Journal of Future Generation of Communication and Internet of Things
Volume:2 Issue: 4, Oct 2023

Medical technology has made incredible strides in recent years , altering the way we approach patient care. Intelligent prosthetic limbs have emerged as a game-changer in terms of enhancing patients' motor function among these ground-breaking inventions. These innovative prostheses are pushing the limits of what people with limb loss or disability can do by seamlessly interacting with the Internet of Things (IoT). This review explores the crucial role technology plays in improving patients' motor abilities and provides a look into a future in which prosthetic limbs would automatically adapt to their users' demands and enable them to reclaim their independence.

In recent decades, the convergence of Internet of Things (IoT) technology and medical imaging has transformed healthcare. This research explores IoT-enabled medical imaging, its potential, applications, and feasibility in enhancing healthcare services. IoT in medical imaging boosts diagnostic precision and treatment capabilities, ensuring accurate disease diagnoses while preserving patient privacy through secure image uploads with encrypted data. Incorporating artificial intelligence (AI) into IoT-based imaging enhances disease detection and treatment. AI algorithms improve image quality and accuracy, raising the standard of care. IoT enables remote medical imaging and precise patient monitoring, emphasizing the importance of data security through encryption. This research highlights IoT's vital role in healthcare, fostering collaboration between devices and data to enhance public health.

Today, most people use the Internet for web searching, accessing multimedia services, and engaging in social networks, providing smart communication between machines and electronic devices. In fact, the goal of the Internet of Things (IoT) is to connect anything, anytime, anywhere, using any path or network and serving any purpose ideally. The application of IoT in the field of medicine reduces waiting times, tracks patients, doctors, equipment, and more. The aim of this paper is to investigate IoT-based disease prediction and diagnosis systems,artificial intelligence, and machine learning methods.Methods and techniques such as Machine Learning (ML) on IoT data, healthcare datasets, model evaluation, and machine learning description are mentioned for disease prediction and diagnosis systems. Real-world machine learning models for healthcare applications are then discussed in this paper. Some successful applications of machine learning in disease diagnosis through IoT data are presented. Finally, future trends in machine learning for disease diagnosis, collaboration between Artificial Intelligence and the Internet of Things in disease diagnosis, were introduced.

This paper presented the hybrid auto-tuning technique for the brushless direct current motor speed control combining fuzzy logic controller and genetic algorithm (GA). Based on the combination of Genetic algorithm (GA) that belongs to the larger class of evolutionary algorithms with Fuzzy logic controller that operates based on the database rules and intelligent decision making, an optimized speed controller is proposed. In this control framework, the GA-Fuzzy controller contains current feedback loop which is to adjust the torque of the motor and the fuzzy logic controller loop whose control rules are optimized off-line and parameters are adjusted based on the genetic algorithm. The simulation results can proved that the proposed technique has better performance than conventional PID controller

Epilepsy is a type of brain disease that can be diagnosed by observing EEG signals. The disease often occurs in children. However, some cases are also seen in adults. Diagnosing this disease in the early stages is a challenging task for doctors. In this work, the authors have classified epileptic and normal EEG signal by adopting deep learning approach. To achieve the efficient features, the dual tree complex wavelet (DTCWT) is considered. Then, the decomposed wavelet coefficients are applied to nonlinear feature extraction. These features are used as input to the Radial Hybrid Basis Function (RBF) class. Using the proposed method, about 99% classification accuracy is observed. This requires significant improvement of the proposed algorithm compared to other previously presented algorithms. It is the first time that nonlinear feature extraction on DT-CWT coefficients of an EEG signal is used to diagnose epilepsy.