Doreen Böhnstedt

Extended explicit semantic analysis for calculating semantic relatedness of web resources

Finding semantically similar documents is a common task in Recommender Systems. Explicit Semantic Analysis (ESA) is an approach to calculate semantic relatedness between terms or documents based on similarities to documents of a reference corpus. Here, usually Wikipedia is applied as reference corpus. We propose enhancements to ESA (called Extended Explicit Semantic Analysis) that make use of further semantic properties of Wikipedia like article link structure and categorization, thus utilizing the additional semantic information that is included in Wikipedia. We show how we apply this approach to recommendation of web resource fragments in a resource-based learning scenario for self-directed, on-task learning with web resources.

Collaborative Semantic Tagging of Web Resources on the Basis of Individual Knowledge Networks

The web is increasingly used as an information source to gain new knowledge but the management of found web pages can be a challenging task. Often social tagging systems are used for resource management. Besides the obvious use of tags --- organizing a collection of web resources --- they support functionalities like sharing resources with other users and recommendation of further possibly relevant web pages. This paper describes a novel application based on an extended tagging concept that can improve resource management and recommendation. Adding semantic information to tags and tagging fragments of web pages instead of whole web pages enhance the possibilities of well-known tagging applications. Individual knowledge networks are the basis of this tagging concept. A first prototype is developed as proof of concept.

Adaptive task-oriented message template for in-network processing

In disaster situations or on emergency terrains, Internet and Cloud access may be restricted; it may still be important to process complex resource-intensive tasks and to acquire distributed information for emergency response, using ad-hoc networks among, e.g., first responder mobile devices. Corresponding approaches towards coordination, resource utilization, and interoperability are still challenging. This paper introduces the concept of adaptive task-oriented message templates (ATMT) as a basis for overcoming these issues and for enabling cooperative in-network processing without additional synchronization overhead for mobile devices. An ATMT serves as a self-encapsulated message containing the operation chains that need to be executed as well as the required data. In order to address heterogeneity and interoperability issues, we integrate a lightweight ontology. Depending on the current utilization, devices can autonomously decide whether to participate in the network or not. We evaluate our approach in an indoor testbed with 8 wireless mesh nodes. The results confirm that our approach efficiently supports cooperation among heterogeneous devices towards utilizing available in-network resources while reducing network traffic.

SMARTENERGY.KOM: An intelligent system for energy saving in smart home

Over the last twenty years, energy conservation has always been of great importance to individuals, societies and decision makers around the globe. As a result, IT researchers have shown a great interest in providing efficient, reliable and easy-to-use IT services which help users saving energy at home by making use of the current advances in Information and Communications Technology (ICT). Driven by the aforementioned motivation, we developed SMARTENERGY.KOM, our framework for realizing energy efficient smart homes based on wireless sensor networks and human activity detection. Our work is based on the idea that most of the user activities at home are related to a set of electrical appliances which are necessary to perform these activities. Therefore, we show how it is possible to detect the users current activity by monitoring his fine-grained appliance-level energy consumption. This relation between activities and electrical appliances makes it possible to detect appliances which could be wasting energy at home. Our framework is organized in two components. On one hand, the activity detection framework which is responsible for detecting the users current activity based on his energy consumption. On the other hand, the EnergyAdvisor framework which utilizes the activity detection for the purpose of recognizing the appliances which are wasting energy at home and informing the user about optimization potential.

Automatic identification of tag types in a resource-based learning scenario

When users use tags they often have a rich semantic structure in mind, which can not be fully explicated using existing tagging systems. However, a tagging system needs to be simple in order to be successful, otherwise it will not be accepted by users. In our ELWMS.KOM system for the support of self-regulated Resource-Based Learning users can assign specific semantic types to the tags they use in order to manage their web-based learning resources. However studies have shown that most users would appreciate an automatic identification of tag types. In this paper we present a knowledge-based approach for the automatic identification of the tag types used in the ELWMS.KOM system. Evaluations conducted on different corpora show that the algorithm works with an overall accuracy of up to 84%.

