Concept Of Artificial Neural Network Research Articles

Healthcare Big Data Analysis with Artificial Neural Network for Cardiac Disease Prediction

The generation of a huge volume of structured, semi-structured and unstructured real-time health monitoring data and its storage in the form of electronic health records (EHRs) need to be processed and analyzed intelligently to provide timely healthcare. A big data analytic platform is an alternative to the traditional warehouse paradigms for the processing, analysis and storage of the tremendous volume of healthcare data. However, the manual analysis of these voluminous, multi-variate patients data is tedious and error-prone. Therefore, an intelligent solution method is highly essential to perform multiple correlation analyses for disease diagnosis and prediction. In this paper, first, a structural framework is proposed to process the huge volume of cardiological big data generated from the hospital and patients. Then, an intelligent analytical model for the cardiological big data analysis is proposed by combining the concept of artificial neural network (ANN) and particle swarm optimization (PSO) to predict the abnormalities in the cardiac health of a person. In the proposed cardiac disease prediction model, an extensive electrocardiogram (ECG) data analysis method is developed to identify the probable normal and abnormal cardiac feature points. Simulation results show the effects of a number of attributes for improving the accuracy of the cardiac disease prediction and data processing time in the cloud with an increase in the number of the cardiac patients.

Predicting Future Land Use Utilizing Economic and Land Surface Parameters with ANN and Markov Chain Models

The main aim of this study is to comprehensively analyze the dynamics of land use and land cover (LULC) changes in the Bathinda region of Punjab, India, encompassing historical, current, and future trends. To forecast future LULC, the Cellular Automaton–Markov Chain (CA) based on artificial neural network (ANN) concepts was used using cartographic variables such as environmental, economic, and cultural. For segmenting LULC, the study used a combination of ML models, such as support vector machine (SVM) and Maximum Likelihood Classifier (MLC). The study is empirical in nature, and it employs quantitative analyses to shed light on LULC variations through time. The result indicates that the barren land is expected to shrink from 55.2 km2 in 1990 to 5.6 km2 in 2050, signifying better land management or increasing human activity. Vegetative expanses, on the other hand, are expected to rise from 81.3 km2 in 1990 to 205.6 km2 in 2050, reflecting a balance between urbanization and ecological conservation. Agricultural fields are expected to increase from 2597.4 km2 in 1990 to 2859.6 km2 in 2020 before stabilizing at 2898.4 km2 in 2050. Water landscapes are expected to shrink from 13.4 km2 in 1990 to 5.6 km2 in 2050, providing possible issues for water resources. Wetland regions are expected to decrease, thus complicating irrigation and groundwater reservoir sustainability. These findings are confirmed by strong statistical indices, with this study’s high kappa coefficients of Kno (0.97), Kstandard (0.95), and Klocation (0.97) indicating a reasonable level of accuracy in CA prediction. From the result of the F1 score, a significant issue was found in MLC for segmenting vegetation, and the issue was resolved in SVM classification. The findings of this study can be used to inform land use policy and plans for sustainable development in the region and beyond.

New Machine-Learning Control Charts for Simultaneous Monitoring of Multivariate Normal Process Parameters with Detection and Identification

Simultaneous monitoring of the process parameters in a multivariate normal process has caught researchers’ attention during the last two decades. However, only statistical control charts have been developed so far for this purpose. On the other hand, machine-learning (ML) techniques have rarely been developed to be used in control charts. In this paper, three ML control charts are proposed using the concepts of artificial neural networks, support vector machines, and random forests techniques. These ML techniques are trained to obtain linear outputs, and then based on the concepts of memory-less control charts, the process is classified into in-control or out-of-control states. Two different input scenarios and two different training methods are used for the proposed ML structures. In addition, two different process control scenarios are utilized. In one, the goal is only the detection of the out-of-control situation. In the other one, the identification of the responsible variable (s)/process parameter (s) for the out-of-control signal is also an aim (detection–identification). After developing the ML control charts for each scenario, we compare them to one another, as well as to the most recently developed statistical control charts. The results show significantly better performance of the proposed ML control charts against the traditional memory-less statistical control charts in most compared cases. Finally, an illustrative example is presented to show how the proposed scheme can be implemented in a healthcare process.

