Sharif Digital Repository

The emergence of textile-based wearable sensors as light-weight portable devices to monitor desired parameters, has recently gained much interest and has led to the development of flexible electronics on non-rigid substrates. The flexible biosensors may result in improved sports performance, to monitor the desired bodies for injuries, improved clinical diagnostics and monitor biological molecules and ions in biological fluids such as saliva, sweat. In addition, they could help users with different types of disorders such as blindness. In this context, new composite and nanomaterials have been found to be promising candidates to obtain improved performance of the textile based wearable... 

Over the past few years, development of wearable devices has gained increasing momentum. Notably, the demand for stretchable strain sensors has significantly increased due to many potential and emerging applications such as human motion monitoring, prosthetics, robotic systems, and touch panels. Recently, hydrogels have been developed to overcome the drawbacks of the elastomer-based wearable strain sensors, caused by insufficient biocompatibility, brittle mechanical properties, complicated fabrication process, as the hydrogels can provide a combination of various exciting properties such as intrinsic electrical conductivity, suitable mechanical properties, and biocompatibility. There are... 

Advances in the manufacturing of miniaturized low-power embedded systems are paving the way for ultra-lightweight wearable cameras that can visually log the minute details of people's daily lives. This survey highlights the possible applications of wearable cameras, from industrial to personal, and outlines the main challenges in realizing their full potential. © 2017 IEEE  

Objective: A novel electrocardiogram (ECG) classification algorithm is proposed for continuous cardiac monitoring on wearable devices with limited processing capacity. Methods: The proposed solution employs a novel architecture consisting of wavelet transform and multiple long short-term memory (LSTM) recurrent neural networks (see Fig. 1). Results: Experimental evaluations show superior ECG classification performance compared to previous works. Measurements on different hardware platforms show the proposed algorithm meets timing requirements for continuous and real-time execution on wearable devices. Conclusion: In contrast to many compute-intensive deep-learning based approaches, the... 

This paper presents a novel ECG classification algorithm for inclusion as part of real-time cardiac monitoring systems in ultra low-power wearable devices. The proposed solution is based on spiking neural networks which are the third generation of neural networks. In specific, we employ spike-timing dependent plasticity (STDP), and reward-modulated STDP (R-STDP), in which the model weights are trained according to the timings of spike signals, and reward or punishment signals. Experiments show that the proposed solution is suitable for real-time operation, achieves comparable accuracy with respect to previous methods, and more importantly, its energy consumption in real-time classification...