liu.seSearch for publications in DiVA
Change search
Link to record
Permanent link

Direct link
BETA
Publications (10 of 24) Show all publications
Bendtsen, M., Müssener, U., Linderoth, C. & Thomas, K. (2020). A Mobile Health Intervention for Mental Health Promotion Among University Students: Randomized Controlled Trial. JMIR mhealth and uhealth
Open this publication in new window or tab >>A Mobile Health Intervention for Mental Health Promotion Among University Students: Randomized Controlled Trial
2020 (English)In: JMIR mhealth and uhealth, E-ISSN 2291-5222Article in journal (Refereed) Published
National Category
Public Health, Global Health, Social Medicine and Epidemiology
Identifiers
urn:nbn:se:liu:diva-164919 (URN)
Available from: 2020-04-01 Created: 2020-04-01 Last updated: 2020-04-01
Bendtsen, M. (2020). Heterogeneous treatment effects of a text messaging smoking cessation intervention among university students. PLoS ONE, 15(3), Article ID e0229637.
Open this publication in new window or tab >>Heterogeneous treatment effects of a text messaging smoking cessation intervention among university students
2020 (English)In: PLoS ONE, E-ISSN 1932-6203, Vol. 15, no 3, article id e0229637Article in journal (Refereed) Published
Abstract [en]

Introduction

Despite tobacco being an important preventable factor with respect to ill health and death, it is a legal substance that harms and kills many of those who use it. Text messaging smoking cessation interventions have been evaluated in a variety of contexts, and are generally considered to have a positive effect on smoking cessation success. In order for text messaging interventions to continue to be useful as prevalence of smoking decreases, it may be necessary to tailor the interventions to specific individuals. However, little is known with regard to who benefits the most and least from existing interventions.

Methods

In order to identify heterogenous treatment effects, we analyzed data from a randomized controlled trial of a text messaging smoking cessation intervention targeting university students in Sweden. We used a Bayesian hierarchical model where the outcome was modelled using logistic regression, and so-called horseshoe priors were used for coefficients. Predictive performance of the model, and heterogeneous treatment effects, were calculated using cross-validation over the trial data.

Results

Findings from the study of heterogenous treatment effects identified less effect of the intervention among university students with stronger dependence of nicotine and students who smoke a greater quantity of cigarettes per week. No heterogeneity was found with respect to sex, number of years smoking, or the use of snuff.

Discussion

Results emphasize that individuals with a more developed dependence of nicotine may have a harder time quitting smoking even with support. This questions the dissemination and development of text messaging interventions to university students in the future, as they may not be the optimal choice of intervention for those with a more developed dependence. On the other hand, text messaging interventions may be useful to disseminate among university students that are at risk of developing a strong dependence.

Trial registration

International Standard Randomized Controlled Trial Number (ISRCTN): 75766527; http://www.controlled-trials.com/ISRCTN75766527.

Place, publisher, year, edition, pages
San Francisco, CA, United States: Public Library of Science, 2020
National Category
Public Health, Global Health, Social Medicine and Epidemiology
Identifiers
urn:nbn:se:liu:diva-164917 (URN)10.1371/journal.pone.0229637 (DOI)32134977 (PubMedID)2-s2.0-85081007357 (Scopus ID)
Available from: 2020-04-01 Created: 2020-04-01 Last updated: 2020-04-07Bibliographically approved
Müssener, U., Linderoth, C., Thomas, K. & Bendtsen, M. (2020). mHealth smoking cessation intervention among high school students: 3-month primary outcome findings from a randomized controlled trial. PLoS ONE, 15(3), Article ID e0229411.
Open this publication in new window or tab >>mHealth smoking cessation intervention among high school students: 3-month primary outcome findings from a randomized controlled trial
2020 (English)In: PLoS ONE, E-ISSN 1932-6203, Vol. 15, no 3, article id e0229411Article in journal (Refereed) Published
Abstract [en]

Background

Smoking among adolescents remains a global public health issue as youth continue to maintain high prevalence rates. The evidence for the efficacy of text messaging interventions to reduce smoking behavior is well established, yet there is still a need for studies targeting high school students. The aim of the study was to determine the effectiveness of a text-based smoking cessation intervention among high school students in Sweden.

