scholarly journals An Intelligent Approach to Recognizing Human Movements Based on a Wearable Device

2021 ◽  
Author(s):  
Anastasya Grecheneva ◽  
Nikolay Dorofeev ◽  
Maxim Goryachev
Keyword(s):  
Neural Network ◽  
Basic Structure ◽  
Activation Function ◽  
Training Sample ◽  
Wearable Device ◽  
Output Layer ◽  
The Neural Network ◽  
Human Movements ◽  
Hidden Layer ◽  
Propagation Network

n this paper, we consider the possibility of distinguishing the movements of a person and people by their gait based on data obtained from the accelerometer of a wearable device. A mobile phone was used as a wearable device. The paper considers the features of recognizing human movements based on a wearable device. A recognition algorithm based on a neural network with preliminary data processing and correlation analysis is proposed. The volume of the training sample consisted of 32 subjects with various physiological characteristics. The sample size in the subgroup of four people ranged from 2000 to 3000 movements. The main motor patterns for classification were the movements performed when walking in a straight line and stairs with a load (a bag with a laptop weighing 3.5 kg) and without it. The direct propagation network is chosen as the basic structure for the neural network. The neural network has 260 input neurons, 100 neurons in one hidden layer, and 4 neurons in the output layer. When training the neural network, the gradient reverse descent function was used. Cross- entropy was used as an optimization criterion. The activation function of the hidden layer was a sigmoid, and the output layer was a normalized exponential function. The presented algorithm makes it possible to distinguish between subjects when performing different movements in more than 90% of cases. The practical application of the results of the work is relevant for automated information systems of the medical, law enforcement and banking sectors.

scholarly journals Perancangan Model Jaringan Syaraf Tiruan Propagasi Balik Untuk Mengestimasi Curah Hujan

2012 ◽  
Vol 9 (2) ◽  
Author(s):  
Elohansen Padang
Keyword(s):  
Neural Network ◽  
Gradient Descent ◽  
Back Propagation ◽  
Activation Function ◽  
Back Propagation Neural Network ◽  
Rainfall Data ◽  
Training Method ◽  
Output Layer ◽  
Input Layer ◽  
Hidden Layer

This research was conducted to investigate the ability of backpropagation artificial neural network in estimating rainfall. Neural network used consists of input layer, 2 hidden layers and output layer. Input layer consists of 12 neurons that represent each input; first hidden layer consists of 12 neurons with activation function tansig, while the second hidden layer consists of 24 neurons with activation function logsig. Output layer consists of 1 neuron with activation function purelin. Training method used is the method of gradient descent with momentum. Training method used is the method of gradient descent with momentum. Learning rate and momentum parameters defined respectively by 0.1 and 0.5. To evaluate the performance of the network model to recognize patterns of rainfall data is used in Biak city rainfall data from January 1997 - December 2008 (12 years). This data is divided into 2 parts, namely training and testing data using rainfall data from January 1997-December 2005 and data estimation using rainfall data from January 2006-December 2008. From the results of this study concluded that rainfall patterns Biak town can be recognized quite well by the model of back propagation neural network. The test results and estimates of the model results testing the value of R = 0.8119, R estimate = 0.53801, MAPE test = 0.1629, and MAPE estimate = 0.6813.

scholarly journals Determining Hidden Neurons with Variant Experiments in Multilayer Perception using Machine Learning Neural Networks

2019 ◽  
Vol 8 (9) ◽  
pp. 2725-2729
Keyword(s):  
Neural Network ◽  
Adaptive Learning ◽  
Intermediate Layer ◽  
Activation Function ◽  
Vital Role ◽  
Learning Ability ◽  
Output Layer ◽  
Hidden Layer ◽  
Hidden Neurons

Neural network has broadly been employed in various fields for its efficacy and its superiority. Excellence results provided can be directly provided in various analyses. Besides the variant types of neural network, Multi layer perceptron plays a vital role for its adaptive learning ability. The network makes prediction based on learn of training set. Neural has three layers then the layers are the Input, Hidden and the Output Layers. There may be more than one hidden layer but there is one input and output layer. The hidden or the intermediate layer is considered as an engine of the complete network as it has the non linear activation function and they has a sensational domination in the finishing result . The amount of neurons in three layers determines the excellence of the network. The neuron in the input and the output layer is fixed as per the dataset while for the intermediate layer it is fixed by the user in random. Increase in neuron cause over-fitting while decrease cause under fitting and these assumptions have a great impact in the final outcome. This paper discusses the existing approaches for fixing the hidden neurons and proposes a method to fix the neurons in the intermediate layer and analyse the quality of the group. The proposed procedure has variant approaches to determine the hidden neuron and they are compared. The experiment is done in WEKA and the accuracy is checked with measures.

scholarly journals Application of a multilayer perceptron artificial neural network for identification of peach cultivars based on physical characteristics

