A efficient and robust privacy-preserving framework for cross-device federated learning
Authors (first, second and last of 6)
Collection
Swarm and Evolutionary Intelligence for sensor and IoT-based large scale healthcare applications
IoT and Sensor Networks that includes bio sensors, chemical sensors, physical sensors have emerged as a very efficient and effective tool in the healthcare service sector as the integration of IoT devices with medical applications is expected to improve the quality of service. In the last two decades, IoT and Sensor Networks have been applied for various e-Health applications and thus improve the diagnostic tools.
Evolutionary and swarm intelligence has grown extensively and are quite effective for solving complex problems. In recent times with the emergence of sensor technology, cloud computing, and IoT platform there is a substantial change in the healthcare domain from many perspectives that includes monitoring, testing, diagnosis, prognosis. suggests treatment and follow up. The system has become quite complex in nature, and most of the solutions suffer from the drawbacks of inaccuracy, lack of convergence and exponential time complexity making it difficult for providing real-time solutions. Hence, these systems are generally replaced by intelligence based systems which are much superior to the conventional systems. Intelligent techniques are mostly hybrid in nature and include Artificial Neural Networks (ANN), fuzzy theory, evolutionary algorithms, swarm and memetic computing. Though most of the techniques have been proved to be quite sound both theoretically and empirically, the potential of these algorithms are not fully explored for practical applications like healthcare. IoT based healthcare system are now evolving and the present day research is slowly moving towards deployment and testing in large scale. Large scale deployment and testing leads to complex issues. Most of the algorithms are proved to be NP-Hard or complete problems and there do not exist any know polynomial time complexity algorithm for this. When the system becomes large the complexity increases exponentially. Swarm and Evolutionary algorithms have been proved to be quite effective in these type of scenarios. Researchers need to address the problem in totality instead of addressing the issues in isolation.
Editors
-
Suresh Chandra Satapathy
Prof. Suresh Chandra Satapathy (Handling Editor) Professor School of Computer Science and Engineering KIIT University, Orissa. suresh.satapathyfcs@kiit.ac.in, sureshsatapathy@ieee.org
-
Siba Kumar Udgata
Prof. Siba Kumar Udgata Professor School of Computer and Information Sciences University of Hyderabad, India Email: udgata@uohyd.ac.in
-
Yu-Dong Zhang
Prof. Yu-Dong Zhang Professor School of Informatics University of Leicester, UK Email: yudongzhang@ieee.org
Articles (14 in this collection)
-
-
-
-
-
-
Reinforcement learning for the traveling salesman problem with refueling
Authors (first, second and last of 4)
-
ST-V-Net: incorporating shape prior into convolutional neural networks for proximal femur segmentation
Authors (first, second and last of 13)
-
A review on Deep Learning approaches for low-dose Computed Tomography restoration
Authors (first, second and last of 4)
-
Security for eHealth system: data hiding in AMBTC compressed images via gradient-based coding
Authors (first, second and last of 4)
-
O-WCNN: an optimized integration of spatial and spectral feature map for arrhythmia classification
Authors (first, second and last of 5)
-
Diabetic retinopathy detection and classification using capsule networks
Authors (first, second and last of 4)
-
Human gait analysis for osteoarthritis prediction: a framework of deep learning and kernel extreme learning machine
Authors (first, second and last of 7)
-
-
Intelligent IoT-based large-scale inverse planning system considering postmodulation factors
Authors (first, second and last of 5)
