Witschel, Hans Friedrich
E-Mail-Adresse
Geburtsdatum
Suchergebnisse
Practice track: a learning tracker using digital biomarkers for autistic preschoolers
Preschool children, when diagnosed with Autism Spectrum Disorder (ASD), often ex- perience a long and painful journey on their way to self-advocacy. Access to standard of care is poor, with long waiting times and the feeling of stigmatization in many social set- tings. Early interventions in ASD have been found to deliver promising results, but have a high cost for all stakeholders. Some recent studies have suggested that digital biomarkers (e.g., eye gaze), tracked using affordable wearable devices such as smartphones or tablets, could play a role in identifying children with special needs. In this paper, we discuss the possibility of supporting neurodiverse children with technologies based on digital biomark- ers which can help to a) monitor the performance of children diagnosed with ASD and b) predict those who would benefit most from early interventions. We describe an ongoing feasibility study that uses the “DREAM dataset”, stemming from a clinical study with 61 pre-school children diagnosed with ASD, to identify digital biomarkers informative for the child’s progression on tasks such as imitation of gestures. We describe our vision of a tool that will use these prediction models and that ASD pre-schoolers could use to train certain social skills at home. Our discussion includes the settings in which this usage could be embedded.
KvGR: A graph-based interface for explorative sequential question answering on heterogeneous information sources
Exploring a knowledge base is often an iterative process: initially vague information needs are refined by interaction. We propose a novel approach for such interaction that supports sequential question answering (SQA) on knowledge graphs. As opposed to previous work, we focus on exploratory settings, which we support with a visual representation of graph structures, helping users to better understand relationships. In addition, our approach keeps track of context – an important challenge in SQA – by allowing users to make their focus explicit via subgraph selection. Our results show that the interaction principle is either understood immediately or picked up very quickly – and that the possibility of exploring the information space iteratively is appreciated.
Learning and engineering similarity functions for business recommenders
We study the optimisation of similarity measures in tasks where the computation of similarities is not directly visible to end users, namely clustering and case-based recommenders. In both, similarity plays a crucial role, but there are also other algorithmic components that contribute to the end result. Our suggested approach introduces a new form of interaction into these scenarios that make the use of similarities transparent to end users and thus allows to gather direct feedback about similarity from them. This happens without distracting them from their goal – rather allowing them to obtain better and more trustworthy results by excluding dissimilar items. We then propose to use the feedback in a way that incorporates machine learning for updating weights and decisions of knowledge engineers about possible additional features, based on insights derived from a summary of user feedback. The reviewed literature and our own previous empirical investigations suggest that this is the most feasible way – involving both machine and human, each in a task that they are particularly good at.
Random walks on human knowledge: incorporating human knowledge into data-driven recommenders
We explore the use of recommender systems in business scenarios such as consultancy. In these situations, apart from personal preferences of users, knowledge about objective business-driven criteria plays a role. We investigate strategies for representing and incorporating such knowledge into data-driven recommenders. As a baseline, we choose a robust and flexible paradigm that is based on a simple graph-based representation of past customer cases and choices, in combination with biased random walks. On a real data set from a business intelligence consultancy firm, we study how the incorporation of two important types of explicit human knowledge – namely taxonomic and associative knowledge – impacts the effectiveness of a data-driven recommender. Our results show no consistent improvement for taxonomic knowledge, but quite substantial and significant gains when using associative knowledge.
Natural language-based user guidance for knowledge graph exploration: a user study
Large knowledge graphs hold the promise of helping knowledge workers in their tasks by answering simple and complex questions in specialised domains. However, searching and exploring knowledge graphs in current practice still requires knowledge of certain query languages such as SPARQL or Cypher, which many untrained end users do not possess. Approaches for more user-friendly exploration have been proposed and range from natural language querying over visual cues up to query-by-example mechanisms, often enhanced with recommendation mechanisms offering guidance. We observe, however, a lack of user studies indicating which of these approaches lead to a better user experience and optimal exploration outcomes. In this work, we make a step towards closing this gap by conducting a qualitative user study with a system that relies on formulating queries in natural language and providing answers in the form of subgraph visualisations. Our system is able to offer guidance via query recommendations based on a current context. The user study evaluates the impact of this guidance in terms of both efficiency and effectiveness (recall) of user sessions. We find that both aspects are improved, especially since query recommendations provide inspiration, leading to a larger number of insights discovered in roughly the same time.
