Abstract: In this paper, ways of modeling dynamic measurement
systems are discussed. Specially, for linear system with single-input
single-output, it could be modeled with shallow neural network.
Then, gradient based optimization algorithms are used for searching
the proper coefficients. Besides, method with normal equation and
second order gradient descent are proposed to accelerate the modeling
process, and ways of better gradient estimation are discussed. It
shows that the mathematical essence of the learning objective is
maximum likelihood with noises under Gaussian distribution. For
conventional gradient descent, the mini-batch learning and gradient
with momentum contribute to faster convergence and enhance model
ability. Lastly, experimental results proved the effectiveness of second
order gradient descent algorithm, and indicated that optimization with
normal equation was the most suitable for linear dynamic models.
Abstract: In electrical discharge machining (EDM), a complete and clear theory has not yet been established. The developed theory (physical models) yields results far from reality due to the complexity of the physics. It is difficult to select proper parameter settings in order to achieve better EDM performance. However, modelling can solve this critical problem concerning the parameter settings. Therefore, the purpose of the present work is to develop mathematical model to predict performance characteristics of EDM on Ti-5Al-2.5Sn titanium alloy. Response surface method (RSM) and artificial neural network (ANN) are employed to develop the mathematical models. The developed models are verified through analysis of variance (ANOVA). The ANN models are trained, tested, and validated utilizing a set of data. It is found that the developed ANN and mathematical model can predict performance of EDM effectively. Thus, the model has found a precise tool that turns EDM process cost-effective and more efficient.
Abstract: In recent years, waste tyre problem is considered as one of the most crucial environmental pollution problems facing the world. Thus, reusing waste rubber crumb from recycled tyres to develop highly damping concrete is technically feasible and a viable alternative to landfill or incineration. The utilization of waste rubber in concrete generally enhances the ductility, toughness, thermal insulation, and impact resistance. However, the mechanical properties decrease with the amount of rubber used in concrete. The aim of this paper is to develop artificial neural network (ANN) models to predict the compressive strength of rubberised concrete (RuC). A trained and tested ANN was developed using a comprehensive database collected from different sources in the literature. The ANN model developed used 5 input parameters that include: coarse aggregate (CA), fine aggregate (FA), w/c ratio, fine rubber (Fr), and coarse rubber (Cr), whereas the ANN outputs were the corresponding compressive strengths. A parametric study was also conducted to study the trend of various RuC constituents on the compressive strength of RuC.
Abstract: Studies estimate that there will be 266,120 new cases
of invasive breast cancer and 40,920 breast cancer induced deaths
in the year of 2018 alone. Despite the pervasiveness of this
affliction, the current process to obtain an accurate breast cancer
prognosis is tedious and time consuming. It usually requires a
trained pathologist to manually examine histopathological images and
identify the features that characterize various cancer severity levels.
We propose MITOS-RCNN: a region based convolutional neural
network (RCNN) geared for small object detection to accurately
grade one of the three factors that characterize tumor belligerence
described by the Nottingham Grading System: mitotic count. Other
computational approaches to mitotic figure counting and detection
do not demonstrate ample recall or precision to be clinically viable.
Our models outperformed all previous participants in the ICPR 2012
challenge, the AMIDA 2013 challenge and the MITOS-ATYPIA-14
challenge along with recently published works. Our model achieved
an F- measure score of 0.955, a 6.11% improvement in accuracy from
the most accurate of the previously proposed models.
Abstract: The Semi Interlocking Masonry (SIM) system has been developed in Masonry Research Group at the University of Newcastle, Australia. The main purpose of this system is to enhance the seismic resistance of framed structures with masonry panels. In this system, SIM panels dissipate energy through the sliding friction between rows of SIM units during earthquake excitation. This paper aimed to find the applicability of artificial neural network (ANN) to predict the displacement behaviour of the SIM panel under out-of-plane loading. The general concept of ANN needs to be trained by related force-displacement data of SIM panel. The overall data to train and test the network are 70 increments of force-displacement from three tests, which comprise of none input nodes. The input data contain height and length of panels, height, length and width of the brick and friction and geometry angle of brick along the compressive strength of the brick with the lateral load applied to the panel. The aim of designed network is prediction displacement of the SIM panel by Multi-Layer Perceptron (MLP). The mean square error (MSE) of network was 0.00042 and the coefficient of determination (R2) values showed the 0.91. The result revealed that the ANN has significant agreement to predict the SIM panel behaviour.
