A Hybrid Data Compression Scheme for Power Reduction in Wireless Sensors for IoT

A Hybrid Lossless ECG Compressor with Morphological Detection and QRS Prediction

This paper proposes a hybrid approach to lossless ECG signal compression, capitalizing on the repetitive patterns inherent in the QRS complex. The proposed processor integrates a morphological filter QRS detection channel and 12 lead channels for linear prediction and packaging. By subtracting the detected QRS complexes using predictions based on previous buffers, the proposed algorithm generates Non-QRS signals with a smaller dynamic range. The Non-QRS signals undergo further processing using a linear predictor before being formatted into 32-bit packaged outputs. The proposed method achieves an average compression ratio of 2.32, showcasing a 3% improvement over the MIT-BIH dataset compared to methods without QRS removal. The proposed work was implemented with 40nm CMOS technology. The 12-lead ECG compression chip consumes a power of 179nW under 0.9V and occupies a silicon area of 16,032µm2 per channel. These results yield a 19× higher FoM than prior works, underscoring the superior efficiency and effectiveness of the proposed approach.

Lossless Data Compression for Time-Series Sensor Data Based on Dynamic Bit Packing

In this paper, we propose a bit depth compression (BDC) technique, which performs bit packing by dynamically determining the pack size based on the pattern of the bit depth level of the sensor data, thereby maximally reducing the space wastage that may occur during the bit packing process. The proposed technique can dynamically perform bit packing according to the data's characteristics, which may have many outliers or several multidimensional variations, and therefore has a high compression ratio. Furthermore, the proposed method is a lossless compression technique, which is especially useful as training data in the field of artificial intelligence or in the predictive analysis of data science. The proposed method effectively addresses the spatial inefficiency caused by unpredictable outliers during time-series data compression. Additionally, it offers high compression efficiency, allowing for storage space savings and optimizing network bandwidth utilization while transmitting large volumes of data. In the experiment, the BDC method demonstrated an improvement in the compression ratio of up to 247%, with 30% on average, compared with other compression algorithms. In terms of energy consumption, the proposed BDC also improves data transmission using Bluetooth up to 34%, with 18% on average, compared with other compression algorithms.

An Ultra-Low Power Reconfigurable Biomedical AI Processor With Adaptive Learning for Versatile Wearable Intelligent Health Monitoring

Wearable intelligent health monitoring devices with on-device biomedical AI processor can be used to detect the abnormity in users' biomedical signals (e.g., ECG arrythmia classification, EEG-based seizure detection). This requires ultra-low power and reconfigurable biomedical AI processor to support battery-supplied wearable devices and versatile intelligent health monitoring applications while achieving high classification accuracy. However, existing designs have issues in meeting one or more of the above requirements. In this work, a reconfigurable biomedical AI processor (named BioAIP) is proposed, mainly featuring: 1) a reconfigurable biomedical AI processing architecture to support versatile biomedical AI processing. 2) an event-driven biomedical AI processing architecture with approximate data compression to reduce the power consumption. 3) an AI-based adaptive-learning architecture to address patient-to-patient variation and improve the classification accuracy. The design has been implemented and fabricated using a 65nm CMOS process technology. It has been demonstrated with three typical biomedical AI applications, including ECG arrythmia classification, EEG-based seizure detection and EMG-based hand gesture recognition. Compared with the state-of-the-art designs optimized for single biomedical AI tasks, the BioAIP achieves the lowest energy per classification among the designs with similar accuracy, while supporting various biomedical AI tasks.

In-sensor neural network for high energy efficiency analog-to-information conversion

This work presents an on-chip analog-to-information conversion technique that utilizes analog hyper-dimensional computing based on reservoir-computing paradigm to process electrocardiograph (ECG) signals locally in-sensor and reduce radio frequency transmission by more than three orders-of-magnitude. Instead of transmitting the naturally sparse ECG signal or extracted features, the on-chip analog-to-information converter analyzes the ECG signal through a nonlinear reservoir kernel followed by an artificial neural network, and transmits the prediction results. The proposed technique is demonstrated for detection of sepsis onset and achieves state-of-the-art accuracy and energy efficiency while reducing sensor power by [Formula: see text] with test-chips prototyped in 65 nm CMOS.

