Publications by authors named "Amir H Gandomi"

14 Publications

  • Page 1 of 1

HVD-LSTM based recognition of epileptic seizures and normal human activity.

Comput Biol Med 2021 Sep 27;136:104684. Epub 2021 Jul 27.

Faculty of Engineering and Information Technology, University of Technology Sydney, Ultimo, NSW, 2007, Australia. Electronic address:

In this paper, we detect the occurrence of epileptic seizures in patients as well as activities namely stand, walk, and exercise in healthy persons, leveraging EEG (electroencephalogram) signals. Using Hilbert vibration decomposition (HVD) on non-linear and non-stationary EEG signal, we obtain multiple monocomponents varying in terms of amplitude and frequency. After decomposition, we extract features from the monocomponent matrix of the EEG signals. The instantaneous amplitude of the HVD monocomponents varies because of the motion artifacts present in EEG signals. Hence, the acquired statistical features from the instantaneous amplitude help in identifying the epileptic seizures and the normal human activities. The features selected by correlation-based Q-score are classified using an LSTM (Long Short Term Memory) based deep learning model in which the feature-based weight update maximizes the classification accuracy. For epilepsy diagnosis using the Bonn dataset and activity recognition leveraging our Sensor Networks Research Lab (SNRL) data, we achieve testing classification accuracies of 96.00% and 83.30% respectively through our proposed method.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.compbiomed.2021.104684DOI Listing
September 2021

Experimental dataset on water levels, sediment depths and wave front celerity values in the study of multiphase shock wave for different initial up- and down-stream conditions.

Data Brief 2021 Jun 22;36:107082. Epub 2021 Apr 22.

Professor, Faculty of Engineering and Information Technology, University of Technology Sydney, Ultimo, NSW 2007, Australia.

This data article presents a rich original experimental video sources and wide collections of laboratory data on water levels, sediment depths and wave front celerity values arose from different multiphase dam-break scenarios. The required data of dam-break shock waves in highly silted-up reservoirs with various initial up- and down-stream hydraulic conditions is obtained directly from high-quality videos. The multi-layer shock waves were recorded by three professional cameras mounted along the laboratory channel. The extracted video images were rigorously scrutinized, and the datasets were obtained through the images via image processing method. Different sediment depths in the upstream reservoir and dry- or wet-bed downstream conditions were considered as initial conditions, compromising a total of 32 different scenarios. A total of 198 original experimental videos are made available online in the public repository "Mendeley Data" in 8 groups based on 8 different initial upstream sediment depths [1], [2], [3], [4], [5], [6], [7], [8]. 20 locations along the flume and 15 time snaps after the dam breaks were considered for data collecting. Consequently, a total of 18,000 water level and sediment depth data points were collected to prepare four datasets, which are uploaded in the public repository "Mendeley Data". A total of 9600 water level data points could be accessed in [9], [10], while 8400 sediment depth data points are available online in [11], [12] and could be utilized for validation and practical purposes by other researchers. This data article is related to another research article entitled "Experimental study and numerical verification of silted-up dam-break" [13].
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.dib.2021.107082DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8134713PMC
June 2021

Groundwater sustainability: Developing a non-cooperative optimal management scenario in shared groundwater resources under water bankruptcy conditions.

J Environ Manage 2021 Aug 19;292:112807. Epub 2021 May 19.

Water Science and Engineering, Faculty of Agriculture, Shiraz University, Shiraz, Iran. Electronic address:

Groundwater level drawdown changes the hydrological cycle and poses challenges such as land subsidence and reduction of the groundwater quality. In this study, a new approach using a simulation-optimization framework was developed for shared groundwater management under water bankruptcy conditions (where water demand is greater than the allowable discharge capacity of water resources). The novelty of this study lies in using bankruptcy rules and a game model to manage a bankrupted shared groundwater resource considering aquifer sustainability. Accordingly, groundwater flow in the aquifer was numerically simulated by a finite-differences model (MODFLOW). Then, the repeated performance code of the finite-differences model was run for different discharge scenarios, and the results were applied to develop an MLP-ANN meta-model. By coupling the meta-model with a non-dominated sorting genetic algorithm II (NSGA-II)-based multi-objective optimization model, an optimized cultivation pattern under water bankruptcy conditions was achieved. Then, six different bankruptcy methods were utilized to specify groundwater allocation between three stakeholders. To manage the water bankruptcy conditions, different scenarios considering various groundwater extraction rates and cultivation areas were defined, and the optimization model was recoded for each scenario to find the corresponding optimized cultivation pattern. To consider the competition between stakeholders for groundwater extraction, a non-cooperative 3-player game was applied to achieve a compromise for different combinations of management strategies, which maximizes the profit and yields the best cultivation scenario. Applicability of the proposed methodology was investigated in an aquifer system located in Golestan Province, Iran, including three regions (Minudasht, Azadshahr, and Gonbade-kavus). Results show that the proposed method is capable of managing the bankruptcy conditions by generating greater agricultural profit and reducing groundwater drawdowns.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.jenvman.2021.112807DOI Listing
August 2021

A Prediction Model for the Calculation of Effective Stiffness Ratios of Reinforced Concrete Columns.

Materials (Basel) 2021 Apr 5;14(7). Epub 2021 Apr 5.

Department of Civil and Environmental Engineering, Incheon National University, Incheon 22012, Korea.

Nonlinear dynamic analyses of reinforced concrete (RC) frame buildings require the use of effective stiffness of members to capture the effect of cracked section stiffness. In the design codes and practices, the effective stiffness of RC sections is given as an empirical fraction of the gross stiffness. However, a more precise estimation of the effective stiffness is important as it affects the distribution of forces and various demands and response parameters in nonlinear dynamic analyses. In this study, an evolutionary computation method called gene expression programming (GEP) was used to predict the effective stiffness ratios of RC columns. Constitutive relationships were obtained by correlating the effective stiffness ratio with the four mechanical and geometrical parameters. The model was developed using a database of 226 samples of nonlinear dynamic analysis results collected from another study by the author. Subsequent parametric and sensitivity analyses were performed and the trends of the results were confirmed. The results indicate that the GEP model provides precise estimations of the effective stiffness ratios of the RC frames.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.3390/ma14071792DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8038543PMC
April 2021

A review on COVID-19 forecasting models.

Neural Comput Appl 2021 Feb 4:1-11. Epub 2021 Feb 4.

Data Science Institute, University of Technology Sydney, Ultimo, 2007 NSW Australia.

The novel coronavirus (COVID-19) has spread to more than 200 countries worldwide, leading to more than 36 million confirmed cases as of October 10, 2020. As such, several machine learning models that can forecast the outbreak globally have been released. This work presents a review and brief analysis of the most important machine learning forecasting models against COVID-19. The work presented in this study possesses two parts. In the first section, a detailed scientometric analysis presents an influential tool for bibliometric analyses, which were performed on COVID-19 data from the Scopus and Web of Science databases. For the above-mentioned analysis, keywords and subject areas are addressed, while the classification of machine learning forecasting models, criteria evaluation, and comparison of solution approaches are discussed in the second section of the work. The conclusion and discussion are provided as the final sections of this study.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1007/s00521-020-05626-8DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7861008PMC
February 2021

Evolutionary modelling of the COVID-19 pandemic in fifteen most affected countries.

Chaos Solitons Fractals 2020 Nov 17;140:110118. Epub 2020 Jul 17.

Faculty of Engineering & Information Technology, University of Technology Sydney, NSW 2007, Australia.