Abstract: Over the last few years, the amount of data available on the globe has been increased rapidly. This came up with the emergence of recent concepts, such as the big data and the Internet of Things, which have furnished a suitable solution for the availability of data all over the world. However, managing this massive amount of data remains a challenge due to their large verity of types and distribution. Therefore, locating the required file particularly from the first trial turned to be a not easy task, due to the large similarities of names for different files distributed on the web. Consequently, the accuracy and speed of search have been negatively affected. This work presents a method using Electroencephalography signals to locate the files based on their contents. Giving the concept of natural mind waves processing, this work analyses the mind wave signals of different people, analyzing them and extracting their most appropriate features using multi-objective metaheuristic algorithm, and then classifying them using artificial neural network to distinguish among files with similar names. The aim of this work is to provide the ability to find the files based on their contents using human thoughts only. Implementing this approach and testing it on real people proved its ability to find the desired files accurately within noticeably shorter time and retrieve them as a first choice for the user.
Abstract: In this paper, we propose an optimized brain computer
interface (BCI) system for unspoken speech recognition, based on
the fact that the constructions of unspoken words rely strongly on the
Wernicke area, situated in the temporal lobe. Our BCI system has four
modules: (i) the EEG Acquisition module based on a non-invasive
headset with 14 electrodes; (ii) the Preprocessing module to remove
noise and artifacts, using the Common Average Reference method;
(iii) the Features Extraction module, using Wavelet Packet Transform
(WPT); (iv) the Classification module based on a one-hidden layer
artificial neural network. The present study consists of comparing
the recognition accuracy of 5 Arabic words, when using all the
headset electrodes or only the 4 electrodes situated near the Wernicke
area, as well as the selection effect of the subbands produced by
the WPT module. After applying the articial neural network on the
produced database, we obtain, on the test dataset, an accuracy of
83.4% with all the electrodes and all the subbands of 8 levels of the
WPT decomposition. However, by using only the 4 electrodes near
Wernicke Area and the 6 middle subbands of the WPT, we obtain
a high reduction of the dataset size, equal to approximately 19% of
the total dataset, with 67.5% of accuracy rate. This reduction appears
particularly important to improve the design of a low cost and simple
to use BCI, trained for several words.
Abstract: In this paper, we study the factors which determine the capacity of a Convolutional Neural Network (CNN) model and propose the ways to evaluate and adjust the capacity of a CNN model for best matching to a specific pattern recognition task. Firstly, a scheme is proposed to adjust the number of independent functional units within a CNN model to make it be better fitted to a task. Secondly, the number of independent functional units in the capsule network is adjusted to fit it to the training dataset. Thirdly, a method based on Bayesian GAN is proposed to enrich the variances in the current dataset to increase its complexity. Experimental results on the PASCAL VOC 2010 Person Part dataset and the MNIST dataset show that, in both conventional CNN models and capsule networks, the number of independent functional units is an important factor that determines the capacity of a network model. By adjusting the number of functional units, the capacity of a model can better match the complexity of a dataset.
Abstract: This paper presents a deep-learning mechanism for classifying computer generated images and photographic images. The proposed method accounts for a convolutional layer capable of automatically learning correlation between neighbouring pixels. In the current form, Convolutional Neural Network (CNN) will learn features based on an image's content instead of the structural features of the image. The layer is particularly designed to subdue an image's content and robustly learn the sensor pattern noise features (usually inherited from image processing in a camera) as well as the statistical properties of images. The paper was assessed on latest natural and computer generated images, and it was concluded that it performs better than the current state of the art methods.
