Rabita Hasan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Rabita Hasan has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Khondoker Mahmud Parvez
Institute of Disaster Management, Khulna University of Engineering and Technology
3 shared publications - Sheikh Md. Rabiul Islam
Department of Electronics and Communication Engineering (ECE), Khulna University of Engineering and Technology, Khulna, Bangladesh
3 shared publications Sheikh Md. Rabiul Islam
Department of Electronics and Communication Engineering (ECE), Khulna University of Engineering and Technology, Khulna 9203, Bangladesh
2 shared publicationsIbrahim Mahmud Rushdi
1 shared publication- Raihan Khan
Khulna University of Engineering Technology,Department of Electrical and Electronic Engineering,Khulna,Bangladesh,9203
1 shared publication
Latest Publications
- Open Access
- 4 August 2026
- Published by Springer Nature in Discover Applied Sciences
An interpretable frequency-band-aware framework for EEG-based emotion recognition using ensemble classifiers and CNN-LSTM networks
- 4 August 2026
- Published by Springer Nature in Discover Applied Sciences
Open AccessAn interpretable frequency-band-aware framework for EEG-based emotion recognition using ensemble classifiers and CNN-LSTM networks
- Open Access
- 21 July 2026
- Published by Springer Nature in Brain Informatics
- Vol. 13 (1) , 38
Adaptive frequency band attention-guided CNN–BiLSTM for Spatial–Spectral–Temporal EEG emotion recognition
- 21 July 2026
- Published by Springer Nature in Brain Informatics
- Vol. 13 (1) , 38
Open AccessAdaptive frequency band attention-guided CNN–BiLSTM for Spatial–Spectral–Temporal EEG emotion recognition
- Open Access
- 28 March 2026
- Published by Elsevier in Geopsychiatry
- Vol. 3
Mental health impacts of climate migration: Urban adaptation and mitigation challenges in Southwestern Bangladesh
- 28 March 2026
- Published by Elsevier in Geopsychiatry
- Vol. 3
Open AccessMental health impacts of climate migration: Urban adaptation and mitigation challenges in Southwestern Bangladesh
- Open Access
- 7 March 2026
- Published by Elsevier in Geopsychiatry
- Vol. 3
Spatial land transformation and the psychosocial exposure among climate migrants in southwestern Bangladesh
- 7 March 2026
- Published by Elsevier in Geopsychiatry
- Vol. 3
Open AccessSpatial land transformation and the psychosocial exposure among climate migrants in southwestern Bangladesh
- Open Access
- 1 January 2026
- Published by Elsevier in SSRN Electronic Journal
Analysis of Waste-Borne Health Hazards of Disaster-Induced Migrants: A Case Study in Khulna City
Bangladesh is a highly vulnerable region to climate-related disasters such as cyclones, flooding, and river erosion. These disasters displace a large population and force them to migrate to urban areas often settling them in informal slums. In these areas, inadequate waste management, poor sanitation and overcrowded living conditions create significant health risks for migrants, particularly through exposure to improperly managed waste. The importance of this study clearly indicates how the improper waste management system and associated factors are liable for the various kinds of health hazards for the disaster induced migrants. This study investigates the inherent factors that causes waste-borne health hazards in migrant communities in Khulna city. To achieve the objective, 400 different surveys were conducted on the migrants using the snowball sampling method in various informal settlements across Khulna city. The snowball technique was particularly useful in identifying migrants from disaster-prone rural areas as they often live in unregistered, hard-to-reach communities. Data were collected through structured interviews and health assessments to understand the direct and indirect impacts of waste exposure on migrant health. These migrants came from the different disaster-prone areas from Khulna district in Bangladesh. According to the findings, 70% of the surveyed migrant population live in areas where waste is improperly disposed of in open spaces which contaminates the environment. The main causes of public health problems in migrant communities are inadequate waste management systems, reliance on contaminated water, poor sanitation and hygiene practices, overcrowding and unhygienic living conditions. This lack of proper waste management infrastructure in these settlements results in severe exposure to hazardous waste materials, including plastics, human waste and industrial pollutants.
- 1 January 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessAnalysis of Waste-Borne Health Hazards of Disaster-Induced Migrants: A Case Study in Khulna City
Bangladesh is a highly vulnerable region to climate-related disasters such as cyclones, flooding, and river erosion. These disasters displace a large population and force them to migrate to urban areas often settling them in informal slums. In these areas, inadequate waste management, poor sanitation and overcrowded living conditions create significant health risks for migrants, particularly through exposure to improperly managed waste. The importance of this study clearly indicates how the improper waste management system and associated factors are liable for the various kinds of health hazards for the disaster induced migrants. This study investigates the inherent factors that causes waste-borne health hazards in migrant communities in Khulna city. To achieve the objective, 400 different surveys were conducted on the migrants using the snowball sampling method in various informal settlements across Khulna city. The snowball technique was particularly useful in identifying migrants from disaster-prone rural areas as they often live in unregistered, hard-to-reach communities. Data were collected through structured interviews and health assessments to understand the direct and indirect impacts of waste exposure on migrant health. These migrants came from the different disaster-prone areas from Khulna district in Bangladesh. According to the findings, 70% of the surveyed migrant population live in areas where waste is improperly disposed of in open spaces which contaminates the environment. The main causes of public health problems in migrant communities are inadequate waste management systems, reliance on contaminated water, poor sanitation and hygiene practices, overcrowding and unhygienic living conditions. This lack of proper waste management infrastructure in these settlements results in severe exposure to hazardous waste materials, including plastics, human waste and industrial pollutants.
