Artificial Neural Network Learning Research Articles

Remote Recognition of Human Emotions Using Deep Machine Learning of Artificial Neural Networks

Abstract Currently, there is a need in society to use digital and cybernetic methods of remote diagnostics of a person’s mental state. Using a digital or cyberphysical system in the process of remote recognition of the patient’s mental state, it is possible to increase the effectiveness of recognizing the actual psycho-emotional state of the patient, both in the consulting mode and in dynamic observation. For remote assessment of the mental state, methods are widely used based on recognition of facial activity, which is reflexively associated with the display of the psycho-emotional state. In this paper, the authors propose a new approach to creating such a methodology. This work was supported by the RFBR grant 18-07-00987.

Implementation of ANN technique for performance prediction of solar thermal systems: A Comprehensive Review

Solar thermal systems (STS) are efficient and environmentally safe devices to meet the rapid increasing energy demand now a days. But it is very important to optimize their performance under required operating condition for efficient usage. Hence intelligent system-based techniques like artificial neural network (ANN) play an important role for system performance prediction in accurate and speedy way. In present paper, it is attempted to scrutinize the approach of ANN as an intelligent system-based method to accurately optimize the performance prediction of different solar thermal systems. Here, 25 research works related to various solar thermal systems have been reviewed and summarized to understand the impact of different ANN models and learning algorithms on performance prediction of STS. Using ANN, a brief stepwise summary of researchers’ work on various STS like solar air heaters, solar stills, solar cookers, solar dryers and solar hybrid systems, their predictions (results) and architectures (network and learning algorithms) in the literature till now, are also discussed here. This paper will genuinely help future researchers overview the work concisely related to solar thermal system performance prediction using various types of ANN models and learning algorithm and compare it with other global methods of machine learning. Citation: Ahmad, A., Ghritlahre, H. K., and Chandrakar, P. (2020). Implementation of ANN technique for performance prediction of solar thermal systems: A Comprehensive Review. Trends in Renewable Energy, 6, 12-36. DOI: 10.17737/tre.2020.6.1.00110

Logic-Enhanced Adaptive Network-Based Fuzzy Classifier for Fall Recognition in Rehabilitation

Currently, the most widely adopted fall prediction methods use kinematic sensors for data collection and set thresholds to identify a fall based on artificial experience or neural network learning algorithms. These methods require classification and calibration in advance. Striking a balance between sensitivity and specificity is difficult when setting thresholds. Backpropagation (BP), support vector machines (SVMs) and other neural network algorithm models require professional expertise and are too complicated, difficult to understand, and computationally expensive, which renders embedded development with these models difficult. In response to these problems, this paper builds a fuzzy logic-enhanced adaptive neural network classifier (FLEANN); uses the prior knowledge of experts to construct fuzzy rules; employs neural networks to drive the underlying data to confirm and optimize logical rules; and utilizes an adaptive fuzzy neural network. The parameters of the algorithm are modified and optimized using a large amount of data training to improve the heuristics, transparency, and robustness of the neural network. The enhanced adaptive fuzzy neural network is applied in rehabilitation training for the classification of imprecise, uncertain, and nonlinear falls; abnormal gait; and normal gait. The experimental results confirm that the accuracy of this classifier is better than that of conventional neural network classifiers and that its logical structure is clear, which enables its application to embedded development. The reduction in computational demand enables the elimination of high-configuration PCs and reliance on a single chip microcomputer.

The Perception–Action Hierarchy and its Implementation Using Binons (Binary Neurons)

Abstract The perception–action hierarchy contains a model of the environment as experienced based on what has been recognized and done. Binons (binary neurons) can be used to represent and implement this hierarchy. Binons are simple deterministic artificial neural nodes that represent relationships. They have two source nodes and are reused by zero or more target nodes. Binons are general purpose components that interact in an object-oriented fashion. The two types of binons are spatial and temporal. Spatial binons represent simultaneously occurring patterns of percepts and actions. Temporal binons represent sequential patterns of percepts and actions. Two kinds of temporal binons are used to learn and control behaviour. They are the action and expectation control binons. They are equivalent to command neurons in neuroscience, production rules in cognitive architectures, or the forward model in motor control when combined together. Learning takes place in the three stages of babbling, practicing and automaticity. The resulting hierarchy is a transparent, compositional, unsupervised, continuously growing, deep learning artificial neural network. The hierarchy is part of the Adaptron cognitive architecture.