Investigation of Energy Cost of Data Compression Algorithms in WSN for IoT Applications

The exponential growth in remote sensing, coupled with advancements in integrated circuits (IC) design and fabrication technology for communication, has prompted the progress of Wireless Sensor Networks (WSN). WSN comprises of sensor nodes and hubs fit for detecting, processing, and communicating remotely. Sensor nodes have limited resources such as memory, energy and computation capabilities restricting their ability to process large volume of data that is generated. Compressing the data before transmission will help alleviate the problem. Many data compression methods have been proposed but mainly for image processing and a vast majority of them are not pertinent on sensor nodes because of memory impediment, energy utilization and handling speed. To overcome this issue, authors in this research have chosen Run Length Encoding (RLE) and Adaptive Huffman Encoding (AHE) data compression techniques as they can be executed on sensor nodes. Both RLE and AHE are capable of balancing compression ratio and energy utilization. In this paper, a hybrid method comprising RLE and AHE, named as H-RLEAHE, is proposed and further investigated for sensor nodes. In order to verify the efficacy of the data compression algorithms, simulations were run, and the results compared with the compression techniques employing RLE, AHE, H-RLEAHE, and without the use of any compression approach for five distinct scenarios. The results demonstrate the RLE's efficiency, as it surpasses alternative data compression methods in terms of energy efficiency, network speed, packet delivery rate, and residual energy throughout all iterations.

Detection and Monitoring of Viral Infections via Wearable Devices and Biometric Data

Mounting clinical evidence suggests that viral infections can lead to detectable changes in an individual's normal physiologic and behavioral metrics, including heart and respiration rates, heart rate variability, temperature, activity, and sleep prior to symptom onset, potentially even in asymptomatic individuals. While the ability of wearable devices to detect viral infections in a real-world setting has yet to be proven, multiple recent studies have established that individual, continuous data from a range of biometric monitoring technologies can be easily acquired and that through the use of machine learning techniques, physiological signals and warning signs can be identified. In this review, we highlight the existing knowledge base supporting the potential for widespread implementation of biometric data to address existing gaps in the diagnosis and treatment of viral illnesses, with a particular focus on the many important lessons learned from the coronavirus disease 2019 pandemic.

A Dynamically Reconfigurable ECG Analog Front-End With a 2.5× Data-Dependent Power Reduction

This paper presents a reconfigurable electrocardiogram (ECG) analog front-end (AFE) exploiting bio-signals' inherent low activity and quasi-periodicity to reduce power consumption. This is realized by an agile, on-the-fly dynamic noise-power trade-off performed over specific cardiac cycle regions guided by a least mean squares (LMS)-based adaptive predictor leading to ∼2.5× data-dependent power savings. Implemented in 65 nm CMOS, the AFE has tunable performance exhibiting an input-referred noise ranging from 2.38 - 3.64 μV_rms while consuming 307 - 769 nW from a 0.8 V supply. A comprehensive system performance verification was performed using ECG records from standard databases to establish the feasibility of the proposed predictor-based approach for power savings without compromising the system's anomaly detection capability or ability to extract pristine ECG features.

Dimensionality Reduction for Smart IoT Sensors

Smart IoT sensors are characterized by their ability to sense and process signals, producing high-level information that is usually sent wirelessly while minimising energy consumption and maximising communication efficiency. Systems are getting smarter, meaning that they are providing ever richer information from the same raw data. This increasing intelligence can occur at various levels, including in the sensor itself, at the edge, and in the cloud. As sending one byte of data is several orders of magnitude more energy-expensive than processing it, data must be handled as near as possible to its generation. Thus, the intelligence should be located in the sensor; nevertheless, it is not always possible to do so because real data is not always available for designing the algorithms or the hardware capacity is limited. Smart devices detecting data coming from inertial sensors are a good example of this. They generate hundreds of bytes per second (100 Hz, 12-bit sampling of a triaxial accelerometer) but useful information comes out in just a few bytes per minute (number of steps, type of activity, and so forth). We propose a lossy compression method to reduce the dimensionality of raw data from accelerometers, gyroscopes, and magnetometers, while maintaining a high quality of information in the reconstructed signal coming from an embedded device. The implemented method uses an adaptive vector-quantisation algorithm that represents the input data with a limited set of codewords. The adaptive process generates a codebook that evolves to become highly specific for the input data, while providing high compression rates. The codebook’s reconstruction quality is measured with a peak signal-to-noise ratio (PSNR) above 40 dB for a 12-bit representation.