Case model for the RoboInnoCase recommender system for cases of digital business transformation: structuring information for a case of digital change
In this work, we develop a case model to structure cases of past digital transformations which act as input data for a recommender system. The purpose of that recommender is to act as an inspiration and support for new cases of digital transformation. To define the case model, case analyses, where 40 cases of past digital transformations are analysed and coded to determine relevant attributes and values, literature research and the particularities of the case for digital change, are used as a basis. The case model is evaluated by means of an experiment where two different scenarios are fed into a prototypical case-based recommender system and then matched, based on an entropically derived weighting system, with the case base that contains cases structured according to the case model. The results not only suggest that the case model’s functionality can be guaranteed, but that a good quality of the given recommendations is achieved by applying a case-based recommender system using the proposed case model. The results not only suggest that the case model’s functionality can be guaranteed, but that a good quality of the given recommendations is achieved by applying a case-based recommender system using the proposed case model.
Enhance classroom preparation for flipped classroom using AI and analytics
In a flipped classroom setting, it is important for students to come prepared for the classroom. Being prepared in advance helps students to grasp the concepts taught during classroom sessions. A recent student survey at Fachhochschule Nordwestschweiz (FHNW), Business School, Switzerland, revealed that only 27.7% students often prepared before a class and only 7% always prepared before a class. The main reason for not preparing for classes was lack of time and workload. A literature review study revealed that there is a growth of the use of Artificial Intelligence (AI), for example, chatbots and teaching assistants, which support both teachers and students for classroom preparation. There is also a rise in the use of data analytics to support tutor decision making in real time. However, many of these tools are based on external motivation factors like grading and assessment. Intrinsic motivation among students is more rewarding in the long term. This paper proposes an application based on AI and data analysis that focuses on intrinsically motivating and preparing students in a flipped classroom approach.
Hybrid conversational AI for intelligent tutoring systems
We present an approach to improve individual and self-regulated learning in group assignments. We focus on supporting individual reflection by providing feedback through a conversational system. Our approach leverages machine learning techniques to recognize concepts in student utterances and combines them with knowledge representation to infer the student’s understanding of an assignment’s cognitive requirements. The conversational agent conducts end-to-end conversations with the students and prompts them to reflect and improve their understanding of an assignment. The conversational agent not only triggers reflection but also encourages explanations for partial solutions.
Enhancing reflective practices within business management education: what kinds of e-learning scenarios can be designed?
Contrary to the dominant appearance of the topic ‘digitalization,’ a majority of managers do not know what it means and how they can leverage the development of new technologies and disruptive innovations for their business. Furthermore, doing business is getting increasingly complex due to globalization and specialization. Thus, it looks like everybody is hyperactively looking for an external solution to their managerial challenges while, at the same time, managers seem to have lost their intuition for future direction and are unable to step back and think about intended and unintended consequences of the digital revolution. We, who provide business management education for future leaders, are concerned about this development and teach our students to appreciate the discomfort with the hard work of thinking and reflecting to learn from the insights about innovation, strategy and personal development to achieve improved leadership competence. In this paper, we will present our lessons learnt from asking students of a leadership class at an applied university to write a reflective journal for deep learning purpose.
Training and re-using human experience: a recommender for more accurate cost estimates in project planning
In many industries, companies deliver customised solutions to their (business) customers within projects. Estimating the human effort involved in such projects is a difficult task and underestimating efforts can lead to non-billable hours, i.e. financial loss on the side of the solution provider. Previous work in this area has focused on automatic estimation of the cost of software projects and has largely ignored the interaction between automated estimation support and human project leads. Our main hypothesis is that an adequate design of such interaction will increase the acceptance of automatically derived estimates and that it will allow for a fruitful combination of data-driven insights and human experience. We therefore build a recommender that is applicable beyond software projects and that suggests job positions to be added to projects and estimated effort of such positions. The recommender is based on the analysis of similar cases (case-based reasoning), "explains" derived similarities and allows human intervention to manually adjust the outcomes. Our experiments show that recommendations were considered helpful and that the ability of the system to explain and adjust these recommendations was heavily used and increased the trust in the system. We conjecture that the interaction of project leads with the system will help to further improve the accuracy of recommendations and the support of human learning in the future.