Real-time analysis of Internet of Things sensor data is crucial for players in the industrial sector for staying competitive. That is, why highly capable and easy to integrate solutions are needed for this, which can be deployed close to the data sources. In this paper, we argue that Complex Event Processing (CEP), which is a model-driven data analytics approach, is such a technique. CEP is able to achieve high throughput of data without the need of the computing power available in modern cloud infrastructures, while producing semantically higher value data in real time.Our here presented solution using CEP is easily integrated, scalable and capable of processing big amounts of data while giving semantic assurances through meta data modeling. Users of our solution do not need to learn any languages to model patterns, but can do that with an intuitive, graphical approach running on mobile devices, which makes it a good fit for domain experts working in industrial environments today.Solutions like the one presented in this paper can be a key-enabler for new business models in the industrial sector and smart factories.

Smart Factory Web is a platform for smart factories to enable flexible sharing and management of assets and resources to maximize efficiency and provide visibility on a global market. To join the Smart Factory Web, participants describe their factory capabilities, which are modelled in an ontology. AutomationML is used to assist with this modelling. OPC UA is used as a communication protocol for factory live-data from the machines. However, factory owners are hesitant to share critical production data. Therefore, the communication has to be secure and in the best case, provide control mechanisms for the data owners. The International Data Space is a peer-to-peer network that will support secure exchange of data and data usage control. In this paper, the Smart Factory Web approach is discussed and extended by an implementation with the current state of the International Data Space.

Anomaly detection is the process of discovering some anomalous behaviour in the real-time operation of a system. It is a difficult task, since in a general case (multivariate anomaly detection) an anomaly can be related to the behaviour of several parameters which are not necessarily behaving anomalously per se, but their (complex) relation is anomalous (not usual/normal). This implies the need for a very efficient modeling of the normal behaviour in order to know what should be treated as anomalous/outlier/unusual. Consequently, classical model-driven approaches, due to their focus on the selected parameters for creating models, are not able to model the behaviour of the whole system. This is why data-driven approaches for anomaly detection are getting even more important for the industry use cases where hundreds (thousands) of parameters should be taken into account. However, current approaches are usually focused on the univariate anomaly detection (or some variations of it), so without observing the entire space of relations since the computation is very complex. In this paper we present a novel approach for the multivariate anomaly detection that is based on modeling and managing the streams of variations in a multidimensional space. The main advantage of this approach is the possibility to observe the relations between variations in a large set of parameters and create clusters of “normal/usual” variations. In order to ensure scaling, which is one of the most challenging requirements, the approach is based on the usage of the big data technologies for realizing data analytics tasks/calculations. The approach is realized as a part of D2Lab (Data Diagnostics Laboratory) framework and has been applied in several industrial use cases. In this paper we present an interesting usage for the anomaly detection in the process of functional testing of home appliances (in particular case refrigerators) after manufacturing/assembling process. It has been done for a big vendor (Whirlpool), who expects huge saving in testing and improved customer satisfaction from this approach.

In this paper we present a novel approach for data-driven Quality Management in industry processes that enables a multidimensional analysis of the anomalies that can appear and their real-time detection in the running system. The approach revolutionizes the way how quality control (and esp. anomaly detection) will be realized in production processes influenced by many parameters that can be in complex nonlinear correlations. It consists of two main steps: learning the normal behavior of the system (based on past data) and detecting an anomalous behavior in the real-time (by processing real-time data). The approach is especially suitable for modern industry systems that follow Industry 4.0 principles of ubiquity sensing and proactive responding. One of the main advantages is the self-adaptive nature of the approach due to its data-driven orientation, so that the model and parameters of the approach will be continuously updated to the dynamicity of data. The approach has been applied in the process of manufacturing microwave ovens (Whirlpool) and in this paper we present results for the data-driven quality control of one of the most critical parts - microwave oven fan. Due to the high speed of the rotation, every item has to be very precisely produced (according to the CAD model), which requires very strong quality control process.

One of the most important challenges in manufacturing is the continuous process improvement that requires new insights about the behavior/quality control of processes in order to understand the optimization/improvement potential. The paper elaborates on usage of big data-driven clustering for an efficient discovering of real-time unusualities in the process and their route-cause analysis. Our approach extends traditional clustering algorithms (like k-Means) with methods for better understanding the nature of clusters and provides a very efficient big data realization. We argue that this approach paves the way for a new generation of quality management tools based on big data analytics that will extend traditional statistical process control and empower Lean Six Sigma through big data processing. The proposed approach has been applied for improving process control in Whirlpool (washing machine tests, factory in Italy) and we present the most important finding from the evaluation study.

In this paper we present a novel approach for dynamic remote activity monitoring based on mobile complex event processing that has been used in a use case in the eHealth domain. Using complex event processing (CEP) in mobile environment enables a more flexible and efficient processing of personal sensor data and environment data, which are detected by sensors embedded in a mobile device. The main advantages of our approach are: an efficient combination of the mobile and server-side event processing through the semantic event model, optimal usage of mobile resources through dynamic management of mobile event processing and modelling of complex situations by using more expressive knowledge representation formalism. We present the settings for the use case and the results from the preliminary evaluation.