Performance Evaluation of Data Compression Algorithms for IoT-Based Smart Water Network Management Applications

IoT-based smart water supply network management applications generate a huge volume of data from the installed sensing devices which are required to be processed (sometimes in-network), stored and transmitted to a remote centre for decision making. When the volume of data produced by diverse IoT smart sensing devices intensify, processing and storage of these data begin to be a serious issue. The large data size acquired from these applications increases the computational complexities, occupies the scarce bandwidth of data transmission and increases the storage space. Thus, data size reduction through the use of data compression algorithms is essential in IoT-based smart water network management applications. In this paper, the performance evaluation of four different data compression algorithms used for this purpose is presented. These algorithms, which include RLE, Huffman, LZW and Shanon-Fano encoding were realised using MATLAB software and tested on six water supply system data. The performance of each of these algorithms was evaluated based on their compression ratio, compression factor, percentage space savings, as well as the compression gain. The results obtained showed that the LZW algorithm shows better performance base on the compression ratio, compression factor, space savings and the compression gain. However, its execution time is relatively slow compared to the RLE and the two other algorithms investigated. Most importantly, the LZW algorithm has a significant reduction in the data sizes of the tested files than all other algorithms

Power Efficiency Comparison of Event-Driven and Fixed-Rate Signal Conversion and Compression for Biomedical Applications

Energy-constrained biomedical recording systems need power-efficient data converters and good signal compression in order to meet the stringent power consumption requirements of many applications. In literature today, typically a SAR ADC in combination with digital compression is used. Recently, alternative event-driven sampling techniques have been proposed that incorporate compression in the ADC, such as level-crossing A/D conversion. This paper describes the power efficiency analysis of such level-crossing ADC (LCADC) and the traditional fixed-rate SAR ADC with simple compression. A model for the power consumption of the LCADC is derived, which is then compared to the power consumption of the SAR ADC with zero-order hold (ZOH) compression for multiple biosignals (ECG, EMG, EEG, and EAP). The LCADC is more power efficient than the SAR ADC up to a cross-over point in quantizer resolution (for example 8 bits for an EEG signal). This cross-over point decreases with the ratio of the maximum to average slope in the signal of the application. It also changes with the technology and design techniques used. The LCADC is thus suited for low to medium resolution applications. In addition, the event-driven operation of an LCADC results in fewer data to be transmitted in a system application. The event-driven LCADC without timer and with single-bit quantizer achieves a reduction in power consumption at system level of two orders of magnitude, an order of magnitude better than the SAR ADC with ZOH compression. At system level, the LCADC thus offers a big advantage over the SAR ADC.

Low-Power Embedded System for Gait Classification Using Neural Networks

Abnormal foot postures can be measured during the march by plantar pressures in both dynamic and static conditions. These detections may prevent possible injuries to the lower limbs like fractures, ankle sprain or plantar fasciitis. This information can be obtained by an embedded instrumented insole with pressure sensors and a low-power microcontroller. However, these sensors are placed in sparse locations inside the insole, so it is not easy to correlate manually its values with the gait type; that is why a machine learning system is needed. In this work, we analyse the feasibility of integrating a machine learning classifier inside a low-power embedded system in order to obtain information from the user’s gait in real-time and prevent future injuries. Moreover, we analyse the execution times, the power consumption and the model effectiveness. The machine learning classifier is trained using an acquired dataset of 3000+ steps from 6 different users. Results prove that this system provides an accuracy over 99% and the power consumption tests obtains a battery autonomy over 25 days.

Event-Driven ECG Sensor in Healthcare Devices for Data Transfer Optimization

The long-term monitoring of cardiovascular signs requires a wearable and connected electrocardiogram (ECG) healthcare device. It increases user's comfort and diagnosis quality of chronic cardiac and/or high-risk patients. This paper covers the enormous data to be transmitted from the ECG device to the physician's, namely the cardiologist's, control unit. Existent ECG devices uniformly sample analog signals and convert them to digital samples which are compressed before data transmission. However, event-driven sampling simultaneously compresses and samples. Therefore, this paper quantitatively compares successive approximation register analog-to-digital converter (SAR ADC) with discrete wavelet transform (DWT) compression and level-crossing analog-to-digital converter (LC-ADC). Evaluation metrics are the percent root-mean-square difference ( PRD ), bit compression ratio ( BCR ) and data length in bits. When a 12-bit reconstruction is operated on the outputs of an 8-bit LC-ADC with 12-bit and 10-kHz reference counter, the BCR is equal to 80% for 75% of test ECG signals. That is better than the 71.87% BCR of the 12-bit 1-kHz SAR ADC with DWT compression. The modeled LC-ADC guarantees a signal quality in terms of PRD comparable to the PRD of the SAR ADC with DWT compression. The data length in bits of the LC-ADC is lower than the data length in bits of the SAR ADC with more than 14-bit resolution with DWT compression for 82% of the test ECG signals. However, for lower resolutions, to obtain lower power consumption for radiofrequency transmission, a better alternative remains the SAR ADC with DWT compression.

