Improved neural network tomography by initial learning with coarse reconstructed image

2016 ◽  
Vol 172 ◽  
pp. 399-404
Author(s):  
Masaru Teranishi
Keyword(s):  
Neural Network ◽  
Reconstructed Image ◽  
Network Tomography ◽  
Initial Learning

scholarly journals Eigenstate extraction with neural-network tomography

2020 ◽  
Vol 102 (2) ◽  
Author(s):  
Abhijeet Melkani ◽  
Clemens Gneiting ◽  
Franco Nori
Keyword(s):  
Neural Network ◽  
Network Tomography

scholarly journals Deep Convolutional Neural Network for Rice Density Prescription Map at Ripening Stage Using Unmanned Aerial Vehicle-Based Remotely Sensed Images

2021 ◽  
Vol 14 (1) ◽  
pp. 46
Author(s):  
Lele Wei ◽  
Yusen Luo ◽  
Lizhang Xu ◽  
Qian Zhang ◽  
Qibing Cai ◽  
...  
Keyword(s):  
Neural Network ◽  
Unmanned Aerial Vehicle ◽  
Severe Infection ◽  
Batch Size ◽  
Kriging Interpolation ◽  
Support Vector ◽  
Health States ◽  
Initial Learning ◽  
Wide Range ◽  
Aerial Vehicle

In this paper, UAV (unmanned aerial vehicle, DJI Phantom4RTK) and YOLOv4 (You Only Look Once) target detection deep neural network methods were employed to collected mature rice images and detect rice ears to produce a rice density prescription map. The YOLOv4 model was used for rice ear quick detection of rice images captured by a UAV. The Kriging interpolation algorithm was used in ArcGIS to make rice density prescription maps. Mature rice images collected by a UAV were marked manually and used to build the training and testing datasets. The resolution of the images was 300 × 300 pixels. The batch size was 2, and the initial learning rate was 0.01, and the mean average precision (mAP) of the best trained model was 98.84%. Exceptionally, the network ability to detect rice in different health states was also studied with a mAP of 95.42% in the no infection rice images set, 98.84% in the mild infection rice images set, 94.35% in the moderate infection rice images set, and 93.36% in the severe infection rice images set. According to the severity of rice sheath blight, which can cause rice leaves to wither and turn yellow, the blighted grain percentage increased and the thousand-grain weight decreased, the rice images were divided into these four infection levels. The ability of the network model (R2 = 0.844) was compared with traditional image processing segmentation methods (R2 = 0.396) based on color and morphology features and machine learning image segmentation method (Support Vector Machine, SVM R2 = 0.0817, and K-means R2 = 0.1949) for rice ear counting. The results highlight that the CNN has excellent robustness, and can generate a wide range of rice density prescription maps.

scholarly journals Learning Rate Scheduling Policies

2019 ◽  
Vol 9 (1) ◽  
pp. 3641-3644
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Learning Rate ◽  
Training Algorithms ◽  
Training Process ◽  
Learning Capability ◽  
Scheduling Policy ◽  
Learning Rates ◽  
Initial Learning ◽  
Rate Scheduling

With the availability of high processing capability hardwares at less expensive prices, it is possible to successfully train multi-layered neural networks. Since then, several training algorithms have been developed, from algorithms which are statically initialized to algorithms which adaptively change. It is observed that to improve the training process of neural networks, the hyper-parameters are to be fine tuned. Learning Rate, Decay rate, number of epochs, number of hidden layers and number of neurons in the network are some of the hyper-parameters in concern. Of these, the Learning rate plays a crucial role in enhancing the learning capability of the network. Learning rate is the value by which the weights are adjusted in a neural network with respect to the gradient descending towards the expected optimum value. This paper discusses four types of learning rate scheduling which helps to find the best learning rates in less number of epochs. Following these scheduling methods, facilitates to find better initial learning rate value and step-wise updation during the later phase of the training process. In addition the discussed learning rate schedules are demonstrated using COIL-100, Caltech-101 and CIFAR-10 datasets trained on ResNet. The performance is evaluated using the metrics, Precision, Recall and F1-Score. The results analysis show that, depending on the nature of the dataset, the performance of the Learning Rate Scheduling policy varies. Hence the choice of the scheduling policy to train a neural network is made, based on the data.