Adaptive behavior is one of the main challenges in building computerized systems, especially in the case of systems which are delivering information to the end users. Indeed, since the information overload has become the main drawback for the future development of such systems (cf. Big Data challenge), there is a huge movement in the research community to develop concepts for better adaptation of the form and size of information that will be delivered to a user (usually taking different forms of the personalization). However, the main effort has been dedicated to the contextualization of the user's task in order to determine what is the best way to tailor/adapt the presentation of information to the user, neglecting the role of the user's internal context, expressed as the user's (short-term) interest. The same is valid for the AR systems. In this tutorial we present novel results in modeling users' interest in the context of AR systems and demonstrate some practical results in realizing such an approach in a multisensor AR system based on the usage of the see-through AR glasses. Due to the need for continuously adapt the AR content to the user's interest, such models are facing many challenges in sensing the user's behavior (using acoustic-, video-, gesture- and bio-sensors), interpreting it as an interest and deciding in real-time what kind of the adaptation to perform. We argue that this lead to a new class of AR system that we coined as adaptive AR (AR) systems. This work has been partially realized within the scope of the FP7 ICT research project ARtSENSE (www.artsense.eu), that is developing new AR concepts for improving personalized museum's experience. The tutorial will present practical results from applying the approach in three cultural heritage institutions in Europe (Paris, Madrid and Liverpool).

In this paper we present the idea of inverse search - an approach that aims to stimulate the diffusion of documents from the private spaces of individual workers into the shared space of an organization. Therefore we derive an organizational information need (OIN) based on query logs and further usage statistics of our system. This information is used to recommend people to share private documents containing relevant knowledge.

In this paper we present a method for tagging web pages using more formal conceptual structures than a set of keywords. We have developed a formal Tag model and a method to map a set of keywords on it. Moreover, this model is used as the basis for the conceptual tag refinement, which searches for terms which are conceptually related to the tags that are assigned to an information source. In that way the meaning of the tags can be disambiguated, which supports a better usage of tags for further management of tagged documents. We have developed a software tool, an annotation framework, which realizes this approach. We present results from the first evaluation studies regarding its application for ontology pruning.

We present a logic-based approach for query refinement in ontology-based information portal. The approach enables a user to navigate through the information content incrementally and interactively. In each refinement step a user is provided with a complete but minimal set of refinements, which enables him to develop/express his information need in a step-by-step fashion. The approach is based on the model-theoretic interpretation of the refinement problem, so that the query refinement process can be considered as the process of inferring all queries which are subsumed by a given query. Moreover, query refinements are ranked according to their relevance to user's needs, whereas these needs are online discovered by analysing a user's behaviour. The approach is very suitable for modelling information retrieval tasks based on the database repositories, like searching product catalogues.

In this paper we present a comprehensive approach for the refinement of ontology-based queries, which is based on incrementally (step-by-step) and interactively tailoring a query to the current information needs of a user, whereas these needs are implicitly and on-line elicited by analysing the user's behaviour during the searching process. The gap between a user's need and his query is quantified by measuring several types of query ambiguities. Consequently, in the refinement process a user is provided with a ranked list of refinements, which leads to a decrease of some of these ambiguities. Moreover, by exploiting the ontology background, the approach supports finding "similar" results that can help a user to satisfy his information need.

In this paper we present the conceptual architecture of ONTOLOGER, a system for usage-driven management of querying for information in ontology-based information portals. The system is based on the analysis of users' activities that are acquired in the so-called semantic log file, which contains information about the content of a visited page as well. These analyses are used for managing (i) the underlying ontology, (ii) querying mechanism and (iii) the content of the information repository, in order to ensure that (a) the structure of the vocabulary reflects the needs of users, (b) the highly-relevant results can be found by users although they make short queries and read only top-ranked results and (c) the information repository contains (only) resources users are interested in. The focus of the paper is on improving querying (retrieval) mechanism based on the usage data. We present a case study, which shows how a portal can benefit from implementing presented management system.

In this paper we present an approach to model ontology evolution as reconfiguration-design problem solving. The problem is reduced to a graph search where the nodes are evolving ontologies and the edges represent the changes that transform the source node into the target node. The search is guided by the constraints provided partially by a user and partially by a set of rules defining ontology consistency. In this way we allow a user to specify an arbitrary request declaratively and ensure its resolving. The approach is implemented in the KAON framework and the evaluation study shows its benefits.

The vision of the Semantic Web can only be realized through proliferation of well-known ontologies describing different domains. To enable interoperability in the Semantic Web, it will be necessary to break these ontologies down into smaller, well-focused units that may be reused. Currently, three problems arise in that scenario. Firstly, it is difficult to locate ontologies to be reused, thus leading to many ontologies modeling the same thing. Secondly, current tools do not provide means for reusing existing ontologies while building new ontologies. Finally, ontologies are rarely static, but are being adapted to changing requirements. Hence, an infrastructure for management of ontology changes, taking into account dependencies between ontologies is needed. In this paper we present such an infrastructure addressing the aforementioned problems.