Methods and means for real-time object recognition accuracy increase in video images on ios mobile platform

2021 ◽  
Vol 3 (1) ◽  
pp. 80-88
Author(s):  
D Kushnir ◽  
Keyword(s):  
Neural Network ◽  
Real Time ◽  
Recognition Accuracy ◽  
Activation Function ◽  
Frame Rate ◽  
Mobile Platform ◽  
Additional Layer ◽  
The Neural Network ◽  
Analytical Review ◽  
Accuracy Increase

As a result of the analytical review, it was established that the family of Yolo models is a promising area of search and recognition of objects. However, existing implementations do not support the ability to run the model on the iOS platform. To achieve these goals, a comprehensive scalable conversion system has been developed to improve the recognition accuracy of arbitrary models based on the Docker system. The method of improvement is to add a layer with the Mish activation function to the original model. The method of conversion is to quickly convert any Yolo model to CoreML format. As part of the study of these techniques, a model of the neural network Yolov4_TCAR was created. Additionally, a method of accelerating the load on the CPU using an additional layer of neural network with the function of activating Mish in Swift for the iOS mobile platform was added. As a result, the effectiveness of the Mish activation function, the CPU load of the mobile device, the amount of RAM used, and the frame rate when using the improved original Yolov4-TCAR model were studied. The results of the research confirmed the functioning of the algorithm for conversion and accuracy increase of the neural network model in real-time.

PID control of an omnidirectional mobile platform based on an RBF neural network controller

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Niu Zijie ◽  
Zhang Peng ◽  
Yongjie Cui ◽  
Zhang Jun
Keyword(s):  
Neural Network ◽  
Real Time ◽  
Network Model ◽  
Neural Network Model ◽  
Control Algorithm ◽  
Rbf Neural Network ◽  
Mobile Platform ◽  
Content Type ◽  
The Neural Network ◽  
Omnidirectional Mobile Platform

Purpose Omnidirectional mobile platforms are still plagued by the problem of heading deviation. In four-Mecanum-wheel systems, this problem arises from the phenomena of dynamic imbalance and slip of the Mecanum wheels while driving. The purpose of this paper is to analyze the mechanism of omnidirectional motion using Mecanum wheels, with the aim of enhancing the heading precision. A proportional-integral-derivative (PID) setting control algorithm based on a radial basis function (RBF) neural network model is introduced. Design/methodology/approach In this study, the mechanism of omnidirectional motion using Mecanum wheels is analyzed, with the aim of enhancing the heading precision. A PID setting control algorithm based on an RBF neural network model is introduced. The algorithm is based on a kinematics model for an omnidirectional mobile platform and corrects the driving heading in real time. In this algorithm, the neural network RBF NN2 is used for identifying the state of the system, calculating the Jacobian information of the system and transmitting information to the neural network RBF NN1. Findings The network RBF NN1 calculates the deviations ?Kp, ?Ki and ?Kd to regulate the three coefficients Kp, Ki and Kd of the heading angle PID controller. This corrects the driving heading in real time, resolving the problems of low heading precision and unstable driving. The experimental data indicate that, for a externally imposed deviation in the heading angle of between 34º and ∼38°, the correction time for an omnidirectional mobile platform applying the algorithm during longitudinal driving is reduced by 1.4 s compared with the traditional PID control algorithm, while the overshoot angle is reduced by 7.4°; for lateral driving, the correction time is reduced by 1.4 s and the overshoot angle is reduced by 4.2°. Originality/value In this study, the mechanism of omnidirectional motion using Mecanum wheels is analyzed, with the aim of enhancing the heading precision. A PID setting control algorithm based on an RBF neural network model is introduced. The algorithm is based on a kinematics model for an omnidirectional mobile platform and corrects the driving heading in real time. In this algorithm, the neural network RBF NN2 is used for identifying the state of the system, calculating the Jacobian information of the system and transmitting information to the neural network RBF NN1. The method is innovative.