Methods

The study was a two-arm randomized trial conducted from January 10 2018 to January 11 2019, data were analysed from April 12 2019 to May 21 2019. Inclusion criteria were high school students who were daily or weekly smokers willing to attempt to quit smoking and owned a mobile phone. The study invited all students at 630 high schools units throughout Sweden. The intervention group received text messages based on components of effective smoking cessation interventions for 12 weeks. The control group were offered treatment as usual. The primary outcomes were self-reported prolonged abstinence (not having smoked more than 5 cigarettes over the last 8 weeks) and 4-week point prevalence of smoking abstinence.

Findings

A total of 535 participants, with a median age of 17 (IQR 16–18), were randomized into the study; 276 (164 [59.4%] women) were allocated to the intervention and 259 (162 [62.5%] women) to the control group. The outcomes of the trial were analyzed on a total of 212 (76.8%) participants in the intervention group and 201 (77.6%) participants in the control group. Prolonged abstinence at the 3-month follow-up was reported by 49 (23.1%) individuals in the intervention group and 39 (19.4%) individuals in the control group (adjusted OR, 1.21; 95% CI, 0.73–2.01; P value, .46). Four-week point prevalence of complete smoking cessation was reported by 53 (25.0%) individuals in the intervention group and 31 (15.4%) individuals in the control group (adjusted OR, 1.87; 95% CI, 1.12–3.17; P value, .018).

Conclusions

Estimates of 4-week point prevalence of complete cessation was 10 percentage points higher in the group that were given access to the intervention compared to the control. Findings provide confirmation that text messaging-based smoking cessation programs can affect quit rates among adolescents.

Trial registration

ISRCTN15396225; registration date October 13, 2017, https://trialsjournal.biomedcentral.com/articles/10.1186/s13063-018-3028-2.

Place, publisher, year, edition, pages
San Francisco, CA, United States: Public Library of Science, 2020
National Category
Public Health, Global Health, Social Medicine and Epidemiology
Identifiers
urn:nbn:se:liu:diva-164918 (URN)10.1371/journal.pone.0229411 (DOI)32142514 (PubMedID)2-s2.0-85081208901 (Scopus ID)
Available from: 2020-04-01 Created: 2020-04-01 Last updated: 2020-04-07Bibliographically approved
Müssener, U., Löf, M., Bendtsen, P. & Bendtsen, M. (2020). Using Mobile Devices to Deliver Lifestyle Interventions Targeting At-Risk High School Students: Protocol for a Participatory Design Study. JMIR Research Protocols, 1(9)
Open this publication in new window or tab >>Using Mobile Devices to Deliver Lifestyle Interventions Targeting At-Risk High School Students: Protocol for a Participatory Design Study
2020 (English)In: JMIR Research Protocols, ISSN 1929-0748, E-ISSN 1929-0748, Vol. 1, no 9Article in journal (Refereed) Published
Abstract [en]

Background: Unhealthy lifestyle behaviors such as insufficient physical activity, unhealthy diet, smoking, and harmful use of alcohol tend to cluster (ie, individuals may be at risk from more than one lifestyle behavior that can be established in early childhood and adolescence and track into adulthood). Previous research has underlined the potential of lifestyle interventions delivered via mobile phones. However, there is a need for deepened knowledge on how to design mobile health (mHealth) interventions taking end user views into consideration in order to optimize the overall usability of such interventions. Adolescents are early adopters of technology and frequent users of mobile phones, yet research on interventions that use mobile devices to deliver multiple lifestyle behavior changes targeting at-risk high school students is lacking.

Objective: This protocol describes a participatory design study with the aim of developing an mHealth lifestyle behavior intervention to promote healthy lifestyles among high school students.

Methods: Through an iterative process using participatory design, user requirements are investigated in terms of technical features and content. The procedures around the design and development of the intervention, including heuristic evaluations, focus group interviews, and usability tests, are described.

Results: Recruitment started in May 2019. Data collection, analysis, and scientific reporting from heuristic evaluations and usability tests are expected to be completed in November 2019. Focus group interviews were being undertaken with high school students from October through December, and full results are expected to be published in Spring 2020. A planned clinical trial will commence in Summer 2020. The study was funded by a grant from the Swedish Research Council for Health, Working Life, and Welfare.

Conclusions: The study is expected to add knowledge on how to design an mHealth intervention taking end users’ views into consideration in order to develop a novel, evidence-based, low-cost, and scalable intervention that high school students want to use in order to achieve a healthier lifestyle.

