Stanisław Karkosz
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Stanisław Karkosz has a total of 20 co-authors. Here are the top co-authors by number of shared publications:
Anna Maj
Uniwersytet SWPS, Instytut Psychologii, StresLab: Centrum Badań nad Stresem
2 shared publications- Ewelina Smoktunowicz
StresLab Research Centre, Institute of Psychology, SWPS University, Warsaw, Poland
2 shared publications - Jaroslaw M. Michalowski
Poznań Laboratory of Affective Neuroscience, Institute of Psychology, SWPS University, Warsaw, Poland
2 shared publications - Julie Prescott
University of Law, Psychology Faculty
2 shared publications - Katarzyna Sanna
Affiliation Center for Research on Personality Development, Department of Psychology, SWPS University, Poznań, Poland
2 shared publications - Magdalena Lesnierowska
Institute of Psychology, SWPS University, Warsaw, Poland
2 shared publications
Latest Publications
- Open Access
- 16 January 2026
- Published by Frontiers Media SA in Frontiers in Psychology
- Vol. 16, 1710963
Imagine yourself as a little girl…—efficacy and psychophysiology of imagery techniques targeting adverse autobiographical childhood experiences- multi-arm randomised controlled trial
Fear of failure is often rooted in highly self-critical autobiographical memories that elicit persistent distress and avoidance. Imagery-based interventions aim to reduce the impact of such memories, yet their mechanisms of action remain unclear. In this three-arm parallel group randomised controlled trial, 180 young adults with elevated fear of failure were randomly assigned to imagery exposure, standard imagery rescripting, or imagery rescripting with a 10-min delay designed to disrupt memory reconsolidation. Across four sessions delivered over 2 weeks, outcomes were assessed using self-report measures and physiological markers, with follow-ups at 3 and 6 months. All interventions led to significant and sustained reductions in negative emotions, arousal, and fear of failure, as well as decreased physiological reactivity to autobiographical memories of criticism. Contrary to predictions, delayed rescripting did not show superiority, while planned contrasts suggested more consistent benefits of standard rescripting compared to delayed rescripting and a rebound effect after exposure. Notably, prediction error, operationalised as transient increases in physiological arousal during rescripting, predicted stronger therapeutic change in rescripting but not in exposure. These findings demonstrate that both common therapeutic factors and prediction error contribute to durable improvements in emotional responses to adverse memories, advancing the understanding of mechanisms underlying imagery-based techniques. Clinical trials registration: ClinicalTrials.gov Identifier: NCT07048756, https://clinicaltrials.gov/ct2/show/NCT07048756 .
- 16 January 2026
- Published by Frontiers Media SA in Frontiers in Psychology
- Vol. 16, 1710963
Open AccessImagine yourself as a little girl…—efficacy and psychophysiology of imagery techniques targeting adverse autobiographical childhood experiences- multi-arm randomised controlled trial
Fear of failure is often rooted in highly self-critical autobiographical memories that elicit persistent distress and avoidance. Imagery-based interventions aim to reduce the impact of such memories, yet their mechanisms of action remain unclear. In this three-arm parallel group randomised controlled trial, 180 young adults with elevated fear of failure were randomly assigned to imagery exposure, standard imagery rescripting, or imagery rescripting with a 10-min delay designed to disrupt memory reconsolidation. Across four sessions delivered over 2 weeks, outcomes were assessed using self-report measures and physiological markers, with follow-ups at 3 and 6 months. All interventions led to significant and sustained reductions in negative emotions, arousal, and fear of failure, as well as decreased physiological reactivity to autobiographical memories of criticism. Contrary to predictions, delayed rescripting did not show superiority, while planned contrasts suggested more consistent benefits of standard rescripting compared to delayed rescripting and a rebound effect after exposure. Notably, prediction error, operationalised as transient increases in physiological arousal during rescripting, predicted stronger therapeutic change in rescripting but not in exposure. These findings demonstrate that both common therapeutic factors and prediction error contribute to durable improvements in emotional responses to adverse memories, advancing the understanding of mechanisms underlying imagery-based techniques. Clinical trials registration: ClinicalTrials.gov Identifier: NCT07048756, https://clinicaltrials.gov/ct2/show/NCT07048756 .
