A Novel Method for Measuring the Color of Edible Oil on the Lovibond Scale Based on Spectral Detection and Convolutional Neural Network

2018 ◽  
Vol 61 (3) ◽  
pp. 839-847 ◽  
Author(s):  
Chi Zhang ◽  
Hao Dang ◽  
Xiaoguang Zhou ◽  
Huiling Zhou ◽  
Digvir S. Jayas
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Transmission Spectrum ◽  
Maximum Error ◽  
Edible Oil ◽  
Visible Range ◽  
Average Error ◽  
Logarithmic Method ◽  
Spectral Detection ◽  
Lovibond Scale

Abstract. A fast, high-precision method for measuring the color of edible oil on the Lovibond scale was developed and validated. It involves two components: spectral detection and data processing. The former was used for measuring the edible oil’s transmission spectrum in the visible range. The latter included a logarithmic method and a convolutional neural network (CNN) for calculating the color value from the transmission spectrum. The logarithmic method converted the multiplicative combination of spectra to an additive combination, which greatly improved the performance. A CNN with three convolutional layers was developed using Tensorflow. Validation tests of the method using ten different oil types showed a maximum error of 0.5, average error of 0.32, and error variance of 0.04. Thus, the proposed method can meet the needs of the edible oil industry, and it has great application potential. Keywords: CNN, Color of edible oil, Convolutional neural network, Lovibond scale, Spectral detection.

scholarly journals Generating Point Cloud from Measurements and Shapes Based on Convolutional Neural Network: An Application for Building 3D Human Model

2019 ◽  
Vol 2019 ◽  
pp. 1-15 ◽  
Author(s):  
Mau Tung Nguyen ◽  
Thanh Vu Dang ◽  
Minh Kieu Tran Thi ◽  
Pham The Bao
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Point Cloud ◽  
Data Representation ◽  
Human Model ◽  
Average Error ◽  
Shape Information ◽  
Hierarchical Learning ◽  
3D Data ◽  
3D Shapes

It has been widely known that 3D shape models are comprehensively parameterized using point cloud and meshes. The point cloud particularly is much simpler to handle compared with meshes, and it also contains the shape information of a 3D model. In this paper, we would like to introduce our new method to generating the 3D point cloud from a set of crucial measurements and shapes of importance positions. In order to find the correspondence between shapes and measurements, we introduced a method of representing 3D data called slice structure. A Neural Networks-based hierarchical learning model is presented to be compatible with the data representation. Primary slices are generated by matching the measurements set before the whole point cloud tuned by Convolutional Neural Network. We conducted the experiment on a 3D human dataset which contains 1706 examples. Our results demonstrate the effectiveness of the proposed framework with the average error 7.72% and fine visualization. This study indicates that paying more attention to local features is worthwhile when dealing with 3D shapes.

scholarly journals Face Recognition Using the Convolutional Neural Network for Barrier Gate System

2021 ◽  
Vol 15 (10) ◽  
pp. 138
Author(s):  
Mochammad Langgeng Prasetyo ◽  
Achmad Teguh Wibowo ◽  
Mujib Ridwan ◽  
Mohammad Khusnu Milad ◽  
Sirajul Arifin ◽  
...  
Keyword(s):  
Neural Network ◽  
Face Recognition ◽  
Convolutional Neural Network ◽  
Real Time ◽  
Recognition System ◽  
Average Error ◽  
The Real ◽  
The Face ◽  
Gate System ◽  
Recognition Technique

The implementation of face recognition technique using CCTV is able to prevent unauthorized person enter the gate. Face recognition can be used for authentication, which can be implemented for preventing of criminal incidents. This re-search proposed a face recognition system using convolutional neural network to open and close the real-time barrier gate. The process consists of a convolutional layer, pooling layer, max pooling, flattening, and fully connected layer for detecting a face. The information was sent to the microcontroller using Internet of Thing (IoT) for controlling the barrier gate. The face recognition results are used to open or close the gate in the real time. The experimental results obtained average error rate of 0.320 and the accuracy of success rate is about 93.3%. The average response time required by microcontroller is about 0.562ms. The simulation result show that the face recognition technique using CNN is highly recommended to be implemented in barrier gate system.

scholarly journals Mango Grading System Based on Optimized Convolutional Neural Network

2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Bin Zheng ◽  
Tao Huang
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Small Sample ◽  
Parameters Optimization ◽  
Average Error ◽  
Grading System ◽  
Data Set ◽  
Operation Speed ◽  
Sample Data