Place, publisher, year, edition, pages
Toronto, Canada: J M I R Publications, Inc., 2020
Keywords
mHealth intervention; lifestyle behavior; high school students; qualitative methods; participatory design
National Category
Public Health, Global Health, Social Medicine and Epidemiology
Identifiers
urn:nbn:se:liu:diva-163115 (URN)10.2196/14588 (DOI)31904576 (PubMedID)
Available from: 2020-01-13 Created: 2020-01-13 Last updated: 2020-02-17Bibliographically approved
Müssener, U., Linderoth, C. & Bendtsen, M. (2019). Exploring the Experiences of Individuals Allocated to a Control Setting: Findings From a Mobile Health Smoking Cessation Trial. JMIR Human Factors, 6(2), Article ID e12139.
Open this publication in new window or tab >>Exploring the Experiences of Individuals Allocated to a Control Setting: Findings From a Mobile Health Smoking Cessation Trial
2019 (English)In: JMIR Human Factors, E-ISSN 2292-9495, Vol. 6, no 2, article id e12139Article in journal (Refereed) Published
Abstract [en]

Background: Tobacco smoking is the primary cause of preventable premature disease and death worldwide. Evidence of the efficacy of text messaging interventions to reduce smoking behavior is well established, but there is still a need for studies targeting young people, especially because young adult smokers are less likely to seek treatment than older adults. A mobile health intervention, Nicotine Exit (NEXit), targeting smoking among university students was developed to support university students to quit smoking. Short-term effectiveness was measured through a randomized controlled trial, which found that immediately after the 12-week intervention, 26% of smokers in the intervention group had prolonged abstinence compared with 15% in the control group.

Objective: The objective of this study was to explore the experience of being allocated to the control group in the NEXit smoking cessation intervention.

Methods: We asked students who were allocated to the control group in the main NEXit randomized controlled trial to report their experiences. An email was sent to the participants with an electronic link to a short questionnaire. We assessed the distribution of the responses to the questionnaire by descriptive analysis. We analyzed free-text comments to 4 questions.

Results: The response rate for the questionnaire was 33.8% (258/763), and we collected 143 free-text comments. Of the responders, 60.9% (157/258) experienced frustration, disappointment, and irritation about being allocated to the control group; they felt they were being denied support by having to wait for the intervention. Monthly text messages during the waiting period thanking them for taking part in the trial were perceived as negative by 72.3% (189/258), but for some the messages served as a reminder about the decision to quit smoking. Of the responders, 61.2% (158/258) chose to wait to quit smoking until they had access to the intervention, and 29.8% (77/258) decided to try to quit smoking without support. Of the respondents, 77.5% (200/258) claimed they were still smoking and had signed up or were thinking about signing up for the smoking cessation program at the time of the questionnaire.

Conclusions: Most of the respondents reported negative feelings about having to wait for the support of the intervention and that they had decided to continue smoking. A similar number decided to wait to quit smoking until they had access to the intervention, and these respondents reported a high interest in the intervention. Free-text comments indicated that some control group participants believed that they had been excluded from the trial, while others were confused when asked to sign up for the intervention again.

Place, publisher, year, edition, pages
Toronto, Canada: J M I R Publications, Inc., 2019
Keywords
tobacco smoking; smoking cessation; students; text messaging; mobile phones; cell phone; control groups
National Category
Public Health, Global Health, Social Medicine and Epidemiology
Identifiers
urn:nbn:se:liu:diva-162804 (URN)10.2196/12139 (DOI)30938682 (PubMedID)2-s2.0-85067306510 (Scopus ID)
Available from: 2019-12-18 Created: 2019-12-18 Last updated: 2020-01-22Bibliographically approved
Bendtsen, M. (2019). Text Messaging Interventions for Reducing Alcohol Consumption Among Harmful and Hazardous Drinkers: Protocol for a Systematic Review and Meta-Analysis. JMIR Research Protocols, 8(4), Article ID e12898.
Open this publication in new window or tab >>Text Messaging Interventions for Reducing Alcohol Consumption Among Harmful and Hazardous Drinkers: Protocol for a Systematic Review and Meta-Analysis
2019 (English)In: JMIR Research Protocols, ISSN 1929-0748, E-ISSN 1929-0748, Vol. 8, no 4, article id e12898Article in journal (Refereed) Published
Abstract [en]

Background: Mobile phone-based interventions have become popular for lifestyle behavior change, particularly the use of text messaging as it is a technology ubiquitous in mobile phones. Reviews and meta-analyses of digital interventions for reducing harmful and hazardous use of alcohol have mainly focused on Web-based interventions; thus, there is a need for a body of evidence to guide health practitioners, policy makers, and researchers with respect to the efficacy of available text messaging interventions.

