- Computer Science, Artificial Intelligence, Machine Learning, Future of artificial intelligence, Artificial Neural Networks for modeling purposes, Applications of Artificial Intelligence in Manufacturing, and 25 moreArtficial Neural Networks, Information Technology and System Integration, System Modeling and Simulation, Dynamic Systems and Control, Integration Technology of Automation Systems, Optimization Technology, Simulation, Numerical Analysis, Computational Mathematics, Environmental Informatics, Soft Computing, Intelligent Systems, Fuzzy Logic, Fuzzy Control, Support Vector Machines, Artificial Neural Networks, Hybrid Systems, Multi Agent Systems and Technologies, Data Mining, Clustering, Bioinformatics, Databases, Social Networks, Application of Artificial Intelligence in Oil and Gas Reservoir Characterization, and Application of artificial intelligence in oil and energyedit
Research Interests:
Cyberspace is a virtual environment where communication over computer networks happen. This space is vulnerable to cyber-attacks. After the attack happened, it has left many questions. The most important one is "who did it?". In... more
Cyberspace is a virtual environment where communication over computer networks happen. This space is vulnerable to cyber-attacks. After the attack happened, it has left many questions. The most important one is "who did it?". In order to improve cyber-attribution process Machine Learning can be used, and that is what has been done in this study. The proposed model is built based on Amazon Web Services (AWS) Honeypot dataset. Five models were built using five techniques: K-Nearest Neighbor (KNN), Support Vector Machine (SVM), Decision Tree (DT), Naïve Bayesian (NB) and Bayesian Network (BN). This study builds machine learning based cyber attribution models that are able to effectively aid analysts in attributing a cyber-attack appropriately and accurately. Experimental results indicated that the SVM model achieved the best accuracy, among others, which is 94.79%.
Research Interests:
Research Interests:
Schizophrenia is a severe chronic mental disorder, which affects the behavior, the perception and the thinking of the patient. The purpose of this research is to develop a predictive system to preemptively diagnose Schizophrenia Disease... more
Schizophrenia is a severe chronic mental disorder, which affects the behavior, the perception and the thinking of the patient. The purpose of this research is to develop a predictive system to preemptively diagnose Schizophrenia Disease using computational intelligence-based techniques. The system will show the possibilities of getting the disease at an early stage, which will improve the health state of the patients. This will be done using machine learning techniques. The used dataset has 86 records, which was obtained from the Machine Learning for Signal Processing (MLSP) 2014 Schizophrenia Classification Kaggle Challenge. The used techniques in this paper are Support Vector Machine (SVM), Random Forest (RF), Artificial Neural Network (ANN), and Naive Bayesian (NB). The highest accuracy was 90.6977% reached by using SVM, RF, and NB techniques while ANN technique reached 88.3721% accuracy. The obtained accuracies are reached by using 204 features. Therefore, we conclude that using SVM, RF, and NB techniques are better in this particular problem.
Research Interests:
Extreme Learning machines (ELM) and Support Vector Machines have become two of the most widely used machine learning techniques for both classification and regression problems of recent. However the comparison of both ELM and SVM for... more
Extreme Learning machines (ELM) and Support Vector Machines have become two of the most widely used machine learning techniques for both classification and regression problems of recent. However the comparison of both ELM and SVM for classification and regression problems has often caught the attention of several researchers. In this work, an attempt has been made at investigating how SVM and ELM compared on the unique and important problem of Email spam detection, which is a classification problem. The importance of email in this present age cannot be overemphasized. Hence the need to promptly and accurately detect and isolate unsolicited mails through spam detection system cannot be over emphasized. Empirical results from experiments carried out using very popular dataset indicated that both techniques outperformed the best earlier published techniques on the same popular dataset employed in this study. However, SVM performed better than ELM on comparison scale based on accuracy. But in term of speed of operation, ELM outperformed SVM significantly.
