Farhana Sarker
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Farhana Sarker has a total of 36 co-authors. Here are the top co-authors by number of shared publications:
- Khondaker Abdullah Al Mamun
AIMS Lab, IIRIC, UIU, Dhaka, Bangladesh
7 shared publications - Mohammad Nurul Huda
United International University
2 shared publications - Shehan Irteza Pranto
United International University
2 shared publications - Akm Nazmul Islam
CMED Health (A Digital Health inclusion initiatives for UHC), Dhaka, Bangladesh
1 shared publication - Antora Dev
Idaho State University,Department of Electrical and Computer Engineering,Pocatello,ID,USA
1 shared publication - Arifur Rahman
Advanced Intelligent Multidisciplinary Systems Laboratory (AIMS Lab), IRIIC, United International University, Dhaka, Bangladesh
1 shared publication
Latest Publications
- Open Access
- 19 December 2025
- Published by JMIR Publications Inc. in JMIR Public Health and Surveillance
- Vol. 11, e46122
Stroke Prevalence and Risk Factors in Rural Communities Within a Resource-Constrained South Asian Setting: Population-Based Study of 1.3 Million Individuals
Background: Stroke is a leading cause of death and long-term disability worldwide, with an estimated 6.2 million deaths each year. In Bangladesh, data on stroke prevalence and risk factors in rural areas are limited, making it difficult to develop effective early prevention and intervention programs. Objective: This study aimed (1) to present the prevalence of stroke in a rural community in Bangladesh and (2) to identify and associate various stroke risk factors. Methods: Data collection was done by community health workers, as a part of the “Enriched Sastho” program of the Palli Karma Sahayak Foundation, Bangladesh. Community health workers received 2 weeks of training to ensure data quality. The presence of stroke was determined by a binary survey question, with a history of stroke=1 and absence=0. The prevalence of stroke per 1000 people was examined along with the 95% CI. In addition, the association of stroke risk predictors was calculated using multivariate logistic regression and presented in crude odds ratio (OR) and adjusted OR along with 95% CI. Results: The study analyzed data from 1,341,589 individuals, with an average (SD) age of 29.23 (19.05) years. The overall stroke prevalence was found to be 1.07 per 1000 people, with a higher prevalence in male participants and increasing with age. The highest stroke prevalence was observed in the Khulna division (OR 1.881, 95% CI 1.671‐2.117), and the least in the Rangpur division (OR 0.677, 95% CI 0.576‐0.795). Individuals aged 65‐79 years were at a higher risk of having a stroke than other age groups (crude OR 9.883 and adjusted OR 9.728 [adjusted for sex]). In addition, male participants were at greater risk of having a stroke than female participants were (crude OR 1.565 and adjusted OR 1.469 [adjusted for age]). Conclusions: The study emphasizes the need for early prevention and intervention programs for stroke in rural Bangladesh and the importance of managing hypertension and diabetes to reduce stroke risk.
- 19 December 2025
- Published by JMIR Publications Inc. in JMIR Public Health and Surveillance
- Vol. 11, e46122
Open AccessStroke Prevalence and Risk Factors in Rural Communities Within a Resource-Constrained South Asian Setting: Population-Based Study of 1.3 Million Individuals
Background: Stroke is a leading cause of death and long-term disability worldwide, with an estimated 6.2 million deaths each year. In Bangladesh, data on stroke prevalence and risk factors in rural areas are limited, making it difficult to develop effective early prevention and intervention programs. Objective: This study aimed (1) to present the prevalence of stroke in a rural community in Bangladesh and (2) to identify and associate various stroke risk factors. Methods: Data collection was done by community health workers, as a part of the “Enriched Sastho” program of the Palli Karma Sahayak Foundation, Bangladesh. Community health workers received 2 weeks of training to ensure data quality. The presence of stroke was determined by a binary survey question, with a history of stroke=1 and absence=0. The prevalence of stroke per 1000 people was examined along with the 95% CI. In addition, the association of stroke risk predictors was calculated using multivariate logistic regression and presented in crude odds ratio (OR) and adjusted OR along with 95% CI. Results: The study analyzed data from 1,341,589 individuals, with an average (SD) age of 29.23 (19.05) years. The overall stroke prevalence was found to be 1.07 per 1000 people, with a higher prevalence in male participants and increasing with age. The highest stroke prevalence was observed in the Khulna division (OR 1.881, 95% CI 1.671‐2.117), and the least in the Rangpur division (OR 0.677, 95% CI 0.576‐0.795). Individuals aged 65‐79 years were at a higher risk of having a stroke than other age groups (crude OR 9.883 and adjusted OR 9.728 [adjusted for sex]). In addition, male participants were at greater risk of having a stroke than female participants were (crude OR 1.565 and adjusted OR 1.469 [adjusted for age]). Conclusions: The study emphasizes the need for early prevention and intervention programs for stroke in rural Bangladesh and the importance of managing hypertension and diabetes to reduce stroke risk.