Tourism Demand and the COVID-19 Pandemic: An LSTM Approach

This paper investigates the expected results of the current COVID-19 outbreak to arrivals of Chinese tourists to the USA and Australia. The growing market share of Chinese tourism and the fact that the county was the first to experience the pandemic make China a suitable proxy for predictions on global tourism. We employ data from the 2003 SARS outbreak to train a deep learning artificial neural network named Long Short Term Memory (LSTM). The neural network is calibrated for the particulars of the current pandemic. Our findings, which are cross-validated using backtesting, suggest that recovery of arrivals to pre-crisis levels can take from 6 to 12 months and this can have significant adverse effects not only on the tourism industry but also on other sectors that interact with it.

Optimization of Interval Type-2 Fuzzy Logic System for Software Reliability Prediction

Since real world application is fraught with high amount of uncertainty, such as applicable to software reliability, there should be a method of handling the uncertainty. This paper presents a model to properly handle uncertainty in software data for effective prediction of the reliability of software at the early phase of software development process. In this paper we employed a Takagi-Sugeno-Kang (TSK)-based interval type 2 fuzzy logic systems with artificial neural network learning for the prediction of software reliability. The degree of membership grades of the interval type 2 fuzzy sets (IT2FSs) are obtained using interval type Gaussian membership function with fixed mean and uncertain standard deviation. The parameters of the IT2FLS membership functions are optimized using gradient descent (GD) back-propagation algorithm. As inputs to the system, reliability relevant software requirement metrics and the software size metrics are used. The proposed new approach makes use of qualitative data of requirement metrics of twenty three real software projects to examine its predictive ability. The performance of the model is evaluated using five performance metrics and found to provide better results when compared with existing approaches.

Attribution of Marine Crop Production in the United States of America Based on Artificial Neural Network Learning

Liu, C., 2019. Attribution of marine crop production in the United States of America based on artificial neural network learning. In: Li, L.; Wan, X.; and Huang, X. (eds.), Recent Developments in Practices and Research on Coastal Regions: Transportation, Environment and Economy. Journal of Coastal Research Journal of Coastal Research, Special Issue No. 98, pp. 277–283. Coconut Creek (Florida), ISSN 0749-0208.Marine crops play an important role in the food chain and in agriculture. Marine crop products are used as livestock feed and to meet people's food requirements. This paper examines what factors cause differences in marine crop production and attribution to marine crop yield. The paper builds a marine crop production model based on an artificial neural network. Then it analyzes the sensitivity of all factors to understand their contributions to marine crop production.

Intellectual computer technologies in designing vehicles

Problem. Today, the scientific and technological sphere has become the main arena of competition of states in the world, and the possession of so-called “critical technologies” (CT) is used as one of the important instruments of geopolitics. Such technologies are crucial for expanding the possibilities of the state defense and achieving the goals of national security, primarily military, military-economic and scientific as well as technological security. Selection of CT is used to determine the priorities of scientific and technological development of states and military-technical policy and are crucial for the process of creating promising weapons and military equipment. Goal. The purpose of the article is to analyze the main trends and approaches to the concept of vehicle development based on the convergence of intellectual critical technologies. Methodology. For the effective development of vehicles it is necessary to use the technology of virtual reality, synergistic approach, evolutionary methods of modeling, methods of deep learning of artificial multilayer neural networks. Results. Advanced technology allows us to reduce the cost of developing new models by cutting the number of real prototypes, each of which is created individually and requires significant costs. Originality. Despite all the disadvantages, improved methods of deep learning open up new opportunities for an effective analysis of large volumes of unstructured data. Companies that use deep training in their tasks will be able to get more accurate analytics results without having to spend a lot of time learning the system. The main tendencies and approaches to the concept of the development of vehicles on the basis of convergence of intellectual critical technologies are analyzed. Practical value. National CTs are of key importance for expanding resources of Ukraine and achieving the goals of national security, in particular, scientific and technological security