- 27 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 502-507
Ensemble Model for EEG-Based Emotion Recognition with Non-Linear Fractal Features in Smart Healthcare Automation
Emotional state recognition is essential for mental health assessment and the development of intelligent healthcare systems. This study proposes an EEG-based emotion recognition framework for smart healthcare automation, utilizing non-linear fractal features from the DEAP dataset. Two descriptors: Higuchi Fractal Dimension (HFD) and Petrosian Fractal Dimension (PFD) were extracted from 32-channel EEG signals to capture complex brain dynamics. Ensemble models, including Light Gradient Boosting Machine (Light-GBM) and Random Forest, were applied for binary classification of valence and arousal. After preprocessing (bandpass filtering, 3 -second segmentation, $\mathbf{Z}$ score normalization and binary labeling), results showed that HFD outperformed PFD, achieving 82.47% and 80.62% accuracy for valence and arousal with Light-GBM. Independent-samples t-tests confirmed the statistical significance of these differences. The findings highlight HFD's superior ability to model EEG non-linearity, offering a robust approach for emotion-aware healthcare applications such as mental health monitoring, neurofeedback and personalized smart systems.- 27 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 502-507
Ensemble Model for EEG-Based Emotion Recognition with Non-Linear Fractal Features in Smart Healthcare Automation
Emotional state recognition is essential for mental health assessment and the development of intelligent healthcare systems. This study proposes an EEG-based emotion recognition framework for smart healthcare automation, utilizing non-linear fractal features from the DEAP dataset. Two descriptors: Higuchi Fractal Dimension (HFD) and Petrosian Fractal Dimension (PFD) were extracted from 32-channel EEG signals to capture complex brain dynamics. Ensemble models, including Light Gradient Boosting Machine (Light-GBM) and Random Forest, were applied for binary classification of valence and arousal. After preprocessing (bandpass filtering, 3 -second segmentation, $\mathbf{Z}$ score normalization and binary labeling), results showed that HFD outperformed PFD, achieving 82.47% and 80.62% accuracy for valence and arousal with Light-GBM. Independent-samples t-tests confirmed the statistical significance of these differences. The findings highlight HFD's superior ability to model EEG non-linearity, offering a robust approach for emotion-aware healthcare applications such as mental health monitoring, neurofeedback and personalized smart systems.- 1 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 01-06
Machine Learning Techniques for Brain Stroke Analysis and Prediction
Brain strokes a major contributor to global mortality and morbidity requires prompt prediction and intervention to reduce its impact. The study explores the practice of machine learning techniques for predicting brain strokes with the goal of improving early detection and preventive strategies. Utilizing a comprehensive dataset that includes demographic, lifestyle, and medical factors this study employs various machine learning systems such as logistic regression, random forest, decision tree, K-nearest neighbors, AdaBoost, XGBoost, and voting classifiers to develop predictive models. Feature ranking techniques are applied to detect the most significant variables which causes the incidence of stroke. The analysis incorporates preprocessing steps including data normalization, cleaning and managing missing values to determine the quality of the input data. Performance metrics including F1-score, recall, accuracy and precision are applied to measure the proficiency of the established models. Decision tree, XGBoost and voting classifier are showing best performance in this study with a similar accuracy of 96%. Additionally, this study contributes to build up a stacking model which achieved higher performance with an accuracy of 97%.
- 1 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 01-06
Machine Learning Techniques for Brain Stroke Analysis and Prediction
Brain strokes a major contributor to global mortality and morbidity requires prompt prediction and intervention to reduce its impact. The study explores the practice of machine learning techniques for predicting brain strokes with the goal of improving early detection and preventive strategies. Utilizing a comprehensive dataset that includes demographic, lifestyle, and medical factors this study employs various machine learning systems such as logistic regression, random forest, decision tree, K-nearest neighbors, AdaBoost, XGBoost, and voting classifiers to develop predictive models. Feature ranking techniques are applied to detect the most significant variables which causes the incidence of stroke. The analysis incorporates preprocessing steps including data normalization, cleaning and managing missing values to determine the quality of the input data. Performance metrics including F1-score, recall, accuracy and precision are applied to measure the proficiency of the established models. Decision tree, XGBoost and voting classifier are showing best performance in this study with a similar accuracy of 96%. Additionally, this study contributes to build up a stacking model which achieved higher performance with an accuracy of 97%.