- Open Access
- 31 May 2025
- Published by Elsevier in Data in Brief
- Vol. 61, 111746
DiaBD: A diabetes dataset for enhanced risk analysis and research in Bangladesh
- 31 May 2025
- Published by Elsevier in Data in Brief
- Vol. 61, 111746
Open AccessDiaBD: A diabetes dataset for enhanced risk analysis and research in Bangladesh
- Open Access
- 23 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 35475-35501
Recommender System in Academic Choices of Higher Education: A Systematic Review
Recommender systems have gained significant attention as powerful tools for supporting decision-making processes in various domains. However, the understanding of their impact and application in the field of academic choices in higher education remains limited. This systematic review aims to provide a comprehensive summary of the current knowledge regarding recommender systems utilized in the context of academic choices and advising in higher education. The study is based on the systematic analysis of a set of primary studies (N = 56 out of 1578, published between 2011 and 2023) included according to defined criteria. The articles were categorized based on specific criteria, and their findings were analyzed and synthesized. Results show that the hybrid strategy has been the most effective method for producing recommendations. Evaluation measures such as offline experiments and case-study validation were prominently observed in the empirical studies, providing insights into the effectiveness of recommender systems. The findings reveal that the design of recommender systems in higher education is context-specific, with researchers considering various parameters to tailor recommendations to individual needs. However, most of the selected articles relied on lab-based studies rather than real-world applications, indicating a need for further research in practical settings. This systematic review also identifies future research directions, including the incorporation of deep learning technologies and the analysis of personality traits. By providing a comprehensive overview of the current state of recommender systems for academic choices in higher education, this review offers valuable insights for researchers and practitioners, guiding the development of more effective and personalized recommendation systems to unlock the full potential of individuals in their academic journey.
- 23 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 35475-35501
Open AccessRecommender System in Academic Choices of Higher Education: A Systematic Review
Recommender systems have gained significant attention as powerful tools for supporting decision-making processes in various domains. However, the understanding of their impact and application in the field of academic choices in higher education remains limited. This systematic review aims to provide a comprehensive summary of the current knowledge regarding recommender systems utilized in the context of academic choices and advising in higher education. The study is based on the systematic analysis of a set of primary studies (N = 56 out of 1578, published between 2011 and 2023) included according to defined criteria. The articles were categorized based on specific criteria, and their findings were analyzed and synthesized. Results show that the hybrid strategy has been the most effective method for producing recommendations. Evaluation measures such as offline experiments and case-study validation were prominently observed in the empirical studies, providing insights into the effectiveness of recommender systems. The findings reveal that the design of recommender systems in higher education is context-specific, with researchers considering various parameters to tailor recommendations to individual needs. However, most of the selected articles relied on lab-based studies rather than real-world applications, indicating a need for further research in practical settings. This systematic review also identifies future research directions, including the incorporation of deep learning technologies and the analysis of personality traits. By providing a comprehensive overview of the current state of recommender systems for academic choices in higher education, this review offers valuable insights for researchers and practitioners, guiding the development of more effective and personalized recommendation systems to unlock the full potential of individuals in their academic journey.