Proposing two new metaheuristic algorithms of ALO-MLP and SHO-MLP in predicting bearing capacity of circular footing located on horizontal multilayer soil

In this study, for the issue of shallow circular footing’s bearing capacity (also shown as Fult), we used the merits of artificial neural network (ANN), while optimized it by two metaheuristic algorithms (i.e., ant lion optimization (ALO) and the spotted hyena optimizer (SHO)). Several studies demonstrated that ANNs have significant results in terms of predicting the soil’s bearing capacity. Nevertheless, most models of ANN learning consist of different disadvantages. Accordantly, we focused on the application of two hybrid models of ALO–MLP and SHO–MLP for predicting the Fult placed in layered soils. Moreover, we performed an Extensive Finite Element (FE) modeling on 16 sets of soil layer (soft soil placed onto stronger soil and vice versa) considering a database that consists of 703 testing and 2810 training datasets for preparing the training and testing datasets. The independent variables in terms of ALO and SHO algorithms have been optimized by taking into account a trial and error process. The input data layers consisted of (i) upper layer foundation/thickness width (h/B) ratio, (ii) bottom and topsoil layer properties (for example, six of the most important properties of soil), (iii) vertical settlement (s), (iv) footing width (B), where the main target was taken Fult. According to RMSE and R2, values of (0.996 and 0.034) and (0.994 and 0.044) are obtained for training dataset and values of (0.994 and 0.040) and (0.991 and 0.050) are found for the testing dataset of proposed SHO–MLP and ALO–MLP best-fit prediction network structures, respectively. This proves higher reliability of the proposed hybrid model of SHO–MLP in approximating shallow circular footing bearing capacity.

A value of respiratory muscle strength indicators to determine severity of chronic obstructive pulmonary disease using artificial neural networks

The aim of the study was to analyze a diagnostic value of respiratory muscle (RM) strength indicators to assess severity of chronic obstructive pulmonary disease (COPD) using machine learning methods and artificial neural networks (ANN). Methods . One hundred and fifteen males with acute exacerbation of COPD were involved in the study. RM strength indicators (MEP, MIP, and SNIP), demographic parameters, spirometry, blood gases, dyspnea with mMRC and CAT scales were measured. Statistical analysis was performed using Mann-Whitney’s, Fisher’s and Tukey’s tests and correlation analysis. RM strength model was performed using linear and nonlinear regression analysis. COPD stratification model was performed using ANN. Results . RM strength models in healthy males and COPD patients allowed estimation the impact of different factors on the RM functional status. Comparison of COPD stratification for severity using the mathematical model or expert diagnosis showed that combination of FEV1 with other indicators could increase the accuracy of ANN model. MIP, the total body mass, partial CO2 tension in the arterial blood and serum fibrinogen concentration were the most valuable indicators. Moreover, MIP was considered as the universal predictor increasing the accuracy of all models. Conclusion . Practical application of ANN models in telemedicine projects is related to the improvement of ANN architecture and development of informational services which would allow a real-time assessment of the patient's condition.

Advanced Stochastic Optimization Algorithm for Deep Learning Artificial Neural Networks in Banking and Finance Industries