COVID-19 or SARS-Cov-2, affecting 6 million people and more than 300,000 deaths, the global pandemic has engulfed more than 90% countries of the world. The virus started from a single organism and is escalating at a rate of 3% to 5% daily and seems to be a never ending process. Understanding the basic dynamics and presenting new predictions models for evaluating the potential effect of the virus is highly crucial. In present work, an evolutionary data analytics method called as Genetic programming (GP) is used to mathematically model the potential effect of coronavirus in 15 most affected countries of the world. Two datasets namely confirmed cases (CC) and death cases (DC) were taken into consideration to estimate, how transmission varied in these countries between January 2020 and May 2020. Further, a percentage rise in the number of daily cases is also shown till 8 June 2020 and it is expected that Brazil will have the maximum rise in CC and USA have the most DC. Also, prediction of number of new CC and DC cases for every one million people in each of these countries is presented. The proposed model predicted that the transmission of COVID-19 in China is declining since late March 2020; in Singapore, France, Italy, Germany and Spain the curve has stagnated; in case of Canada, South Africa, Iran and Turkey the number of cases are rising slowly; whereas for USA, UK, Brazil, Russia and Mexico the rate of increase is very high and control measures need to be taken to stop the chains of transmission. Apart from that, the proposed prediction models are simple mathematical equations and future predictions can be drawn from these general equations. From the experimental results and statistical validation, it can be said that the proposed models use simple linkage functions and provide highly reliable results for time series prediction of COVID-19 in these countries.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.chaos.2020.110118DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7367045PMC
November 2020

Partial derivative Nonlinear Global Pandemic Machine Learning prediction of COVID 19.

Chaos Solitons Fractals 2020 Oct 25;139:110056. Epub 2020 Jun 25.

Faculty of Engineering & Information Technology, University of Technology Sydney, Ultimo, NSW 2007, Australia.

The recent worldwide outbreak of the novel coronavirus disease 2019 (COVID-19) opened new challenges for the research community. Machine learning (ML)-guided methods can be useful for feature prediction, involved risk, and the causes of an analogous epidemic. Such predictions can be useful for managing and intercepting the outbreak of such diseases. The foremost advantages of applying ML methods are handling a wide variety of data and easy identification of trends and patterns of an undetermined nature.In this study, we propose a partial derivative regression and nonlinear machine learning (PDR-NML) method for global pandemic prediction of COVID-19. We used a Progressive Partial Derivative Linear Regression model to search for the best parameters in the dataset in a computationally efficient manner. Next, a Nonlinear Global Pandemic Machine Learning model was applied to the normalized features for making accurate predictions. The results show that the proposed ML method outperformed state-of-the-art methods in the Indian population and can also be a convenient tool for making predictions for other countries.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.chaos.2020.110056DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7315984PMC
October 2020

Analysis of high-dimensional genomic data using MapReduce based probabilistic neural network.

Comput Methods Programs Biomed 2020 Oct 27;195:105625. Epub 2020 Jun 27.

VNR VJIET, Hyderabad, Telangana 500090, India. Electronic address:

Background: The size of genomics data has been growing rapidly over the last decade. However, the conventional data analysis techniques are incapable of processing this huge amount of data. For the efficient processing of high dimensional datasets, it is essential to develop some new parallel methods.

Methods: In this work, a novel distributed method is presented using Map-Reduce (MR)-based approach. The proposed algorithm consists of MR-based Fisher score (mrFScore), MR-based ReliefF (mrRefiefF), and MR-based probabilistic neural network (mrPNN) using a weighted chaotic grey wolf optimization technique (WCGWO). Here, mrFScore, and mrRefiefF methods are introduced for feature selection (FS), and mrPNN is implemented as an effective method for microarray classification. The proper choice of smoothing parameter (σ) plays a major role in the prediction ability of the PNN which is addressed using a novel technique namely, WCGWO. The WCGWO algorithm is used to select the optimal value of σ in PNN.

Results: These algorithms have been successfully implemented using the Hadoop framework. The proposed model is tested by using three large and one small microarray datasets, and a comparative analysis is carried out with the existing FS and classification techniques. The results suggest that WCGWO-mrPNN can outperform other methods for high dimensional microarray classification.

Conclusion: The effectiveness of the proposed methods are compared with other existing schemes. Experimental results reveal that the proposed scheme is accurate and robust. Hence, the suggested scheme is considered to be a reliable framework for microarray data analysis.