PeerJ ◽  
2021 ◽  
Vol 9 ◽  
pp. e11529
Author(s):  
Adel M. Al-Saif ◽  
Mahmoud Abdel-Sattar ◽  
Abdulwahed M. Aboukarima ◽  
Dalia H. Eshra
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Multilayer Perceptron ◽  
Activation Function ◽  
Cross Entropy ◽  
Output Layer ◽  
Entropy Error ◽  
Artificial Neural ◽  
The Cross ◽  
Hidden Layer

In the fresh fruit industry, identification of fruit cultivars and fruit quality is of vital importance. In the current study, nine peach cultivars (Dixon, Early Grande, Flordaprince, Flordastar, Flordaglo, Florda 834, TropicSnow, Desertred, and Swelling) were evaluated for differences in skin color, firmness, and size. Additionally, a multilayer perceptron (MLP) artificial neural network was applied for identification of the cultivars according to these attributes. The MLP was trained with an input layer including six input nodes, a single hidden layer with six hidden nodes, and an output layer with nine output nodes. A hyperbolic tangent activation function was used in the hidden layer and the cross entropy error was given because the softmax activation function was functional to the output layer. Results showed that the cross entropy error was 0.165. The peach identification process was significantly affected by the following variables in order of contribution (normalized importance): polar diameter (100%), L∗ (89.0), b∗ (88.0%), a∗ (78.5%), firmness (71.3%), and cross diameter (37.5.3%). The MLP was found to be a viable method of peach cultivar identification and classification because few identifying attributes were required and an overall classification accuracy of 100% was achieved in the testing phase. Measurements and quantitative discrimination of peach properties are provided in this research; these data may help enhance the processing efficiency and quality of processed peaches.

scholarly journals Automatic colorization of digital halftone images using neural networks

2019 ◽  
Author(s):  
M. E. Serdyuk ◽  
S. F. Syryk ◽  
O. O. Sokol
Keyword(s):  
Neural Network ◽  
Film Industry ◽  
Activation Function ◽  
Training Sample ◽  
Software System ◽  
Network Training ◽  
The Neural Network ◽  
Fully Automatic ◽  
Images Processing ◽  
Grayscale Images

The problem of automatic colorization of monochrome images is considered. methods of colorizing are used in film industry to restore chromaticity of old movies and photographic materials, in computer vision problems, in medical images processing etc. Modern techniques of colorization contain many manual operations, take a lot of time and are expensive. Many methods of colorization require human participation to correctly determine colors, since there is no one-to-one accordance between grayscale and color. In this paper we discuss method for fully automatic colorization of monochrome images using a convolutional neural network. This approach has reduced using of manual operations to minimum. Structure of the neural network for coloration based on the VGG16 model is considered in the paper. Types of layers that are appropriate for solving the problem of colorization are determined and analyzed. Proposed structure consists of 13 convolutional layers and three upsampling layers. The subsample layers are replaced with the necessary zero addition with a step of 2x2. All layers’ filters have 3x3 size. The activation function of all convolutional layers is ReLU and hyperbolic tangent of the last layer. The presented model is implemented in a software system for automatic image colorization. The software system includes two parts. The first part implements construction and training of the neural network. The second part uses obtained neural network to generate colorized images from grayscale images. Network training was carried out on a sample of Caltech-256, which contains 256 categories of objects. After training the system was tested on series of grayscale images. Testing showed that the system performs enough plausible colorization of certain types objects. Acceptable results were obtained in the colorization of images of nature, ordinary animals, portrait photos. In unsuccessful cases objects were painted in brown shades. Unsuccessful results were obtained for images that contained only parts of objects or these objects were represented in the training sample in too different colors.

Experimental and Comparison Based Study on Diabetes Prediction Using Artificial Neural Network

2019 ◽  
Vol 12 ◽  
Author(s):  
Nitesh Pradhan ◽  
VijayPal Singh Dhaka ◽  
Satish Chandra Kulhari
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Nearest Neighbor ◽  
Activation Function ◽  
Support Vector ◽  
K Nearest Neighbor ◽  
Output Layer ◽  
Diabetes Prediction ◽  
Artificial Neural ◽  
Hidden Layer

