“…In the recent paper by Kacprzyk et al [14], the authors claim that linguistic data summaries in Yager's sense can be considered an ultimately human consistent form of human-centric aggregation. This paper extends our previous works devoted to the statistical process control that aimed at the monitoring of the autocorrelated health-related processes [10,11,17] and works dedicated to the incorporation of linguistic summaries into time series forecasting [16].…”
Section: Related Worksupporting
confidence: 57%
“…The objective data automatically collected using smartphones become valid markers of a mood state [9]. Kaczmarek-Majer et al [17] recently showed that statistical process control is an adequate methodology to build patient-dependent models and generate alarms when the patient's behaviour related to the smartphone usage changes.…”
Personalized linguistic summaries are developed with the use of protoforms in the sense of Yager and Kacprzyk. We discuss the construction and usefulness of such patientdependent and disease-state-dependent linguistic summaries that may be examplied as Most outgoing calls in mania state (disease period) are short compared to the calls recorded in the euthymia state (healthy period). Such linguistic summaries may become important features in the smartphonebased monitoring of the bipolar disorder patients and inform about the detected change in patient's state. The main advantage of the personalized linguistic summaries is their human-centricity. The performance of the proposed approach is illustrated with examples based on the real-life data collected within the observational study.
“…In the recent paper by Kacprzyk et al [14], the authors claim that linguistic data summaries in Yager's sense can be considered an ultimately human consistent form of human-centric aggregation. This paper extends our previous works devoted to the statistical process control that aimed at the monitoring of the autocorrelated health-related processes [10,11,17] and works dedicated to the incorporation of linguistic summaries into time series forecasting [16].…”
Section: Related Worksupporting
confidence: 57%
“…The objective data automatically collected using smartphones become valid markers of a mood state [9]. Kaczmarek-Majer et al [17] recently showed that statistical process control is an adequate methodology to build patient-dependent models and generate alarms when the patient's behaviour related to the smartphone usage changes.…”
Personalized linguistic summaries are developed with the use of protoforms in the sense of Yager and Kacprzyk. We discuss the construction and usefulness of such patientdependent and disease-state-dependent linguistic summaries that may be examplied as Most outgoing calls in mania state (disease period) are short compared to the calls recorded in the euthymia state (healthy period). Such linguistic summaries may become important features in the smartphonebased monitoring of the bipolar disorder patients and inform about the detected change in patient's state. The main advantage of the personalized linguistic summaries is their human-centricity. The performance of the proposed approach is illustrated with examples based on the real-life data collected within the observational study.
“…At the same time, applications of statistical process control are rich and already include smartphone-based monitoring of mental illnesses. For example, in [11,12], the authors show the usefulness of the weighted model averaging in the residual control charts for early detection of change in the state of Bipolar Disorder (BD) basing on the behavioural data about smartphone usage and the limited amount of diagnostic data. However, the problem arises for non-stationary and imprecise processes such as acoustic data streams.…”
This paper introduces a novel procedure for statistical monitoring of acoustic data streams supported by possibilistic aggregation and multi-label learning. The primary goal is to learn improved control limits for the residual control charts due to the objective removal of measurements from the non-healthy state of a patient determined through multi-label learning.The proposed procedure is illustrated with real-life acoustic data collected from smartphones of Bipolar Disorder patient. Multi-label classification enabled to distinguish between different degrees of severity of manic and depressive symptoms, and especially for the mixed state -their simultaneous occurrence.
“…Contrary to the supervised approaches, there are works that apply completely unsupervised approaches to monitor changes in the severity of the depressive and manic symptoms [24] or to analyze behavioural data about smartphone usage [15,16]. However, unsupervised learning approaches insufficiently benefit of the a-priori knowledge given by labeled data of the psychiatric assessments [27].…”
Bipolar Disorder (BD) is a chronic mental illness characterized by changing episodes from euthymia (healthy state) through depression and mania to the mixed states. In this context, data collected through the interaction of patients with smartphones enable the creation of predictive models to support the early prediction of a starting episode. Previous research on predicting a new BD episode use mostly supervised learning methods that require labeled data and hence force a filtering of the available data to retain only those data that have valid labels (from the psychiatric assessment). To avoid limitations of supervised learning, in this paper we investigate the use of a semi-supervised learning approach that combines both labeled and unlabeled data to derive a model for BD episode prediction. Specifically we apply the DISSFCM (Dynamic Incremental Semi-Supervised Fuzzy C-Means) algorithm which offers the possibility to process in an incremental fashion the data stream of the voice signal captured by the smartphone, thus exploiting the evolving time structure of data which is ignored by static learning methods. DISS-FCM processes data in form of chunks and creates a dynamic collection of clusters thanks to a splitting mechanism that generates new clusters to better capture the hidden geometrical structure of data. This gives DISSFCM the ability to detect changes in data and dynamically adapt the model to them, thus improving the prediction accuracy. Preliminary results on real-world data collected at the Department of Affective Disorders, Institute of Psychiatry and Neurology in Warsaw (Poland) show that DISSFCM is able to predict some of healthy episodes (euthymia) and disease episodes even when only 25% of labeled data are available. Moreover DISSFM performs better than its previous version without split (ISSFCM) and it also overcomes the batch algorithm (SSFCM) that uses the whole dataset to create the model.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.