Abstract: What people say on social media has turned into a
rich source of information to understand social behavior. Specifically,
the growing use of Twitter social media for political communication
has arisen high opportunities to know the opinion of large numbers
of politically active individuals in real time and predict the global
political tendencies of a specific country. It has led to an increasing
body of research on this topic. The majority of these studies have
been focused on polarized political contexts characterized by only
two alternatives. Unlike them, this paper tackles the challenge
of forecasting Spanish political trends, characterized by multiple
political parties, by means of analyzing the Twitters Users political
tendency. According to this, a new strategy, named Tweets Analysis
Strategy (TAS), is proposed. This is based on analyzing the users
tweets by means of discovering its sentiment (positive, negative or
neutral) and classifying them according to the political party they
support. From this individual political tendency, the global political
prediction for each political party is calculated. In order to do this,
two different strategies for analyzing the sentiment analysis are
proposed: one is based on Positive and Negative words Matching
(PNM) and the second one is based on a Neural Networks Strategy
(NNS). The complete TAS strategy has been performed in a Big-Data
environment. The experimental results presented in this paper reveal
that NNS strategy performs much better than PNM strategy to analyze
the tweet sentiment. In addition, this research analyzes the viability
of the TAS strategy to obtain the global trend in a political context
make up by multiple parties with an error lower than 23%.
Abstract: This paper has critically examined the use of Machine Learning procedures in curbing unauthorized access into valuable areas of an organization. The use of passwords, pin codes, user’s identification in recent times has been partially successful in curbing crimes involving identities, hence the need for the design of a system which incorporates biometric characteristics such as DNA and pattern recognition of variations in facial expressions. The facial model used is the OpenCV library which is based on the use of certain physiological features, the Raspberry Pi 3 module is used to compile the OpenCV library, which extracts and stores the detected faces into the datasets directory through the use of camera. The model is trained with 50 epoch run in the database and recognized by the Local Binary Pattern Histogram (LBPH) recognizer contained in the OpenCV. The training algorithm used by the neural network is back propagation coded using python algorithmic language with 200 epoch runs to identify specific resemblance in the exclusive OR (XOR) output neurons. The research however confirmed that physiological parameters are better effective measures to curb crimes relating to identities.
Abstract: Cardiologists perform cardiac auscultation to detect
abnormalities in heart sounds. Since accurate auscultation is
a crucial first step in screening patients with heart diseases,
there is a need to develop computer-aided detection/diagnosis
(CAD) systems to assist cardiologists in interpreting heart sounds
and provide second opinions. In this paper different algorithms
are implemented for automated heart sound classification using
unsegmented phonocardiogram (PCG) signals. Support vector
machine (SVM), artificial neural network (ANN) and cartesian
genetic programming evolved artificial neural network (CGPANN)
without the application of any segmentation algorithm has been
explored in this study. The signals are first pre-processed to remove
any unwanted frequencies. Both time and frequency domain features
are then extracted for training the different models. The different
algorithms are tested in multiple scenarios and their strengths and
weaknesses are discussed. Results indicate that SVM outperforms
the rest with an accuracy of 73.64%.
Abstract: Modeling sediment transport processes by means of numerical approach often poses severe challenges. In this way, a number of techniques have been suggested to solve flow and sediment equations in decoupled, semi-coupled or fully coupled forms. Furthermore, in order to capture flow discontinuities, a number of techniques, like artificial viscosity and shock fitting, have been proposed for solving these equations which are mostly required careful calibration processes. In this research, a numerical scheme for solving shallow water and Exner equations in fully coupled form is presented. First-Order Centered scheme is applied for producing required numerical fluxes and the reconstruction process is carried out toward using Monotonic Upstream Scheme for Conservation Laws to achieve a high order scheme. In order to satisfy C-property of the scheme in presence of bed topography, Surface Gradient Method is proposed. Combining the presented scheme with fourth order Runge-Kutta algorithm for time integration yields a competent numerical scheme. In addition, to handle non-prismatic channels problems, Cartesian Cut Cell Method is employed. A trained Multi-Layer Perceptron Artificial Neural Network which is of Feed Forward Back Propagation (FFBP) type estimates sediment flow discharge in the model rather than usual empirical formulas. Hydrodynamic part of the model is tested for showing its capability in simulation of flow discontinuities, transcritical flows, wetting/drying conditions and non-prismatic channel flows. In this end, dam-break flow onto a locally non-prismatic converging-diverging channel with initially dry bed conditions is modeled. The morphodynamic part of the model is verified simulating dam break on a dry movable bed and bed level variations in an alluvial junction. The results show that the model is capable in capturing the flow discontinuities, solving wetting/drying problems even in non-prismatic channels and presenting proper results for movable bed situations. It can also be deducted that applying Artificial Neural Network, instead of common empirical formulas for estimating sediment flow discharge, leads to more accurate results.