NNeduca: A software environment to teach artificial neural networks

AbstractArtificial neural networks are an integral part of the curriculum in many undergraduate computer science programs. This paper introduces NNeduca, a simulation software system designed to teach undergraduate students the fundamental concepts of artificial neural networks. The system is written in Java and aims to provide an intuitive user interface, support for research and learning activities, and the ability to expand. This tool allows students to design and train a neural network with any architecture they desire and visualize some artificial neural network theoretical concepts such as definitions, topologies, training methods, and structure. An overview of educational software systems to aid in learning the fundamental concepts of neural networks was created based on a systematic literature review. A comparison of existing simulation systems and the developed NNeduca tool was performed in this paper. The evaluation was carried out using a newly developed model for assessing the quality of selected systems using established criteria formed as a result of a thorough examination of relevant methods of evaluating educational software. The usability evaluation results show that the NNeduca tool received the highest ratings, indicating that it can significantly improve the teaching process in artificial neural network courses.

A Short Overview of the Main Concepts of Artificial Neural Networks

A significant increase in computer performance, the accumulation of a large amount of data necessary for training deep neural networks, the development of training methods for neural networks that allow you to quickly and efficiently train networks consisting of a hundred or more layers, has led to significant progress in training deep neural networks. This allowed deep neural networks to take a leading position among machine learning methods. In this work, neural network paradigms (and their methods of training and functioning) considers, such as Rosenblatt perceptron, multilayer perceptrons, radial basis function network, Kohonen network, Hopfield network, Boltzmann machine, and deep neural networks. As a result of comparative consideration of these paradigms, it can be concluded that they all successfully solve the tasks set before them, but now, deep neural networks are the most effective mechanism for solving intellectual practical tasks.

Parameter identification for a damage phase field model using a physics-informed neural network

This work applies concepts of artificial neural networks to identify the parameters of a mathematical model based on phase fields for damage and fracture. Damage mechanics is the part of the continuum mechanics that models the effects of micro-defect formation using state variables at the macroscopic level. The equations that define the model are derived from fundamental laws of physics and provide important relationships among state variables. Simulations using the model considered in this work produce good qualitative and quantitative results, but many parameters must be adjusted to reproduce certain material behavior. The identification of model parameters is considered by solving an inverse problem that uses pseudo-experimental data to find the best values that fit the data. We apply physics informed neural network and combine some classical estimation methods to identify the material parameters that appear in the damage equation of the model. Our strategy consists of a neural network that acts as an approximating function of the damage evolution with output regularized using the residue of the differential equation. Three stages of optimization seek the best possible values for the neural network and the material parameters. The training alternates between the fitting of only the pseudo-experimental data or the total loss that includes the regularizing terms. We test the robustness of the method to noisy data and its generalization capabilities using a simple physical case for the damage model. This procedure deals better with noisy data in comparison with a more standard PDE-constrained optimization method, and it also provides good approximations of the material parameters and the evolution of damage.

Heart disease prediction using scaled conjugate gradient backpropagation of artificial neural network

Heart disease is a deadly disease in human life. The mortality rate from any disease is the highest in the world. Therefore, before reaching the final stage of this heart disease, all precautionary measures must be taken. For this reason without the help of any kind of traditional methods, if we can scientifically diagnose heart disease at an early stage through various decision support systems, then surely death rate of this disease will decrease in the whole world. Many researchers investigate the diagnosis of heart disease by creating various intelligent medical decision support systems. Artificial neural network concepts represent the highest predictive accuracy over medical data compared to other decision support systems. In this paper, we propose a better prediction method for the existence of heart disease through the scaled conjugate gradient backpropagation of artificial neural networks using K-fold cross-validation. For cardiac datasets, the University of California Irvine (UCI) Machine Learning Repository and IEEE data port have been used. For Cleveland processed heart dataset, the proposed system uses 13 input attributes and provides minimum 63.3803% and maximum 100% accurate results; similarly, for Cleveland Hungarian Statlog heart dataset, the proposed system uses 11 input attributes and provides minimum 88.4754% and maximum 100% accurate results by estimating the presence and absence of heart disease during testing.

