ApproxCS: Near-Sensor Approximate Compressed Sensing for IoT-Healthcare Systems

Abstract

Internet of Things (IoTs) is an emerging trend that has enabled an upgrade in the design of wearable healthcare monitoring systems through the (integrated) edge, fog, and cloud computing paradigm. Energy efficiency is one of the most important design metrics in such IoT-healthcare systems especially, for the edge and fog nodes. Due to the sensing noise and inherent redundancy in the input data, even the most safety-critical biomedical applications can sometimes afford a slight degradation in the output quality. Hence, such inherent error tolerance in the bio-signals can be exploited to achieve high energy savings through the emerging trends like, the Approximate Computing which is applicable at both software and hardware levels. In this paper, we propose to leverage the approximate computing in digital Compressed Sensing (CS), through low-power approximate adders (LPAA) in an accurate Bernoulli sensing based CS acquisition (BCS). We demonstrate that approximations can indeed be safely employed in IoT-healthcare without affecting the detection of critical events in the biomedical signals. Towards this, we explored the trade-off between energy efficiency and output quality using the state-of-the-art lp 2d RLS reconstruction algorithm. The proposed framework is validated with the MIT-BIH Arrhythmia database. Our results demonstrated approximately 59% energy savings as compared to the accurate design.

Optimizing Real-Time ECG Data Transmission in Constrained Environments

“…In wireless sensor networks, there are five categories of compression techniques [31]: string-based, image-based, compressed sensing, distributed source coding, and data aggregation. String-based, image-based, and compressed sensing are commonly used techniques in the healthcare domain [32] [33] [34].…”

The Internet of Medical Thing: A Comprehensive Survey

“…The usage of blockchain, according to the researchers, improves the reliability and security of data gathered by sensor network. In [17] A. Siddique et al use compressive sensing (CS) to compress the data sensed. By assuming data redundancies, the proposed technique optimizes the power system., which make up a substantial component of biomedical data.…”

Exploring Fault-Energy Trade-offs in Approximate DNN Hardware Accelerators

“…For enhancing the energy efficiency of such devices, many energy-aware systolic array-based DNN accelerators have been recently developed [2] but their large size requirement for fast data processing poses meager energy gains in energy-constrained devices [3]. This problem can be addressed with approximate computing that trades the accuracy of an application-specific system, by exploiting its intrinsic error resilience, for energy savings [4]. It incorporates loop skipping and sampling rate reduction at the software level, and adopts inexact arithmetic units (e.g., multipliers and adders with truncated carry chains [5] or bit-wise structural modifications [6]) and memory skipping [7] at the hardware level.…”