- Open Access
- 22 December 2025
- Published by Uniwersytet Warminsko-Mazurski in Przegląd Psychologiczny
- Vol. 68 (4) , 231-251
Evidence-Based Psychological Internet Interventions: Challenges, Best Practices, and Recommendations
Goal: The number of psychological interventions delivered through new technologies, such as apps, chatbots and online platforms (so called ‘internet interventions’) is growing rapidly. Their development is recommended by the World Health Organisation (WHO) due to their accessibility both in the context of geographic and economic exclusion, the limited number of psychotherapists, and long waiting times to receive psychological services. Internet interventions, delivered as standalone programs or as a supplement to traditional psychological support and psychotherapy, have been confirmed to be effective by numerous meta-analyses. However, some solutions which have appeared on the market are not based on theoretical models and their effectiveness remains untested or insufficiently researched. This article, based on a narrative literature review, positions internet interventions as evidence-based solutions, while also discussing the key challenges facing this field of research and clinical practice. Thesis: The current most important challenges are: (1) difficulties with the classification and naming of internet interventions; (2) the need for high-quality scientific evidence which confirms the effectiveness of specific interventions rather than just its theoretical basis; and (3) accounting for specific aspects of internet interventions, such as co-designing solutions, user-experience, digital therapeutic tools, and gamification. This article outlines current practices concerning internet interventions, discusses examples of associated regulations, and outlines user needs regarding the safe selection and use of internet interventions. Conclusion: Internet interventions are evidence-based. Given the current state of regulation however, particular care should be taken in clearly communicating how the effectiveness of any given intervention has been tested against standards, enabling patients and professionals to make informed choices.
- 22 December 2025
- Published by Uniwersytet Warminsko-Mazurski in Przegląd Psychologiczny
- Vol. 68 (4) , 231-251
Open AccessEvidence-Based Psychological Internet Interventions: Challenges, Best Practices, and Recommendations
Goal: The number of psychological interventions delivered through new technologies, such as apps, chatbots and online platforms (so called ‘internet interventions’) is growing rapidly. Their development is recommended by the World Health Organisation (WHO) due to their accessibility both in the context of geographic and economic exclusion, the limited number of psychotherapists, and long waiting times to receive psychological services. Internet interventions, delivered as standalone programs or as a supplement to traditional psychological support and psychotherapy, have been confirmed to be effective by numerous meta-analyses. However, some solutions which have appeared on the market are not based on theoretical models and their effectiveness remains untested or insufficiently researched. This article, based on a narrative literature review, positions internet interventions as evidence-based solutions, while also discussing the key challenges facing this field of research and clinical practice. Thesis: The current most important challenges are: (1) difficulties with the classification and naming of internet interventions; (2) the need for high-quality scientific evidence which confirms the effectiveness of specific interventions rather than just its theoretical basis; and (3) accounting for specific aspects of internet interventions, such as co-designing solutions, user-experience, digital therapeutic tools, and gamification. This article outlines current practices concerning internet interventions, discusses examples of associated regulations, and outlines user needs regarding the safe selection and use of internet interventions. Conclusion: Internet interventions are evidence-based. Given the current state of regulation however, particular care should be taken in clearly communicating how the effectiveness of any given intervention has been tested against standards, enabling patients and professionals to make informed choices.
