Semantic Features for Context Organization

Abstract

Abstract-In recent years the technological world has grown by incorporating billions of small sensing devices, collecting and sharing real-world information. As the number of such devices grows, it becomes increasingly difficult to manage all these new information sources. There is no uniform way to share, process and understand context information. In previous publications we discussed efficient ways to organize context information that is independent of structure and representation. However, our previous solution suffers from semantic sensitivity. In this paper we review semantic methods that can be used to minimize this issue, and propose an unsupervised semantic similarity solution that combines distributional profiles with public web services. Our solution was evaluated against MillerCharles dataset, achieving a correlation of 0.6.

On the application of contextual IoT service discovery in Information Centric Networks

“…In the current paper we extend the core concepts of the solution proposed in [12] with novel functionalities for supporting service discovery mechanisms turning it into a full fledged Semantic Matching Engine. Added functionalities include (un)registration of services, process incoming service discovery queries, match query terms with service description tags, respond with the results of the matchmaking process.…”

“…In [12], authors study the application of semantic methods for M2M scenarios and proposed the use of external public services (e.g., conventional search engines) as a replacement for large corpus, and as a solution to the rather poor vocabulary associated with M2M scenarios. In the current paper we will leverage these concepts for the implementation of a flexible IoT service discovery mechanism in the context of ICN.…”

“…The process of calculation of the distributional profiles comprises three major components (i) Corpus Extraction, which acts as a bridge between the solution and the search engine (i.e., Bing 4 and Faroo 5 APIs); (ii) Text Processing, a pipeline that process and cleans the corpus; (iii) Distributional Profile Extraction, which analyses the output of the previous pipeline and extract the profile of the term. The initial work in [12] extracted distributional profiles based only in unigrams, while here we handle unigrams, bigrams and trigrams. Additionally, a filtering mechanism for removing low frequency dimensions and consequently improving system accuracy was introduced.…”

“…Consequently, we integrate and evaluate the unsupervised semantic similarity solution proposed in [12] with an ICN-based discovery mechanism developed on top of the Named Data Networking (NDN) architecture [13]. In doing so, some of the core concepts of [12] had to be further evolved and a novel service-query matchmaking interface was developed.…”

Improve IoT/M2M Data Organization Based on Stream Patterns

“…As an alternative, we accepted the diversity of context representation as a consequence of economic pressures, and devised a bottom-up model [4], [10], [15] to organize context information without enforcing a specific representation. Our organization model is divided into four main parts, as depicted in Figure 1 The first two represent the structured component of our model and account for the source ID and fixed ddimensions respectively.…”