Search

Presentation performed in the range of the First School on Smart Data Processing and Systems of Deep Insight (H2020 Destini), This presentation introduces the main features and challenges tackled by the H2020 DataCloud Project, with a focus on the research and technical solutions to the discovery of data pipelines.

Healthcare is one of the largest business segments in the world and is a critical area for future growth. In order to ensure efficient access to medical and patient-related information, hospitals have invested heavily in improving clinical mobile technologies and spread their use among doctors. Notwithstanding the benefits of mobile technologies towards a more efficient and personalized delivery of care procedures, there are also indications that their use may have a negative impact on patient-centeredness and often places many cognitive and physical demands on doctors, making them prone to make medical errors. To tackle this issue, in this paper we present the main outcomes of the project TESTMED, which aimed at realizing a clinical system that provides operational support to doctors using mobile technologies for delivering care to patients, in a bid to minimize medical errors. The system exploits concepts from Business Process Management on how to manage a specific class of care procedures, called clinical guidelines, and how to support their execution and mobile orchestration among doctors. As a viable solution for doctors' interaction with the system, we investigated the use of vocal and touch interfaces. User evaluation results indicate a good usability of the system.

Process mining methods allow analysts to use logs of historical executions of business processes in order to gain knowledge about the actual behavior of these processes. One of the most widely studied process mining operations is automated process discovery. An event log is taken as input by an automated process discovery method and produces a business process model as output that captures the control-flow relations between tasks that are described by the event log. In this setting, this paper provides a systematic comparative evaluation of existing implementations of automated process discovery methods with domain experts by using a real-life event log extracted from an international software engineering company and four quality metrics. The evaluation results highlight gaps and unexplored trade-offs in the field and allow researchers to improve the lacks in the automated process discovery methods in terms of usability of process discovery techniques in industry.

Process mining allows analysts to exploit logs of historical executions of business processes to extract insights regarding the actual performance of these processes. One of the most widely studied process mining operations is automated process discovery. An automated process discovery method takes as input an event log, and produces as output a business process model that captures the control-flow relations between tasks that are observed in or implied by the event log. Various automated process discovery methods have been proposed in the past two decades, striking different tradeoffs between scalability, accuracy and complexity of the resulting models. However, these methods have been evaluated in an ad-hoc manner, employing different datasets, experimental setups, evaluation measures and baselines, often leading to incomparable conclusions and sometimes unreproducible results due to the use of closed datasets. This article provides a systematic review and comparative evaluation of automated process discovery methods, using an open-source benchmark covering twelve publicly-available real-life event logs and eight quality metrics. The results highlight gaps and unexplored tradeoffs in the field, including the lack of scalability of several methods and a strong divergence in their performance with respect to the different quality metrics used.

Audio recordings and the corresponding transcripts are often used as prosthetic memory (PM) after meetings and lectures. While current research is mainly developing novel features for prosthetic memory, less is known on how and why audio recordings and transcripts are used. We investigate how users interact with audio and transcripts as prosthetic memory, whether interaction strategies change over time, and analyse potential differences in accuracy and efficiency. In contrast to the subjective user perception, our results show that audio recordings and transcripts are equally efficient, but that transcripts are generally preferred due to their easily accessible contextual information. We further identified that prosthetic memory is not only used as a recall aid but frequently also consulted for verifying information that has been recalled from organic memory (OM). Our findings are summarised in a number of design implications for prosthetic memory solutions.

One of the main promises of process conformance is the opportunity to align normative processes (i.e. how the process should behave) and event logs (i.e. how does the process actually behaves). Results of conformance checking are valid as long as normative processes correspond to actual norms. Recent developments advocate the use of Natural Language Processing (NLP) to process model discovery from texts. We present a series of challenges in textual process discovery that limit its applicability to real norms. The challenges emerges from experiences with legal practitioners in the digitalization of administrative processes in Danish and Italian municipalities, and they need to be solved in order to provide accurate normative processes that reflect the intent of laws.