Significance: Such a method promotes the application of parallel programming using Hadoop cluster for the analysis of large-scale genomics data, particularly when the dataset is of high dimension.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.cmpb.2020.105625DOI Listing
October 2020

Time Series Analysis and Forecast of the COVID-19 Pandemic in India using Genetic Programming.

Chaos Solitons Fractals 2020 Sep 30;138:109945. Epub 2020 May 30.

Faculty of Engineering & Information Technology, University of Technology Sydney, NSW 2007, Australia.

COVID-19 declared as a global pandemic by WHO, has emerged as the most aggressive disease, impacting more than 90% countries of the world. The virus started from a single human being in China, is now increasing globally at a rate of 3% to 5% daily and has become a never ending process. Some studies even predict that the virus will stay with us forever. India being the second most populous country of the world, is also not saved, and the virus is spreading as a community level transmitter. Therefore, it become really important to analyse the possible impact of COVID-19 in India and forecast how it will behave in the days to come. In present work, prediction models based on genetic programming (GP) have been developed for confirmed cases (CC) and death cases (DC) across three most affected states namely Maharashtra, Gujarat and Delhi as well as whole India. The proposed prediction models are presented using explicit formula, and impotence of prediction variables are studied. Here, statistical parameters and metrics have been used for evaluated and validate the evolved models. From the results, it has been found that the proposed GEP-based models use simple linkage functions and are highly reliable for time series prediction of COVID-19 cases in India.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.chaos.2020.109945DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7260529PMC
September 2020

Association Rule Learning Is an Easy and Efficient Method for Identifying Profiles of Traumas and Stressors that Predict Psychopathology in Disaster Survivors: The Example of Sri Lanka.

Int J Environ Res Public Health 2020 04 21;17(8). Epub 2020 Apr 21.

Faculty of Engineering and Information Technology, University of Technology Sydney, Ultimo, NSW 2007, Australia.

Research indicates that psychopathology in disaster survivors is a function of both experienced trauma and stressful life events. However, such studies are of limited utility to practitioners who are about to go into a new post-disaster setting as (1) most of them do not indicate which specific traumas and stressors are especially likely to lead to psychopathology; and (2) each disaster is characterized by its own unique traumas and stressors, which means that practitioners have to first collect their own data on common traumas, stressors and symptoms of psychopathology prior to planning any interventions. An easy-to-use and easy-to-interpret data analytical method that allows one to identify profiles of trauma and stressors that predict psychopathology would be of great utility to practitioners working in post-disaster contexts. We propose that association rule learning (ARL), a big data mining technique, is such a method. We demonstrate the technique by applying it to data from 337 survivors of the Sri Lankan civil war who completed the Penn/RESIST/Peradeniya War Problems Questionnaire (PRPWPQ), a comprehensive, culturally-valid measure of experienced trauma, stressful life events, anxiety and depression. ARL analysis revealed five profiles of traumas and stressors that predicted the presence of some anxiety, three profiles that predicted the presence of severe anxiety, four profiles that predicted the presence of some depression and five profiles that predicted the presence of severe depression. ARL allows one to identify context-specific associations between specific traumas, stressors and psychological distress, and can be of great utility to practitioners who wish to efficiently analyze data that they have collected, understand the output of that analysis, and use it to provide psychosocial aid to those who most need it in post-disaster settings.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.3390/ijerph17082850DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7215723PMC
April 2020

Personalised modelling with spiking neural networks integrating temporal and static information.

Neural Netw 2019 Nov 14;119:162-177. Epub 2019 Aug 14.

Faculty of Engineering & Information Technology, University of Technology, Sydney, Ultimo, NSW 2007, Australia; School of Business, Stevens Institute of Technology, Hoboken, NJ 07030, USA.