Abstract: This paper presents a method for improving object search accuracy using a deep learning model. A major limitation to provide accurate similarity with deep learning is the requirement of huge amount of data for training pairwise similarity scores (metrics), which is impractical to collect. Thus, similarity scores are usually trained with a relatively small dataset, which comes from a different domain, causing limited accuracy on measuring similarity. For this reason, this paper proposes a deep learning model that can be trained with a significantly small amount of data, a clustered data which of each cluster contains a set of visually similar images. In order to measure similarity distance with the proposed method, visual features of two images are extracted from intermediate layers of a convolutional neural network with various pooling methods, and the network is trained with pairwise similarity scores which is defined zero for images in identical cluster. The proposed method outperforms the state-of-the-art object similarity scoring techniques on evaluation for finding exact items. The proposed method achieves 86.5% of accuracy compared to the accuracy of the state-of-the-art technique, which is 59.9%. That is, an exact item can be found among four retrieved images with an accuracy of 86.5%, and the rest can possibly be similar products more than the accuracy. Therefore, the proposed method can greatly reduce the amount of training data with an order of magnitude as well as providing a reliable similarity metric.
Abstract: Inspired by topology of humpback whale flippers, a meta-model is designed for wing planform design. The net is trained based on experimental data using cascade-forward artificial neural network (ANN) to investigate effects of the amplitude and wavelength of sinusoidal leading edge configurations on the wing performance. Afterwards, the trained ANN is coupled with a genetic algorithm method towards an optimum design strategy. Finally, flow physics of the problem for an optimized rectangular planform and also a real flipper geometry planform is simulated using Lam-Bremhorst low Reynolds number turbulence model with damping wall-functions resolving to the wall. Lift and drag coefficients and also details of flow are presented along with comparisons to available experimental data. Results show that the proposed strategy can be adopted with success as a fast-estimation tool for performance prediction of wing planforms with wavy leading edge at preliminary design phase.
Abstract: The application of neural network using pattern recognition to study the fluid dynamics and predict the groundwater reservoirs properties has been used in this research. The essential of geophysical survey using the manual methods has failed in basement environment, hence the need for an intelligent computing such as predicted from neural network is inevitable. A non-linear neural network with an XOR (exclusive OR) output of 8-bits configuration has been used in this research to predict the nature of groundwater reservoirs and fluid dynamics of a typical basement crystalline rock. The control variables are the apparent resistivity of weathered layer (p1), fractured layer (p2), and the depth (h), while the dependent variable is the flow parameter (F=λ). The algorithm that was used in training the neural network is the back-propagation coded in C++ language with 300 epoch runs. The neural network was very intelligent to map out the flow channels and detect how they behave to form viable storage within the strata. The neural network model showed that an important variable gr (gravitational resistance) can be deduced from the elevation and apparent resistivity pa. The model results from SPSS showed that the coefficients, a, b and c are statistically significant with reduced standard error at 5%.
Abstract: Developing countries are nowadays confronted with great challenges related to domestic sanitation services in view of the imminent water scarcity. Contemporary sanitation technologies established in these countries are likely to pose health risks unless waste management standards are followed properly. This paper provides a solution to sustainable sanitation with the development of an innovative toilet system, called Nano Membrane Toilet (NMT), which has been developed by Cranfield University and sponsored by the Bill & Melinda Gates Foundation. The particular technology converts human faeces into energy through gasification and provides treated wastewater from urine through membrane filtration. In order to evaluate the environmental profile of the NMT system, a deterministic life cycle assessment (LCA) has been conducted in SimaPro software employing the Ecoinvent v3.3 database. The particular study has determined the most contributory factors to the environmental footprint of the NMT system. However, as sensitivity analysis has identified certain critical operating parameters for the robustness of the LCA results, adopting a stochastic approach to the Life Cycle Inventory (LCI) will comprehensively capture the input data uncertainty and enhance the credibility of the LCA outcome. For that purpose, Monte Carlo simulations, in combination with an artificial neural network (ANN) model, have been conducted for the input parameters of raw material, produced electricity, NOX emissions, amount of ash and transportation of fertilizer. The given analysis has provided the distribution and the confidence intervals of the selected impact categories and, in turn, more credible conclusions are drawn on the respective LCIA (Life Cycle Impact Assessment) profile of NMT system. Last but not least, the specific study will also yield essential insights into the methodological framework that can be adopted in the environmental impact assessment of other complex engineering systems subject to a high level of input data uncertainty.