Implementation and Evaluation of a Tool for Setting Goals in Self-regulated Learning with Web Resources

Learning effectively and efficiently with web resources demands distinct competencies in self-organization and self-motivation. According to the theory of Self-Regulated Learning, learning processes can be facilitated and supported by an effective goal-management. Corresponding to these theoretic principles, a goal-management tool has been implemented in an interdisciplinary project. It allows learners to set goals for internet research and assign relevant web resources to them. An evaluation study is presented that focuses on short-term learning episodes and selected results are shown that reinforce the benefits of our approach.

Presence detection, identification and tracking in smart homes utilizing bluetooth enabled smartphones

Advances in ubiquitous computing over the last decade have allowed us to inch closer to the realization of true smart homes. Many sensors are already embedded in our living environments which can monitor several environmental parameters such as temperature, humidity, brightness and appliance-level power consumption. However, in order to achieve the primary goal of the smart home, we should be able to detect, identify, and localize the entities inside it. Therefore, the user detection, identification and localization problems represent a crucial facet of the challenges introduced by the smart home problem. Our approach towards solving these challenges entailed the usage of Bluetooth technology for user identification and tracking, alongside a Wireless Local Area Network setup to collate the sensor data at a centralized server such as a home gateway which subsequently processed and stored the entries. Moreover, we have studied the efficacy of various pattern recognition algorithms for real time processing and decision modeling on the received data. We have hence demonstrated our solution represents a non-intrusive, inexpensive and energy-conserving methodology to solve an essential part of the smart home problem by integrating already existent devices and infrastructure in an innocuous manner to obtain good results with minimum overhead.

Towards language-independent web genre detection

The term web genre denotes the type of a given web resource, in contrast to the topic of its content. In this research, we focus on recognizing the web genres blog, wiki and forum. We present a set of features that exploit the hierarchical structure of the web pages HTML mark-up and thus, in contrast to related approaches, do not depend on a linguistic analysis of the pages content. Our results show that it is possible to achieve a very good accuracy for a fully language independent detection of structured web genres.

Impact of Time in Network Selection for Mobile Nodes

Today, mobile nodes use multiple Internet access networks inefficiently. State-of-the-art network selection strategies distribute data traffic to available networks, but ignore an important second dimension: time. Time selection offers the opportunity to plan usage of future-available networks for delay-tolerant data traffic. We hypothesize, that concurrent selection of network and time leads to synergy effects, which reduce transmission cost and boost connectivity performance. To assess data distribution to wireless networks and time, we propose a novel rating model for joint network and time selection. The proposed model rates the satisfaction of Quality-of-Service (QoS) application requirements and trades off conflicting optimization goals. Moreover, we analyze the impact of time in network selection and present three network selection schedulers, which differ in their time selection strategy. Evaluation of the results reveals a strong impact of time selection on network performance. This gives evidence, that our initial hypothesis holds and forward-looking scheduling strategies provide a substantial benefit over state-of-the-art approaches.

MoVeNet: Mobility Management for Vehicular Networking

Vehicle Internet access benefits from using heterogeneous multi-provider networks. However, such access suffers significantly from insufficient handover processes. Due to high vehicle speeds, handover happens frequently and is substantially impaired by high handover delays. To solve correlated issues, we propose MoVeNet, a client-controlled, distributed mobility management approach with three substantial characteristics. Firstly, it pools parallel resources of wireless multi-provider networks for efficient common use. Secondly, MoVeNet reduces overhead for mobility management due to publish-subscribe methods. Thirdly, it provides a low-latency option for critical data flows, which enables flow-wise trade-off between latency and overhead. The architecture splits control from data, introducing lightweight Data Agents, which provide protocol transparency towards communication partners. Data Agents are located near the optimal route to provide low-latency packet routes. Moreover, MoVeNet introduces a Control Agent, which offloads communication-intensive tasks from the mobile node to reduce signaling overhead. The result solves deficiencies of related approaches and satisfies typical requirements of modern mobility management protocols. As shown by simulation, MoVeNet reaches excellent handover performance even for the harsh environment of the connected vehicle scenario.