Jani Mäntyjärvi

Recognizing human motion with multiple acceleration sensors

In this paper experiments with acceleration sensors are described for human activity recognition of a wearable device user. The use of principal component analysis and independent component analysis with a wavelet transform is tested for feature generation. Recognition of human activity is examined with a multilayer perceptron classifier. Best classification results for recognition of different human motion were 83-90%, and they were achieved by utilizing independent component analysis and principal component analysis. The difference between these methods turned out to be negligible.

Hand gesture recognition of a mobile device user

Experiments with acceleration sensors is described for static and dynamic gesture recognition of a mobile device user. Static gestures are recognized with the self-organizing mapping scheme of Kohonen while a hidden Markov model is used for recognizing dynamic gestures. An experimental sensor box for the research of context-awareness is also explained. Experimental results show great promise of the chosen technologies for recognizing gestures of a user of a mobile device.

An ontology for mobile device sensor-based context awareness

In mobile computing, the efficient utilisation of the information gained from the sensors embedded in the devices is difficult. Instead of using raw measurement data application specifically, as currently is customary, higher abstraction level semantic descriptions of the situation, context, can be used to develop mobile applications that are more usable. This article introduces an ontology of context constituents, which are derived from a set of sensors embedded in a mobile device. In other words, a semantic interface to the sensor data is provided. The ontology promotes the rapid development of mobile applications, more efficient use of resources, as well as reuse and sharing of information between communicating entities. A few mobile applications are presented to illustrate the possibilities of using the ontology.

Developing design guidelines for context-aware mobile applications

Context-aware computing sets new challenges for interaction design. This paper introduces the special characteristics of context-aware mobile devices that should be taken into account in interaction and user interface design, and proposes design guidelines for context-aware mobile applications. The proposed guidelines are evaluated with two design exercises.

Automatic feature selection for context recognition in mobile devices

In mobile devices there exist several in-built sensor units and sources which provide data for context reasoning. More context sources can be attached via wireless network connections. Usually, the mobile devices and the context sources are battery powered and their computational and space resources are limited. This sets special requirements for the context recognition algorithms. In this paper, several classification and automatic feature selection algorithms are compared in the context recognition domain. The main goal of this study is to investigate how much advantage can be achieved by using sophisticated and complex classification methods compared with a simple method that can easily be implemented in mobile devices. The main result is that even a simple linear classification algorithm can achieve a reasonably good accuracy if the features calculated from raw data are selected in a suitable way. Usually context recognition algorithms are fitted to a particular problem instance in an off-line manner and modifying methods for on-line learning is difficult or impossible. An on-line version of the Minimum-distance classifier is presented in this paper and it is justified that it leads to considerably higher classification accuracies compared with the static off-line version of the algorithm. Moreover, we report superior performance for the Minimum-distance classifier compared to other classifiers from the view point of computational load and power consumption of a smart phone.

Visualization of hand gestures for pervasive computing environments

Visualization method is proposed as an additional feature for accelerometer-based gesture control. The motivation for visualization of gesture control is justified and the challenges related to visualization are presented. The gesture control is based on Hidden Markov Models. This paper describes basic concepts of the gesture visualization and studies how well the developed visualization method can animate hand movement performed during the gesture control. The results indicate that visualization clearly provides information about the performed gesture, and it could be utilized in providing essential feedback and guidance to the user in future gesture control applications.

Animated UI transitions and perception of time: a user study on animated effects on a mobile screen

The capability to present advanced graphics in the present mobile devices can be utilized to improve their usability and overall user experience. Mobile devices have limitations compared to PCs due to their inferior computing power and small screens, but a successful design of animated transitions can hide processing delays and make the user experience smoother. In this paper, we describe the design of animated transitions and present a user study on how they are perceived. The results show that in the transition between two images, bringing up the next image earlier dominates the perception of a fast transition over other variables examined in the study.

Animated Transitions for Adaptive Small Size Mobile Menus

This paper explores how the user interface of a mobile device could support human perception and conception of changes in its environment. Animated transition effects may hold potential for visualizing changes in the resources available for the user through the context-aware user interface. Four different transition types are investigated. Each transition represents a different approach for visualizing changes in UI. The transitions are evaluated with 40 test subjects, half in India and half in Europe. Statistical analysis of the results indicates that animated transition effects have a clear positive effect on perception and conception of change.

Evaluating context-aware user interface migration in multi-device environments

People access applications and services through different devices depending on location and needs. During a single day, people can use a smartphone, tablet, PC and a TV, sequentially or simultaneously, depending on the context of use. Even within a single task, people often start with one device, such as a smartphone, and continue with another device, such as a PC, as the task evolves. To provide fluent task continuation, the system should provide ways to migrate on-going sessions from one device to another in a seamless manner. In this paper, we present a solution for migrating user interface and maintaining the interaction session across devices when changing situations. With two studies we gain insights into user needs and technical requirements for context-aware information sharing in multi-device environments. A longitudinal diary study was conducted to uncover specific situations where users have needs for information sharing, and how they would prefer the system to react in those situations. We also conducted a controlled user study using a prototype system for session migration between devices in changing contexts, with three different operational modes: manual, assisted and automatic, to gain a deeper knowledge into the requirements. The findings indicate a need for easier interaction whilst switching between devices and that these needs are often situation-specific. We also report in detail how people would prefer the system to perform migrations automatically and intelligently suggest them in some situations. Moreover, we draw technical requirements for such a system in order to develop seamless context-aware migration.

Distributed RESTful Web Services for Mobile Person-to-Person Collaboration

The mobile devices have a key role in aggregating information while people are on the go. Therefore it would be beneficial to use that potential also for sharing information collaboratively. In this paper, one possible solution to this challenge is given. The proposed approach is to use distributed, lightweight Web services for mobile collaboration. The collaboration between the people is direct without the need for centralized information storage. Therefore the approach is described here as mobile person-to-person collaboration. In this paper this concept is described by providing a list of requirements and by presenting an architectural approach. To evaluate the approach, a prototype service was implemented as a case study. To discuss the focus and contribution of this work the architecture is evaluated against the requirements and compared with the relevant state-of-the-art studies in the field. The results indicate that this approach provides a prominent and novel way of leveraging on the existing content for collaboration in a mobile environment as well as refines the requirements for future mobile collaborative applications and services.