No abstract

additional analog converters, imposing issues with scalability and power consumption. [2][3][4][5] Development of next-generation materials and devices for neuromorphic electronics entails detailed understanding of the fundamental device characteristics and their possible emulation capabilities at an elemental level. Ionically gated transistors harness diffusive mechanics to achieve continuous modulation of channel conductance at low-power, but require coupling of two disparate electronically and ionically active material sets. [6,7] Solutions based on drift-memristors are inherently disadvantaged due to digital-like abrupt switching transitions, which limit their plasticity. [8] Very recently, second-order drift memristors, [9,10] electrochemical metallization cells, [11] and diffusive memristors [8] have been engineered to approximate the biological Ca 2+ dynamics based on metal atom diffusion, thermal dissipation, [9] mobility decay, [12] and spontaneous nanoparticle formation, but often require additional nonvolatile elements in series for long-term memory storage. An ionic semiconductor which intimately combines rapid electronic transitions with slow drift-diffusive ionic kinetics will enable dynamic tuning of metastable memristive conductance states, allowing efficient emulation of synaptic characteristics and catering for novel low-power architectures that exploit electronic properties of the semiconductor.Emulation of brain-like signal processing is the foundation for development of efficient learning circuitry, but few devices offer the tunable conductance range necessary for mimicking spatiotemporal plasticity in biological synapses. An ionic semiconductor which couples electronic transitions with drift-diffusive ionic kinetics would enable energy-efficient analog-like switching of metastable conductance states. Here, ionic-electronic coupling in halide perovskite semiconductors is utilized to create memristive synapses with a dynamic continuous transition of conductance states. Coexistence of carrier injection barriers and ion migration in the perovskite films defines the degree of synaptic plasticity, more notable for the larger organic ammonium and formamidinium cations than the inorganic cesium counterpart. Optimized pulsing schemes facilitates a balanced interplay of short-and longterm plasticity rules like paired-pulse facilitation and spike-time-dependent plasticity, cardinal for learning and computing. Trained as a memory array, halide perovskite synapses demonstrate reconfigurability, learning, forgetting, and fault tolerance analogous to the human brain. Network-level simulations of unsupervised learning of handwritten digit images utilizing experimentally derived device parameters, validates the utility of these memristors for energy-efficient neuromorphic computation, paving way for novel ionotronic neuromorphic architectures with halide perovskites as the active material. Artificial SynapsesThe ORCID identification number(s) for the author(s) of this article can be found under https://doi.C...

Ultra low power sensor node for wireless health monitoring system was designed and implemented in 0.18-µm CMOS. The sensor node functions as an interface circuit to both sensor and RF transceiver. The sensor node consists of an amplifier, an ADC (analog-to-digital converter) as well as digital system. The digital system is embedded with DSP (digital signal processing) for heart rate processing and RF interface for transceiver. The sensor node draws a total current of 7.5-µA from a 0.9-V single supply. The decoding scheme in the RF transceiver can tolerate up to ±22% clock frequency variation.

Condition monitoring is one of the routine tasks in all major process industries. The mechanical parts such as a motor, gear, bearings are the major components of a process industry and any fault in them may cause a total shutdown of the whole process, which may result in serious losses. Therefore, it is very crucial to predict any approaching defects before its occurrence. Several methods exist for this purpose and many research are being carried out for better and efficient models. However, most of them are based on the processing of raw sensor signals, which is tedious and expensive. Recently, there has been an increase in the feature based condition monitoring, where only the useful features are extracted from the raw signals and interpreted for the prediction of the fault. Most of these are handcrafted features, where these are manually obtained based on the nature of the raw data. This of course requires the prior knowledge of the nature of data and related processes. This limits the feature extraction process. However, recent development in the autoencoder based feature extraction method provides an alternative to the traditional handcrafted approaches; however, they have mostly been confined in the area of image and audio processing. In this work, we have developed an automated feature extraction method for on-line condition monitoring based on the stack of the traditional autoencoder and an on-line sequential extreme learning machine(OSELM) network. The performance of this method is comparable to that of the traditional feature extraction approaches. The method can achieve 100% detection accuracy for determining the bearing health states of NASA bearing dataset. The simple design of this method is promising for the easy hardware implementation of Internet of Things(IoT) based prognostics solutions.

No abstract

No abstract

In Industry 4.0, predictive maintenance (PdM) is one of the most important applications pertaining to the Internet of Things (IoT). Machine learning is used to predict the possible failure of a machine before the actual event occurs. However, main challenges in PdM are: (a) lack of enough data from failing machines, and (b) paucity of power and bandwidth to transmit sensor data to cloud throughout the lifetime of the machine. Alternatively, edge computing approaches reduce data transmission and consume low energy. In this paper, we propose Anomaly Detection based Power Saving (ADEPOS) scheme using approximate computing through the lifetime of the machine. In the beginning of the machine's life, low accuracy computations are used when machine is healthy. However, on detection of anomalies as time progresses, system is switched to higher accuracy modes. We show using the NASA bearing dataset that using ADEPOS, we need 8.8X less neurons on average and based on post-layout results, the resultant energy savings are 6.4-6.65X. CCS CONCEPTS• Computing methodologies → Ensemble methods; Anomaly detection;

No abstract