A Logically Reversible Double Feynman Gate with Molecular Engineered Bacteria Arranged in an Artificial Neural Network-Type Architecture.

Reversible logic gates are the key components of reversible computing that map inputs and outputs in a certain one-to-one pattern so that the output signals can reveal the pattern of the input signals. One of the main research foci of reversible computing is the implementation of basic reversible gates by various modalities. Though true thermodynamic reversibility cannot be attained within living cells, the high energy efficiency of biological reactions inspires the implementation of reversible computation in living cells. The implementation of synthetic genetic circuits is mostly based on conventional irreversible computing, and the implementation of logical reversibility in living cells is rare. Here, we constructed a 3-input-3-output synthetic genetic reversible double Feynman logic gate with a population of genetically engineered E. coli cells. Instead of following hierarchical electronic design principles, we adapted the concept of artificial neural networks (ANN) and built a single-layer artificial network-type architecture with five different engineered bacteria, named bactoneurons. We used three extracellular chemicals as input signals and the expression of three fluorescence proteins as the output signals. The cellular devices, which combine the input chemical signals linearly and pass them through a nonlinear activation function and represent specific bactoneurons, were built by designing and creating small synthetic genetic networks inside E. coli. The weights of each of the inputs and biases of individual bactoneurons in the bacterial ANN were adjusted by optimizing the synthetic genetic networks. When arranging the five bactoneurons through an ANN-type architecture, the system generated a double Feynman gate function at the population level. To our knowledge, this is the first reversible double Feynman gate realization with living cells. This work may have significance in development of biocomputer technology, reversible computation, ANN wetware, and synthetic biology.

A neural network-based approach for bending analysis of strain gradient nanoplates

Purpose of this paper is the presentation of a novel Machine Learning (ML) technique for nanoscopic study of thin nanoplates. The second-order strain gradient theory is used to derive the governing equations and account for size effects. The ML framework is based on Physics-Informed Neural Networks (PINNs), a new concept of Artificial Neural Networks (ANNs) enriched with the mathematical model of the problem. Training of PINNs is performed using a highly efficient learning algorithm, known as Extreme Learning Machine (ELM). Two applications of this ANNs-based method are illustrated: solution of the Partial Differential Equations (PDEs) modeling the flexural response of thin nanoplates (direct problem), and identification of the length scale parameter of the nanoplate mathematical model with the aid of measurement data (inverse problem). Comparison with analytical and Finite Element (FE) solutions demonstrate the accuracy and efficiency of this ML framework as meshfree solver of high-order PDEs. The stability and reliability of the present method are verified through parameter studies on hyperparameters, network architectures, data noise and training initializations. The results presented give evidence of the effectiveness and robustness of this new ML approach for solving both direct and inverse nanoplate problems.

Performance Prediction of solar still using Artificial neural network

The development of various solar energy systems has emerged as one of the most important answers to the problem of rising energy demand. By utilising the notion of Intelligent system-based methodologies to forecast the performance of solar stills working in an air-dry environment. The artificial neural network concept was applied to forecast the performance of single slope single basin solar stills in this study.Data gathered from previously published articles and used it to forecast the performance of conventional solar still. The developed model can be used to forecast productivity with accuracy of 0.99459 by using LM algorithm.