- 29 September 2022
- Published by Springer Nature
- p. 76-91
AI Reception: An Intelligent Bengali Receptionist System Integrating with Face, Speech, and Interaction Recognition
- 29 September 2022
- Published by Springer Nature
- p. 76-91
AI Reception: An Intelligent Bengali Receptionist System Integrating with Face, Speech, and Interaction Recognition
- Top Cited PapersOpen Access
- 26 January 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 16756-16781
Exploration of EEG-Based Depression Biomarkers Identification Techniques and Their Applications: A Systematic Review
Depression is the most common mental illness, which has become the major cause of fear and suicidal mortality or tendencies. Currently, about 10% of the world population has been suffering from depression. The classical approach for detecting depression relies on the clinical questionnaire, which depends on the patients’ responses as well as observing their behavioral activities. However, there is no established method to detect depression from EEG biomarkers. Therefore, exploration of EEG biomarkers for depression assessments is vital and has a great potential to improve our understanding and clinical interventions. In this study, we have conducted a systematic review of 52 research articles using the PRISMA-P systematic review protocol, where we analyzed their research methodologies and outcomes. We categorized the experimentations in these articles according to their physical and psychological aspects scaled by the commonly used clinical questionnaire-based assessments. This study finds that the negative stimuli are the better identification strategies for evaluating depression through EEG signals. From this exploration, researchers observed that the Neural Connectivity Analysis and Brain Topological Mapping have huge potentials for finding depression biomarkers, and it is evident that the right-side hemisphere and frontal and parietal-occipital cortex are distinct regions to detect depression using EEG signals. For this mechanism, researchers are using many signal processing and machine learning approaches. In the case of filtering, Independent Component Analysis (ICA) is commonly used to eliminate physiological and non-physiological artifacts. Among machine learning approaches, Convolutional Neural Network (CNN) and Support Vector Machine (SVM) showed better performance for classifying healthy and depressed brains. The authors hope, this study will create an opportunity to explore more in the future for EEG as diagnostic tool by analyzing brain functional connectivity for focusing on clinical interventions.
- 26 January 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 16756-16781
Top Cited PapersOpen AccessExploration of EEG-Based Depression Biomarkers Identification Techniques and Their Applications: A Systematic Review
Depression is the most common mental illness, which has become the major cause of fear and suicidal mortality or tendencies. Currently, about 10% of the world population has been suffering from depression. The classical approach for detecting depression relies on the clinical questionnaire, which depends on the patients’ responses as well as observing their behavioral activities. However, there is no established method to detect depression from EEG biomarkers. Therefore, exploration of EEG biomarkers for depression assessments is vital and has a great potential to improve our understanding and clinical interventions. In this study, we have conducted a systematic review of 52 research articles using the PRISMA-P systematic review protocol, where we analyzed their research methodologies and outcomes. We categorized the experimentations in these articles according to their physical and psychological aspects scaled by the commonly used clinical questionnaire-based assessments. This study finds that the negative stimuli are the better identification strategies for evaluating depression through EEG signals. From this exploration, researchers observed that the Neural Connectivity Analysis and Brain Topological Mapping have huge potentials for finding depression biomarkers, and it is evident that the right-side hemisphere and frontal and parietal-occipital cortex are distinct regions to detect depression using EEG signals. For this mechanism, researchers are using many signal processing and machine learning approaches. In the case of filtering, Independent Component Analysis (ICA) is commonly used to eliminate physiological and non-physiological artifacts. Among machine learning approaches, Convolutional Neural Network (CNN) and Support Vector Machine (SVM) showed better performance for classifying healthy and depressed brains. The authors hope, this study will create an opportunity to explore more in the future for EEG as diagnostic tool by analyzing brain functional connectivity for focusing on clinical interventions.
- Open Access
- 28 January 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 122943-122959
Technological Evolvement in AAC Modalities to Foster Communications of Verbally Challenged ASD Children: A Systematic Review
Augmentative and Alternative Communication (AAC) emerged as a combination of methods or strategies that constitute any device, such as Speech Generating Device (SGD), Program (mobile applications), Procedure (PECS, Picture Exchange Communication System), which enhances individual’s communication ability. Autism Spectrum Disorder (ASD) is a spectrum of comprehensive neurodevelopment disorder that leads to speech impairments, repetitive behavior, and social communication difficulties; therefore, it is imperative to underscore that at the core of all impediments are communication impairment. This article represents a systematic review of research initiatives that investigate multi-modal AAC strategies and functionality, features of mobile applications to reinforce communication and communal skills in verbally challenged ASD children because other researches are focused only on low or high-tech AAC or interventions to provide insights on ASD children respond to a particular approach. Following the PRISMA method, a total of 60 (January 2015 to October 2020) research articles were reviewed, indexed by Springer, Science Direct, Scopus, ACM, IEEE databases, and published in the AAC journal. The selected research articles are categorized into different themes where most of them focused on interactive mobile applications to improve emotional, social, learning, and overall communication skills in verbally challenged ASD children. This systematic review provides an outline of the paradigm shift in AAC modalities from PECS to Artificial Intelligence (AI), Machine Learning (ML), and Augmented Reality (AR) based applications. It opens up underline future opportunities to integrate intelligent analytics features in mobile applications to strengthen communication skills in verbally undermined ASD children.