One of the objectives of this paper is to incorporate fat-tail effects into, for instance, Sigmoid in order to introduce Transparency and Stability into the existing stochastic Activation Functions. Secondly, according to the available literature reviewed, the existing set of Activation Functions were introduced into the Deep learning Artificial Neural Network through the “Window” not properly through the “Legitimate Door” since they are “Trial and Error “and “Arbitrary Assumptions”, thus, the Author proposed a “Scientific Facts”, “Definite Rules: Jameel’s Stochastic ANNAF Criterion”, and a “Lemma” to substitute not necessarily replace the existing set of stochastic Activation Functions, for instance, the Sigmoid among others. This research is expected to open the “Black-Box” of Deep Learning Artificial Neural networks. The author proposed a new set of advanced optimized fat-tailed Stochastic Activation Functions EMANATED from the AI-ML-Purified Stocks Data namely; the Log – Logistic (3P) Probability Distribution (1st), Cauchy Probability Distribution (2nd), Pearson 5 (3P) Probability Distribution (3rd), Burr (4P) Probability Distribution (4th), Fatigue Life (3P) Probability Distribution (5th), Inv. Gaussian (3P) Probability Distribution (6th), Dagum (4P) Probability Distribution (7th), and Lognormal (3P) Probability Distribution (8th) for the successful conduct of both Forward and Backward Propagations of Deep Learning Artificial Neural Network. However, this paper did not check the Monotone Differentiability of the proposed distributions. Appendix A, B, and C presented and tested the performances of the stressed Sigmoid and the Optimized Activation Functions using Stocks Data (2014-1991) of Microsoft Corporation (MSFT), Exxon Mobil (XOM), Chevron Corporation (CVX), Honda Motor Corporation (HMC), General Electric (GE), and U.S. Fundamental Macroeconomic Parameters, the results were found fascinating. Thus, guarantee, the first three distributions are excellent Activation Functions to successfully conduct any Stock Deep Learning Artificial Neural Network. Distributions Number 4 to 8 are also good Advanced Optimized Activation Functions. Generally, this research revealed that the Advanced Optimized Activation Functions satisfied Jameel’s ANNAF Stochastic Criterion depends on the Referenced Purified AI Data Set, Time Change and Area of Application which is against the existing “Trial and Error “and “Arbitrary Assumptions” of Sigmoid, Tanh, Softmax, ReLu, and Leaky ReLu.

Detection of sunn pest-damaged wheat grains using artificial bee colony optimization-based artificial intelligence techniques.

In this study, artificial intelligence models that identify sunn pest-damaged wheat grains (SDG) and healthy wheat grains (HWG) are presented. Svevo durum wheat cultivated in Konya province, Turkey is used for the process, with 150 HWG and 150 SDG being used for classification. Thanks to the constructed imaging setup, photos of the 300 wheat grains are obtained. Seventeen visual features of each wheat grain are extracted by image-processing techniques and evaluated in three different groups of dimension, texture and pattern as visual parameters. Artificial bee colony (ABC) optimization-based artificial neural network (ANN) and extreme learning machine (ELM) algorithms are implemented to classify the damaged wheat grains. A correlation-based feature selection (CFS) technique is also utilized to find the most effective among the 17 features. In the classification process using five selected features, the mean absolute error (MAE) and root mean square error (RMSE) values for ABC-based ANN are calculated as 0.00174 and 0.00433 respectively. The proposed technique is integrated into graphical user interface (GUI) software to construct an effective detection system for practical use. The results indicate that, thanks to the modified ANN algorithm and implemented CFS algorithm, the detection accuracy of damaged wheat grains is considerably increased. © 2019 Society of Chemical Industry.

Performance evaluation of Botnet DDoS attack detection using machine learning

Botnet is regarded as one of the most sophisticated vulnerability threats nowadays. A large portion of network traffic is dominated by Botnets. Botnets are conglomeration of trade PCs (Bots) which are remotely controlled by their originator (BotMaster) under a Command and-Control (C&C) foundation. They are the keys to several Internet assaults like spams, Distributed Denial of Service Attacks (DDoS), rebate distortions, malwares and phishing. To over the problem of DDoS attack, various machine learning methods typically Support Vector Machine (SVM), Artificial Neural Network (ANN), Naive Bayes (NB), Decision Tree (DT), and Unsupervised Learning (USML) (K-means, X-means etc.) were proposed. With the increasing popularity of Machine Learning in the field of Computer Security, it will be a remarkable accomplishment to carry out performance assessment of the machine learning methods given a common platform. This could assist developers in choosing a suitable method for their case studies and assist them in further research. This paper performed an experimental analysis of the machine learning methods for Botnet DDoS attack detection. The evaluation is done on the UNBS-NB 15 and KDD99 which are well-known publicity datasets for Botnet DDoS attack detection. Machine learning methods typically Support Vector Machine (SVM), Artificial Neural Network (ANN), Naive Bayes (NB), Decision Tree (DT), and Unsupervised Learning (USML) are investigated for Accuracy, False Alarm Rate (FAR), Sensitivity, Specificity, False positive rate (FPR), AUC, and Matthews correlation coefficient (MCC) of datasets. Performance of KDD99 dataset has been experimentally shown to be better as compared to the UNBS-NB 15 dataset. This validation is significant in computer security and other related fields.