Advanced Technology in Agriculture Industry by Implementing Image Annotation Technique and Deep Learning Approach: A Review

The implementation of intelligent technology in agriculture is seriously investigated as a way to increase agriculture production while reducing the amount of human labor. In agriculture, recent technology has seen image annotation utilizing deep learning techniques. Due to the rapid development of image data, image annotation has gained a lot of attention. The use of deep learning in image annotation can extract features from images and has been shown to analyze enormous amounts of data successfully. Deep learning is a type of machine learning method inspired by the structure of the human brain and based on artificial neural network concepts. Through training phases that can label a massive amount of data and connect them up with their corresponding characteristics, deep learning can conclude unlabeled data in image processing. For complicated and ambiguous situations, deep learning technology provides accurate predictions. This technology strives to improve productivity, quality and economy and minimize deficiency rates in the agriculture industry. As a result, this article discusses the application of image annotation in the agriculture industry utilizing several deep learning approaches. Various types of annotations that were used to train the images are presented. Recent publications have been reviewed on the basis of their application of deep learning with current advancement technology. Plant recognition, disease detection, counting, classification and yield estimation are among the many advancements of deep learning architecture employed in many applications in agriculture that are thoroughly investigated. Furthermore, this review helps to assist researchers to gain a deeper understanding and future application of deep learning in agriculture. According to all of the articles, the deep learning technique has successfully created significant accuracy and prediction in the model utilized. Finally, the existing challenges and future promises of deep learning in agriculture are discussed.

Methodology for Evaluating Projects Aimed at Service Quality Using Artificial Intelligence Techniques

The quality of the electrical energy distribution service has a significant impact on consumer satisfaction and the guarantee of the right of concession for the distribution companies. For the utility that is the object of the case study, the main continuity of service indicators was at levels below the regulatory limits. Still, due to budget constraints, the forecast of the benefit that improvement or expansion projects bring to continuity indicators must be assertive for a proper direction of investments and decision making. In this work, a methodology for evaluating projects to improve the quality of service was proposed, with the realization of the estimated benefit associated with the reduction in continuity indicators (DEC and FEC), using concepts of artificial neural networks and evolutionary algorithms. The results were obtained from a three-year history of execution of the utility’s projects. Based on the correlation analysis, a variable selection procedure was developed, where the historical values of interruptions by cause were considered as input, and the results of the continuity indicators associated with the types of projects studied form the outputs of the model. The model was developed using an artificial neural network of the multilayer perceptron type. The results obtained by simulating the new methodology presented absolute relative errors 100 times smaller for estimating the benefits of the projects compared to the current method used by the electric power distributor.

Data Analysis of Related Factors of Adolescent Physical Exercise Behavior Based upon Artificial Neural Network Model

Physical exercise behavior is to protect physical health through scientific physical activity (certain frequency, time, and intensity) in leisure time. The purpose of this paper is to study how to analyze and study the related factors of adolescent physical exercise behavior based on an artificial neural network model and describe the BP learning algorithm. This paper raises the question of the influencing factors of adolescents’ physical exercise behavior. This problem is based on an artificial neural network, so the paper expounds around the concept of artificial neural network and related algorithms and designs and analyzes relevant factors. The experimental results show that among the 4-17-year-old respondents, 45 students have the habit of physical exercise, accounting for 37.5% of the respondents in this age group. Among the 59 people with the habit of physical exercise in this survey, 41 people, accounting for 69.5%, believed that their interest in sports was greatly influenced by their surrounding classmates. There are 40 parents who have one parent who is college or above, accounting for 67.8% and other data. All of them show that the influencing factors of adolescents’ physical exercise behavior come from many aspects.

A Novel Neuro-Optimization Techniques for Inventory Models in Manufacturing Sectors

Inventory modeling or policies are the necessity of every business or a new oil for any industry. In other words, inventory control and management are needed by businessmen or entrepreneurs to make effective strategies, i.e., for making their business profitable. It becomes a lot and a lot of vital for enterprises within the real-life things like producing sector like industry, food trade, etc. Inventory issues common in producing, remanufacturing, and lots of helpful applications like pharmaceutical. An associate improvement model for internal control of circulation enterprises was established to minimize the typical total price in the unit time of the inventory system. As we have seen, lot of researchers have made several attempts in the previous decade for improving inventory control/inventory policies, but due to the dynamic nature of human beings, it is difficult to make perfect and unique inventory for all business sectors. So, in this study, we will use collected data (from several research works done by the researchers, questionnaires, interviews) and then will apply an artificial neural network (ANN) concept to provide an optimized solution. Finally, our model shows economical, correct results, which can be additionally helpful for the inventory researchers to seek out the acceptable technique for determining the economic order quantity systems or creating AN assumption for making new inventory policies. Hence, this study provides helpful algorithms, economical inventory models for producing sectors, and future analysis direction toward our planned work.