In order to achieve the accuracy of mango grading, a mango grading system was designed by using the deep learning method. The system mainly includes CCD camera image acquisition, image preprocessing, model training, and model evaluation. Aiming at the traditional deep learning, neural network training needs a large number of sample data sets; a convolutional neural network is proposed to realize the efficient grading of mangoes through the continuous adjustment and optimization of super-parameters and batch size. The ultra-lightweight SqueezeNet related algorithm is introduced. Compared with AlexNet and other related algorithms with the same accuracy level, it has the advantages of small model scale and fast operation speed. The experimental results show that the convolutional neural network model after super-parameters optimization and adjustment has excellent effect on deep learning image processing of small sample data set. Two hundred thirty-four Jinhuang mangoes of Panzhihua were picked in the natural environment and tested. The analysis results can meet the requirements of the agricultural industry standard of the People’s Republic of China—mango and mango grade specification. At the same time, the average accuracy rate was 97.37%, the average error rate was 2.63%, and the average loss value of the model was 0.44. The processing time of an original image with a resolution of 500 × 374 was only 2.57 milliseconds. This method has important theoretical and application value and can provide a powerful means for mango automatic grading.

scholarly journals A High-Precision Implementation of the Sigmoid Activation Function for Computing-in-Memory Architecture

Micromachines ◽  
2021 ◽  
Vol 12 (10) ◽  
pp. 1183
Author(s):  
Siqiu Xu ◽  
Xi Li ◽  
Chenchen Xie ◽  
Houpeng Chen ◽  
Cheng Chen ◽  
...  
Keyword(s):  
Neural Network ◽  
High Precision ◽  
Maximum Error ◽  
Activation Function ◽  
Average Error ◽  
Network Computing ◽  
Von Neumann ◽  
Non Linear ◽  
Sigmoid Activation Function ◽  
The Ideal

Computing-In-Memory (CIM), based on non-von Neumann architecture, has lately received significant attention due to its lower overhead in delay and higher energy efficiency in convolutional and fully-connected neural network computing. Growing works have given the priority to researching the array of memory and peripheral circuits to achieve multiply-and-accumulate (MAC) operation, but not enough attention has been paid to the high-precision hardware implementation of non-linear layers up to now, which still causes time overhead and power consumption. Sigmoid is a widely used non-linear activation function and most of its studies provided an approximation of the function expression rather than totally matched, inevitably leading to considerable error. To address this issue, we propose a high-precision circuit implementation of the sigmoid, matching the expression exactly for the first time. The simulation results with the SMIC 40 nm process suggest that the proposed circuit implemented high-precision sigmoid perfectly achieves the properties of the ideal sigmoid, showing the maximum error and average error between the proposed simulated sigmoid and ideal sigmoid is 2.74% and 0.21%, respectively. In addition, a multi-layer convolutional neural network based on CIM architecture employing the simulated high-precision sigmoid activation function verifies the similar recognition accuracy on the test database of handwritten digits compared to utilize the ideal sigmoid in software, with online training achieving 97.06% and with offline training achieving 97.74%.

Modeling Research on the Hysteresis Nonlinearity of the Piezoelectric Ceramics Micropositioning Staging

2014 ◽  
Vol 971-973 ◽  
pp. 98-102
Author(s):  
Gui Hua Yang
Keyword(s):  
Neural Network ◽  
Genetic Algorithm ◽  
Mathematical Model ◽  
Piezoelectric Actuator ◽  
Bp Neural Network ◽  
Maximum Error ◽  
Average Error ◽  
Online Modeling ◽  
Hysteresis Nonlinearity ◽  
Modeling Accuracy

It is difficult to obtain precise mathematical model with the traditional methods because of the hysteresis nonlinearity of piezoceramics, and it affects the displacement output accuracy of piezoelectric actuator. The paper proposes an online modeling technique combined with neural network and genetic algorithm (GA). It make the initial parameters of BP neural network be optimized, and so improves the modeling accuracy. Experimental results show that displacement maximum error is 71nm, and the average error is 26nm in the whole trip. It meets the nanopositioning accuracy requirements of piezoelectric staging .

scholarly journals Convolutional Neural Network Models Help Effectively Estimate Legume Coverage in Grass-Legume Mixed Swards

2022 ◽  
Vol 12 ◽  
Author(s):  
Ryo Fujiwara ◽  
Hiroyuki Nashida ◽  
Midori Fukushima ◽  
Naoya Suzuki ◽  
Hiroko Sato ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Efficient Estimation ◽  
Fine Tuning ◽  
Aerial Images ◽  
Mean Bias Error ◽  
Average Error ◽  
Bias Error ◽  
Neural Network Models ◽  
The Mean