Detection of flood disaster system based on IoT, big data and convolutional deep neural network

Natural disasters could be defined as a blend of natural risks and vulnerabilities. Each year, natural as well as human-instigated disasters, bring about infrastructural damages, distresses, revenue losses, injuries in addition to huge death roll. Researchers around the globe are trying to find a unique solution to gather, store and analyse Big Data (BD) in order to predict results related to flood based prediction system. This paper has proposed the ideas and methods for the detection of flood disaster based on IoT, BD, and convolutional deep neural network (CDNN) to overcome such difficulties. First, the input data is taken from the flood BD. Next, the repeated data are reduced by using HDFS map-reduce (). After removal of repeated data, the data are pre-processed using missing value imputation and normalization function. Then, centred on the pre-processed data, the rule is generated by using a combination of attributes method. At the last stage, the generated rules are provided as the input to the CDNN classifier which classifies them as a) chances for the occurrence of flood and b) no chances for the occurrence of a flood. The outcomes obtained from the proposed CDNN method is compared parameters like Sensitivity, Specificity, Accuracy, Precision, Recall and F-score. Moreover, when the outcomes is compared other existing algorithms like Artificial Neural Network (ANN) & Deep Learning Neural Network (DNN), the proposed system gives is very accurate result than other methods.

Assessment of Artificial Neural Networks Learning Algorithms and Training Datasets for Solar Photovoltaic Power Production Prediction

The capability of accurately predicting the Solar Photovoltaic (PV) power productions is crucial to effectively control and manage the electrical grid. In this regard, the objective of this work is to propose an efficient Artificial Neural Network (ANN) model in which 10 different learning algorithms (i.e., different in the way in which the adjustment on the ANN internal parameters is formulated to effectively map the inputs to the outputs) and 23 different training datasets (i.e., different combinations of the real-time weather variables and the PV power production data) are investigated for accurate one day-ahead power production predictions with short computational time. In particular, the correlations between different combinations of the historical wind speed, ambient temperature, global solar radiation, PV power productions, and the time stamp of the year are examined for developing an efficient solar PV power production prediction model. The investigation is carried out on a 231 kWac grid-connected solar PV system located in Jordan. An ANN that receives in input the whole historical weather variables and PV power productions, and the time stamp of the year accompanied with Levenberg-Marquardt (LM) learning algorithm is found to provide the most accurate predictions with less computational efforts. Specifically, an enhancement reaches up to 15%, 1%, and 5% for the Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and Coefficient of Determination (R2) performance metrics, respectively, compared to the Persistence prediction model of literature.

Coercing machine learning to output physically accurate results

Many machine/deep learning artificial neural networks are trained to simply be interpolation functions that map input variables to output values interpolated from the training data in a linear/nonlinear fashion. Even when the input/output pairs of the training data are physically accurate (e.g. the results of an experiment or numerical simulation), interpolated quantities can deviate quite far from being physically accurate. Although one could project the output of a network into a physically feasible region, such a postprocess is not captured by the energy function minimized when training the network; thus, the final projected result could incorrectly deviate quite far from the training data. We propose folding any such projection or postprocess directly into the network so that the final result is correctly compared to the training data by the energy function. Although we propose a general approach, we illustrate its efficacy on a specific convolutional neural network that takes in human pose parameters (joint rotations) and outputs a prediction of vertex positions representing a triangulated cloth mesh. While the original network outputs vertex positions with erroneously high stretching and compression energies, the new network trained with our physics “prior” remedies these issues producing highly improved results.

