Nonintrusive load monitoring (NILM) enables the disaggregation of the global power consumption of multiple loads, taken from a single smart electrical meter, into appliance-level details. ...State-of-the-art approaches are based on machine learning methods and exploit the fusion of time- and frequency-domain features from current and voltage sensors. Unfortunately, these methods are compute-demanding and memory-intensive. Therefore, running low-latency NILM on low-cost resource-constrained microcontroller unit (MCU)-based meters is currently an open challenge. This article addresses the optimization of the feature spaces as well as the computational and storage cost reduction needed for executing state-of-the-art (SoA) NILM algorithms on memory- and compute-limited MCUs. We compare four supervised learning techniques on different classification scenarios and characterize the overall NILM pipeline's implementation on an MCU-based Smart Measurement Node . Experimental results demonstrate that optimizing the feature space enables edge MCU-based NILM with 95.15% accuracy, resulting in a small drop compared to the most accurate feature vector deployment (96.19%) while achieving up to 5.45× speedup and 80.56% storage reduction. Furthermore, we show that low-latency NILM relying only on current measurements reaches almost 80% accuracy, allowing a major cost reduction by removing voltage sensors from the hardware (HW) design.
The closed-loop application of electrical stimulation via chronically implanted electrodes is a novel approach to stop seizures in patients with focal-onset epilepsy. To this end, an energy efficient ...seizure detector that can be implemented in an implantable device is of crucial importance. In this study, we first evaluated the performance of two machine learning algorithms (Random Forest classifier and support vector machine (SVM)) by using selected time and frequency domain features with a limited need of computational resources. Performance of the algorithms was further compared to a detection strategy implemented in an existing closed loop neurostimulation device for the treatment of epilepsy. The results show a superior performance of the Random Forest classifier compared to the SVM classifier and the reference approach. Next, we implemented the feature extraction and classification process of the Random Forest classifier on a microcontroller to evaluate the energy efficiency of this seizure detector. In conclusion, the feature set in combination with Random Forest classifier is an energy efficient hardware implementation that shows an improvement of detection sensitivity and specificity compared to the presently available closed-loop intervention in epilepsy while preserving a low detection delay.
A smart sensor label based on the integration of ultra high frequency (UHF) radio frequency identification (RFID) technology and sensors is presented. The label is composed of a semi-active system ...that measures temperature, light, relative humidity and gravimetric water content (GWC) in the soil. The deployed system provides a simple, cost effective solution to monitor and control the growing of plants in modern agriculture and is intended be a part of a smart wireless sensor network (WSN) for agricultural monitoring. This paper is focused on analysis and development of a moisture sensor to measure GWC. It is based on a capacitance measurement solution, the accuracy of which is enhanced using several sensor driving frequencies. Thanks to the cancellation of supply voltage variations, the modeling of the GWC sensor and readout circuit was correct. The results we measured were close to modeled values. The maximum measurement resolution of the capacitive moisture sensor was 0.07 pF. To get the GWC from measured capacitance, a scale was used to weigh the mass of water in the soil. The comparison between capacitance measurement and calculated soil GWC is presented. The RFID measurement system has energy harvesting capabilities and an ultra-low power microcontroller, which uses embedded software to control the measurement properties. The microcontroller has to choose the appropriate model depending on the measured amplitude and chosen frequency to calculate the actual voltage on the sensing capacitor.
Wireless short-range communication has become widespread in the modern era, partly due to the advancement of the Internet of Things (IoT) and smart technology. This technology is now utilized in ...various sectors, including lighting, medical, and industrial applications. This article aims to examine the historical, present, and forthcoming advancements in wireless short-range communication. Additionally, the review will analyze the modifications made to communication protocols, such as Bluetooth, RFID and NFC, in order to better accommodate modern applications. Batteryless technology, particularly batteryless NFC, is an emerging development in short-range wireless communication that combines power and data transmission into a single carrier. This modification will significantly influence the trajectory of short-range communication and its applications. The foundation of most low-power, short-range communication applications relies on an ultra-low-power microcontroller. Therefore, this study will encompass an analysis of ultra-low-power microcontrollers and an investigation into the potential limitations they might encounter in the future. In addition to offering a thorough examination of current Wireless short-range communication, this article will also attempt to forecast future patterns and identify possible obstacles that future research may address.
