Combination of hyperspectral imaging and entropy weight method for the comprehensive assessment of antioxidant enzyme activity in Tan mutton.

The antioxidant enzymes play the crucial role in inhibiting mutton spoilage. In this study, visible near-infrared (Vis-NIR) hyperspectral imaging (HSI) combined with entropy weight method (EWM) was developed for the first time to evaluate the antioxidant properties of Tan mutton. The comprehensive index of antioxidant enzymes (AECI) consisting of peroxidase (49.34%), catalase (37.97%) and superoxidase (12.69%) was constructed by the EWM. Partial least squares regression, least squares support vector machine and artificial neural networks (ANN) were developed based on characteristic wavelengths extracted by successful projections algorithm, uninformative variable selection, iteratively retains informative variables (IRIV), regression coefficient and competitive adaptive reweighted sampling (CARS). The textural features (TF) were extracted by the gray level co-occurrence matrix and fused with the spectral data to establish models. Visualization of the changes in antioxidant enzyme activity was constructed from the optimal model. In addition, two-dimensional correlation spectra (2D-COS) with AECI as a perturbation variable was used to identify spectral features, revealing chemical bond changes order under the characteristic peaks at 612-799-473-708-559 nm. The results showed that the IRIV-CARS-TF-ANN model performed the best, with prediction set coefficient of determination (RP2) of 0.8813, which improved 2.12%, 1.11% and 2.77% over the RP2 of full band, IRIV and IRIV-CARS, respectively. It was suggested that fusion data of HSI may effectively predict the activity of antioxidant enzymes in Tan mutton.

A Low-Cost End-to-End sEMG-Based Gait Sub-Phase Recognition System.

As surface electromyogram (sEMG) signals have the ability to detect human movement intention, they are commonly used to be control inputs. However, gait sub-phase classification typically requires monotonous manual labeling process, and commercial sEMG acquisition devices are quite bulky and expensive, thus current sEMG-based gait sub-phase recognition systems are complex and have poor portability. This study presents a low-cost but effective end-to-end sEMG-based gait sub-phase recognition system, which contains a wireless multi-channel signal acquisition device simultaneously collecting sEMG of thigh muscles and plantar pressure signals, and a novel neural network-based sEMG signal classifier combining long-short term memory (LSTM) with multilayer perceptron (MLP). We evaluated the system with subjects walking under five conditions: flat terrain at 5 km/h, flat terrain at 3 km/h, 20 kg backpack at 5 km/h, 20 kg shoulder bag at 5 km/h and 15° slope at 5 km/h. Experimental results show that the proposed method achieved average classification accuracies of 94.10%, 87.25%, 90.71%, 94.02%, and 87.87%, respectively, which were significantly higher than existing recognition methods. Additionally, the proposed system had a good real-time performance with low average inference time in the range of 3.25 ~ 3.31 ms.