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.

scholarly journals Augmented Reality Maintenance Assistant Using YOLOv5

2021 ◽  
Vol 11 (11) ◽  
pp. 4758
Author(s):  
Ana Malta ◽  
Mateus Mendes ◽  
Torres Farinha
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Object Recognition ◽  
Augmented Reality ◽  
Real Time ◽  
Recognition System ◽  
High Accuracy ◽  
Video Streams ◽  
The Neural Network ◽  
Deep Learning Neural Network

Maintenance professionals and other technical staff regularly need to learn to identify new parts in car engines and other equipment. The present work proposes a model of a task assistant based on a deep learning neural network. A YOLOv5 network is used for recognizing some of the constituent parts of an automobile. A dataset of car engine images was created and eight car parts were marked in the images. Then, the neural network was trained to detect each part. The results show that YOLOv5s is able to successfully detect the parts in real time video streams, with high accuracy, thus being useful as an aid to train professionals learning to deal with new equipment using augmented reality. The architecture of an object recognition system using augmented reality glasses is also designed.

The Design of a Wavelet-Based Neural Network Adaptive Filter

2013 ◽  
Vol 860-863 ◽  
pp. 2791-2795
Author(s):  
Qian Xiao ◽  
Yu Shan Jiang ◽  
Ru Zheng Cui
Keyword(s):  
Neural Network ◽  
Wavelet Transform ◽  
Real Time ◽  
Adaptive Filter ◽  
Adaptive Algorithm ◽  
Distributed Storage ◽  
Hopfield Neural Network ◽  
Lms Algorithm ◽  
The Neural Network ◽  
Simulation Results

Aiming at the large calculation workload of adaptive algorithm in adaptive filter based on wavelet transform, affecting the filtering speed, a wavelet-based neural network adaptive filter is constructed in this paper. Since the neural network has the ability of distributed storage and fast self-evolution, use Hopfield neural network to implement adaptive filter LMS algorithm in this filter so as to improve the speed of operation. The simulation results prove that, the new filter can achieve rapid real-time denoising.

Analysis of Fin-Tube Evaporator Performance With Limited Experimental Data Using Artificial Neural Networks

2000 ◽  
Author(s):  
Arturo Pacheco-Vega ◽  
Mihir Sen ◽  
Rodney L. McClain
Keyword(s):  
Neural Network ◽  
Heat Rate ◽  
Network Models ◽  
Activation Function ◽  
Operating Conditions ◽  
Training Data ◽  
Neural Network Models ◽  
The Neural Network ◽  
Artificial Neural ◽  
Fin Tube

Abstract In the current study we consider the problem of accuracy in heat rate estimations from artificial neural network models of heat exchangers used for refrigeration applications. The network configuration is of the feedforward type with a sigmoid activation function and a backpropagation algorithm. Limited experimental measurements from a manufacturer are used to show the capability of the neural network technique in modeling the heat transfer in these systems. Results from this exercise show that a well-trained network correlates the data with errors of the same order as the uncertainty of the measurements. It is also shown that the number and distribution of the training data are linked to the performance of the network when estimating the heat rates under different operating conditions, and that networks trained from few tests may give large errors. A methodology based on the cross-validation technique is presented to find regions where not enough data are available to construct a reliable neural network. The results from three tests show that the proposed methodology gives an upper bound of the estimated error in the heat rates.

