The paper presents results from the SmartSleep project which aims at developing a smartphone app that gives users individual advice on how to change their behaviour to improve their sleep. The advice is generated by identifying correlations between behaviour during the day and sleep architecture. To this end, the project addressed two sub-tasks: detecting a user’s daytime behaviour and recognising sleep stages in an everyday setting. In the case of daytime activity detection the best results were achieved using an accelerometer at the wrist and another one at the ankle (87%). A subsequent smoothing step increased the accuracy to over 90%. For recognising sleep architecture we experimented with various consumer wearables that we used in addition to the usual PSG sensors in a sleep lab. Several sleep stage classifiers were learned from the resulting sensor data streams segmented into labelled sleep stages of 30 s each. Apart from handcrafted features we experimented with unsupervised feature learning based on the deep learning paradigm. Our best results for correctly classified sleep stages are between 86 and 90% for Wake, REM, N2 and N3, while the best recognition rate for N1 is 37%. Finally, we discuss a preliminary design of the algorithm for determining correlations between daytime behaviour and sleep architecture.

The support of workplace learning is increasingly relevant as the change in every form determines today's working world in the industry and public administrations alike. Adapting quickly to a new job, a new task or a new team is a significant challenge that must be dealt with ever faster. Workplace learning differs significantly from school learning as it is aligned with business goals. Our approach supports workplace learning by suggesting historical cases and providing recommendations of experts and learning resources. We utilize users' workplace environment, we consider their learning preferences, provide them with useful prior lessons, and compare required and acquired competencies to issue the best-suited recommendations. Our research work follows a Design Science Research strategy and is part of the European funded project Learn PAd. The recommender system introduced here is evaluated in an iterative manner, first by comparing it to previously elicited user requirements and then through practical application in a test process conducted by the project application partner.

The paper presents results from the SmartSleep project which aims at developing a smartphone app that gives users individual advice on how to change their behaviour to improve their sleep. The advice is generated by identifying correlations between behaviour during the day and sleep architecture. To this end, the project addresses two sub-tasks: detecting a user’s daytime behaviour and recognising sleep stages in an everyday setting. The focus of the paper is on the second task. Various sensor devices from the consumer market were used in addition to the usual PSG sensors in a sleep lab. An expert assigned a sleep stage for every 30 seconds. Subsequently, a sleep stage classifier was learned from the resulting sensor data streams segmented into labelled sleep stages of 30 seconds each. Apart from handcrafted features we also experimented with unsupervised feature learning based on the deep learning paradigm. Our best results for correctly classified sleep stages are in the range of 90 to 91% for Wake, REM and N3, while the best recognition rate for N2 is 83%. The classification results for N1 turned out to be much worse, N1 being mostly confused with N2.

The accessibility of project knowledge obtained from experiences is an important and crucial issue in enterprises. This information need about project knowledge can be different from one person to another depending on the different roles he or she has. Therefore, a new ontology-based case-based reasoning OBCBR approach that utilises an enterprise ontology is introduced in this article to improve the accessibility of this project knowledge. Utilising an enterprise ontology improves the case-based reasoning CBR system through the systematic inclusion of enterprise-specific knowledge. This enterprise-specific knowledge is captured using the overall structure given by the enterprise ontology named ArchiMEO, which is a partial ontological realisation of the enterprise architecture framework EAF ArchiMate. This ontological representation, containing historical cases and specific enterprise domain knowledge, is applied in a new OBCBR approach. To support the different information needs of different stakeholders, this OBCBR approach has been built in such a way that different views, viewpoints, concerns and stakeholders can be considered. This is realised using a case viewpoint model derived from the ISO/IEC/IEEE 42010 standard. The introduced approach was implemented as a demonstrator and evaluated using an application case that has been elicited from a business partner in the Swiss research project.

This work focuses on case-based reasoning in domains where cases have complex structures with relationships to an arbitrary number of other (potentially complex and structured) entities and where case characterisations (queries) are potentially incomplete. We summarise the requirements for such domains in terms of case representation and retrieval functions. We then analyse properties of existing similarity measures used in CBR – above all symmetry – and argue that some of these properties are not desirable. By exploiting analogies with retrieval functions in the area of information retrieval – where similar functions have been replaced by new ones not exhibiting the aforementioned undesired properties – we derive a new asymmetric ranking function for case retrieval. On a generated test-bed, we show that indeed the new function results in different ranking of cases – and use testbed examples to illustrate why this is desirable from a user’s perspective.