- Open Access
- 22 December 2025
- Published by Uniwersytet Warminsko-Mazurski in Przegląd Psychologiczny
- Vol. 68 (4) , 93-115
Psychologiczne interwencje internetowe o skuteczności popartej dowodami naukowymi: wyzwania, dobre praktyki i rekomendacje
Cel: Liczba oddziaływań psychologicznych dostarczanych za pomocą nowych technologii, takich jak aplikacje, chatboty, platformy internetowe, czyli tzw. interwencji internetowych, dynamicznie rośnie. Światowa Organizacja Zdrowia zaleca ich rozwijanie ze względu na dostępność – zarówno w kontekście wykluczenia geograficznego i ekonomicznego, jak i ograniczonej liczby psychoterapeutów oraz długiego czasu oczekiwania na usługi w obszarze zdrowia psychicznego. Interwencje internetowe, dostarczane jako samodzielne programy lub uzupełnienie tradycyjnej pomocy psychologicznej i psychoterapii, mają skuteczność potwierdzoną licznymi metaanalizami. Jednak część rozwiązań, które pojawiają się na rynku nie jest tworzona na podstawie modeli teoretycznych, a ich efektywność pozostaje niezbadana lub zbadana w sposób niewystarczający. Niniejszy artykuł, bazując na narracyjnym przeglądzie literatury, pozycjonuje interwencje internetowe jako rozwiązania oparte na dowodach, a jednocześnie omawia najważniejsze z wyzwań stojących przed tą dziedziną badań i praktyki klinicznej. Tezy: Najważniejsze obecnie wyzwania to: (1) trudności w klasyfikowaniu i nazywaniu interwencji internetowych; (2) konieczność dostarczania wysokiej jakości dowodów naukowych potwierdzających efektywność konkretnej interwencji, a nie tylko jej podstaw teoretycznych; (3) wzięcie pod uwagę specyficznych aspektów interwencji internetowych, takich jak współprojektowanie rozwiązań, doświadczenia użytkownika, cyfrowe przymierze terapeutyczne czy grywalizacja. W artykule przedstawiono aktualne praktyki dotyczące interwencji, omówiono przykłady regulacji oraz potrzeby i oczekiwania użytkowników w zakresie ich bezpiecznego wyboru i użytkowania. Konkluzja: Interwencje internetowe są praktykami opartymi na dowodach naukowych. Biorąc pod uwagę obecny stan regulacji, należy szczególnie zadbać, aby jasno komunikować, w jaki sposób skuteczność danej interwencji została zbadana w odniesieniu do standardów, co umożliwi świadomy wybór interwencji pacjentom i profesjonalistom.
- 22 December 2025
- Published by Uniwersytet Warminsko-Mazurski in Przegląd Psychologiczny
- Vol. 68 (4) , 93-115
Open AccessPsychologiczne interwencje internetowe o skuteczności popartej dowodami naukowymi: wyzwania, dobre praktyki i rekomendacje
Cel: Liczba oddziaływań psychologicznych dostarczanych za pomocą nowych technologii, takich jak aplikacje, chatboty, platformy internetowe, czyli tzw. interwencji internetowych, dynamicznie rośnie. Światowa Organizacja Zdrowia zaleca ich rozwijanie ze względu na dostępność – zarówno w kontekście wykluczenia geograficznego i ekonomicznego, jak i ograniczonej liczby psychoterapeutów oraz długiego czasu oczekiwania na usługi w obszarze zdrowia psychicznego. Interwencje internetowe, dostarczane jako samodzielne programy lub uzupełnienie tradycyjnej pomocy psychologicznej i psychoterapii, mają skuteczność potwierdzoną licznymi metaanalizami. Jednak część rozwiązań, które pojawiają się na rynku nie jest tworzona na podstawie modeli teoretycznych, a ich efektywność pozostaje niezbadana lub zbadana w sposób niewystarczający. Niniejszy artykuł, bazując na narracyjnym przeglądzie literatury, pozycjonuje interwencje internetowe jako rozwiązania oparte na dowodach, a jednocześnie omawia najważniejsze z wyzwań stojących przed tą dziedziną badań i praktyki klinicznej. Tezy: Najważniejsze obecnie wyzwania to: (1) trudności w klasyfikowaniu i nazywaniu interwencji internetowych; (2) konieczność dostarczania wysokiej jakości dowodów naukowych potwierdzających efektywność konkretnej interwencji, a nie tylko jej podstaw teoretycznych; (3) wzięcie pod uwagę specyficznych aspektów interwencji internetowych, takich jak współprojektowanie rozwiązań, doświadczenia użytkownika, cyfrowe przymierze terapeutyczne czy grywalizacja. W artykule przedstawiono aktualne praktyki dotyczące interwencji, omówiono przykłady regulacji oraz potrzeby i oczekiwania użytkowników w zakresie ich bezpiecznego wyboru i użytkowania. Konkluzja: Interwencje internetowe są praktykami opartymi na dowodach naukowych. Biorąc pod uwagę obecny stan regulacji, należy szczególnie zadbać, aby jasno komunikować, w jaki sposób skuteczność danej interwencji została zbadana w odniesieniu do standardów, co umożliwi świadomy wybór interwencji pacjentom i profesjonalistom.
