Jukka Riekki

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.

Plug-and-play application platform: towards mobile peer-to-peer

While peer-to-peer (P2P) has emerged as a new hot communication concept among the Internet users, mobile usage of P2P applications is still taking its first steps. This article first elaborates the evolutionary process that P2P architectures are going through. Challenges and requirements for mobile P2P are then identified, followed by a definition of a novel Plug-and-Play Application Platform (PnPAP). This platform enables dynamic selections between diverse P2P and session management protocols while preserving the best available network connectivity through Holistic Connectivity (HCon) management. On-the-fly reconfiguration and run-time parameter optimization can be done with a lightweight interpretable state machine. The concept enables flexible and seamless communications for mobile devices in P2P networks.

Supporting distributed private and public user interfaces in urban environments

Proliferation of large public displays in urban cityscape gives rise to applications distributed between public displays and mobile devices. However, real deployment of distributed applications on top of this new infrastructure is challenging as no commonly accepted architectural solutions exist to rely on. In this paper, we present a platform supporting distributed application user interfaces on interactive large public screens and personal mobile devices. We demonstrate the functionality and potential of our approach by presenting a deployment of the platform with multiple distributed applications in authentic setting in a city center. We found this platform feasible to deploy interactive, appealing services on top of, and a non-cost information pick-up service as the most appealing to users.

Context-aware pervasive service composition and its implementation

Incorporating service composition and pervasive computing into managing users’ complex everyday activities calls for the Pervasive Service Composition paradigm for everyday life. In this paper, we propose the concept of Context-Aware Pervasive Service Composition (CAPSC), which aims at enabling a pervasive system to provide user service compositions that are relevant to the situation at hand. We investigate CAPSC requirements and design a CAPSC architecture by taking into account context-aware peer coordination, context-aware process service adaptation, and context-aware utility service adaptation. We present a proof of concept application prototype as well.

Towards connectivity management adaptability: context awareness in policy representation and end-to-end evaluation algorithm

An infrastructure based on multiple heterogeneous access networks is one of the leading enablers for the emerging pervasive and ubiquitous computing paradigm, in which the optimal management of diverse networking resources is a challenging problem. This paper presents a context-aware policy mechanism and related end-to-end evaluation algorithm for adaptive connectivity management of multi-access wireless networks. A policy is used to express the criteria for adaptive selection of the best local and remote network interfaces. The best connection can then be used for the establishment of a channel as well as the maintenance of on-going data transmission. Rich context information is considered in the policy representation with respect to user profile and preference, application characteristics, device capability, and network QoS condition. The decision of the best access networks to be used is made on the basis of an end-to-end evaluation process. The decision can be made in both Master-Slave and Peer-to-Peer modes. The paper focuses on the methods for policy representation and connection evaluation algorithm. A case study is presented to show the usability of the proposed policy mechanism and decision-making algorithm in the adaptive management of heterogeneous networking resources.

A distributed architecture for executing complex tasks with multiple robots

This paper presents a software architecture for the network-transparent control of distributed robotic systems. The system consists of two main components: a generic and easily extensible CORBA-based interface to distributed services, and a high-level XML-based description language for specifying the behavior of the robots. The architecture makes it possible to create dynamically modifiable, extensible control software with ease. It is successfully utilized in implementing a coffee serving system in which the co-operation of two very different robots and two other distributed services are needed.

NFC-based interactive learning environments for children

Near Field Communication (NFC) technology enables interactive, participatory learning applications that integrate digital learning material seamlessly to our everyday environment. NFC permits tagging objects in the environment and interacting with applications by touching the tagged objects with mobile devices. Touching a tag triggers an application in the mobile device to perform an operation that is related to the touched object. In this paper, we report how NFC can be used to create interactive applications that help children in their learning process and persuade them to do physical exercise. We report fully working applications we have developed to support children in learning to read, in learning a foreign language, in studying biology, and one application developed to persuade children to run outdoors.

Adaptive connectivity management middleware for heterogeneous wireless networks

The trends of network convergence and mobile accessibility in the Internet are bringing new challenges to the connectivity management of end hosts. Concerning network convergence, the configuration of heterogeneous access networks should be taken into consideration. As for mobile accessibility, seamless handoff between diverse access points is a challenging issue. This article presents the design and implementation of connectivity management middleware (CMM), a channel-based architecture for context-aware connectivity management. This architecture can both provide network awareness to applications and manage network resources in an adaptive fashion. In the case of network awareness, the platform provides interfaces for applications to query network QoS and availability status, as well as subscribe connection events. As for adaptive resource management, channel-based transport services for seamless access switching and disconnection treatment are provided based on a policy mechanism. A prototype is implemented with which experiments were performed in a GPRS-WLAN integrated environment in order to demonstrate the operational correctness of the architecture. Performance metrics are measured and analyzed.

Multimodal interaction with speech and physical touch interface in a media center application

We present a multimodal media center interface based on a novel combination of new modalities. The application is based on a combination of a large high-definition display and a mobile phone. Users can interact with the system using speech input (speech recognition), physical touch (touching physical icons with the mobile phone), and gestures. We present the key results from a laboratory experiment where user expectations and actual usage experiences are compared.

Semantic Reasoning for Context-Aware Internet of Things Applications

Acquiring knowledge from continuous and heterogeneous data streams is a prerequisite for Internet of Things (IoT) applications. Semantic technologies provide comprehensive tools and applicable methods for representing, integrating, and acquiring knowledge. However, resource-constraints, dynamics, mobility, scalability, and real-time requirements introduce challenges for applying these methods in IoT environments. We study how to utilize semantic IoT data for reasoning of actionable knowledge by applying state-of-the-art semantic technologies. For performing these studies, we have developed a semantic reasoning system operating in a realistic IoT environment. We evaluate the scalability of different reasoning approaches, including a single reasoner, distributed reasoners, mobile reasoners, and a hybrid of them. We evaluate latencies of reasoning introduced by different semantic data formats. We verify the capabilities of promising semantic technologies for IoT applications through comparing the scalability and real-time response of different reasoning approaches with various semantic data formats. Moreover, we evaluate different data aggregation strategies for integrating distributed IoT data for reasoning processes.