Background Tinnitus is often described as the phantom perception of a sound and is experienced by 5.1% to 42.7% of the population worldwide, at least once during their lifetime. The symptoms often reduce the patient’s quality of life. The TrackYourTinnitus (TYT) mobile health (mHealth) crowdsensing platform was developed for two operating systems (OS)—Android and iOS—to help patients demystify the daily moment-to-moment variations of their tinnitus symptoms. In all platforms developed for more than one OS, it is important to investigate whether the crowdsensed data predicts the OS that was used in order to understand the degree to which the OS is a confounder that is necessary to consider. Objective In this study, we explored whether the mobile OS—Android and iOS—used during user assessments can be predicted by the dynamic daily-life TYT data. Methods TYT mainly applies the paradigms ecological momentary assessment (EMA) and mobile crowdsensing to collect dynamic EMA (EMA-D) daily-life data. The dynamic daily-life TYT data that were analyzed included eight questions as part of the EMA-D questionnaire. In this study, 518 TYT users were analyzed, who each completed at least 11 EMA-D questionnaires. Out of these, 221 were iOS users and 297 were Android users. The iOS users completed, in total, 14,708 EMA-D questionnaires; the number of EMA-D questionnaires completed by the Android users was randomly reduced to the same number to properly address the research question of the study. Machine learning methods—a feedforward neural network, a decision tree, a random forest classifier, and a support vector machine—were applied to address the research question. Results Machine learning was able to predict the mobile OS used with an accuracy up to 78.94% based on the provided EMA-D questionnaires on the assessment level. In this context, the daily measurements regarding how users concentrate on the actual activity were particularly suitable for the prediction of the mobile OS used. Conclusions In the work at hand, two particular aspects have been revealed. First, machine learning can contribute to EMA-D data in the medical context. Second, based on the EMA-D data of TYT, we found that the accuracy in predicting the mobile OS used has several implications. Particularly, in clinical studies using mobile devices, the OS should be assessed as a covariate, as it might be a confounder.

In object-aware process management, processes are represented as multiple interacting objects rather than a sequence of activities, enabling data-driven and highly flexible processes. In such flexible scenarios, however, it is crucial to be able to check to what degree the process is executed according to the model (i.e., guided behavior). Conformance checking algorithms (e.g., Token Replay or Alignments) deal with this issue for activity-centric processes based on a process model (e.g., specified as a petri net) and a given event log that reflects how the process instances were actually executed. This paper applies conformance checking algorithms to the behavior of objects. In object-aware process management, object lifecycle processes specify the various states into which corresponding objects may transition as well as the object attribute values required to complete these states. The approach accounts for flexible lifecycle executions using multiple workflow nets and conformance categories, therefore facilitating process analysis for engineers.

Real-time monitoring of business processes offers promising perspectives to discover problems and optimisation potentials. Early detection is a key part in this endeavour. One crucial aspect of real-time monitoring is to determine the current progress of a running business process. This is particularly challenging for business processes that consist of a multitude of loosely coupled, smaller processes that interact with each other, like object lifecycle processes in data-centric approaches to business process management. In this paper, an approach to predict the remaining portion of the process path to be still executed in relation to the overall process is proposed. This prediction is based on a one-dimensional Kalman Filter. As a major benefit of this approach, real-time progress determination can start directly with the first run of the process, i.e., without need for comprehensive event log data. This becomes possible due to the procedure applied by the Kalman Filter, which requires no log data. A quantitative study with 250 progress estimations for large object lifecycle processes results in a deviation of the average estimated progress from the real progress, calculated after the completion of the process, of about 5%. This emphasises that reasonable progress predictions are possible even in the absence of an event log, as it is the case when deploying new or changed processes to the run-time system.

One aspect of monitoring business processes in real-time is to determine their current progress. For any real-time progress determination it is of utmost importance to accurately predict the remaining share still to be executed in relation to the total process. At run-time, however, this constitutes a particular challenge, as unexpected ad-hoc changes of the ongoing business processes may occur at any time. To properly consider such changes in the context of progress determination, different progress variants may be suitable. In this paper, an empirical study with 194 participants is presented that investigates user acceptance of different progress variants in various scenarios. The study aims to identify which progress variant, each visualised by a progress bar, is accepted best by users in case of dynamic process changes, which usually effect the current progress of the respective progress instance. The results of this study allow for an implementation of the most suitable variant in business process monitoring systems. In addition, the study provides deeper insights into the general acceptance of different progress measurements. As a key observation for most scenarios, the majority of the participants give similar answers, e.g., progress jumps within a progress bar are rejected by most participants. Consequently, it can be assumed that a general understanding of progress exists. This underlines the importance of comprehending the users' intuitive understanding of progress to implement the latter in the most suitable fashion.

Object-aware processes enable the data-driven generation of forms based on the object behavior, which is pre-specified by the respective object lifecycle process. Each state of a lifecycle process comprises a number of object attributes that need to be set (e.g., via forms) before transitioning to the next state. When initially modeling a lifecycle process, the optimal ordering of the form fields is often unknown and only a guess of the lifecycle process modeler. As a consequence, certain form fields might be obsolete, missing, or ordered in a non-intuitive manner. Though this does not affect process executability, it decreases the usability of the automatically generated forms. Discovering respective problems, therefore, provides valuable insights into how object-and process-aware information systems can be evolved to improve their usability. This paper presents an approach for deriving improvements of object lifecycle processes by comparing the respective positions of the fields of the generated forms with the ones according to which the fields were actually filled by users during runtime. Our approach enables us to discover missing or obsolete form fields, and additionally considers the order of the fields within the generated forms. Finally, we can derive the modeling operations required to automatically restructure the internal logic of the lifecycle process states and, thus, to automatically evolve lifecycle processes and corresponding forms.