Evaluation of the legume proportion in grass-legume mixed swards is necessary for breeding and for cultivation research of forage. For objective and time-efficient estimation of legume proportion, convolutional neural network (CNN) models were trained by fine-tuning the GoogLeNet to estimate the coverage of timothy (TY), white clover (WC), and background (Bg) on the unmanned aerial vehicle-based images. The accuracies of the CNN models trained on different datasets were compared using the mean bias error and the mean average error. The models predicted the coverage with small errors when the plots in the training datasets were similar to the target plots in terms of coverage rate. The models that are trained on datasets of multiple plots had smaller errors than those trained on datasets of a single plot. The CNN models estimated the WC coverage more precisely than they did to the TY and the Bg coverages. The correlation coefficients (r) of the measured coverage for aerial images vs. estimated coverage were 0.92–0.96, whereas those of the scored coverage by a breeder vs. estimated coverage were 0.76–0.93. These results indicate that CNN models are helpful in effectively estimating the legume coverage.

scholarly journals Automated Flood Depth Estimates from Online Traffic Sign Images: Explorations of a Convolutional Neural Network-Based Method

Sensors ◽  
2021 ◽  
Vol 21 (16) ◽  
pp. 5614
Author(s):  
Zhiqing Song ◽  
Ye Tuo
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Damage Control ◽  
Mirror Reflection ◽  
Average Error ◽  
Traffic Sign ◽  
Efficient Manner ◽  
Urban Flood ◽  
Depth Data ◽  
Flood Depth

Flood depth monitoring is crucial for flood warning systems and damage control, especially in the event of an urban flood. Existing gauge station data and remote sensing data still has limited spatial and temporal resolution and coverage. Therefore, to expand flood depth data source taking use of online image resources in an efficient manner, an automated, low-cost, and real-time working frame called FloodMask was developed to obtain flood depth from online images containing flooded traffic signs. The method was built on the deep learning framework of Mask R-CNN (regional convolutional neural network), trained by collected and manually annotated traffic sign images. Following further the proposed image processing frame, flood depth data were retrieved more efficiently than manual estimations. As the main results, the flood depth estimates from images (without any mirror reflection and other inference problems) have an average error of 0.11 m, when compared to human visual inspection measurements. This developed method can be further coupled with street CCTV cameras, social media photos, and on-board vehicle cameras to facilitate the development of a smart city with a prompt and efficient flood monitoring system. In future studies, distortion and mirror reflection should be tackled properly to increase the quality of the flood depth estimates.

A fuzzy neural network approach for modeling the growth kinetics of FeB and Fe2B layers during the boronizing process

2018 ◽  
Vol 106 (6) ◽  
pp. 603 ◽  
Author(s):  
Bendaoud Mebarek ◽  
Mourad Keddam
Keyword(s):  
Neural Network ◽  
Experimental Data ◽  
Fuzzy Neural Network ◽  
Treatment Time ◽  
Calculation Model ◽  
Average Error ◽  
Network Approach ◽  
Neural Network Approach ◽  
Fuzzy Neural ◽  
Kinetics Of

In this paper, we develop a boronizing process simulation model based on fuzzy neural network (FNN) approach for estimating the thickness of the FeB and Fe2B layers. The model represents a synthesis of two artificial intelligence techniques; the fuzzy logic and the neural network. Characteristics of the fuzzy neural network approach for the modelling of boronizing process are presented in this study. In order to validate the results of our calculation model, we have used the learning base of experimental data of the powder-pack boronizing of Fe-15Cr alloy in the temperature range from 800 to 1050 °C and for a treatment time ranging from 0.5 to 12 h. The obtained results show that it is possible to estimate the influence of different process parameters. Comparing the results obtained by the artificial neural network to experimental data, the average error generated from the fuzzy neural network was 3% for the FeB layer and 3.5% for the Fe2B layer. The results obtained from the fuzzy neural network approach are in agreement with the experimental data. Finally, the utilization of fuzzy neural network approach is well adapted for the boronizing kinetics of Fe-15Cr alloy.

CONVOLUTIONAL NEURAL NETWORK BASED ALGORITHM FOR CECUM ACHIEVEMENT CONFIRMATION

2020 ◽  
Author(s):  
S Kashin ◽  
D Zavyalov ◽  
A Rusakov ◽  
V Khryashchev ◽  
A Lebedev
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network
Sign in / Sign up

Export Citation Format

Share Document