Objective: The aim of this systematic review and meta-analysis is to assess the effectiveness of text messaging interventions for reducing the amount of alcohol consumed among harmful and hazardous drinkers; this is compared to receiving no, minimal, or unrelated health information. Specifically, we ask the following questions: (1) Can interventions consisting of only text messages be effective in reducing alcohol consumption compared to no intervention or a minimal or unrelated intervention? (2) Can interventions consisting of only text messages be effective in reducing the prevalence of risky drinking compared to no intervention or a minimal or unrelated intervention?

Methods: Several databases will be searched, including the Cochrane Central Register of Controlled Trials (CENTRAL), MEDLINE, PsycINFO, the Conference Proceedings Citation Index, ClinicalTrials.gov, OpenGrey, among others. Reports of studies that evaluate text messaging interventions for reducing the amount of alcohol consumed will be included. Primary outcomes of interest will be weekly alcohol consumption and frequency of heavy episodic drinking. The Cochrane Collaboration Risk of Bias tool will be used to assess bias in reports, and the Grades of Recommendation, Assessment, Development, and Evaluation (GRADE) approach will be used to assess the quality of the body of evidence. A narrative review will be presented, and a meta-analysis will be conducted in case of homogeneity among included studies.

Results: The systematic review has not yet begun but is expected to start in May of 2019; publication of the final review and meta-analysis is expected at the end of 2019.

Conclusions: The technology for text messaging is ubiquitous in mobile phones; thus, the potential reach of interventions utilizing this technique is great. However, there are no meta-analyses to date that limit the scope to the use of text messaging interventions for alcohol consumption reduction. Therefore, the proposed systematic review and meta-analysis will help health practitioners, policy decision makers, researchers, and others to better understand the effects of these interventions.

Place, publisher, year, edition, pages
Toronto, Canada: J M I R Publications, Inc., 2019
Keywords
text messaging; SMS; risky drinking; harmful drinking; hazardous drinking; intervention; systematic review; meta-analysis
National Category
Medical and Health Sciences
Identifiers
urn:nbn:se:liu:diva-162802 (URN)10.2196/12898 (DOI)000466496800014 ()31012866 (PubMedID)2-s2.0-85067872129 (Scopus ID)
Available from: 2019-12-18 Created: 2019-12-18 Last updated: 2020-03-28Bibliographically approved
Müssener, U., Andersson, E. K., Linderoth, C., Leijon, M. E. & Bendtsen, M. (2018). A Text Message-Based Intervention Targeting Alcohol Consumption Among University Students: User Satisfaction and Acceptability Study.. JMIR Human Factors, 5(3), Article ID e23.
Open this publication in new window or tab >>A Text Message-Based Intervention Targeting Alcohol Consumption Among University Students: User Satisfaction and Acceptability Study.
Show others...
2018 (English)In: JMIR Human Factors, E-ISSN 2292-9495, Vol. 5, no 3, article id e23Article in journal (Refereed) Published
Abstract [en]

BACKGROUND: Heavy consumption of alcohol among university students is a global problem, with excessive drinking being the social norm. Students can be a difficult target group to reach, and only a minority seek alcohol-related support. It is important to develop interventions that can reach university students in a way that does not further stretch the resources of the health services. Text messaging (short message service, SMS)-based interventions can enable continuous, real-time, cost-effective, brief support in a real-world setting, but there is a limited amount of evidence for effective interventions on alcohol consumption among young people based on text messaging. To address this, a text messaging-based alcohol consumption intervention, the Amadeus 3 intervention, was developed.

OBJECTIVE: This study explored self-reported changes in drinking habits in an intervention group and a control group. Additionally, user satisfaction among the intervention group and the experience of being allocated to a control group were explored.

METHODS: Students allocated to the intervention group (n=460) were asked about their drinking habits and offered the opportunity to give their opinion on the structure and content of the intervention. Students in the control group (n=436) were asked about their drinking habits and their experience in being allocated to the control group. Participants received an email containing an electronic link to a short questionnaire. Descriptive analyses of the distribution of the responses to the 12 questions for the intervention group and 5 questions for the control group were performed.

RESULTS: The response rate for the user feedback questionnaire of the intervention group was 38% (176/460) and of the control group was 30% (129/436). The variation in the content of the text messages from facts to motivational and practical advice was appreciated by 77% (135/176) participants, and 55% (97/176) found the number of messages per week to be adequate. Overall, 81% (142/176) participants stated that they had read all or nearly all the messages, and 52% (91/176) participants stated that they were drinking less, and increased awareness regarding negative consequences was expressed as the main reason for reduced alcohol consumption. Among the participants in the control group, 40% (52/129) stated that it did not matter that they had to wait for access to the intervention. Regarding actions taken while waiting for access, 48% (62/129) participants claimed that they continued to drink as before, whereas 35% (45/129) tried to reduce their consumption without any support.

