Blog
Enhancing Cardiovascular Disease Prediction via Hybrid Deep Learning Architectures: A Step Towards Smart Healthcare
We get inspired by nature to save lives! We mimic the strategies adopted by coatis while hunting iguanas and their behavior when confronting and fleeing from predators!
I am happy to announce that our research paper, titled "Enhancing Cardiovascular Disease Prediction via Hybrid Deep Learning Architectures: A Step Towards Smart Healthcare," has been accepted for publication at the prestigious 2nd IEEE International Conference on Emerging Trends in Electrical, Control and Telecommunication Engineering (ETECTE'23) in Lahore, Pakistan, scheduled for 2023.
Aitzaz Ahmed Murtaza, Amina Saher, Hassan Mohyuddin, Syed Kumayl Raza Moosavi, Muhammad Hamza Zafar, and Filippo Sanfilippo. Enhancing Cardiovascular Disease Prediction via Hybrid Deep Learning Architectures: A Step Towards Smart Healthcare. Accepted for publication to the Proc. of the 2nd IEEE International Conference on Emerging Trends in Electrical, Control and Telecommunication Engineering (ETECTE'23), Lahore, Pakistan, 2023.
Abstract: Cardiovascular disease presents a serious and increasing global health challenge, making a substantial contribution to morbidity and mortality rates on a global scale. This research study presents a novel methodology for predicting Cardiovascular Diseases by employing a, recently developed, metaheuristic optimisation algorithm within a neural network framework. The Coati Optimisation Algorithm (COA) is employed in an artificial neural network (ANN) to enhance the predictive accuracy of outcomes related to Cardiovascular Diseases. The enhanced performance of the COA can be ascribed to its adept utilisation of both exploration and exploitation phenomena. This research employs publicly available datasets pertaining to heart and stroke disorders, integrating two datasets focused on heart disease and one dataset focused on stroke disease. A comparison analysis is undertaken between the proposed COA-ANN and existing approaches, namely Particle Swarm Optimizer based ANN (PSO-ANN), Grey Wolf Optimizer based ANN (GWO-ANN), and backpropagation based ANN (BP-ANN). The findings of the study indicate that the COA-ANN model exhibits the highest level of predictive accuracy. The COA-ANN outperformed the other three networks, namely GWO-ANN, PSO-ANN, and BP-ANN, with an average accuracy of 98.43%. As a result, the utilisation of the COA-ANN leads to an improvement in predictive accuracy for these datasets, with an increase of up to 2.64%. Additional assessment metrics, such as F1-Score, Precision, and Recall, provide more insight into the balanced performance of the COA-ANN architecture when applied to imbalanced class datasets. These results prove that the integration of nature-inspired algorithms with cardiovascular diseases (CVDs) is a promising direction for future research.
I am grateful to my co-authors and the entire research team for their dedication and hard work throughout this project. Stay tuned for more updates on our research journey, and feel free to reach out if you're interested in learning more about our work or would like to connect for future collaborations.
Kick-off meeting of Beyond the Classroom: Virtual Reality, Augmented Reality, and Haptics for Enhanced Surgical Training and Education (ImmersiveSurgicalEdu)
The journey begins for the "Beyond the Classroom: Virtual Reality, Augmented Reality, and Haptics for Enhanced Surgical Training and Education" project, ImmersiveSurgicalEdu!
I am happy to announce the successful kick-off meeting of our groundbreaking research initiative, ImmersiveSurgicalEdu.
Our mission is to revolutionize surgical training and education through the integration of virtual reality (VR), augmented reality (AR), and haptic technology, creating a truly immersive hands-on laboratory experience.
Thanks to the generous grant of 250,000 Euros from the Erasmus+ Cooperation Partnerships in Higher Education KA220-HED call, we are ready to embark on this exciting journey.
The project is led by the Biomechatronics and Collaborative Robotics research group at the Top Research Center Mechatronics (TRCM), University of Agder (UiA), Norway.
Project partners: Kaunas University of Technology, Lithuania; the University of Siena, Italy; and the Lithuanian University of Health Sciences, Lithuania.
Our kick-off meeting was graced by the presence of Prof. Guido Gabriele, a maxillofacial surgeon who provided us with invaluable insights from the medical perspective. We couldn't help but notice the irony of a surgeon donning a surgical mask at our meeting!
Stay tuned for more updates and progress as we delve into the immersive world of surgical education.
Early Mental Stress Detection Using Q-Learning Embedded Starling Murmuration Optimiser-Based Deep Learning Model
I am thrilled to share with you our recently published article:
- Syed Kumayl Raza Moosavi, Muhammad Hamza Zafar, Filippo Sanfilippo, Malik Naveed Akhter, and Shahzaib Farooq Hadi. Early Mental Stress Detection Using Q-Learning Embedded Starling Murmuration Optimiser-based Deep Learning Model. IEEE Access (2023).
Abstract: Stress affects individual of all ages as a regular part of life, but excessive and chronic stress can lead to physical and mental health problems, decreased productivity, and reduced quality of life. By identifying stress at an early stage, individuals can take steps to manage it effectively and improve their overall well-being. Feature selection is a critical aspect of early stress detection because it helps identify the most relevant and informative features that can differentiate between stressed and non-stressed individuals. This paper firstly proposes a variance based feature selection technique that uses q-learning embedded Starling Murmuration Optimiser (QLESMO) to choose relevant features from a publicly available dataset in which stresses experienced by nurses working during the Covid’19 Pandemic is recorded using bio-signals and user surveys. Furthermore, a comparative study with other metaheuristic based feature selection techniques have been demonstrated. Next, to evaluate the efficacy of the proposed algorithm, 10 benchmark test functions have been used. The reduced feature subset is then classified through a 1D convolutional neural network (CNN) model (QLESMO-CNN) and is seen to perform well in terms of the evaluation metrics in comparison to other competitive algorithms. Finally, the proposed technique is compared with the State-of-the-Art methodologies present in literature. The experiments provide a strong basis to determine features that are most relevant for early mental stress classification using a hybrid model combining CNN, Reinforcement Learning and metaheuristic algorithms.
You can access the full article and delve into the details by following this DOI link.
I take this opportunity to express my gratitude to all my coauthors for their valuable contributions to this work. This achievement reflects our shared commitment to advancing the field of mental health research and improving the lives of individuals dealing with mental stress.
I am excited to see how this research will contribute to the broader understanding of mental health and, hopefully, make a positive impact in the lives of those who may benefit from our findings.
Filippo Sanfilippo