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Abstract Strontium titanate semiconductor is multi-functional metallic oxide with perovskite structure and wide range of applications in oxygen gas sensors (in storage batteries), superconductivity, ferro-electricity, dielectric constant... more
Abstract Strontium titanate semiconductor is multi-functional metallic oxide with perovskite structure and wide range of applications in oxygen gas sensors (in storage batteries), superconductivity, ferro-electricity, dielectric constant materials, dye-sensitized solar cells photo-electrodes, optoelectronics applications and photocatalysis. The wide band gap of strontium titanate metal oxide constrains its response to ultraviolent light with light harvesting capacity of 5% for incoming solar energy in generating photocatalytic activity. Anions and cations incorporation into the parent strontium titanate compound strongly break the semiconductor symmetry and ultimately influence the energy gap with stretches as well as distortions in perovskite structural architecture. This work develops genetic algorithm based support vector regression (GABSVR) hybrid model and stepwise regression algorithm (SRA) for modeling the energy gap of distorted strontium titanate semiconductor using structural lattice constants and the size of its nano-particles as model descriptors. The developed GABSVR model performs better than SRA model with performance improvement of 62.98%, 79.12% and 81.05% using coefficient of correlation (CC), mean absolute error (MAE) and root mean square error (RMAE) metrics, respectively. The developed model investigates the influence of preparation method, silver dopants, nitrogen dopants and sulfur incorporation on energy gap of strontium titanate photocatalytic activity. The developed GABSVR model was further validated externally for determining the significance of cobalt dopants on the activity of strontium titanate and the obtained energy gaps agree well with the measured values. High level of precision demonstrated by the developed hybrid model is of enormous significance for strengthening light harvesting capacity of the semiconductor for optoelectronics and photocatalysis applications.
Research Interests:
One of the most widely spread diseases around the world is Parkinson’s disease (PD). This disease affects the human brain and results in sudden and random body movements. It progresses slowly and differently at every stage. Moreover, the... more
One of the most widely spread diseases around the world is Parkinson’s disease (PD). This disease affects the human brain and results in sudden and random body movements. It progresses slowly and differently at every stage. Moreover, the disease has few known symptoms. Therefore, it is difficult for doctors to discover it in its initial stages. One of the main symptoms that can help researchers to predict the disease as early as possible is speech disorder. Many researchers have conducted several studies using voice recordings to produce an accurate PD diagnosis system. One unique promising way to use the speech disorder as a helping factor to predict PD is by using machine learning techniques. In this paper, we used NNge classification algorithms to analyze voice recordings for PD classification. NNge classification is known to be an efficient algorithm for analyzing voice signals but has not been explored in details in this area. In this paper, a literature review of previous research papers about PD prediction was briefly presented. Then, an experiment using NNge classification algorithm to classify people into healthy people and PD patients was performed. The parameters of the NNge algorithm were optimized. Moreover, SMOTE algorithm was used to balance the data. Finally, NNge and ensemble algorithms specifically, AdaBoostM1 was implemented on the balanced data. The final implementation of NNge using AdaBoost ensemble classifier had an accuracy of 96.30%.
Research Interests:
Research Interests:
Abstract Ionic liquids have enormous applications in various areas of technology. Among their usage is for the destabilization of crude oil emulsions produced in oilfields. Herein, we propose a support vector regression (SVR) based model... more
Abstract Ionic liquids have enormous applications in various areas of technology. Among their usage is for the destabilization of crude oil emulsions produced in oilfields. Herein, we propose a support vector regression (SVR) based model for smart screening and prediction water/oil separation driven by ionic liquids demulsifiers. The proposed SVR model applies attributes such as crude oil-water volumes, asphaltenes/resins content, emulsification speed/time, demulsification temperature, ionic liquid concentration, ionic liquid molecular weight, and demulsification time to predict the extent of demulsification performance of representative ionic liquids. Accordingly, the predicted demulsification efficiencies of the assessed ionic liquids exhibited significant matches with the experimental results. The developed approach demonstrated excellent accuracy as indicated by the root mean square error (RSME) values: 4.0123 and 19.6478 for the training and testing datasets, respectively. Additionally, the model demonstrated a considerable correlation coefficient (R2): 97.86 % and 75.97 % for the demulsification efficiency of tested ionic liquids in the training and testing datasets, respectively, thereby consolidating an appreciable agreement between the measured and the predicted results. It is envisaged that the SVR model employed in this study would greatly enhance the smart screening of ionic liquids used for demulsification activities in the petroleum and other related industries.