Background: Diabetes is spreading in the entire world. In a survey, it is observed that every generation from child to old age people are suffering from diabetes. If diabetes is not identified in time, it may lead to deadliest disease. Prediction of diabetes is of the utmost challenging task by machines. In the human body, diabetes is one of the perilous maladies that creates depended disease such as kidney disease, heart attack, blindness etc. Thus it is very important to diagnose diabetes in time. Objective: Our target is to develop a system using Artificial Neural Network(ANN), with the ability to predict whether a patient suffers from diabetes or not. Method: This paper illustrates various machine learning techniques in form of literature review; such as Support Vector Machine, Naïve Bayes, K Nearest Neighbor, Decision Tree, Random Forest Etc. We applied ANN to predict diabetes. In this paper, the architecture of ANN consists of four hidden layers each of six neurons and one output layer with one neuron. Optimizer used for the architecture is ‘Adam’. Results: We have Pima Indian diabetes dataset of sufficient number of patients with nine different symptoms with respect to the patients and nine different features in connection with the mathematical computation/prediction. Hence we bifurcate the dataset into training and testing set in majority and minority ratio of 80:20 respectively. It facilitates us the majority patient’s data to be used as training set and minority data to be used as testing set. We train our network for multiple epoch with different activation function. We used four hidden layers with six neurons in each hidden layer and one output layer. On the hidden layer, we used multiple activation functions such as sigmoid, ReLU etc. and obtained beat accuracy (88.71%) in 600 epochs with ReLU activation function. On the output layer, we used only sigmoid activation function because we have only two classes in our dataset. Conclusion: Diabetes prediction by machine is a challenging task. So many machine learning algorithms exist to predict the diabetes such as Naïve Bayes, decision tree, K nearest neighbor, support vector machine etc. This paper presents a novel approach to predict whether a patient has diabetes or not based on Pima Indian diabetes dataset. In this paper, we used artificial neural network to train out network and it is observed that artificial neural network approach performs better than all other classifiers

SCORING MODELING BASED ON NEURAL NETWORKS FOR DETERMINING A BANK BORROWER'S RATING

2020 ◽  
Vol 2020 (10) ◽  
pp. 54-62
Author(s):  
Oleksii VASYLIEV ◽  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Network Architecture ◽  
Statistical Data ◽  
Activation Function ◽  
Decision Making Process ◽  
Neural Network Architecture ◽  
Acceptable Accuracy ◽  
The Neural Network ◽  
Sigmoid Activation Function

The problem of applying neural networks to calculate ratings used in banking in the decision-making process on granting or not granting loans to borrowers is considered. The task is to determine the rating function of the borrower based on a set of statistical data on the effectiveness of loans provided by the bank. When constructing a regression model to calculate the rating function, it is necessary to know its general form. If so, the task is to calculate the parameters that are included in the expression for the rating function. In contrast to this approach, in the case of using neural networks, there is no need to specify the general form for the rating function. Instead, certain neural network architecture is chosen and parameters are calculated for it on the basis of statistical data. Importantly, the same neural network architecture can be used to process different sets of statistical data. The disadvantages of using neural networks include the need to calculate a large number of parameters. There is also no universal algorithm that would determine the optimal neural network architecture. As an example of the use of neural networks to determine the borrower's rating, a model system is considered, in which the borrower's rating is determined by a known non-analytical rating function. A neural network with two inner layers, which contain, respectively, three and two neurons and have a sigmoid activation function, is used for modeling. It is shown that the use of the neural network allows restoring the borrower's rating function with quite acceptable accuracy.

Breast cancer diagnosis using multiple activation deep neural network

2021 ◽  
pp. 1063293X2110251
Author(s):  
K Vijayakumar ◽  
Vinod J Kadam ◽  
Sudhir Kumar Sharma
Keyword(s):  
Breast Cancer ◽  
Neural Network ◽  
Deep Neural Network ◽  
Breast Cancer Diagnosis ◽  
Activation Function ◽  
Linear Functions ◽  
Cancer Data ◽  
Final Layer ◽  
Improved Performance ◽  
Hidden Layer

Deep Neural Network (DNN) stands for multilayered Neural Network (NN) that is capable of progressively learn the more abstract and composite representations of the raw features of the input data received, with no need for any feature engineering. They are advanced NNs having repetitious hidden layers between the initial input and the final layer. The working principle of such a standard deep classifier is based on a hierarchy formed by the composition of linear functions and a defined nonlinear Activation Function (AF). It remains uncertain (not clear) how the DNN classifier can function so well. But it is clear from many studies that within DNN, the AF choice has a notable impact on the kinetics of training and the success of tasks. In the past few years, different AFs have been formulated. The choice of AF is still an area of active study. Hence, in this study, a novel deep Feed forward NN model with four AFs has been proposed for breast cancer classification: hidden layer 1: Swish, hidden layer, 2:-LeakyReLU, hidden layer 3: ReLU, and final output layer: naturally Sigmoidal. The purpose of the study is twofold. Firstly, this study is a step toward a more profound understanding of DNN with layer-wise different AFs. Secondly, research is also aimed to explore better DNN-based systems to build predictive models for breast cancer data with improved accuracy. Therefore, the benchmark UCI dataset WDBC was used for the validation of the framework and evaluated using a ten-fold CV method and various performance indicators. Multiple simulations and outcomes of the experimentations have shown that the proposed solution performs in a better way than the Sigmoid, ReLU, and LeakyReLU and Swish activation DNN in terms of different parameters. This analysis contributes to producing an expert and precise clinical dataset classification method for breast cancer. Furthermore, the model also achieved improved performance compared to many established state-of-the-art algorithms/models.