Human Location Classification for Outdoor Environment

Outdoor localisation can offer great capabilities in security and perimeter surveillance applications. The localisation of people become more challenges when involving with the nonlinear environment. GPS and CCTV are two localisation techniques usually use to localise human in an outdoor environment. However, they have weaknesses which result in low localisation accuracy. Therefore, the application of Device-free localisation (DFL), together with the Internet of things (IoT) is more appropriate due to their capability to detect the human body in all environmental conditions, and there is no problem losing signals as faced by GPS. This system offers excellent potential in humans localisation because humans can be detected wirelessly without any tracking device attached. In developing the DFL system, the main concern is the localisation accuracy. Although the existing DFL system gives significant result to the localisation, the accuracy is still low due to the large variation in RSSI values. Hence, a Radio Tomographic Imaging-based ANN classification (RTI-ANN) approach is proposed to increase the localisation accuracy. This Artificial Neural Network (ANN) is designed to learn the Radio Tomography imaging (RTI) input for classification purpose. Even though the RTI gives a good result to the localisation, however, it suffers from smearing effect. To eliminates this smearing area and background noise, pre-processing of the RTI image is required. Thus, extracting the valuable information technique from the RTI image has been proposed. By extracting the valuable information data from the RTI image, about 61% to 66% of the smearing noise is removed depending on the size of the RTI image. Only data directly associated with human attenuation used for training and learning of ANN. The experimental results show ANN system can localise human in the right zone for a given dataset.

Replacement of numerical simulations with machine learning in the inverse problem of two-phase flow in porous medium

A possibility to replace full-physics numerical simulations with machine-learning-based algorithms in inverse problems of multiphase flow in porous media is studied on an example of specialized oil-well tests. The performance function is computed at each iteration of the inverse problem solution using an artificial neural network (ANN) instead of forward numerical simulations. Proper ANN structure, training set, and learning algorithm are established and implemented. Achieved approximation quality for the performance function on a test sample is well suitable for the inverse problem solution. Further improvements and alternative ANN formulations are proposed for practical applications.

Artificial Neural Network and Machine Learning Based Methods for Population Estimation of Rohingya Refugees: Comparing Data-Driven and Satellite Image-Driven Approaches

Manual field-based population census data collection method is slow and expensive, especially for refugee management situations where more frequent censuses are necessary. This study aims to explore the approaches of population estimation of Rohingya migrants using remote sensing and machine learning. Two different approaches of population estimation viz., (i) data-driven approach and (ii) satellite image-driven approach have been explored. A total of 11 machine learning models including Artificial Neural Network (ANN) are applied for both approaches. It is found that, in situations where the surface population distribution is unknown, a smaller satellite image grid cell length is required. For data-driven approach, ANN model is placed fourth, Linear Regression model performed the worst and Gradient Boosting model performed the best. For satellite image-driven approach, ANN model performed the best while Ada Boost model has the worst performance. Gradient Boosting model can be considered as a suitable model to be applied for both the approaches.

Feasibility study on application of an artificial neural network for automatic design of a reactor core at the Kyoto University Critical Assembly

Designing reactor cores by means of an artificial neural network is a difficult challenge, because there are many variables in the core configuration. Especially, for designing a new type of reactor core with an artificial neural network, little (if any) previous data exists, and the appropriate number of results, such as multiplication factors and neutron fluxes, which require a large computational time for a single calculation, should be previously obtained for training the machine learning of the artificial neural network. This paper presents a feasibility study on the automatic design of a research reactor core (a simplified core based on the Kyoto University Critical Assembly) using an artificial neural network. By imitating conventional design procedure, a way to design the core is developed by means of the artificial neural network and automatic machine learning. After setting a design goal of the reactor core, the fuel assembly and core are designed by the proposed method and compared with those designed by conventional design procedure. The results reveal that the reactor core designed by the proposed method performs well and will, therefore, provide a clue to innovation in future reactor design with artificial intelligence.