Figure 4
Finite state machine block diagram for the proposed hardware architecture. The system iterates through six states and only one state is active at a time.
Source publication
Modern wearable rehabilitation devices and health support systems operate by sensing and analysing human body activities. The information produced by such systems requires efficient methods for classification and analysis. Deep learning algorithms have shown remarkable potential regarding such analyses, however, the use of such algorithms on low-po...
Context in source publication
Context 1
... illustrated in Fig. 4, the proposed hardware classifier functions as a finite state machine that iterates through six states and only one state is active at a time. This structure can also be implemented in a pipelined form with multiple active states and higher throughput at the expense of increased power and area consumption. The general functionality of ...
Citations
Predictive analytics and event forecasting using deep learning techniques require processing long–term historical data which is infeasible in low–power wearable devices. Such devices are constrained in memory and computational power, and are pushed to their limits by resource hungry deep neural networks. Current techniques either ignore historical data, or convert temporal sequences to pattern sequences, eliminating valuable properties such as time and/or recency. The proposed model maps arbitrary–length multivariate discrete time series to a concise sequence, called mapped interval sequence (MIS). MIS retains original data properties such as time, recency, and scale, without being susceptible to missing values. Life Model for time series (LMts) mapping, is capable of mapping billions of data elements with sampling rate of several kHz or higher into a sequence of 32 elements or fewer. Furthermore, a new loss function called as tolerance error is introduced to improve long-term forecasting events using LMts. In a smart health internet of things environment, LMts enables real–time health predictions depending on both recent and historical data. In addition, the LMts model can predict the approximate time of events, with granularity of seconds and up to years. Experimental results show that, compared to previous studies in fall prediction, LMts achieves the same 100% accuracy with a single long short–term memory layer, while covering 16× longer time period and using 80× less weight parameters. LMts is also used to forecast human fall up to 14 seconds in advance even with 50% missing values. IEEE