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Purpose This study aims to investigate the prediction of the nonlinear response of three-dimensional-printed polymeric lattice structures with and without structural defects. Unlike metallic structures, the deformation behavior of... more
Purpose This study aims to investigate the prediction of the nonlinear response of three-dimensional-printed polymeric lattice structures with and without structural defects. Unlike metallic structures, the deformation behavior of polymeric components is difficult to quantify through the classical numerical analysis approach as a result of their nonlinear behavior under mechanical loads. Design/methodology/approach Geometric models of periodic lattice structures were designed via PTC Creo. Imperfections in the form of missing unit cells are introduced in the replica of the lattice structure. The perfect and imperfect lattice structures have the same dimensions – 10 mm × 14 mm × 30 mm (w × h × L). The fused deposition modelling technique is used to fabricate the parts. The fabricated parts were subjected to physical compression tests to provide a measure of their transverse compressibility resistance. The ensuing nonlinear response from the experimental tests is deployed to develop a support vector machine surrogate model. Findings Results from the surrogate model’s performance, in terms of correlation coefficient, rose to as high as 99.91% for the nonlinear compressive stress with a minimum achieved being 98.51% across the four datasets used. In the case of deflection response, the model accuracy rose to as high as 99.74% while the minimum achieved is 98.56% across the four datasets used. Originality/value The developed model facilitates the prediction of the quasi-static response of the structures in the absence and presence of defects without the need for repeated physical experiments. The structure investigated is designed for target applications in hierarchical polymer packaging, and the methodology presents a cost-saving method for data-driven constitutive modelling of polymeric parts.
Research Interests:
The unique power of type-2 fuzzy logic system is demonstrated in this work by using it to improve the prediction accuracy of permeability in a hybrid intelligent model system. A hybrid intelligent model through the hybridization of type-2... more
The unique power of type-2 fuzzy logic system is demonstrated in this work by using it to improve the prediction accuracy of permeability in a hybrid intelligent model system. A hybrid intelligent model through the hybridization of type-2 FLS (T2) and extreme learning machines (ELM) is presented and have been shown to considerably achieved improved performance over the constituent models. It is generally believed that a hybrid scheme performed better than any of its constituent model and this work has fully corroborated this established slogan in the field of machine learning and data mining. ELM, as a learning tool, have gained popularity due to its unique characteristics and performance. However, the generalization capability of ELM and other neural network based solutions often depend, to a large extent on the characteristics of the dataset, particularly on whether uncertainty is present in the dataset or not. This work proposes a hybrid system through the combination of type-2 fuzzy logic systems (type-2 FLS) and ELM, and then use it to predict permeability of carbonate reservoir. Type-2 FLS has been chosen to be a precursor to ELM in order to better handle uncertainties existing in datasets. The dataset first pass through the type-2 FLS for possible uncertainty handling and prediction and then the output from the type-2 FLS is then passed to the ELM for its training and then final prediction is done using the unseen testing dataset. Simulations have been carried out, using the built hybrid model, on different industrial permeability datasets obtained from middle Easter oil fields. Results from empirical studies show that the proposed hybrid system performed better than each of the constituent parts, though the improvement made over that of ELM performance is higher compared to that of type-2 FLS, possibly because type-2 FLS is originally adept at modeling uncertainties. Overall, the proposed scheme achieved improved permeability prediction accuracy thereby setting another unique area to be looked into in the quest to achieving better accurate predictions of other petro physical properties in the oil and gas field.
Research Interests:
Research Interests:
Recent years have witnessed lots of development on face recognition systems including the ability to adapt to new genuine user features. Self-adapted Face Recognition systems are powerful tools to overcome the limitation of performance... more
Recent years have witnessed lots of development on face recognition systems including the ability to adapt to new genuine user features. Self-adapted Face Recognition systems are powerful tools to overcome the limitation of performance degradation over time. In this paper, a self-adapted face verification system (AFVS) that can efficiently classify genuine user samples for the update process using deep learning techniques has been proposed. The adaptivity feature of the proposed system model ensures performance stability in the long run. The proposed model has been developed using deep learning techniques which showed improved performance on Krassar model with higher F1-score and more tolerance to facial changes than the state-of-the-art face verification models.
