Shahina Begum, Associate Professor


Dr. Shahina Begum, Associate Professor, deputy leader of the Artificial Intelligence and Intelligent Systems group at MDH. Shahina’s research focuses on developing intelligent systems in medical and industrial applications. Shahina Begum received her PhD in Computer Science/Artificial Intelligence in 2011Mälardalen University. Her research areas are Decision Support Systems, Knowledge-based Systems, Machine Learning, Big Data Analytics, and Intelligent Monitoring Systems. 

Shahina has been principal applicant and project manager for a number of research projects at MDH. She has received a Swedish Knowledge Foundation’s Prospect individual grant for prominent young researchers in 2011 and is today leading several research projects in the area of intelligent vehicle driver-monitoring and prediction systems in collaboration with industrial partners.

Shahina has been involved (as course main responsible/designer/teacher/examiner) of total 15 distant and campus-based courses/learning modules mainly in Artificial Intelligence and Machine learning at MDH both for regular students and industrial professionals. She is the co-applicant and main responsible for the Artificial Intelligence contents for the proposal “Bachelor program in Applied AI” at MDH. Shahina has been involved in several initiatives for lifelong learning at MDH for example,

  • IntoDeep  (Project leader for MDH, AI and Deep learning materials for Process industries), https://aiclass.se
  • KIT (WP: AI and Big Data for Production Industries, leader for MDH ),
  • Prompt (Main responsible for the courses, 'Machine Learning with Big Data course' with more than 500 applicants in HT 2018, MOOC course: Basic Knowledge on ML),
  • FutureE (Main responsible for the course: Predictive Data Analytics,  Developer and teacher: Deep Learning for Industrial Imaging)

 

Shahina Begum has an extensive involvement of both research and teaching activities driven by industry need and collaborative initiatives with both the public and private sectors. Shahina is active in the research community and has served as a steering committee member, program chair, co-chair and organizer of international conferences and workshops.

Press: 

 

 

 
 

 

 
 

[Show all publications]

Latest publications:

Deep Learning for Automatic EEG Feature Extraction: An Application in Drivers' Mental Workload Classification (Nov 2019)
Mir Riyanul Islam, Shaibal Barua, Mobyen Uddin Ahmed, Shahina Begum, Gianluca Di Flumeri
The 3rd International Symposium on Human Mental Workload: Models and Applications (H-WORKLOAD 2019)

Non-contact-based Driver's Cognitive Load Classification using Physiological and Vehicular Parameters (Nov 2019)
Hamidur Rahman, Mobyen Uddin Ahmed, Shaibal Barua, Shahina Begum
Biomedical Signal Processing and Control (BSPC)

A Vision based Indoor Navigation System for Individual with Visual Impairment (Sep 2019)
Mobyen Uddin Ahmed, Mohammed Ghaith Altarabichi, Shahina Begum, Fredrik Ginsberg , Robert Glaes , Magnus Östgren , Hamidur Rahman, Magnus Sörensen
International Journal of Artificial Intelligence (IJAI)

Hypothyroid Disease Diagnosis with Causal Explanation using Case-based Reasoning and Domain-specific Ontology (Sep 2019)
Mir Riyanul Islam, Shaibal Barua, Shahina Begum, Mobyen Uddin Ahmed
Workshop on CBR in the Health Science (WHS ICCBR 2019)

Non-contact Physiological Parameters Extraction using Facial Video considering Illumination, Motion, Movement and Vibration (May 2019)
Hamidur Rahman, Mobyen Uddin Ahmed, Shahina Begum
IEEE Transactions on Biomedical Engineering (TBME)

Drivers' Sleepiness Classification using Machine Learning with Physiological and Contextual data (Mar 2019)
Shaibal Barua, Mobyen Uddin Ahmed, Shahina Begum
First International Conference on Advances in Signal Processing and Artificial Intelligence (ASPAI' 2019)

PhD students supervised as main supervisor:

Hamidur Rahman
Mir Riyanul Islam
Mohammed Ghaith Altarabichi
Shaibal Barua (former)

PhD students supervised as assistant supervisor:

Sara Abbaspour (former)
Taha Kahn (former)

MSc theses supervised (or examined):
Thesis TitleStatus
Feature Selection through Artificial Intelligence for EEG Signal Classification available
A Decision Support System for medical diagnosis using Data Mining and Machine Learning available
A systematic review on theoretical aspects of k-nearest neighbour algorithm available
Activity monitoring in daily life using Shimmer sensing available
Correlation analysis among EEG, EOG and EMG signals for identification of ocular and muscle activities available
Data-driven actors modelling for road transportation available
Data-driven cognitive load classification system using machine-learning algorithm available
Data-driven Modelling on Powered Two Wheelers using Machine Learning available
Deep Learning based Eye Tracking and Head Movement Detection available
Deep learning to classify driving events using GPS data available
Detect drug abuse by AI processed eye movement data from a smart phone film available
GameAlyzer - a wearables and AI based system to monitor gambling and gaming available
Non-Contact Intelligent System to monitor driver’s alcoholic state using Biological Signals available
Artifact handling or filtering noise from the biological sensor signals EEG and ECG selected
Distributed case retrieval for big data using Spark platform and Case-Based Reasoning selected
A case study on Heart Rate Variability and Finger Temperature to use it in a stress diagnosis system finished
Using AI and Statistics on Structured Electronic Patient Records for Clinical Decision Support Systems finished
A decision support system for stress diagnosis using ECG signal. finished
An Intelligent Portable Sensor System in Diagnosing Stress finished
An optimized case matching algorithm in diagnosing the stress patients finished
Case representation methodology for a scalable Case-Based Reasoning finished
Decision Support System for Lung Diseases (DSS) finished
Decision support system: Knowledge capture and sharing for Telecom network management finished
Develop an Automated System for EEG Artifacts Identification finished
Evaluation of jCOLIBRI finished
Feature Extraction From Sensor Data To Represent And Matching Cases For Patient Health Care finished
Individual Stress Diagnosis Using Skin Conductance Sensor Signals finished
Intelligent System for Monitoring Physiological Parameters Using Camera finished
Investigation of Feature Optimization Algorithms for EEG Signal Analysis For Monitoring the Drivers finished
MACHINE LEARNING BASED PEDESTRIAN EVENT MONITORING USING IMU AND GPS finished
Monitoring of Micro-sleep and Sleepiness for the Drivers Using EEG Signal finished
Multi-Sensor Information Fusion for Classification of Driver's Physiological Sensor Data finished
NOISY BIG DATA CLASSIFICATION USING MAPREDUCE DISTRIBUTED FUZZY RANDOM FOREST finished