Signal processing algorithm for neural networks with integrodifferential splines as an activation function and its particular case of image classification

2021 ◽  
Author(s):  
T.K. Biryukova
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Image Classification ◽  
Activation Function ◽  
Experimental Comparison ◽  
Training Time ◽  
Operation Speed ◽  
The Neural Network ◽  
Linear Algebraic Equations ◽  
Network Operation

Classic neural networks suppose trainable parameters to include just weights of neurons. This paper proposes parabolic integrodifferential splines (ID-splines), developed by author, as a new kind of activation function (AF) for neural networks, where ID-splines coefficients are also trainable parameters. Parameters of ID-spline AF together with weights of neurons are vary during the training in order to minimize the loss function thus reducing the training time and increasing the operation speed of the neural network. The newly developed algorithm enables software implementation of the ID-spline AF as a tool for neural networks construction, training and operation. It is proposed to use the same ID-spline AF for neurons in the same layer, but different for different layers. In this case, the parameters of the ID-spline AF for a particular layer change during the training process independently of the activation functions (AFs) of other network layers. In order to comply with the continuity condition for the derivative of the parabolic ID-spline on the interval (x x0, n) , its parameters fi (i= 0,...,n) should be calculated using the tridiagonal system of linear algebraic equations: To solve the system it is necessary to use two more equations arising from the boundary conditions for specific problems. For exam- ple the values of the grid function (if they are known) in the points (x x0, n) may be used for solving the system above: f f x0 = ( 0) , f f xn = ( n) . The parameters Iii+1 (i= 0,...,n−1 ) are used as trainable parameters of neural networks. The grid boundaries and spacing of the nodes of ID-spline AF are best chosen experimentally. The optimal selection of grid nodes allows improving the quality of results produced by the neural network. The formula for a parabolic ID-spline is such that the complexity of the calculations does not depend on whether the grid of nodes is uniform or non-uniform. An experimental comparison of the results of image classification from the popular FashionMNIST dataset by convolutional neural 0, x< 0 networks with the ID-spline AFs and the well-known ReLUx( ) =AF was carried out. The results reveal that the usage x x, ≥ 0 of the ID-spline AFs provides better accuracy of neural network operation than the ReLU AF. The training time for two convolutional layers network with two ID-spline AFs is just about 2 times longer than with two instances of ReLU AF. Doubling of the training time due to complexity of the ID-spline formula is the acceptable price for significantly better accuracy of the network. Wherein the difference of an operation speed of the networks with ID-spline and ReLU AFs will be negligible. The use of trainable ID-spline AFs makes it possible to simplify the architecture of neural networks without losing their efficiency. The modification of the well-known neural networks (ResNet etc.) by replacing traditional AFs with ID-spline AFs is a promising approach to increase the neural network operation accuracy. In a majority of cases, such a substitution does not require to train the network from scratch because it allows to use pre-trained on large datasets neuron weights supplied by standard software libraries for neural network construction thus substantially shortening training time.

scholarly journals Real-Time Guitar Amplifier Emulation with Deep Learning

2020 ◽  
Vol 10 (3) ◽  
pp. 766 ◽  
Author(s):  
Alec Wright ◽  
Eero-Pekka Damskägg ◽  
Lauri Juvela ◽  
Vesa Välimäki
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Real Time ◽  
Reference Signal ◽  
Network Models ◽  
Neural Network Models ◽  
Desktop Computer ◽  
The Neural Network ◽  
Highly Nonlinear ◽  
The Difference

This article investigates the use of deep neural networks for black-box modelling of audio distortion circuits, such as guitar amplifiers and distortion pedals. Both a feedforward network, based on the WaveNet model, and a recurrent neural network model are compared. To determine a suitable hyperparameter configuration for the WaveNet, models of three popular audio distortion pedals were created: the Ibanez Tube Screamer, the Boss DS-1, and the Electro-Harmonix Big Muff Pi. It is also shown that three minutes of audio data is sufficient for training the neural network models. Real-time implementations of the neural networks were used to measure their computational load. To further validate the results, models of two valve amplifiers, the Blackstar HT-5 Metal and the Mesa Boogie 5:50 Plus, were created, and subjective tests were conducted. The listening test results show that the models of the first amplifier could be identified as different from the reference, but the sound quality of the best models was judged to be excellent. In the case of the second guitar amplifier, many listeners were unable to hear the difference between the reference signal and the signals produced with the two largest neural network models. This study demonstrates that the neural network models can convincingly emulate highly nonlinear audio distortion circuits, whilst running in real-time, with some models requiring only a relatively small amount of processing power to run on a modern desktop computer.