Research Interests:
The unique power of type-2 fuzzy logic system is harnessed in this work by way of using it to improve the prediction accuracy of permeability and PVT properties in a hybrid intelligent model setting. In this proposed setup, hybridization... more
The unique power of type-2 fuzzy logic system is harnessed in this work by way of using it to improve the prediction accuracy of permeability and PVT properties in a hybrid intelligent model setting. In this proposed setup, hybridization of type-2 FLS (T2) and sensitivity based linear learning method (SBLLM) is presented and have been shown to considerably achieved improved performance over the constituent models, particularly the SBLLM. SBLLM, as a learning tool, have gained popularity due to its unique characteristics and performance. However, the generalization capability of SBLLM and other neural network based solutions often depend, to a large extent on the characteristics of the dataset, particularly on whether uncertainty is present in the dataset or not. The celebrated unique ability of type-2 fuzzy logic system in modeling uncertainties cannot be overemphasized. In this work, a hybrid system through the combination of type-2 fuzzy logic systems (type-2 FLS) and SBLLM is established, and then use to predict both permeability and PVT properties, which are very germane to the field of reservoir engineering and management; type-2 FLS has been chosen to be a precursor to SBLLM in order to harness the power of type-2 FLS thereby facilitating a means to better handle uncertainties existing in datasets. The dataset first pass through the type-2 FLS for possible uncertainty handling and prediction and then the output from the type-2 FLS is then passed to the SBLLM for its training and testing and then final prediction is done using the unseen testing dataset. Simulations have been carried out, using the built hybrid model, on different industrial datasets, for permeability and PVT properties separately. Results from empirical studies show that the proposed enhanced hybrid system performed better than each of the constituent parts, though the improvement made over that of SBLLM performance is higher compared to that of type-2 FLS, possibly because type-2 FLS is originally adept at modeling uncertainties. Thus it has been established here the huge benefit that could accrue from properly harnessing the power of type-2 fuzzy logic system.
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Sentiment classification is the process of classifying emotions and opinions in texts. In this study, the problem of Arabic sentiment analysis was addressed. A support vector machine (SVM) model was proposed to classify opinions in Arabic... more
Sentiment classification is the process of classifying emotions and opinions in texts. In this study, the problem of Arabic sentiment analysis was addressed. A support vector machine (SVM) model was proposed to classify opinions in Arabic micro-texts as being positive or negative. To evaluate the performance of the SVM model, a dataset was built from tweets discussing several social issues in Saudi Arabia. These issues include changes that were implemented by the country as part of a newly established vision, known as Saudi Arabia Vision 2030. The constructed dataset was manually annotated according to the sentiment conveyed in the text. To achieve the best sentiment classification accuracy, several procedures were implemented within the proposed framework including light stemming, feature extraction (Ngrams, emoji and tweet-topic features), parameter optimisation and feature-set reduction. The experimental results revealed excellent outcomes. An accuracy of 89.83% was achieved using the proposed SVM model.
Research Interests:
Abstract Improvement of superconducting properties of MgB2 superconductor becomes necessary in several medium and large scale commercial practical applications where generation of high magnetic field is of significant interest. High power... more
Abstract Improvement of superconducting properties of MgB2 superconductor becomes necessary in several medium and large scale commercial practical applications where generation of high magnetic field is of significant interest. High power cables, energy storage devices, wind turbines and magnetic resonance imaging are the potential areas of application where MgB2 superconductor with improved property is indispensable. In order to facilitate quick determination of transition temperature of MgB2 superconductor and to determine the conditions at which this superconducting property is optimal for the desired application, this present contribution hybridizes genetic algorithm (HGA) with support vector regression (SVR) machine learning to model the transition temperature of doped MgB2 superconductor using ambient room temperature resistivity (RTR), residual resistivity ratio (RRR) and structural lattice distortion (SLD) due to the incorporated dopants as descriptors. The developed HGA-SVR-RTR model that utilizes RTR as descriptor shows better performance than the proposed HGA-SVR-RRR model (that employs RRR as descriptor) and HGA-SVR-SLD model (that implements SLD as descriptors) with improvement in performance by 88.45% and 71.41%, respectively using mean absolute error (MAE) as a parameter that evaluates the model performance. The developed HGA-SVR-RTR model also outperforms the existing models such as GPR-prediction (2020), STTE model (2016) and STTE model (2014) with performance improvement of 74.85%, 74.76% and 92.96%, respectively using MAE as a yardstick for performance comparison. The developed HGA-SVR-RRR model performs better than HGA-SVR-SLD model with percentage improvement of 59.6% on the basis of MAE. The performance of the developed models would definitely facilitate cost effective search for doped MgB2 superconductor for desired application without experimental stress.
