scholarly journals Expression Analysis System

2021 ◽  
Vol 10 (3) ◽  
pp. 13-15
Author(s):  
Riya KalburgI ◽  
Punit Solanki ◽  
Rounak Suthar ◽  
Saurabh Suman
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Personality Traits ◽  
Facial Expressions ◽  
Network Algorithms ◽  
Periodic Monitoring ◽  
Derivative System ◽  
Analysis System ◽  
The Individual ◽  
Backward Propagation

Expression is the most basic personality trait of an individual. Expressions, ubiquitous to humans from all cultures, can be pivotal in analyzing the personality which is not confined to boundaries. Analyzing the changes in the expression of the individual can bolster the process of deriving his/her personality traits underscoring the paramount reactions like anger, happiness, sadness and so on. This paper aims to exercise Neural Network algorithms to predict the personality traits of an individual from his/her facial expressions. In this paper, a methodology to analyze the personality traits of the individual by periodic monitoring of the changes in facial expressions is presented. The proposed system is intended to analyze the expressions by exploiting Neural Networks strategies to first analyze the facial expressions of the individual by constantly monitoring an individual under observation. This monitoring is done with the help of OpenCV which captures the facial expression at an interval of 15 secs. Thousands of images per expression are used to train the model to aptly distinguish between expression using prominent Neural Network Methodologies of Forward and Backward Propagation. The identified expression is then be fed to a derivative system which plots a graph highlighting the changes in the expression. The graph acts as the crux of the proposed system. The project is important from the perspective of serving as an alternative to manual monitoring which are prone to errors and subjective in nature.

Dynamic statistical evaluation of safety emergency management in coal enterprises based on neural network algorithms

2020 ◽  
Vol 39 (4) ◽  
pp. 5521-5534
Author(s):  
Ying Liu ◽  
Zhongqi Fan ◽  
Hongliang Qi
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Emergency Management ◽  
Coal Mine ◽  
Evaluation System ◽  
Statistical Evaluation ◽  
Specific Situation ◽  
Network Algorithms ◽  
Management Capability ◽  
Coal Enterprises

By establishing the evaluation system of emergency management capability for coal mine enterprises, we can identify the problems and shortcomings in coal mine emergency management, improve and improve its emergency management capability for coal mine emergencies. In this paper, the authors analyze the dynamic statistical evaluation of safety emergency management in coal enterprises based on neural network algorithms. Neural networks can form any form of topological structure through neurons, so they can directly simulate fuzzy reasoning in structure, that is to say, the equivalent structure of neural networks and fuzzy systems can be formed. This paper constructs the index system based on accident causes, and verifies the scientific rationality of the system. On this basis, according to the specific situation of coal mine emergency management, we design the evaluation criteria of coal mine emergency management capability evaluation index. Because coal mine accidents have the characteristics of complexity, variability and sudden dynamic, it is necessary to adjust and improve the accidents dynamically at any time. The model combines qualitative and quantitative indicators, and can make an overall evaluation of coal mine emergency management capability. It has the characteristics of clear results and strong fitting of simulation results.

scholarly journals Comparison of the efficiency of neural network algorithms in recognition and classification problems

2020 ◽  
Vol 224 ◽  
pp. 01025
Author(s):  
Alexey Beskopylny ◽  
Alexandr Lyapin ◽  
Nikita Beskopylny ◽  
Elena Kadomtseva
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Computation Time ◽  
Classification Problems ◽  
Handwritten Digit Recognition ◽  
Network Algorithms ◽  
Digit Recognition ◽  
Labour Intensity ◽  
Handwritten Digit ◽  
Accuracy Of Results

The article is devoted to the problem of comparing the effectiveness of feedforward (FF) and convolutional neural networks (CNN) algorithms in the problems of handwritten digit recognition and classification. In recent years, the attention of many researchers to the FF and CNN algorithms has given rise to many hybrid models focused on solving specific problems. At the same time, the efficiency of each algorithm in terms of accuracy and labour intensity remains unclear. It is shown that in classical problems, FFs can have advantages over CNN in terms of labour intensity with the same accuracy of results. Using the handwritten digits data from the MNIST database as an example, it is shown that FF algorithms provide greater accuracy and require less computation time than CNN.