Hand gesture recognition by means of region-based convolutional neural networks

2017 ◽  
Vol 10 (27) ◽  
pp. 1329-1342 ◽  
Author(s):  
Javier O. Pinzon Arenas ◽  
Robinson Jimenez Moreno ◽  
Paula C. Useche Murillo
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Convolutional Neural Network ◽  
Real Time ◽  
Convolutional Neural Networks ◽  
Gesture Recognition ◽  
Hand Gesture ◽  
Hand Gestures ◽  
The Neural Network ◽  
Average Accuracy

This paper presents the implementation of a Region-based Convolutional Neural Network focused on the recognition and localization of hand gestures, in this case 2 types of gestures: open and closed hand, in order to achieve the recognition of such gestures in dynamic backgrounds. The neural network is trained and validated, achieving a 99.4% validation accuracy in gesture recognition and a 25% average accuracy in RoI localization, which is then tested in real time, where its operation is verified through times taken for recognition, execution behavior through trained and untrained gestures, and complex backgrounds.

Research on the Key Technologies of Intelligent Control for Cap-Shape Bending of Sheet Metal

2011 ◽  
Vol 239-242 ◽  
pp. 2867-2872
Author(s):  
Hong Lei Sun ◽  
Chun Jian Su ◽  
Rui Xue Zhai
Keyword(s):  
Neural Network ◽  
Control System ◽  
Real Time ◽  
Sheet Metal ◽  
Intelligent Control ◽  
Feed Forward Neural Network ◽  
Forming Process ◽  
Intelligent Control System ◽  
The Neural Network ◽  
Real Time Identification

The blueprint for an intelligent control system of cap-shape bending has been advanced in this paper using neural network technology, aiming at an accurate control of bending springback, the prominent problem during the forming process for the cap-shape bending of sheet metal. The feed-forward neural network of real-time identification for material performance parameters and the friction coefficient have been established. The neural network identifies the parameters for real-time needed material performance, which utilizes the measurability of the physical quantities, and predicts the parameters for optimum technology, so a satisfied accuracy of convergence has been achieved. The intelligent control experimentation system of cap-shape bending has been established, the validity of which has been tested for four kinds of materials. The result of the tests proves the feasibility of the blueprint of the intelligent control system.

An Efficient Neural Network Model for Path Planning of Car-like Robots in Dynamic Environment

2000 ◽  
Vol 4 (3) ◽  
pp. 220-229 ◽  
Author(s):  
Simon X. Yang ◽  
◽  
Max Meng ◽  
Keyword(s):  
Neural Network ◽  
Path Planning ◽  
Real Time ◽  
Dynamic Environment ◽  
Lyapunov Stability Theory ◽  
Network Size ◽  
Computationally Efficient ◽  
Neural Network Approach ◽  
The Neural Network ◽  
The Stability

In this paper, an effcient neural network approach to real-time path planning with obstacle avoidance of holonomic car-like robots in a dynamic environment is proposed. The dynamics of each neuron in this biologically inspired, topologically organized neural network is characterized by a shunting equation or an additive equation. The state space of the neural network is the configuration space of the robot. There are only local lateral connections among neurons. Thus the computational complexity linearly depends on the neural network size. The real-time collision-free path is planned through the dynamic neural activity landscape of the neural network without explicitly searching over neither the free workspace nor the collision paths, without any prior knowledge of the dynamic environment, without any learning procedures, and without any local collision checking procedures at each step of the robot movement. Therefore it is computationally efficient. The stability of the neural network is proven by both qualitative analysis and the Lyapunov stability theory. The effectiveness and efficiency are demonstrated through simulation studies.

Sign in / Sign up

Export Citation Format

Share Document