Mikko Perttunen

Distributed road surface condition monitoring using mobile phones

The objective of this research is to improve traffic safety through collecting and distributing up-to-date road surface condition information using mobile phones. Road surface condition information is seen useful for both travellers and for the road network maintenance. The problem we consider is to detect road surface anomalies that, when left unreported, can cause wear of vehicles, lesser driving comfort and vehicle controllability, or an accident. In this work we developed a pattern recognition system for detecting road condition from accelerometer and GPS readings. We present experimental results from real urban driving data that demonstrate the usefulness of the system. Our contributions are: 1) Performing a throughout spectral analysis of tri-axis acceleration signals in order to get reliable road surface anomaly labels. 2) Comprehensive preprocessing of GPS and acceleration signals. 3) Proposing a speed dependence removal approach for feature extraction and demonstrating its positive effect in multiple feature sets for the road surface anomaly detection task. 4) A framework for visually analyzing the classifier predictions over the validation data and labels.

Inferring Presence in a Context-Aware Instant Messaging System

The increasing volume of digital communication is raising new challenges in the management of the information flow. We discuss the usage of context to infer presence information automatically for instant messaging applications. This results in easy-to-use applications and more reliable presence information. We suggest a new model, context relation, for representing the contexts that are relevant for inferring presence. The key idea is to represent both the communication initiator’s and the receiver’s contexts. The model allows sophisticated control over presence information. We describe a fully functional prototype utilizing context relations.

Lease-Based Resource Management in Smart Spaces

We present a lease-based method for managing various resources in smart spaces. We argue that leases introduce a flexible way of utilizing context information in the management, and thus facilitate the optimization of resource usage. This work-in-progress paper presents our initial concept and methodology, along with ideas for further development

Applying wavelet packet decomposition and one-class support vector machine on vehicle acceleration traces for road anomaly detection

Road condition monitoring through real-time intelligent systems has become more and more significant due to heavy road transportation. Road conditions can be roughly divided into normal and anomaly segments. The number of former should be much larger than the latter for a useable road. Based on the nature of road condition monitoring, anomaly detection is applied, especially for pothole detection in this study, using accelerometer data of a riding car. Accelerometer data were first labeled and segmented, after which features were extracted by wavelet packet decomposition. A classification model was built using one-class support vector machine. For the classifier, the data of some normal segments were used to train the classifier and the left normal segments and all potholes were for the testing stage. The results demonstrate that all 21 potholes were detected reliably in this study. With low computing cost, the proposed approach is promising for real-time application.

Urban traffic analysis through multi-modal sensing

This paper makes contributions toward adopting a systemic view of city-wide ubiquitous systems. Here, we present methods and techniques for combining multiple sensing modalities to measure and model traffic patterns in urban environments. We show how noise in one modality can be reduced by considering another more reliable modality and how two modalities can be combined. While much work in the literature deals with simulated data or small data sets, our work focuses on analyzing data from a permanent data collection infrastructure in a downtown area. We present results using a 3-week data set containing data of two modalities: inductive loop traffic detectors and Bluetooth scanners.

Introducing context-aware features into everyday mobile applications

We describe our approach of introducing context-awareness into everyday applications to make them more easy-to-use. The approach aims in shortening both the learning curve when introducing new technology to end-users and prototype development time, as well as results in more reliable prototypes. Moreover, we expect that the approach yields better quality user test results. To demonstrate the approach, we have employed context-based availability inference to automatically update the availability of IBM Lotus Sametime Everyplace users. This is likely to result in more reliable availability information and to make the application easier to use. Context inference is done using information from Lotus Notes Calendar and WLAN positioning technology.

Experiments on mobile context-aware instant messaging

In a ubiquitous context-aware system, the context of the users can be employed in managing communications. Instant messaging systems utilize awareness in communication and are commonly used to coordinate workplace collaborations. We describe a context-aware instant messaging prototype that aims to reduce unsuccessful communication attempts by updating the availability of the users automatically. The system utilizes the contexts of both the communication initiator and receiver to infer the availability of the receiver. We strive to identify the needs for, and further requirements of such systems by analyzing the results of a week-long user test period, conducted in an everyday working environment. The users generally find automatic availability updating with awareness information to improve the value of instant messaging in collaborative work. Moreover, we clarify and generalize the terminology related to context-aware instant messaging

An Implementation of Auditory Context Recognition for Mobile Devices

Auditory contexts are recognized from mixtures of sounds from mobile users’ everyday environments. We describe our implementation of auditory context recognition for mobile devices. In our system we use a set of support vector machine classifiers to implement the recognizer. Moreover, static and runtime resource consumption of the system are measured and reported.

Spatio-temporal patterns link your digital identities

An important challenge for mobility analysis is the development of techniques that can associate users’ identities across multiple datasets. These can assist in developing hybrid sensing and tracking mechanisms across large urban spaces, inferring context by combining multiple datasets, but at the same time have important implications for privacy. In this paper we present a scheme to associate different identities of a person across two movement databases. Our two key contributions are the reformulation of this problem in terms of a two-class classification, and the development of efficient techniques for pruning the search space. We evaluate performance of the scheme on synthetic and real data from two co-located city-wide WiFi and Bluetooth networks, and show that the pruning has a remarkable effect on the performance of the scheme in identifying individuals across two distinct mobility datasets. Finally, we discuss the privacy implications of this scheme in the light of our findings.

Web tool for traffic engineers: direct manipulation and visualization of vehicular traffic using Google maps

We present a lightweight web-based tool aimed for traffic engineers that allows an engineer-friendly way to interact and explore traffic volume statistics. This system has been created in participatory design with experienced traffic engineers from a local traffic center. The tool has been built using common web technologies and utilizing an existing traffic detection loop network, and public online GIS and graph tool APIs.