- Top Cited PapersOpen Access
- 20 March 2024
- Published by JMIR Publications Inc. in JMIR Formative Research
- Vol. 8, e47960
Effectiveness of a Web-based and Mobile Therapy Chatbot on Anxiety and Depressive Symptoms in Subclinical Young Adults: Randomized Controlled Trial
Background: There has been an increased need to provide specialized help for people with depressive and anxiety symptoms, particularly teenagers and young adults. There is evidence from a 2-week intervention that chatbots (eg, Woebot) are effective in reducing depression and anxiety, an effect that was not detected in the control group that was provided self-help materials. Although chatbots are a promising solution, there is limited scientific evidence for the efficacy of agent-guided cognitive behavioral therapy (CBT) outside the English language, especially for highly inflected languages. Objective: This study aimed to measure the efficacy of Fido, a therapy chatbot that uses the Polish language. It targets depressive and anxiety symptoms using CBT techniques. We hypothesized that participants using Fido would show a greater reduction in anxiety and depressive symptoms than the control group. Methods: We conducted a 2-arm, open-label, randomized controlled trial with 81 participants with subclinical depression or anxiety who were recruited via social media. Participants were divided into experimental (interacted with a fully automated Fido chatbot) and control (received a self-help book) groups. Both intervention methods addressed topics such as general psychoeducation and cognitive distortion identification and modification via Socratic questioning. The chatbot also featured suicidal ideation identification and redirection to suicide hotlines. We used self-assessment scales to measure primary outcomes, including the levels of depression, anxiety, worry tendencies, satisfaction with life, and loneliness at baseline, after the 2-week intervention and at the 1-month follow-up. We also controlled for secondary outcomes, including engagement and frequency of use. Results: There were no differences in anxiety and depressive symptoms between the groups at enrollment and baseline. After the intervention, depressive and anxiety symptoms were reduced in both groups (chatbot: n=36; control: n=38), which remained stable at the 1-month follow-up. Loneliness was not significantly different between the groups after the intervention, but an exploratory analysis showed a decline in loneliness among participants who used Fido more frequently. Both groups used their intervention technique with similar frequency; however, the control group spent more time (mean 117.57, SD 72.40 minutes) on the intervention than the Fido group (mean 79.44, SD 42.96 minutes). Conclusions: We did not replicate the findings from previous (eg, Woebot) studies, as both arms yielded therapeutic effects. However, such results are in line with other research of Internet interventions. Nevertheless, Fido provided sufficient help to reduce anxiety and depressive symptoms and decreased perceived loneliness among high-frequency users, which is one of the first pieces of evidence of chatbot efficacy with agents that use a highly inflected language. Further research is needed to determine the long-term, real-world effectiveness of Fido and its efficacy in a clinical sample. Trial Registration: ClinicalTrials.gov NCT05762939; https://clinicaltrials.gov/study/NCT05762939; Open Science Foundation Registry 2cqt3; https://osf.io/2cqt3
- 20 March 2024
- Published by JMIR Publications Inc. in JMIR Formative Research
- Vol. 8, e47960
Top Cited PapersOpen AccessEffectiveness of a Web-based and Mobile Therapy Chatbot on Anxiety and Depressive Symptoms in Subclinical Young Adults: Randomized Controlled Trial
Background: There has been an increased need to provide specialized help for people with depressive and anxiety symptoms, particularly teenagers and young adults. There is evidence from a 2-week intervention that chatbots (eg, Woebot) are effective in reducing depression and anxiety, an effect that was not detected in the control group that was provided self-help materials. Although chatbots are a promising solution, there is limited scientific evidence for the efficacy of agent-guided cognitive behavioral therapy (CBT) outside the English language, especially for highly inflected languages. Objective: This study aimed to measure the efficacy of Fido, a therapy chatbot that uses the Polish language. It targets depressive and anxiety symptoms using CBT techniques. We hypothesized that participants using Fido would show a greater reduction in anxiety and depressive symptoms than the control group. Methods: We conducted a 2-arm, open-label, randomized controlled trial with 81 participants with subclinical depression or anxiety who were recruited via social media. Participants were divided into experimental (interacted with a fully automated Fido chatbot) and control (received a self-help book) groups. Both intervention methods addressed topics such as general psychoeducation and cognitive distortion identification and modification via Socratic questioning. The chatbot also featured suicidal ideation identification and redirection to suicide hotlines. We used self-assessment scales to measure primary outcomes, including the levels of depression, anxiety, worry tendencies, satisfaction with life, and loneliness at