Research Interests:
Research Interests:
Research Interests:
Lung cancer is a malignant disease that im-poses serious complications restricting patients from performing daily tasks in the early stages and eventu-ally cause their death. The prevalence of this disease has been highlighted by numerous... more
Lung cancer is a malignant disease that im-poses serious complications restricting patients from performing daily tasks in the early stages and eventu-ally cause their death. The prevalence of this disease has been highlighted by numerous statistics worldwide. The preemptive diagnosis of individuals with lung can-cer can enhance chances of prevention and treatment. Therefore, the purpose of this study is to predict lung cancer preemptively utilizing simple clinical and demo-graphical features obtained from the “data world” website. The experiment was conducted using Support Vector Machine (SVM), K-Nearest Neighbor (K-NN), and Logistic Regression (LR) classifiers. To improve models' accuracy, SMOTETomek was employed along with GridsearchCV to tune hyperparameters. The Re-cursive Feature Elimination method was also utilized to find the best feature subset. Results indicated that SVM achieved the best performance with 98.33% recall, 96.72% precision, and an accuracy of 97.27% using 15 attributes.
Research Interests:
Analysts, researchers, and other users from different fields may spend a lot of time recognizing their work-related documents and organizing them in a way that allows them to make the best use of their content. In this regard, we propose... more
Analysts, researchers, and other users from different fields may spend a lot of time recognizing their work-related documents and organizing them in a way that allows them to make the best use of their content. In this regard, we propose a Document Categorization Engine (DCE) that utilizes concepts of machine learning techniques and data mining. The project aims to develop a system that is capable of classifying documents based on user defined criteria.
Research Interests:
The rapid spread of the Covid-19 outbreak led many countries to enforce precautionary measures such as complete lockdowns. These lifestyle-altering measures caused a significant increase in anxiety levels globally. For that reason,... more
The rapid spread of the Covid-19 outbreak led many countries to enforce precautionary measures such as complete lockdowns. These lifestyle-altering measures caused a significant increase in anxiety levels globally. For that reason, decision-makers are in dire need of methods to prevent potential public mental crises. Machine learning has shown its effectiveness in the early prediction of several diseases. Therefore, this study aims to classify two-class and three-class anxiety problems early by utilizing a dataset collected during the Covid-19 pandemic in Saudi Arabia. The data was collected from 3017 participants from all regions of the Kingdom via an online survey containing questions to identify factors influencing anxiety levels, followed by questions from the GAD-7, a screening tool for Generalized Anxiety Disorders. The prediction models were built using the Support Vector Machine classifier for its robust outcomes in medical-related data and the J48 Decision Tree for its interpretability and comprehensibility. Experimental results demonstrated promising results for the early classification of two-class and three-class anxiety problems. As for comparing Support Vector Machine and J48, the Support Vector Machine classifier outperformed the J48 Decision Tree by attaining a classification accuracy of 100%, precision of 1.0, recall of 1.0, and f-measure of 1.0 using 10 features.