Support of workplace learning is increasingly important as change in every form determines today's working world in industry and public administrations alike. Adapt quickly to a new job, a new task or a new team is a major challenge that must be dealt with ever faster. Workplace learning differs significantly from school learning as it should be strictly aligned to business goals. In our approach we support workplace learning by providing recommendations of experts and learning resources in a context-sensitive and personalized manner. We utilize users' workplace environment, we consider their learning preferences and zone of proximal development, and compare required and acquired competencies in order to issue the best suited recommendations. Our approach is part of the European funded project Learn PAd. Applied research method is Design Science Research. Evaluation is done in an iterative process. The recommender system introduced here is evaluated theoretically based on user requirements and practically in an early evaluation process conducted by the Learn PAd application partner.

Enterprises and Public Administrations alike need to ensure that newly hired employees are able to learn the ropes fast. Employers also need to support continuous workplace learning. Workplace learning should be strongly related to business goals and thus, learning goals should directly add to business goals. To measure achievement of both learning and business goals we propose augmented Key Performance Indicators (KPI). In our research we applied model driven engineering. Hence we developed a model for a Learning Scorecard comprising of business and learning goals and their KPIs represented in an ontology. KPI performance values and scores are calculated with formal rules based on the SPARQL Inferencing Notation. Results are presented in a dashboard on an individual level as well as on a team/group level. Requirements, goals and KPIs as well as performance measurement were defined in close cooperation with Marche Region, business partner in Learn PAd.

The Lokahi Enterprise Knowledge Browser provides an intuitive and flexible way to query a company's intranet knowledge. In addition to conventional search capabilities, it allows the user to browse through a semi-automatically generated knowledge map that visualizes intranet knowledge as a network/graph structure of semantic relations that are extracted top-down from structured documents, as well as bottom-up from unstructured documents. This paper describes the underlying fuzzy graph data structure, the method for extracting concepts and associations from text documents, and the merging of the resulting data structure with a predefined enterprise ontology.

Graph edit distance is one of the most flexible mechanisms for error-tolerant graph matching. Its key advantage is that edit distance is applicable to unconstrained attributed graphs and can be tailored to a wide variety of applications by means of specific edit cost functions. The computational complexity of graph edit distance, however, is exponential in the number of nodes, which makes it feasible for small graphs only. In recent years the authors of the present paper introduced several powerful approximations for fast suboptimal graph edit distance computation. The contribution of the present work is a self standing software tool integrating these suboptimal graph matching algorithms. It is about being made publicly available. The idea of this software tool is that the powerful and flexible algorithmic framework for graph edit distance computation can easily be adapted to specific problem domains via a versatile graphical user interface. The aim of the present paper is twofold. First, it reviews the implemented approximation methods and second, it thoroughly describes the features and application of the novel graph matching software.

The retrieval of historical project knowledge is still a challenge for enterprises nowadays. This paper introduces a case-based reasoning (CBR) approach for project knowledge. This approach improves the case-based reasoning by reusing enterprise specific domain knowledge that is defined in an enterprise ontology. Since the retrieval of relevant project knowledge from historical cases is a knowledge intensive task that relies heavily on enterprise specific domain knowledge, we represent both, historical cases as well as the necessary domain knowledge, in an enterprise ontology structure. The contribution of the paper is the introduction of a novel case retrieval mechanism that emphasizes enterprise specific domain knowledge by reusing an enterprise ontology named ArchiMEO. This ontology is a representation of the enterprise architecture ArchiMate® and other integrated standards. This work is based on a real-world scenario elicited from a business partner of the Swiss CTI research project [sic!]. The approach tackles the information need that might occur during a prospective project.

In the APPRIS project an Early-Warning-System (EWS) is developed applying semantic technologies, namely an enterprise ontology and an inference engine, for the assessment of procurement risks. Our approach allows for analyzing internal resources (e.g. ERP and CRM data) and external sources (e.g. entries in the Commercial Register and newspaper reports) to assess known risks, but also for identifying 'black swans', which hit enterprises with no warning but potentially large impact. For proof of concept we developed a prototype that allows for integrating data from various information sources, of various information types (structured and unstructured), and information quality (assured facts, news); automatic identification, validation and quantification of risks and aggregation of assessment results on several granularity levels. The motivating scenario is derived from three business project partners' real requirements for an EWS.

To discover risk as early as possible is a major demand of today’s supply-chainrisk-management. This includes analysis of internal resources (e.g. ERP and CRM data) but also of external sources (e.g. entries in the Commercial Register and newspaper reports). It is not so much the problem of getting the information as to analyze and evaluate it near-term, cross-linked and forward-looking. In the APPRIS project an EarlyWarning-System (EWS) is developed applying semantic technologies, namely an enterprise ontology and an inference engine, for the assessment of procurement risks. The approach allows for integrating data from various information sources, of various information types (structured and unstructured), and information quality (assured facts, news); automatic identification, validation and quantification of risks and aggregation of assessment results on several granularity levels. For representation the graphical user interface of a project partner’s commercial supply-management-system is used. Motivating scenario is derived from three business project partners’ real requirements for an EWS with special reference to the downstream side of supply chain models, to suppliers’ company structures and single sourcing.