A Comparative Assessment of Conventional and Artificial Neural Networks Methods for Electricity Outage Forecasting

The reliability of the power supply depends on the reliability of the structure of the grid. Grid networks are exposed to varying weather events, which makes them prone to faults. There is a growing concern that climate change will lead to increasing numbers and severity of weather events, which will adversely affect grid reliability and electricity supply. Predictive models of electricity reliability have been used which utilize computational intelligence techniques. These techniques have not been adequately explored in forecasting problems related to electricity outages due to weather factors. A model for predicting electricity outages caused by weather events is presented in this study. This uses the back-propagation algorithm as related to the concept of artificial neural networks (ANNs). The performance of the ANN model is evaluated using real-life data sets from Pietermaritzburg, South Africa, and compared with some conventional models. These are the exponential smoothing (ES) and multiple linear regression (MLR) models. The results obtained from the ANN model are found to be satisfactory when compared to those obtained from MLR and ES. The results demonstrate that artificial neural networks are robust and can be used to predict electricity outages with regards to faults caused by severe weather conditions.

A probiotic based product using multi-strain Bacillus species and predictive models for shrimp growth following probiotic intervention

Probiotic bacteria in aquaculture found to have significant effect on health of shrimp and growth by changing the microbial composition of water. The primary objective of the study is to develop a probiotic based product to improve the yield of shrimp by using multi-strain Bacillus species. Towards this, various Bacillus strains, namely, B. subtilis, Bacillus clausii, B. cereus, B. Megaterium, B. pumilus and Bacillus polymyxa were collected and confirmed the strains through biochemical tests in subculture. Further, it is found that all the six strains exhibited good antifungal, antibacterial, antagonistic and enzyme activities. Multi-strain probiotic product as feed for the growth of shrimp was prepared by using the solid state fermentation technique and quality check was done to make sure no contamination. After the product development, the efficacy of the product has been tested by conducting field studies. The parameters such as (i) temperature (ii) pH (iii) dissolved oxygen (iv) total ammonia nitrogen and (v) shrimp weight & (vi) length were investigated for about 120 days and measurements were taken at every 5-day interval. The average initial weight and length of shrimp is 4.2 ± 0.2 g and 0.8 ± 0.1 cm respectively. The average values obtained for 120 days include (i) Temperature (°C): Control = 28 ± 0.3; Treated = 28 ± 0.15 (ii) pH: Control = 8 ± 0.19; Treated = 8 ± 0.12 (iii) Dissolved oxygen (ppm): Control = 5 ± 0.23, Treated = 5 ± 0.21 (iv) Total ammonia nitrogen (ppm): Control = 2 ± 0.2; Treated = 0.8 ± 0.01 (v) Shrimp weight (gm): Control = 16 ± 0.21; Treated = 22 ± 0.14 (vi) Length (cm): Control = 6 ± 0.14; Treated = 8 ± 0.26. The average survival rate was found to be 88.67 ± 1.15% in probiotics ponds and 70.00 ± 3.0% in controlled ponds. From the overall study, it is observed that the weight and length of shrimp has been increased significantly up to sixty days compared to control environment. Two-way ANOVA has been performed to understand the interdependent relation between the input and output variables. Advanced statistical models were developed by using the concepts of Artificial neural network, Multivariate adaptive regression splines and Relevance vector machine to predict the shrimp weight and length. The predicted shrimp weight and shrimp length is found to be in close agreement with those of the corresponding experimental observations. The models are found to be robust, reliable and efficient.