Research Interests:
In recent times, researchers have noticed that chronic diseases have become more common. In the Kingdom of Saudi Arabia, the number of patients with thyroid cancer (TC) has become a concern, necessitating a proactive system that can help... more
In recent times, researchers have noticed that chronic diseases have become more common. In the Kingdom of Saudi Arabia, the number of patients with thyroid cancer (TC) has become a concern, necessitating a proactive system that can help cut down the incidence of this disease, where the system can assist in early interventions to prevent or cure the disease. In this paper, we introduce our work developing machine learning-based tools that can serve as early warning systems by detecting TC at very early stages (pre-symptomatic stage). In addition, we aimed at obtaining the greatest possible accuracy while using fewer features. It must be noted that while there have been past efforts to use machine learning in predicting TC, this is the first attempt using a Saudi Arabian dataset as well as targeting diagnosis in the pre-symptomatic stage (pre-emptive diagnosis). The techniques used in this work include random forest (RF), artificial neural network (ANN), support vector machine (SVM), and naïve Bayes (NB), each of which was selected for their unique capabilities. The highest accuracy rate obtained was 90.91% with the RF technique, while SVM, ANN, and NB achieved 84.09%, 88.64%, and 81.82% accuracy, respectively. These levels were obtained by using only seven features out of an available 15. Considering the pattern of the obtained results, it is clear that the RF technique is better and, hence, recommended for this specific problem.
Research Interests:
Purpose: There are many algorithms and models that are successfully utilized in controlling noises and preventing signal fading in communication networks. Signal strength enhancement studies that utilize component-based quality... more
Purpose: There are many algorithms and models that are successfully utilized in controlling noises and preventing signal fading in communication networks. Signal strength enhancement studies that utilize component-based quality improvement algorithm are not common. Methodology: A signal detection algorithm was developed using the component-based sigma quality improvement flow system. The algorithm was implemented on MATLAB computer programming software. Findings: The algorithm/model was capable of filtering out noises and optimizing RF-signal detection in communication networks. The signal detection results showed super-improved signal Energy to Noise Ratio (ENR) on the balanced probability basis. Unique contribution to theory, practice and policy: Introduction of component-based sigma quality improvement algorithm is an added advantage over the traditional techniques thereby enhancing further fading reduction in communication networks
Research Interests:
Diabetes Mellitus (DM) is one of the most prevalent chronic diseases in the world with around 150 million patients. Patients with chronic diseases are highly susceptible to deterioration in their physical and mental health; consequently,... more
Diabetes Mellitus (DM) is one of the most prevalent chronic diseases in the world with around 150 million patients. Patients with chronic diseases are highly susceptible to deterioration in their physical and mental health; consequently, hindering their independence, restricting their daily activities imposing a large financial burden on them and the government. If not discovered early, chronic diseases may lead to serious health complications or in extreme cases, death. Diagnostic solutions have been explored using intelligent methods, however, different ethnic groups have variant factors leading to the development of a disease. Therefore, the proposed system aims to preemptively diagnose DM in a region never explored before. Data are retrieved from King Fahd University Hospital (KFUH) in Khobar, Saudi Arabia. Data undergoes preprocessing to identify relevant features and prepare for identification/classification process. Experimental results show that ANN outperformed SVM, Naïve Bayes, and K-Nearest Neighbor with the testing accuracy of 77.5%.
Research Interests:
Purpose This study aims to investigate the prediction of the nonlinear response of three-dimensional-printed polymeric lattice structures with and without structural defects. Unlike metallic structures, the deformation behavior of... more
Purpose This study aims to investigate the prediction of the nonlinear response of three-dimensional-printed polymeric lattice structures with and without structural defects. Unlike metallic structures, the deformation behavior of polymeric components is difficult to quantify through the classical numerical analysis approach as a result of their nonlinear behavior under mechanical loads. Design/methodology/approach Geometric models of periodic lattice structures were designed via PTC Creo. Imperfections in the form of missing unit cells are introduced in the replica of the lattice structure. The perfect and imperfect lattice structures have the same dimensions – 10 mm × 14 mm × 30 mm (w × h × L). The fused deposition modelling technique is used to fabricate the parts. The fabricated parts were subjected to physical compression tests to provide a measure of their transverse compressibility resistance. The ensuing nonlinear response from the experimental tests is deployed to develop a...