baseline, after the 2-week intervention and at the 1-month follow-up. We also controlled for secondary outcomes, including engagement and frequency of use. Results: There were no differences in anxiety and depressive symptoms between the groups at enrollment and baseline. After the intervention, depressive and anxiety symptoms were reduced in both groups (chatbot: n=36; control: n=38), which remained stable at the 1-month follow-up. Loneliness was not significantly different between the groups after the intervention, but an exploratory analysis showed a decline in loneliness among participants who used Fido more frequently. Both groups used their intervention technique with similar frequency; however, the control group spent more time (mean 117.57, SD 72.40 minutes) on the intervention than the Fido group (mean 79.44, SD 42.96 minutes). Conclusions: We did not replicate the findings from previous (eg, Woebot) studies, as both arms yielded therapeutic effects. However, such results are in line with other research of Internet interventions. Nevertheless, Fido provided sufficient help to reduce anxiety and depressive symptoms and decreased perceived loneliness among high-frequency users, which is one of the first pieces of evidence of chatbot efficacy with agents that use a highly inflected language. Further research is needed to determine the long-term, real-world effectiveness of Fido and its efficacy in a clinical sample. Trial Registration: ClinicalTrials.gov NCT05762939; https://clinicaltrials.gov/study/NCT05762939; Open Science Foundation Registry 2cqt3; https://osf.io/2cqt3
- Open Access
- 6 April 2023
- Published by JMIR Publications Inc. in JMIR Preprints
Effectiveness of a Web-based and Mobile Therapy Chatbot on Anxiety and Depressive Symptoms in Subclinical Young Adults: Randomized Controlled Trial (Preprint)
BACKGROUND There has been an increased need to provide specialized help for people with depressive and anxiety symptoms, particularly teenagers and young adults. There is evidence from a 2-week intervention that chatbots (eg, Woebot) are effective in reducing depression and anxiety, an effect that was not detected in the control group that was provided self-help materials. Although chatbots are a promising solution, there is limited scientific evidence for the efficacy of agent-guided cognitive behavioral therapy (CBT) outside the English language, especially for highly inflected languages. OBJECTIVE This study aimed to measure the efficacy of Fido, a therapy chatbot that uses the Polish language. It targets depressive and anxiety symptoms using CBT techniques. We hypothesized that participants using Fido would show a greater reduction in anxiety and depressive symptoms than the control group. METHODS We conducted a 2-arm, open-label, randomized controlled trial with 81 participants with subclinical depression or anxiety who were recruited via social media. Participants were divided into experimental (interacted with a fully automated Fido chatbot) and control (received a self-help book) groups. Both intervention methods addressed topics such as general psychoeducation and cognitive distortion identification and modification via Socratic questioning. The chatbot also featured suicidal ideation identification and redirection to suicide hotlines. We used self-assessment scales to measure primary outcomes, including the levels of depression, anxiety, worry tendencies, satisfaction with life, and loneliness at baseline, after the 2-week intervention and at the 1-month follow-up. We also controlled for secondary outcomes, including engagement and frequency of use. RESULTS There were no differences in anxiety and depressive symptoms between the groups at enrollment and baseline. After the intervention, depressive and anxiety symptoms were reduced in both groups (chatbot: n=36; control: n=38), which remained stable at the 1-month follow-up. Loneliness was not significantly different between the groups after the intervention, but an exploratory analysis showed a decline in loneliness among participants who used Fido more frequently. Both groups used their intervention technique with similar frequency; however, the control group spent more time (mean 117.57, SD 72.40 minutes) on the intervention than the Fido group (mean 79.44, SD 42.96 minutes). CONCLUSIONS We did not replicate the findings from previous (eg, Woebot) studies, as both arms yielded therapeutic effects. However, such results are in line with other research of Internet interventions. Nevertheless, Fido provided sufficient help to reduce anxiety and depressive symptoms and decreased perceived loneliness among high-frequency users, which is one of the first pieces of evidence of chatbot efficacy with agents that use a highly inflected language. Further research is needed to determine the long-term, real-world effectiveness of Fido and its efficacy in a clinical sample. CLINICALTRIAL ClinicalTrials.gov NCT05762939; https://clinicaltrials.gov/study/NCT05762939; Open Science Foundation Registry 2cqt3; https://osf.io/2cqt3
- 6 April 2023
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessEffectiveness of a Web-based and Mobile Therapy Chatbot on Anxiety and Depressive Symptoms in Subclinical Young Adults: Randomized Controlled Trial (Preprint)