CONCLUSIONS: Although the main randomized controlled trial was not able to detect a statistically significant effect of the intervention, most participants in this qualitative follow-up study stated that participation in the study helped them reflect upon their consumption, leading to altered drinking habits and reduced alcohol consumption.

TRIAL REGISTRATION: International Standard Randomized Controlled Trial Number ISRCTN95054707; http://www.isrctn.com/ISRCTN95054707 (Archived by WebCite at http://www.webcitation.org/705putNZT).

Place, publisher, year, edition, pages
Toronto, Canada: J M I R Publications, Inc., 2018
Keywords
SMS, alcohol consumption intervention, mobile phones, students, text messages
National Category
Public Health, Global Health, Social Medicine and Epidemiology
Identifiers
urn:nbn:se:liu:diva-153600 (URN)10.2196/humanfactors.9641 (DOI)29991469 (PubMedID)2-s2.0-85052017018 (Scopus ID)
Available from: 2018-12-27 Created: 2018-12-27 Last updated: 2019-05-02Bibliographically approved
Thomas, K., Müssener, U., Linderoth, C., Karlsson, N., Bendtsen, P. & Bendtsen, M. (2018). Effectiveness of a Text Messaging-Based Intervention Targeting Alcohol Consumption Among University Students: Randomized Controlled Trial. JMIR mhealth and uhealth, 6(6), Article ID e146.
Open this publication in new window or tab >>Effectiveness of a Text Messaging-Based Intervention Targeting Alcohol Consumption Among University Students: Randomized Controlled Trial
Show others...
2018 (English)In: JMIR mhealth and uhealth, E-ISSN 2291-5222, Vol. 6, no 6, article id e146Article in journal (Refereed) Published
Abstract [en]

Background: Excessive drinking among university students is a global challenge, leading to significant health risks. However, heavy drinking among students is widely accepted and socially normalized. Mobile phone interventions have attempted to reach students who engage in excessive drinking. A growing number of studies suggest that text message-based interventions could potentially reach many students and, if effective, such an intervention might help reduce heavy drinking in the student community. Objective: The objective of this study was to test the effectiveness of a behavior change theory-based 6-week text message intervention among university students. Methods: This study was a two-arm, randomized controlled trial with an intervention group receiving a 6-week text message intervention and a control group that was referred to treatment as usual at the local student health care center. Outcome measures were collected at baseline and at 3 months after the initial invitation to participate in the intervention. The primary outcome was total weekly alcohol consumption. Secondary outcomes were frequency of heavy episodic drinking, highest estimated blood alcohol concentration, and number of negative consequences attributable to excessive drinking. Results: A total of 896 students were randomized to either the intervention or control group. The primary outcome analysis included 92.0% of the participants in the intervention group and 90.1% of the control group. At follow-up, total weekly alcohol consumption decreased in both groups, but no significant between-group difference was seen. Data on the secondary outcomes included 49.1% of the participants in the intervention group and 41.3% of the control group. No significant between-group difference was seen for any of the secondary outcomes. Conclusions: The present study was under-powered, which could partly explain the lack of significance. However, the intervention, although theory-based, needs to be re-assessed and refined to better support the target group. Apart from establishing which content forms an effective intervention, the optimal length of an alcohol intervention targeting students also needs to be addressed in future studies.

Place, publisher, year, edition, pages
JMIR PUBLICATIONS, INC, 2018
Keywords
alcohol consumption intervention; text message-based intervention; university students; brief intervention
National Category
Substance Abuse
Identifiers
urn:nbn:se:liu:diva-149731 (URN)10.2196/mhealth.9642 (DOI)000436207100005 ()29941417 (PubMedID)
Note

Funding Agencies|Public Health Agency in Sweden [05670-2014-6.2]

Available from: 2018-07-24 Created: 2018-07-24 Last updated: 2019-04-03
Thomas, K. & Bendtsen, M. (2018). Mental Health Promotion Among University Students Using Text Messaging: Protocol for a Randomized Controlled Trial of a Mobile Phone–Based Intervention. JMIR Research Protocols, 8(8)
Open this publication in new window or tab >>Mental Health Promotion Among University Students Using Text Messaging: Protocol for a Randomized Controlled Trial of a Mobile Phone–Based Intervention
2018 (English)In: JMIR Research Protocols, ISSN 1929-0748, E-ISSN 1929-0748, Vol. 8, no 8Article in journal (Refereed) Published
Abstract [en]

Background: There is a growing understanding that well-being and mental illness are 2 separate dimensions of mental health. High well-being is associated with decreased risk of disease and mental illness and increased longevity.