COVIDetection: deep convolutional neural networks-based automatic detection of COVID-19 with chest x-ray images

PurposeUntil recently, COVID-19 was considered a highly contagious air borne infection that leads to fatal pneumonia and other health hazardous infections. The new coronavirus, or type SARS-COV-2, is responsible for COVID-19 and has demonstrated the deadly nature of the respiratory disease that threatens many people worldwide. A clinical study found that a person infected with COVID-19 can experience dry cough, muscle pain, headache, fever, sore throat, and mild to moderate respiratory illness. At the same time, it has a negative effect on the lungs if there is a viral infection. Thus, the lungs can become visible internal organs for diagnosing the severity of COVID-19 infection using chest X-rays and CT scans. Despite the long testing time, RT-PCR is a proven testing method for detecting coronavirus infection. Sometimes there are more false positives and false negatives than the desired percentage. The concept of artificial neural network (ANN) is inspired by the biological neural networks which consists of inter-connected units called artificial neurons. Convolutional neural network (CNN) which is a variant of multilayer perceptron that belongs to a class of feedforward ANN is widely used for various applications due to its enhanced accuracy.MethodTraditional RT-PCR methodology supports for accurate clinical diagnosis, screening for COVID-19 using an X-ray or CT scan of the human lung that can be considered. In this work, a new multi-image augmentation system is proposed based on CNN to detect COVID-19 in the chest using chest X-rays or CT images of people suspected of having the coronavirus.ResultsThe optimal selection of slices/features has led to obtain best results for accuracy and loss. In addition to that the parameter selection reflected optimal true positive rate and false positive rates. The results look promising even with the small publicly available data set in a short period of time.ConclusionThis work presented a model that found to detect positive cases of COVID-19 from chest X-rays using an in-depth training model. The system demonstrates a significant performance improvement over the publicly maintained COVID-19 positive X-ray classification kit, the same dataset of pneumonia chest X-rays. The results look promising even with the small publicly available data set in terms of accuracy and loss as well as with enhanced true positive results.

Real-Time ML-Assisted Hardware-in-the-Loop Electro-Thermal Emulation of LVDC Microgrid on the International Space Station

For being the world’s largest low voltage direct current (LVDC) microgrid (MG) in space, the power generation and distribution systems aboard the International Space Station (ISS) employ a hierarchical assortment of electric power sources, energy storage, control devices, power electronics, and loads operating cooperatively at multifarious system dispositions and multi-stage configurations. At the early phase of design, for such time-critical systems, the trade-off between reliability and convergence rate of device modeling, varying accuracy requirements of control flows, and especially the implementation for real-time performance have brought new challenges and problems for testing and validation of the MG. One of the solutions presented by this paper is to use the hardware-in-the-loop (HIL) emulation, where the MG is emulated using the field-programmable gate array (FPGA) hardware platform. In parallel with the emulation effort, comprehensive modeling solutions for both large-scale photovoltaic (PV) solar array wings (SAWs) and nonlinear behavior model (NBM) of insulated-gate bipolar transistors (IGBTs) have been utilized based on machine learning (ML) concepts of artificial neural network (ANN) and recurrent neural network (RNN). Both system-level (validated by Matlab/Simulink) and device-level (validated by SaberRD) transient simulations are carried out, and the results exhibit high accuracy and fidelity of the models and significant improvements in execution speed and hardware resource consumption.

Topology Optimization for Electromagnetics: A Survey

The development of technologies for the additive manufacturing, in particular of metallic materials, is offering the possibility of producing parts with complex geometries. This opens up to the possibility of using topological optimization methods for the design of electromagnetic devices. Hence, a wide variety of approaches, originally developed for solid mechanics, have recently become attractive also in the field of electromagnetics. The general distinction between gradient-based and gradient-free methods drives the structure of the paper, with the latter becoming particularly attractive in the last years due to the concepts of artificial neural networks. The aim of this paper is twofold. On one hand, the paper aims at summarizing and describing the state-of-art on topology optimization techniques while on the other it aims at showing how the latter methodologies developed in non-electromagnetic framework (e.g., solid mechanics field) can be applied for the optimization of electromagnetic devices. Discussions and comparisons are both supported by theoretical aspects and numerical results.

3D mineral deposit modeling using concepts of blockmodeling and artificial neural networks

3D mineral deposit modeling using concepts of blockmodeling and artificial neural networks