Energy-Efficient Intelligent ECG Monitoring for Wearable Devices

Wearable intelligent ECG monitoring devices can perform automatic ECG diagnosis in real time and send out alert signal together with abnormal ECG signal for doctor's further analysis. This provides a means for the patient to identify their heart problem as early as possible and go to doctors for medical treatment. For such system the key requirements include high accuracy and low power consumption. However, the existing wearable intelligent ECG monitoring schemes suffer from high power consumption in both ECG diagnosis and transmission in order to achieve high accuracy. In this work, we have proposed an energy-efficient wearable intelligent ECG monitor scheme with two-stage end-to-end neural network and diagnosis-based adaptive compression. Compared to the state-of-the-art schemes, it significantly reduces the power consumption in ECG diagnosis and transmission while maintaining high accuracy.

IoT Based Heart Activity Monitoring Using Inductive Sensors

This paper presents a system dedicated to monitoring the heart activity parameters using Electrocardiography (ECG) mobile devices and a Wearable Heart Monitoring Inductive Sensor (WHMIS) that represents a new method and device, developed by us as an experimental model, used to assess the mechanical activity of the hearth using inductive sensors that are inserted in the fabric of the clothes. Only one inductive sensor is incorporated in the clothes in front of the apex area and it is able to assess the cardiorespiratory activity while in the prior of the art are presented methods that predict sensors arrays which are distributed in more places of the body. The parameters that are assessed are heart data-rate and respiration. The results are considered preliminary in order to prove the feasibility of this method. The main goal of the study is to extract the respiration and the data-rate parameters from the same output signal generated by the inductance-to-number convertor using a proper algorithm. The conceived device is meant to be part of the "wear and forget" equipment dedicated to monitoring the vital signs continuously.

Design and Implementation of an Ultra-Low Resource Electrodermal Activity Sensor for Wearable Applications ‡

While modern low-power microcontrollers are a cornerstone of wearable physiological sensors, their limited on-chip storage typically makes peripheral storage devices a requirement for long-term physiological sensing—significantly increasing both size and power consumption. Here, a wearable biosensor system capable of long-term recording of physiological signals using a single, 64 kB microcontroller to minimize sensor size and improve energy performance is described. Electrodermal (EDA) signals were sampled and compressed using a multiresolution wavelet transformation to achieve long-term storage within the limited memory of a 16-bit microcontroller. The distortion of the compressed signal and errors in extracting common EDA features is evaluated across 253 independent EDA signals acquired from human volunteers. At a compression ratio (CR) of 23.3×, the root mean square error (RMSErr) is below 0.016 μS and the percent root-mean-square difference (PRD) is below 1%. Tonic EDA features are preserved at a CR = 23.3× while phasic EDA features are more prone to reconstruction errors at CRs > 8.8×. This compression method is shown to be competitive with other compressive sensing-based approaches for EDA measurement while enabling on-board access to raw EDA data and efficient signal reconstructions. The system and compression method provided improves the functionality of low-resource microcontrollers by limiting the need for external memory devices and wireless connectivity to advance the miniaturization of wearable biosensors for mobile applications.

Wireless EEG System Achieving High Throughput and Reduced Energy Consumption Through Lossless and Near-Lossless Compression

This work presents a wireless multichannel electroencephalogram (EEG) recording system featuring lossless and near-lossless compression of the digitized EEG signal. Two novel, low-complexity, efficient compression algorithms were developed and tested in a low-power platform. The algorithms were tested on six public EEG databases comparing favorably with the best compression rates reported up to date in the literature. In its lossless mode, the platform is capable of encoding and transmitting 59-channel EEG signals, sampled at 500 Hz and 16 bits per sample, at a current consumption of 337 A per channel; this comes with a guarantee that the decompressed signal is identical to the sampled one. The near-lossless mode allows for significant energy savings and/or higher throughputs in exchange for a small guaranteed maximum per-sample distortion in the recovered signal. Finally, we address the tradeoff between computation cost and transmission savings by evaluating three alternatives: sending raw data, or encoding with one of two compression algorithms that differ in complexity and compression performance. We observe that the higher the throughput (number of channels and sampling rate) the larger the benefits obtained from compression.