This paper proposes a new personalised prognostic/diagnostic system that supports classification, prediction and pattern recognition when both static and dynamic/spatiotemporal features are presented in a dataset. The system is based on a proposed clustering method (named d2WKNN) for optimal selection of neighbouring samples to an individual with respect to the integration of both static (vector-based) and temporal individual data. The most relevant samples to an individual are selected to train a Personalised Spiking Neural Network (PSNN) that learns from sets of streaming data to capture the space and time association patterns. The generated time-dependant patterns resulted in a higher accuracy of classification/prediction (80% to 93%) when compared with global modelling and conventional methods. In addition, the PSNN models can support interpretability by creating personalised profiling of an individual. This contributes to a better understanding of the interactions between features. Therefore, an end-user can comprehend what interactions in the model have led to a certain decision (outcome). The proposed PSNN model is an analytical tool, applicable to several real-life health applications, where different data domains describe a person's health condition. The system was applied to two case studies: (1) classification of spatiotemporal neuroimaging data for the investigation of individual response to treatment and (2) prediction of risk of stroke with respect to temporal environmental data. For both datasets, besides the temporal data, static health data were also available. The hyper-parameters of the proposed system, including the PSNN models and the d2WKNN clustering parameters, are optimised for each individual.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.neunet.2019.07.021DOI Listing
November 2019

Multi-stage optimization of a deep model: A case study on ground motion modeling.

PLoS One 2018 19;13(9):e0203829. Epub 2018 Sep 19.

Department of Electrical and Computer Engineering, FAMU-FSU College of Engineering, Tallahassee, Florida 32310-6046, United States of America.

In this study, a multi-stage optimization procedure is proposed to develop deep neural network models which results in a powerful deep learning pipeline called intelligent deep learning (iDeepLe). The proposed pipeline is then evaluated by a challenging real-world problem, the modeling of the spectral acceleration experienced by a particle during earthquakes. This approach has three main stages to optimize the deep model topology, the hyper-parameters, and its performance, respectively. This pipeline optimizes the deep model via adaptive learning rate optimization algorithms for both accuracy and complexity in multiple stages, while simultaneously solving the unknown parameters of the regression model. Among the seven adaptive learning rate optimization algorithms, Nadam optimization algorithm has shown the best performance results in the current study. The proposed approach is shown to be a suitable tool to generate solid models for this complex real-world system. The results also show that the parallel pipeline of iDeepLe has the capacity to handle big data problems as well.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://journals.plos.org/plosone/article?id=10.1371/journal.pone.0203829PLOS
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC6145533PMC
March 2019

Interior search algorithm (ISA): a novel approach for global optimization.

Authors:
Amir H Gandomi

ISA Trans 2014 Jul 29;53(4):1168-83. Epub 2014 Apr 29.

The University of Akron, OH USA. Electronic address:

This paper presents the interior search algorithm (ISA) as a novel method for solving optimization tasks. The proposed ISA is inspired by interior design and decoration. The algorithm is different from other metaheuristic algorithms and provides new insight for global optimization. The proposed method is verified using some benchmark mathematical and engineering problems commonly used in the area of optimization. ISA results are further compared with well-known optimization algorithms. The results show that the ISA is efficiently capable of solving optimization problems. The proposed algorithm can outperform the other well-known algorithms. Further, the proposed algorithm is very simple and it only has one parameter to tune.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.isatra.2014.03.018DOI Listing
July 2014

Decision tree approach for soil liquefaction assessment.

ScientificWorldJournal 2013 30;2013:346285. Epub 2013 Dec 30.

Department of Civil Engineering, The University of Akron, Akron, OH 44325, USA.

In the current study, the performances of some decision tree (DT) techniques are evaluated for postearthquake soil liquefaction assessment. A database containing 620 records of seismic parameters and soil properties is used in this study. Three decision tree techniques are used here in two different ways, considering statistical and engineering points of view, to develop decision rules. The DT results are compared to the logistic regression (LR) model. The results of this study indicate that the DTs not only successfully predict liquefaction but they can also outperform the LR model. The best DT models are interpreted and evaluated based on an engineering point of view.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1155/2013/346285DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC3893014PMC
September 2014
-->