Building Electronic Commerce Recommendation System Based on Ontology Learning and BP Neural Network

2013 ◽  
Vol 718-720 ◽  
pp. 1961-1966
Author(s):  
Hong Sheng Xu ◽  
Qing Tan
Keyword(s):  
Neural Network ◽  
Electronic Commerce ◽  
Bp Neural Network ◽  
Optimization Problem ◽  
Recommendation System ◽  
High Efficiency ◽  
Ontology Learning ◽  
The Neural Network ◽  
Network Process ◽  
Hidden Layer

Electronic commerce recommendation system can effectively retain user, prevent users from erosion, and improve e-commerce system sales. BP neural network using iterative operation, solving the weights of the neural network and close values to corresponding network process of learning and memory, to join the hidden layer nodes of the optimization problem of adjustable parameters increase. Ontology learning is the use of machine learning and statistical techniques, with automatic or semi-automatic way, from the existing data resources and obtaining desired body. The paper presents building electronic commerce recommendation system based on ontology learning and BP neural network. Experimental results show that the proposed algorithm has high efficiency.

scholarly journals Advanced thyroid carcinomas: neural network analysis of ultrasonographic characteristics

2021 ◽  
Vol 14 (1) ◽  
Author(s):  
Michael Cordes ◽  
Theresa Ida Götz ◽  
Elmar Wolfgang Lang ◽  
Stephan Coerper ◽  
Torsten Kuwert ◽  
...  
Keyword(s):  
Neural Network ◽  
Imaging Modality ◽  
Follicular Carcinoma ◽  
Predictive Values ◽  
Thyroid Carcinomas ◽  
The Neural Network ◽  
Group 2 ◽  
Line Imaging ◽  
Hidden Layer ◽  
Group 1

Abstract Background Ultrasound is the first-line imaging modality for detection and classification of thyroid nodules. Certain characteristics observable by ultrasound have recently been identified that may indicate malignancy. This retrospective cohort study was conducted to test the hypothesis that advanced thyroid carcinomas show distinctive clinical and sonographic characteristics. Using a neural network model as proof of concept, nine clinical/sonographic features served as input. Methods All 96 study enrollees had histologically confirmed thyroid carcinomas, categorized (n = 32, each) as follows: group 1, advanced carcinoma (ADV) marked by local invasion or distant metastasis; group 2, non-advanced papillary carcinoma (PTC); or group 3, non-advanced follicular carcinoma (FTC). Preoperative ultrasound profiles were obtained via standardized protocols. The neural network had nine input neurons and one hidden layer. Results Mean age and the number of male patients in group 1 were significantly higher compared with groups 2 (p = 0.005) or 3 (p <  0.001). On ultrasound, tumors of larger volume and irregular shape were observed significantly more often in group 1 compared with groups 2 (p <  0.001) or 3 (p ≤ 0.01). Network accuracy in discriminating advanced vs. non-advanced tumors was 84.4% (95% confidence interval [CI]: 75.5–91), with positive and negative predictive values of 87.1% (95% CI: 70.2–96.4) and 92.3% (95% CI: 83.0–97.5), respectively. Conclusions Our study has shown some evidence that advanced thyroid tumors demonstrate distinctive clinical and sonographic characteristics. Further prospective investigations with larger numbers of patients and multicenter design should be carried out to show whether a neural network incorporating these features may be an asset, helping to classify malignancies of the thyroid gland.

scholarly journals The effect of Kurtosis on the accuracy of artificial neural network predictive model

2018 ◽  
Vol 204 ◽  
pp. 02018
Author(s):  
Aisyah Larasati ◽  
Anik Dwiastutik ◽  
Darin Ramadhanti ◽  
Aal Mahardika
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Predictive Model ◽  
Predictive Models ◽  
Output Layer ◽  
Input Layer ◽  
Artificial Neural ◽  
Misclassification Rates ◽  
Hidden Layer ◽  
Program Data

This study aims to explore the effect of kurtosis level of the data in the output layer on the accuracy of artificial neural network predictive models. The artificial neural network predictive models are comprised of one node in the output layer and six nodes in the input layer. The number of hidden layer is automatically built by the program. Data are generated using simulation approach. The results show that the kurtosis level of the node in the output layer is significantly affect the accuracy of the artificial neural network predictive model. Platycurtic and leptocurtic data has significantly higher misclassification rates than mesocurtic data. However, the misclassification rates between platycurtic and leptocurtic is not significantly different. Thus, data distribution with kurtosis nearly to zero results in a better ANN predictive model.

Sign in / Sign up

Export Citation Format

Share Document