Congestion Prediction System With Artificial Neural Networks

2020 ◽  
Vol 12 (3) ◽  
pp. 28-43
Author(s):  
Fatma Gumus ◽  
Derya Yiltas-Kaplan
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Network Architecture ◽  
Prediction Algorithm ◽  
Learning Stage ◽  
Network Algorithms ◽  
Prediction Scheme ◽  
Machine Learning Approach ◽  
Congestion Prediction ◽  
Nonlinear Autoregressive

Software Defined Network (SDN) is a programmable network architecture that provides innovative solutions to the problems of the traditional networks. Congestion control is still an uncharted territory for this technology. In this work, a congestion prediction scheme has been developed by using neural networks. Minimum Redundancy Maximum Relevance (mRMR) feature selection algorithm was performed on the data collected from the OMNET++ simulation. The novelty of this study also covers the implementation of mRMR in an SDN congestion prediction problem. After evaluating the relevance scores, two highest ranking features were used. On the learning stage Nonlinear Autoregressive Exogenous Neural Network (NARX), Nonlinear Autoregressive Neural Network, and Nonlinear Feedforward Neural Network algorithms were executed. These algorithms had not been used before in SDNs according to the best of the authors knowledge. The experiments represented that NARX was the best prediction algorithm. This machine learning approach can be easily integrated to different topologies and application areas.

scholarly journals Adiabatic superconducting cells for ultra-low-power artificial neural networks

2016 ◽  
Vol 7 ◽  
pp. 1397-1403 ◽  
Author(s):  
Andrey E Schegolev ◽  
Nikolay V Klenov ◽  
Igor I Soloviev ◽  
Maxim V Tereshonok
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
Low Power ◽  
Power Dissipation ◽  
Radial Basis Function Networks ◽  
Activation Functions ◽  
Ultra Low Power ◽  
Network Algorithms ◽  
Low Power Dissipation

We propose the concept of using superconducting quantum interferometers for the implementation of neural network algorithms with extremely low power dissipation. These adiabatic elements are Josephson cells with sigmoid- and Gaussian-like activation functions. We optimize their parameters for application in three-layer perceptron and radial basis function networks.

scholarly journals The Use of Neural Networks in High-Energy Physics

1993 ◽  
Vol 5 (4) ◽  
pp. 505-549 ◽  
Author(s):  
Bruce Denby
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Pattern Recognition ◽  
High Energy Physics ◽  
High Energy ◽  
High Quality ◽  
Network Algorithms ◽  
The Past ◽  
The Neural Network ◽  
Energy Physics

In the past few years a wide variety of applications of neural networks to pattern recognition in experimental high-energy physics has appeared. The neural network solutions are in general of high quality, and, in a number of cases, are superior to those obtained using "traditional'' methods. But neural networks are of particular interest in high-energy physics for another reason as well: much of the pattern recognition must be performed online, that is, in a few microseconds or less. The inherent parallelism of neural network algorithms, and the ability to implement them as very fast hardware devices, may make them an ideal technology for this application.

scholarly journals Epilepsy Detection Using Artificial Neural Networks

2020 ◽  
Vol 8 (4) ◽  
pp. 323-328
Author(s):  
Matheus Adler Soares Pinto ◽  
Bruno Rocha Gomes ◽  
João Pedro Moreno Vale ◽  
André Luis Rolim de Castro Silva ◽  
Joadson Teixeira Castro das Chagas ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
Sudden Death ◽  
Epileptic Seizures ◽  
Accurate Diagnosis ◽  
Brain Cells ◽  
Artificial Neural ◽  
The Individual ◽  
Electroencephalogram Eeg

Epilepsy is a neurological disorder, where there is a cluster of brain cells that behave in a hyperexcitable manner, the individual can promote injuries, trauma or, in more severe cases, sudden death. Electroencephalogram (EEG) is the most used way to detect epileptic seizures. Therefore, more simplified methods of analysis of the EEG can help in the diagnosis and treatment of these individuals more quickly. In this study, we extracted pertinent EEG characteristics to assess the epileptic seizure period. We use Perceptron Multilayer artificial neural networks to classify the period of the crisis, obtaining a more efficient diagnosis. The multilayer neural network obtained an accuracy of 98%. Thus, the strategy of extracting characteristics and the architecture of the assigned network were sufficient for a rapid and accurate diagnosis of epilepsy.

scholarly journals Analysis of Algorithms for Searching Objects in Images Using Convolutional Neural Network

2021 ◽  
Vol 6 (2) ◽  
pp. 128-133
Author(s):  
Ihor Koval ◽  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Comparative Analysis ◽  
Analysis Of Algorithms ◽  
Network Models ◽  
Data Sets ◽  
Neural Network Models ◽  
Network Algorithms ◽  
Modern Computer ◽  
The Neural Network

The problem of finding objects in images using modern computer vision algorithms has been considered. The description of the main types of algorithms and methods for finding objects based on the use of convolutional neural networks has been given. A comparative analysis and modeling of neural network algorithms to solve the problem of finding objects in images has been conducted. The results of testing neural network models with different architectures on data sets VOC2012 and COCO have been presented. The results of the study of the accuracy of recognition depending on different hyperparameters of learning have been analyzed. The change in the value of the time of determining the location of the object depending on the different architectures of the neural network has been investigated.

scholarly journals Practical Aspects of the Design and Use of the Artificial Neural Networks in Materials Engineering