Objective: This study aims to test the efficacy of a mobile phone–based intervention on positive mental health.

Methods: We are conducting a 2-armed randomized controlled trial of university students in Sweden. Recruitment will last for 6 months by digital advertising (eg, university websites). Participants will be randomly allocated to either an intervention (fully automated mobile phone–based mental health intervention) or control group (treatment as usual). The primary outcome will be self-assessed positive mental health (Mental Health Continuum Short Form). Secondary outcomes will be self-assessed depression anxiety symptomatology (Hospital Anxiety Depression Scale). Outcomes will be investigated at baseline, at 3, 6, and 12 months after randomization. Mediators (positive emotions and thoughts) will be investigated at baseline, midintervention, and at follow-ups using 2 single face-valid items.

Results: Data will be collected between autumn 2018 and spring 2019. Results are expected to be published in 2020.

Conclusions: Strengths of the study include the use of a validated comprehensive instrument to measure positive mental health. Mechanisms of change are also investigated. A potential challenge could be recruitment; however, by setting a prolonged recruitment period, we believe that the study will recruit a sufficient sample.

Place, publisher, year, edition, pages
Toronto, Canada: J M I R Publications, Inc., 2018
Keywords
mental health; telemedicine; students; randomized controlled trial
National Category
Public Health, Global Health, Social Medicine and Epidemiology
Identifiers
urn:nbn:se:liu:diva-162801 (URN)10.2196/12396 (DOI)000484378000002 ()31418426 (PubMedID)2-s2.0-85071484310 (Scopus ID)
Available from: 2019-12-18 Created: 2019-12-18 Last updated: 2020-03-27Bibliographically approved
Bendtsen, M. & Peña, J. M. (2017). Modelling regimes with Bayesian network mixtures. In: Niklas Lavesson (Ed.), Proceedings of the 30th Annual Workshop of the Swedish Artificial Intelligence Society SAIS 2017, May 15–16, 2017, Karlskrona, Sweden: . Paper presented at The 30th Annual Workshop of the Swedish Artificial Intelligence Society SAIS 2017, May 15–16, 2017, Karlskrona, Sweden (pp. 20-29). Linköping: Linköping University Electronic Press, 137, Article ID 002.
Open this publication in new window or tab >>Modelling regimes with Bayesian network mixtures
2017 (English)In: Proceedings of the 30th Annual Workshop of the Swedish Artificial Intelligence Society SAIS 2017, May 15–16, 2017, Karlskrona, Sweden / [ed] Niklas Lavesson, Linköping: Linköping University Electronic Press, 2017, Vol. 137, p. 20-29, article id 002Conference paper, Published paper (Refereed)
Abstract [en]

Bayesian networks (BNs) are advantageous when representing single independence models, however they do not allow us to model changes among the relationships of the random variables over time. Due to such regime changes, it may be necessary to use different BNs at different times in order to have an appropriate model over the random variables. In this paper we propose two extensions to the traditional hidden Markov model, allowing us to represent both the different regimes using different BNs, and potential driving forces behind the regime changes, by modelling potential dependence between state transitions and some observable variables. We show how expectation maximisation can be used to learn the parameters of the proposed model, and run both synthetic and real-world experiments to show the model’s potential.

Place, publisher, year, edition, pages
Linköping: Linköping University Electronic Press, 2017
Series
Linköping Electronic Conference Proceedings, ISSN 1650-3686, E-ISSN 1650-3740 ; 137
Keywords
Bayesian networks, hidden Markov models, regimes, algorithmic trading
National Category
Computer Sciences
Identifiers
urn:nbn:se:liu:diva-137664 (URN)9789176854969 (ISBN)
Conference
The 30th Annual Workshop of the Swedish Artificial Intelligence Society SAIS 2017, May 15–16, 2017, Karlskrona, Sweden
Available from: 2017-05-24 Created: 2017-05-24 Last updated: 2019-07-04Bibliographically approved
Organisations
Identifiers
ORCID iD: ORCID iD iconorcid.org/0000-0002-8678-1164

Search in DiVA

Show all publications