A holistic power saving concept for ultra-low-power microcontroller (MCU) systems involving application requirements, system architecture, and circuit design techniques is presented. The key of this ...concept is a digitally enhanced low dropout regulator (LDO) supplying the MCU digital core. By making use of known system power information, the LDO digitally adapts its maximum current drive capability up to 2.56 mA while its quiescent current is as low as 650 nA in light load conditions. In this way, the power management overhead is drastically reduced when operating at low clock speeds enabling system energy savings of 31% at 1 MHz. At the same time, a drastic reduction of the LDO output capacitance enables ultra-low-power consumption during sleep and energy efficient wake-up, resulting in system energy savings up to a factor of 4.6.
This study presents a low-cost, compact and lightweight radio frequency (RF) switching system for wearable head imaging applications. The proposed switching system is made from commercial ...off-the-shelf components. The switching system provides a wideband performance which covers operating frequency band from DC to 4 GHz. A low-power microcontroller is integrated with two RF switches as a control system. An array of 12 wideband monopole antennas were connected to the proposed switching circuit and its performance was evaluated using an artificial human head phantom. To verify the performance of the system, a haemorrhagic stroke was mimicked by placing a spherical target of 30 mm in diameter inside the fabricated head phantom. Two data acquisition methods were applied using the switching system. In the first method, the reflection coefficients of the antennas were collected for healthy and unhealthy brain injury cases. For the second method, the transmission coefficients of the antennas were collected by utilising four antennas in the array as transmitting antennas while the rest of the antennas act as receiving antennas. The authors demonstrate that the proposed compact switching system could be used for future real-time wearable detection systems embedded in various headgear products.
Energy consumption for heating purposes accounts for a significant part of the budgets of individual and collective users. This increases the importance of issues related to the monitoring of heating ...energy flows, analysis of flow parameters, verification of fees and, in the first place, minimization of energy consumption. The goal of this paper is to develop, by employing Global Positioning System receivers, measurement techniques that are suited to the continuous monitoring of the heating substation parameters. This paper presents the design and implementation of GPS/GPRS (Global Positioning System/General Packet Radio Service) system for low power data acquisition using MSP430 Texas Instruments microcontroller for monitoring of the heating substation parameters. The system is implemented in heating stations for a temperature and pressure monitoring. It contains GPS/GPRS gateway and 8 analog sensor inputs. Acquisition module and the server base station are suitable for industrial applications, home applications and for other appliances. The proposed measurement procedures, which are different from commercially available measurement units, are based on general-purpose acquisition hardware and processing software, thus guaranteeing the possibility of being easily reconfigured and reprogrammed according to the specific requirements of different possible fields of application and to their future developments.
Implantable, closed-loop devices for automated early detection and stimulation of epileptic seizures are promising treatment options for patients with severe epilepsy that cannot be treated with ...traditional means. Most approaches for early seizure detection in the literature are, however, not optimized for implementation on ultra-low power microcontrollers required for long-term implantation. In this paper we present a convolutional neural network for the early detection of seizures from in- tracranial EEG signals, designed specifically for this purpose. In addition, we investigate approximations to comply with hardware limits while preserving accuracy. We compare our approach to three previously proposed convolutional neural networks and a feature-based SVM classifier with respect to detection accuracy, latency and computational needs. Evaluation is based on a comprehensive database with long-term EEG recordings. The proposed method outperforms the other detectors with a median sensitivity of 0.96, false detection rate of 10.1 per hour and median detection delay of 3.7 seconds, while being the only approach suited to be realized on a low power microcontroller due to its parsimonious use of computational and memory resources.
We present for the first time a μW-power convolutional neural network for seizure detection running on a low-power microcontroller. On a dataset of 22 patients a median sensitivity of 100% is ...achieved. With a false positive rate of 20.7 fp/h and a short detection delay of 3.4 s it is suitable for the application in an implantable closed-loop device.