Metals ◽  
2021 ◽  
Vol 11 (11) ◽  
pp. 1832
Author(s):  
Wojciech Sitek ◽  
Jacek Trzaska
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
Vital Role ◽  
Materials Engineering ◽  
The Neural Network ◽  
Critical Issues ◽  
Artificial Neural ◽  
The Individual

Artificial neural networks are an effective and frequently used modelling method in regression and classification tasks in the area of steels and metal alloys. New publications show examples of the use of artificial neural networks in this area, which appear regularly. The paper presents an overview of these publications. Attention was paid to critical issues related to the design of artificial neural networks. There have been presented our suggestions regarding the individual stages of creating and evaluating neural models. Among other things, attention was paid to the vital role of the dataset, which is used to train and test the neural network and its relationship to the artificial neural network topology. Examples of approaches to designing neural networks by other researchers in this area are presented.

scholarly journals Diagnosis Kerosakan Litar Menggunakan Pspice dan Rangkaian Neural Tiruan

2012 ◽  
Author(s):  
Jasronita Jasni ◽  
Samsul Bahari Mohd Noor ◽  
Ribhan Zafira Abd Rahman
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Fault Diagnosis ◽  
Power Supply ◽  
Pulse Width ◽  
Analog Circuit ◽  
Switch Mode Power Supply ◽  
Pulse Width Modulator ◽  
Switch Mode ◽  
The Individual

Kerosakan komponen di dalam satu litar sangat sukar dikesan dan mengambil masa yang lama untuk dikenalpasti. Kertas ini membentangkan kaedah mendiagnosis kerosakan litar menggunakan Rangkaian Neural Tiruan (RNT). Litar Pengayun dan Pulse Width Modulator yang merupakan sebahagian dari Switch Mode Power Supply telah digunakan sebagai litar kajian. Litar ini disimulasi menggunakan Pspice dan data voltan pada nod direkodkan dan digunakan dalam sistem rangkaian neural tiruan. Setelah dilatih, sistem ini berupaya mengenalpasti komponen yang rosak dengan mudah. Kata kunci: Diagnosis kerosakan, litar analog, rangkaian neural Faulty components in a circuit is difficult and time consuming to be identified. This paper presents a method of circiut fault diagnosis using artificial neural networks (ANN). Oscillator circuit with Pulse Width Modulator which is part of a Switch Mode Power Supply is used in this study. The system is trained and able to identify the individual faulty components with ease. Key words: Fault diagnosis, analog circuit, neural network

Towards Hallucinating Machines - Designing with Computational Vision

2020 ◽  
pp. 147807712096336
Author(s):  
Matias del Campo ◽  
Alexandra Carlson ◽  
Sandra Manninger
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Architectural Design ◽  
Common Denominator ◽  
Training Methods ◽  
Style Transfer ◽  
Network Algorithms ◽  
Architectural Styles ◽  
Large Databases ◽  
The Common

There are particular similarities in how machines learn about the nature of their environment, and how humans learn to process visual stimuli. Machine Learning (ML), more specifically Deep Neural network algorithms rely on expansive image databases and various training methods (supervised, unsupervised) to “make sense” out of the content of an image. Take for example how students of architecture learn to differentiate various architectural styles. Whether this be to differentiate between Gothic, Baroque or Modern Architecture, students are exposed to hundreds, or even thousands of images of the respective styles, while being trained by faculty to be able to differentiate between those styles. A reversal of the process, striving to produce imagery, instead of reading it and understanding its content, allows machine vision techniques to be utilized as a design methodology that profoundly interrogates aspects of agency and authorship in the presence of Artificial Intelligence in architecture design. This notion forms part of a larger conversation on the nature of human ingenuity operating within a posthuman design ecology. The inherent ability of Neural Networks to process large databases opens up the opportunity to sift through the enormous repositories of imagery generated by the architecture discipline through the ages in order to find novel and bespoke solutions to architectural problems. This article strives to demystify the romantic idea of individual artistic design choices in architecture by providing a glimpse under the hood of the inner workings of Neural Network processes, and thus the extent of their ability to inform architectural design. The approach takes cues from the language and methods employed by experts in Deep Learning such as Hallucinations, Dreaming, Style Transfer and Vision. The presented approach is the base for an in-depth exploration of its meaning as a cultural technique within the discipline. Culture in the extent of this article pertains to ideas such as the differentiation between symbolic and material cultures, in which symbols are defined as the common denominator of a specific group of people.1 The understanding and exchange of symbolic values is inherently connected to language and code, which ultimately form the ingrained texture of any form of coded environment, including the coded structure of Neural Networks. A first proof of concept project was devised by the authors in the form of the Robot Garden. What makes the Robot Garden a distinctively novel project is the motion from a purely two dimensional approach to designing with the aid of Neural Networks, to the exploration of 2D to 3D Neural Style Transfer methods in the design process.

Sign in / Sign up

Export Citation Format

Share Document