Abstract: Electricity prices have sophisticated features such as
high volatility, nonlinearity and high frequency that make forecasting
quite difficult. Electricity price has a volatile and non-random
character so that, it is possible to identify the patterns based on the
historical data. Intelligent decision-making requires accurate price
forecasting for market traders, retailers, and generation companies.
So far, many shallow-ANN (artificial neural networks) models have
been published in the literature and showed adequate forecasting
results. During the last years, neural networks with many hidden
layers, which are referred to as DNN (deep neural networks) have
been using in the machine learning community. The goal of this
study is to investigate electricity price forecasting performance of the
shallow-ANN and DNN models for the Turkish day-ahead electricity
market. The forecasting accuracy of the models has been evaluated
with publicly available data from the Turkish day-ahead electricity
market. Both shallow-ANN and DNN approach would give successful
result in forecasting problems. Historical load, price and weather
temperature data are used as the input variables for the models.
The data set includes power consumption measurements gathered
between January 2016 and December 2017 with one-hour resolution.
In this regard, forecasting studies have been carried out comparatively
with shallow-ANN and DNN models for Turkish electricity markets
in the related time period. The main contribution of this study
is the investigation of different shallow-ANN and DNN models
in the field of electricity price forecast. All models are compared
regarding their MAE (Mean Absolute Error) and MSE (Mean Square)
results. DNN models give better forecasting performance compare to
shallow-ANN. Best five MAE results for DNN models are 0.346,
0.372, 0.392, 0,402 and 0.409.
Abstract: Load forecasting has become crucial in recent years
and become popular in forecasting area. Many different power
forecasting models have been tried out for this purpose. Electricity
load forecasting is necessary for energy policies, healthy and reliable
grid systems. Effective power forecasting of renewable energy load
leads the decision makers to minimize the costs of electric utilities
and power plants. Forecasting tools are required that can be used
to predict how much renewable energy can be utilized. The purpose
of this study is to explore the effectiveness of LSTM-based neural
networks for estimating renewable energy loads. In this study, we
present models for predicting renewable energy loads based on
deep neural networks, especially the Long Term Memory (LSTM)
algorithms. Deep learning allows multiple layers of models to learn
representation of data. LSTM algorithms are able to store information
for long periods of time. Deep learning models have recently been
used to forecast the renewable energy sources such as predicting
wind and solar energy power. Historical load and weather information
represent the most important variables for the inputs within the
power forecasting models. The dataset contained power consumption
measurements are gathered between January 2016 and December
2017 with one-hour resolution. Models use publicly available data
from the Turkish Renewable Energy Resources Support Mechanism.
Forecasting studies have been carried out with these data via deep
neural networks approach including LSTM technique for Turkish
electricity markets. 432 different models are created by changing
layers cell count and dropout. The adaptive moment estimation
(ADAM) algorithm is used for training as a gradient-based optimizer
instead of SGD (stochastic gradient). ADAM performed better than
SGD in terms of faster convergence and lower error rates. Models
performance is compared according to MAE (Mean Absolute Error)
and MSE (Mean Squared Error). Best five MAE results out of
432 tested models are 0.66, 0.74, 0.85 and 1.09. The forecasting
performance of the proposed LSTM models gives successful results
compared to literature searches.
Abstract: Green microgrids using mostly renewable energy (RE) for generation, are complex systems with inherent nonlinear dynamics. Among a variety of different optimization tools there are only a few ones that adequately consider this complexity. This paper evaluates applicability of two somewhat similar optimization tools tailored for standalone RE microgrids and also assesses a machine learning tool for performance prediction that can enhance the reliability of any chosen optimization tool. It shows that one of these microgrid optimization tools has certain advantages over another and presents a detailed routine of preparing input data to simulate RE microgrid behavior. The paper also shows how neural-network-based predictive modeling can be used to validate and forecast solar power generation based on weather time series data, which improves the overall quality of standalone RE microgrid analysis.