Our focus in this research is on the use of deep learning approaches for human activity recognition (HAR) scenario, in which inputs are multichannel time series signals acquired from a set of body-worn inertial sensors and outputs are predefined human activities. Here, we present a feature learning method that deploys convolutional neural networks (CNN) to automate feature learning from the raw inputs in a systematic way. The influence of various important hyper-parameters such as number of convolutional layers and kernel size on the performance of CNN was monitored. Experimental results indicate that CNNs achieved significant speed-up in computing and deciding the final class and marginal improvement in overall classification accuracy compared to the baseline models such as Support Vector Machines and Multi-layer perceptron networks.

Edge computing aims to integrate computing into everyday settings, enabling the system to be context-aware and private to the user. With the increasing success and popularity of deep learning methods, there is an increased demand to leverage these techniques in mobile and wearable computing scenarios. In this paper, we present an assessment of a deep human activity recognition system’s memory and execution time requirements, when implemented on a mid-range smartphone class hardware and the memory implications for embedded hardware. This paper presents the design of a convolutional neural network (CNN) in the context of human activity recognition scenario. Here, layers of CNN automate the feature learning and the influence of various hyper-parameters such as the number of filters and filter size on the performance of CNN. The proposed CNN showed increased robustness with better capability of detecting activities with temporal dependence compared to models using statistical machine learning techniques. The model obtained an accuracy of 96.4% in a five-class static and dynamic activity recognition scenario. We calculated the proposed model memory consumption and execution time requirements needed for using it on a mid-range smartphone. Per-channel quantization of weights and per-layer quantization of activation to 8-bits of precision post-training produces classification accuracy within 2% of floating-point networks for dense, convolutional neural network architecture. Almost all the size and execution time reduction in the optimized model was achieved due to weight quantization. We achieved more than four times reduction in model size when optimized to 8-bit, which ensured a feasible model capable of fast on-device inference.

While a number of literature reviews have been published in recent times on the applications of optical fibre sensors in smart structures research, these have mainly focused on the use of conventional glass‐based fibres. The availability of inexpensive, rugged, and large‐core plastic‐based optical fibres has resulted in growing interest amongst researchers in their use as low‐cost sensors in a variety of areas including chemical sensing, biomedicine, and the measurement of a range of physical parameters. The sensing principles used in plastic optical fibres are often similar to those developed in glass‐based fibres, but the advantages associated with plastic fibres render them attractive as an alternative to conventional glass fibres, and their ability to detect and measure physical parameters such as strain, stress, load, temperature, displacement, and pressure makes them suitable for structural health monitoring (SHM) applications. Increasingly their applications as sensors in the field of structural engineering are being studied and reported in literature. This article will provide a concise review of the applications of plastic optical fibre sensors for monitoring the integrity of engineering structures in the context of SHM.

Femtosecond, subablation threshold photomodification of poly(methyl methacrylate) (PMMA) at $387\mathrm{nm}$ is explored to enable fabrication of optical components. Volatile fragment analysis (thermal desorption gas chromatography–mass spectrometry) and molecular weight distribution monitoring (size exclusion chromatography) suggest photochemical modification, involving direct cleavage of the polymer backbone and propagation via chain unzipping under formation of monomers, similar to the pyrolytic degradation of PMMA. Waveguides were produced in undoped, clinical-grade PMMA, showing an increased refractive index in the laser focal region $(\mathrm{\Delta }{n}_{\max }=4\times {10}^{-3})$.