Convolutional Neural Network Using Bayesian Optimization for Laser Welding Tailor Rolled Blanks Penetration Detection

2019 ◽  
Author(s):  
Zhehao Zhang ◽  
Yi Zhang ◽  
Feng Luo ◽  
Jie Li ◽  
Cheng Lu ◽  
...  
Keyword(s):  
Neural Network ◽  
Laser Welding ◽  
Convolutional Neural Network ◽  
Bayesian Optimization ◽  
Welding Parameters ◽  
Test Accuracy ◽  
Initial Learning ◽  
Tailor Rolled Blanks ◽  
Set Up ◽  
Best Parameters

Abstract Convolutional neural network (CNN) is an efficient and robust method which can accurately detect the Tailor Rolled Blank laser welding pool penetration status. To select proper hyperparameters and optimization of CNN model are black box problem. In this paper, an innovative method based on CNN to identify the penetration status of the weld pool during laser welding was introduced. A coaxial monitoring platform is set up, as well as two-class, three-class and four-class datasets are created for training and validating the CNN. The Bayesian Optimization (BO) method is used to optimize hyper-parameters which are adopted for training CNN model, determine the best parameters of depth, initial learning rate, momentum and L2 regularization. The results show that using BO method leads to accuracy improvement compared with the CNN model trained from scratch with default hyper-parameters, hence it can effectively solve the problem that the hyper-parameters of CNN are difficult to adjust. Under various laser welding parameters, high-accuracy detection of penetration status can be acquired with the test accuracy of four-class reaching 95.2%, which slightly lower than the test accuracy of the three-class and two-class.

Neural network tomography: Network replication from output surface geometry

2011 ◽  
Vol 24 (5) ◽  
pp. 484-492 ◽  
Author(s):  
Rupert C.J. Minnett ◽  
Andrew T. Smith ◽  
William C. Lennon ◽  
Robert Hecht-Nielsen
Keyword(s):  
Neural Network ◽  
Network Tomography ◽  
Surface Geometry ◽  
Output Surface

scholarly journals Effective lossy and lossless color image compression with Multilayer Perceptron

2018 ◽  
Vol 7 (2.22) ◽  
pp. 9
Author(s):  
Dr PL. Chithra ◽  
A Christoper Tamilmathi
Keyword(s):  
Neural Network ◽  
Image Compression ◽  
Multilayer Perceptron ◽  
Color Image ◽  
Compression Algorithm ◽  
Convergence Time ◽  
Reconstructed Image ◽  
Parallel Structure ◽  
Discrete Wavelet ◽  
Color Image Compression

This paper presents the effective lossy and lossless color image compression algorithm with Multilayer perceptron. The parallel structure of neural network and the concept of image compression combined to yield a better reconstructed image with constant bit rate and less computation complexity. Original color image component has been divided into 8x8 blocks. The discrete cosine transform (DCT) applied on each block for lossy compression or discrete wavelet transform (DWT) applied for lossless image compression. The output coefficient values have been normalized by using mod function. These normalized vectors have been passed to Multilayer Perceptron (MLP). This proposed method implements the Back propagation neural network (BPNN) which is suitable for compression process with less convergence time. Performance of the proposed compression work is evaluated based on three ways. First one compared the performance of lossy and lossless compression with BPNN. Second one, evaluated based on different sized hidden layers and proved that increased neurons in hidden layer has been preserved the brightness of an image. Third, the evaluation based on three different types of activation function and the result shows that each function has its own merit. Proposed algorithm has been competed with existing JPEG color compression algorithm based on PSNR measurement. Resultant value denotes that the proposed method well performed to produce the better reconstructed image with PSNR value approximately increased by 21.62%. 

Autofluorescence spectroscopy of oral leukoplakia using an artificial neural network

2000 ◽  
Vol 25 (4) ◽  
pp. 325-325
Author(s):  
J.L.N. Roodenburg ◽  
H.J. Van Staveren ◽  
N.L.P. Van Veen ◽  
O.C. Speelman ◽  
J.M. Nauta ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Oral Leukoplakia ◽  
Autofluorescence Spectroscopy ◽  
Artificial Neural
Sign in / Sign up

Export Citation Format

Share Document