 adults. The experimental results show that in 90% of the test cases the height of a person can be measured with 5.2 cm and 14.3 accuracy in standing and all other postures, respectively.

Human tracking using electric fields

In this paper we describe a simple, cheap, and unobtrusive demo system that can track multiple persons with low-frequency electric fields. The systems operation is based on measuring the capacitance between multiple floor tiles and a receiving electrode. The presented system is invisible to the user and uses a single-chip solution to measure the capacitances. The system was provided for hands-on evaluation for conference attendees with a 3.0 × 1.8 m floor space. The position and the track of the persons walking on the floor were projected on a screen. The floor of the demo system is divided to two different sections that are built of two different sizes of floor tiles to show how the tile size affects the positioning accuracy and the update rate of the system.

Capacitive indoor positioning and contact sensing for activity recognition in smart homes

In smart homes, unobtrusive monitoring of user position and activity are important but challenging tasks. With the current state of technology, this task is especially hard to carry out in private areas where video surveillance is considered undesirable or even offensive. Even though some alternative methods for passive and unobtrusive monitoring of people have been proposed in the past, we still do not have a simple method that could be used to measure user position and activities as a single practical solution. To fulfill this need, this paper presents a single privacy-preserving method to measure user position and activity which can easily be adapted to measure the subjects height and posture as well. The system proposed in this paper can locate a person at floor level and monitor the subjects interaction with common household items such as a bed, sofa, table or refrigerator. The measurement method is based on the conductivity of the human body and on capacitive coupling of low-frequency signals between electrodes embedded in the floor and the in the environment. A test system was built for the TUT Smart Home and was evaluated with multiple test subjects, including a two-week-long living test to show the systems potential in long-term monitoring applications. The results show that a standing person can be positioned to within either 7 or 11-cm accuracy at a 90% confidence level using 30 × 30-cm and 60 × 60-cm-sized transmitting floor electrodes, respectively. For people walking, the respective accuracies are 17 and 33 cm. According to the long-term test results, the interactions with the environment were detected accurately. All the test data from this long-term living test, including the persons position, contact with common household items as well as the user annotations, have been made public and are available for download.

Proactive and adaptive fuzzy profile control for mobile phones

In this paper we describe a context-sensitive way to change an active mobile phone profile. We present a method to create a proactive and adaptive phone profile control system that automatically adapts the profile to the best alternative based on the current context. The adaptation is based on recognizing patterns of human practices, which may change over time. The control system is implemented with a fuzzy controller that supports reinforcement learning. The operation of the system is demonstrated with a mobile phone that is controlled by a PC. The PC lets a user to simulate the context parameters, and the phone works as a user interface for profile selection and display.

Wireless Sensor Networks Energy Optimization Using User Location Information in Smart Homes

Wireless sensor networks have received increased interest in different applications, including smart homes. One of the most important aspects of these networks is the energy consumption, which plays a crucial role in the usefulness of the implementations. In this paper, a new method for decreasing energy consumption is introduced. The method, called Location Based Latency Control (LBLC), will take advantage of the location information of the user in a smart home environment in order to optimize the energy-latency tradeoff present in many networks. The new method is tested by simulation based on power consumption measurements and location data gathered from a living test in actual smart home environment. The results show that using location information as a means of controlling the network parameters provides a useful and promising method in decreasing network energy consumption without sacrificing usability of the connected devices.

Human body tracking with electric field ranging

This paper presents a passive, simple, and affordable electric field based ranging method for capturing human position, leaning, and hand or leg movements. A test system transforms the physical input into a two-dimensional position in an indoor environment. The method and the designed test system can be used, for example, in gaming, virtual exhibition, and virtual reality applications. The proposed system measures the capacitances between a user, standing on a transmitting floor electrode, and four vertically aligned receiver wires placed at the corners of the tracking area. The system converts the measured capacitances to absolute distances, which in turn can be used to resolve the unambiguous position of the user. The design was verified in a 1.8 x 1.8 m-sized test space by using the structures of a virtual reality cave. The test system can track a human body with relative accuracy of less than 10.4 cm at an update rate of 19.5 Hz.

Continuous-time fuzzy control and learning methods

This paper presents a novel approach to continuous-time control and learning methods used in home control systems. The approach is based on a context-aware fuzzy controlled intelligent environment. We propose continuous-time control and stepwise learning methods that allow the home to adapt to the user routines unobtrusively and smoothly. The adaptation is based on recognizing patterns of human practices, which may change over time. The new methods were applied to a fuzzy controlled lighting system and test results were obtained.

Living wood: a self-hiding calm user interface

As user interfaces are becoming more ubiquitous and abundant, users may feel perplexed by the pure number of user interfaces surrounding them. In order to increase user acceptance, ubiquitous user interfaces should be designed to be as calm and nonintrusive as possible. This paper presents the design and evaluation of a calm user interface prototype, Living Wood. Living Wood is a touch sensitive graphical user interface for smart home applications, and designed to fade into the background and hide itself when it is not used. A prototype for lighting control was built and installed in a smart home laboratory. To investigate how the self-hiding nature of the panel, its aesthetic features and usability was experienced by users, we tested Living Wood with 11 users.