BACKGROUND There has been an increased need to provide specialized help for people with depressive and anxiety symptoms, particularly teenagers and young adults. There is evidence from a 2-week intervention that chatbots (eg, Woebot) are effective in reducing depression and anxiety, an effect that was not detected in the control group that was provided self-help materials. Although chatbots are a promising solution, there is limited scientific evidence for the efficacy of agent-guided cognitive behavioral therapy (CBT) outside the English language, especially for highly inflected languages. OBJECTIVE This study aimed to measure the efficacy of Fido, a therapy chatbot that uses the Polish language. It targets depressive and anxiety symptoms using CBT techniques. We hypothesized that participants using Fido would show a greater reduction in anxiety and depressive symptoms than the control group. METHODS We conducted a 2-arm, open-label, randomized controlled trial with 81 participants with subclinical depression or anxiety who were recruited via social media. Participants were divided into experimental (interacted with a fully automated Fido chatbot) and control (received a self-help book) groups. Both intervention methods addressed topics such as general psychoeducation and cognitive distortion identification and modification via Socratic questioning. The chatbot also featured suicidal ideation identification and redirection to suicide hotlines. We used self-assessment scales to measure primary outcomes, including the levels of depression, anxiety, worry tendencies, satisfaction with life, and loneliness at baseline, after the 2-week intervention and at the 1-month follow-up. We also controlled for secondary outcomes, including engagement and frequency of use. RESULTS There were no differences in anxiety and depressive symptoms between the groups at enrollment and baseline. After the intervention, depressive and anxiety symptoms were reduced in both groups (chatbot: n=36; control: n=38), which remained stable at the 1-month follow-up. Loneliness was not significantly different between the groups after the intervention, but an exploratory analysis showed a decline in loneliness among participants who used Fido more frequently. Both groups used their intervention technique with similar frequency; however, the control group spent more time (mean 117.57, SD 72.40 minutes) on the intervention than the Fido group (mean 79.44, SD 42.96 minutes). CONCLUSIONS We did not replicate the findings from previous (eg, Woebot) studies, as both arms yielded therapeutic effects. However, such results are in line with other research of Internet interventions. Nevertheless, Fido provided sufficient help to reduce anxiety and depressive symptoms and decreased perceived loneliness among high-frequency users, which is one of the first pieces of evidence of chatbot efficacy with agents that use a highly inflected language. Further research is needed to determine the long-term, real-world effectiveness of Fido and its efficacy in a clinical sample. CLINICALTRIAL ClinicalTrials.gov NCT05762939; https://clinicaltrials.gov/study/NCT05762939; Open Science Foundation Registry 2cqt3; https://osf.io/2cqt3
- 16 June 2022
- Published by Springer Nature
- p. 424-429
Human-Therapeutic Chatbot Interaction Analysis, on the Example of Fido
- 16 June 2022
- Published by Springer Nature
- p. 424-429
Human-Therapeutic Chatbot Interaction Analysis, on the Example of Fido
- 20 May 2020
- Published by Index Copernicus in Bio-Algorithms and Med-Systems
- Vol. 16 (2)
Feature selection for classification in Steady state visually evoked potentials (SSVEP)-based brain-computer interfaces with genetic algorithm
Objectives: Optimization of Brain-Computer Interface by detecting the minimal number of morphological features of signal that maximize accuracy. Methods: System of signal processing and morphological features extractor was designed, then the genetic algorithm was used to select such characteristics that maximize the accuracy of the signal’s frequency recognition in offline Brain-Computer Interface (BCI). Results: The designed system provides higher accuracy results than a previously developed system that uses the same preprocessing methods, however, different results were achieved for various subjects. Conclusions: It is possible to enhance the previously developed BCI by combining it with morphological features extraction, however, it’s performance is dependent on subject variability.
- 20 May 2020
- Published by Index Copernicus in Bio-Algorithms and Med-Systems
- Vol. 16 (2)
Feature selection for classification in Steady state visually evoked potentials (SSVEP)-based brain-computer interfaces with genetic algorithm
Objectives: Optimization of Brain-Computer Interface by detecting the minimal number of morphological features of signal that maximize accuracy. Methods: System of signal processing and morphological features extractor was designed, then the genetic algorithm was used to select such characteristics that maximize the accuracy of the signal’s frequency recognition in offline Brain-Computer Interface (BCI). Results: The designed system provides higher accuracy results than a previously developed system that uses the same preprocessing methods, however, different results were achieved for various subjects. Conclusions: It is possible to enhance the previously developed BCI by combining it with morphological features extraction, however, it’s performance is dependent on subject variability.