- 28 January 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 122943-122959
Open AccessTechnological Evolvement in AAC Modalities to Foster Communications of Verbally Challenged ASD Children: A Systematic Review
Augmentative and Alternative Communication (AAC) emerged as a combination of methods or strategies that constitute any device, such as Speech Generating Device (SGD), Program (mobile applications), Procedure (PECS, Picture Exchange Communication System), which enhances individual’s communication ability. Autism Spectrum Disorder (ASD) is a spectrum of comprehensive neurodevelopment disorder that leads to speech impairments, repetitive behavior, and social communication difficulties; therefore, it is imperative to underscore that at the core of all impediments are communication impairment. This article represents a systematic review of research initiatives that investigate multi-modal AAC strategies and functionality, features of mobile applications to reinforce communication and communal skills in verbally challenged ASD children because other researches are focused only on low or high-tech AAC or interventions to provide insights on ASD children respond to a particular approach. Following the PRISMA method, a total of 60 (January 2015 to October 2020) research articles were reviewed, indexed by Springer, Science Direct, Scopus, ACM, IEEE databases, and published in the AAC journal. The selected research articles are categorized into different themes where most of them focused on interactive mobile applications to improve emotional, social, learning, and overall communication skills in verbally challenged ASD children. This systematic review provides an outline of the paradigm shift in AAC modalities from PECS to Artificial Intelligence (AI), Machine Learning (ML), and Augmented Reality (AR) based applications. It opens up underline future opportunities to integrate intelligent analytics features in mobile applications to strengthen communication skills in verbally undermined ASD children.
- 1 December 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 856-862
Automated Bangla sign language translation system: Prospects, limitations and applications
Deaf and Dumb people are a big part of growing community where they use sign language i.e., gestures for communicating with others. But interaction between normal and hearing impaired people becomes difficult as most of the normal people can't understand sign language gestures meaning and on the other hand deaf and dumb people can't understand naturally spoken language. There are about 70 million deaf hearing-impaired as well as hearing people in the world who use sign language as their first language or mother tongue. In Bangladesh alone, there are around 2.4 million people use sign language. Therefore, automatic sign language translation system is vital to improve communication for hearing impaired people. This paper represents a review on existing Bangla Sign Language translation systems to communicate with hearing impaired people and also proposes a real time bidirectional Bangla Sign Language translator. Analyzing the existing systems provides us necessary information about their working process, success rate, system drawbacks and limitations indicating the fields where those systems need to upgrade for a better performance. Based on the analysis to overcome the limitations, we propose a bidirectional communication system that includes conversion of naturally spoken Bangla Language to Bangla Sign Language and vice versa. Our proposal includes real time dynamic bidirectional Bangle Sign Language translation system which is preciously needed for a fruitful communication with hearing impaired people.
- 1 December 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 856-862
Automated Bangla sign language translation system: Prospects, limitations and applications
Deaf and Dumb people are a big part of growing community where they use sign language i.e., gestures for communicating with others. But interaction between normal and hearing impaired people becomes difficult as most of the normal people can't understand sign language gestures meaning and on the other hand deaf and dumb people can't understand naturally spoken language. There are about 70 million deaf hearing-impaired as well as hearing people in the world who use sign language as their first language or mother tongue. In Bangladesh alone, there are around 2.4 million people use sign language. Therefore, automatic sign language translation system is vital to improve communication for hearing impaired people. This paper represents a review on existing Bangla Sign Language translation systems to communicate with hearing impaired people and also proposes a real time bidirectional Bangla Sign Language translator. Analyzing the existing systems provides us necessary information about their working process, success rate, system drawbacks and limitations indicating the fields where those systems need to upgrade for a better performance. Based on the analysis to overcome the limitations, we propose a bidirectional communication system that includes conversion of naturally spoken Bangla Language to Bangla Sign Language and vice versa. Our proposal includes real time dynamic bidirectional Bangle Sign Language translation system which is preciously needed for a fruitful communication with hearing impaired people.