In order to apply machine vision technology replacing human vision to identify the plant germplasm resources. This paper select 5 different types of Diospyros lotus seeds, 7 different appearance features and 6 color features were extracted by machine vision technology based on traditional identification method. One input, seven hidden layers and one output has been used for the multilayer perception (MLP) in our system. K-fold cross Validation was used for the modeling and classified of Diospyros lotus seeds. The results showed that the average identification rate of 5 types seeds was reached 91.8%, which indicated that the established seed model could be used as an effective method for the accurate classification of the seeds.

Machine learning for Non-Destructive Evaluation (NDE) has the potential to bring significant improvements in defect characterization accuracy due to its effectiveness in pattern recognition problems. However, the application of modern machine learning methods to NDE has been obstructed by the scarcity of real defect data to train on. This paper demonstrates how an efficient, hybrid finite element and ray-based simulation can be used to train a Convolutional Neural Network (CNN) to characterize real defects. To demonstrate this methodology, an inline-pipe inspection application is considered. This uses four plane wave images from two arrays, and is applied to the characterization of cracks of length 1-5 mm and inclined at angles of up to 20° from the vertical. A standard image-based sizing technique, the 6 dB drop method, is used as a comparison point. For the 6 dB drop method the average absolute error in length and angle prediction is ±1.1 mm, ±8.6° while the CNN is almost four times more accurate at ±0.29 mm, ±2.9°. To demonstrate the adaptability of the deep-learning approach, an error in sound speed estimation is included in the training and test set. With a maximum error of 10% in shear and longitudinal sound speed the 6 dB drop method has an average error of ±1.5 mm, ±12° while the CNN has ±0.45 mm, ±3.0°. This demonstrates far superior crack characterization accuracy by using deep learning rather than traditional image-based sizing.

Abstract-Increasing the number of sensors in a gas identification system generally improves its performance as this will add extra features for analysis. However, this affects the computational complexity, especially if the identification algorithm is to be implemented on a hardware platform. Therefore feature reduction is required to extract the most important information from the sensors for processing. In this paper, linear discriminant analysis (LDA) and principal component analysis (PCA) based feature reduction algorithms have been analyzed using data obtained from two different types of gas sensors i.e. seven commercial Figaro sensors and in-house fabricated 4x4 tin-oxide gas array sensor . A decision tree (DT) based classifier is used to examine the performance of both PCA and LDA approaches. The software implementation is carried out in MATLAB and the hardware implementation is performed using the Zynq system on chip (SoC) platform. It has been found that with the 4x4 array sensor, two discriminant function (DF) of LDA provides 3.3% better classification than five PCA components, while for the seven Figaro sensors two principal components (PC) and one DF show the same performances. The hardware implementation results on the programmable logic of the Zynq SoC shows that LDA outperforms PCA by using 50% less resources as well as by being 11% faster with a maximum running frequency of 122 MHz.

Northumbria University has developed Northumbria Research Link (NRL) to enable users to access the University's research output. Copyright © and moral rights for items on NRL are retained by the individual author(s) and/or other copyright owners. Single copies of full items can be reproduced, displayed or performed, and given to third parties in any format or medium for personal research or study, educational, or not-for-profit purposes without prior permission or charge, provided the authors, title and full bibliographic details are given, as well as a hyperlink and/or URL to the original metadata page. The content must not be changed in any way. Full items must not be sold commercially in any format or medium without formal permission of the copyright holder. The full policy is available online: http://nrl.northumbria.ac.uk/policies.html This document may differ from the final, published version of the research and has been made available online in accordance with publisher policies. To read and/or cite from the published version of the research, please visit the publisher's website (a subscription may be required.) Abstract-Connected health is a technology that associates medical devices, security devices and communication technologies. It enables patients to be monitored and treated remotely from their home. Patients' data and medical records within a connected health system should be securely stored and transmitted for further analysis and diagnosis. This paper presents a set of security solutions that can be deployed in a connected health environment, which includes the advanced encryption standard (AES) algorithm and electrocardiogram (ECG) identification system. Efficient System-on-Chip (SoC) implementations for the proposed algorithms have been carried out on the Xilinx ZC702 prototyping board. The Achieved hardware implementation results have shown that the proposed AES and ECG identification based system met the real-time requirements and outperformed existing field programmable gate array (FPGA)-based systems in different key performance metrics such as processing time, hardware resources and power consumption. The proposed systems can process an ECG sample in 10.71 ms and uses only 30% of the available hardware resources with a power consumption of 107 mW.Keywords-Advanced encryption standard (AES), electrocardiogram (ECG) encryption and identification, field programmable gate array (FPGA), Zynq7 system on chip (SoC).

No abstract

Fall detection is a major problem in healthcare systems, especially for elderly people who are the most vulnerable. It is important to design and implement not only an accurate fall detection system (FDS) but also a system with a real-time response. The achievement of high accuracy and fast response time together allows the development of a system that helps saving lives, time and money in healthcare industry. This paper presents the design, simulation and implementation of a novel FDS using the Shimmer wearable sensor. The discrete wavelet transform (DWT) is applied for preprocessing the data coming from the Shimmer platform, principal component analysis (PCA) is used for dimensionality reduction and feature extraction and finally, a binary decision tree (DT) is utilized for classification purpose. The system is simulated in MATLAB prior to the implementation on the Zynq system-on-chip (SoC) for hardware acceleration. DWT is executed on the processing system (PS) of the Zynq platform in a software manner while PCA and DT are both implemented on the programmable logic (PL) for hardware acceleration. PCA and DT are developed in C and synthesized in Vivado high level synthesis (HLS) tool to transform the C based designed into a register transfer level (RTL) implementation. Various optimization techniques are explored in Vivado HLS. The performance of the FDS in terms of accuracy of the classifier is 88.4% while the overall resources used in PL of the Zynq vary between 2% and 23% depending on the running frequency and optimization technique used.

This paper presents the design of an interactive graphical user interface (GUI) to monitor and quantify a developed electronic nose (EN) platform for gas identification. To this end, an EN system has been implemented using a multi-sensing embedded platform comprised of a data acquisition unit, an RFID module and a signal processing unit. The gas data are collected using two different types of gas sensors, namely, seven commercial Figaro sensors and in-house fabricated 4 × 4 tin-oxide gas array sensor. The collected gas data are processed for identification by means of dimensionality reduction algorithms and classification techniques where the software implementation and the quantification of these algorithms have been carried out. Subsequently, the GUI was designed to enable several operations. The GUI allows the user to visualize the sensors responses for any selected gas at any point of the acquisition process as well as visualizing the data distribution. Beside, it provides an easy approach to evaluate the EN system performance in terms of data identification and execution time by computing the classification accuracy using a 10-fold cross validation technique. Furthermore, the GUI, which is freely distributed, grants the users the privilege to upload other types of data to enable different pattern recognition applications.

No abstract