Research Interests:
Chronic Kidney Disease (CKD) is a major public health concern with rising prevalence. In Saudi Arabia, approximately 2 Billion Riyals are solely allocated for renal replacement therapy which is required for patients with advanced stages... more
Chronic Kidney Disease (CKD) is a major public health concern with rising prevalence. In Saudi Arabia, approximately 2 Billion Riyals are solely allocated for renal replacement therapy which is required for patients with advanced stages of CKD. Therefore, this study aims to decrease the number of patients and the expenses needed for treatment by preemptively diagnosing chronic kidney disease accurately using data mining and machine learning techniques. Data have been collected from a region that has never been explored before in literature. This study uses Saudi data retrieved from King Fahd University Hospital(KFUH) in Khobar to carry out the experiment. Experimental Results show that ANN, SVM, Naïve Bayes achieved a testing accuracy of 98.0% while k-NN has achieved an accuracy of 93.9%.
Research Interests:
ABSTRACT The last half-century has witnessed an astronomical rise in the number of tall building projects in urban centers globally. These projects however frequently experience delays and total abandonment due to economic reasons. This... more
ABSTRACT The last half-century has witnessed an astronomical rise in the number of tall building projects in urban centers globally. These projects however frequently experience delays and total abandonment due to economic reasons. This study presents the application of Machine Learning techniques in the systematic development of a model to estimate the preliminary cost of tall building projects. The techniques considered include Multi-Linear Regression Analysis (MLRA), k-Nearest Neighbors (KNN), Artificial Neural Networks (ANN), Support Vector Machines (SVM), and Multi Classifier Systems. Twelve models were developed and compared using standard performance metrics. The results revealed that the best performing model was based on a Multi Classifier System using KNN as the combining classifier, with a Correlation Coefficient (R2) of 0.81, Root Mean Squared Error (RMSE) of 6.09, and Mean Absolute Percentage Error (MAPE) of 80.95%. This research showed the potential of modern digital technologies such as machine learning to solve problems of the construction industry. The procedure described in this study is of significant value to research and practice in the development of preliminary cost estimation models. The developed model can function as a decision support tool in the preliminary cost estimation stage of tall building projects.
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Titanium dioxide (TiO2) semiconductor is characterized with a wide band gap and attracts a significant attention for several applications that include solar cell carrier transportation and photo-catalysis. The tunable band gap of this... more
Titanium dioxide (TiO2) semiconductor is characterized with a wide band gap and attracts a significant attention for several applications that include solar cell carrier transportation and photo-catalysis. The tunable band gap of this semiconductor coupled with low cost, chemical stability and non-toxicity make it indispensable for these applications. Structural distortion always accompany TiO2 band gap tuning through doping and this present work utilizes the resulting structural lattice distortion to estimate band gap of doped TiO2 using support vector regression (SVR) coupled with novel gravitational search algorithm (GSA) for hyper-parameters optimization. In order to fully capture the non-linear relationship between lattice distortion and band gap, two SVR models were homogeneously hybridized and were subsequently optimized using GSA. GSA-HSVR (hybridized SVR) performs better than GSA-SVR model with performance improvement of 57.2% on the basis of root means square error reducti...
Research Interests:
The optical properties of blood play crucial roles in medical diagnostics and treatment, and in the design of new medical devices. Haemoglobin is a vital constituent of the blood whose optical properties affect all of the optical... more
The optical properties of blood play crucial roles in medical diagnostics and treatment, and in the design of new medical devices. Haemoglobin is a vital constituent of the blood whose optical properties affect all of the optical properties of human blood. The refractive index of haemoglobin has been reported to strongly depend on its concentration which is a function of the physiology of biological cells. This makes the refractive index of haemoglobin an essential non-invasive bio-marker of diseases. Unfortunately, the complexity of blood tissue makes it challenging to experimentally measure the refractive index of haemoglobin. While a few studies have reported on the refractive index of haemoglobin, there is no solid consensus with the data obtained due to different measuring instruments and the conditions of the experiments. Moreover, obtaining the refractive index via an experimental approach is quite laborious. In this work, an accurate, fast and relatively convenient strategy ...
Research Interests:
Research Interests:
Magnetic refrigeration (MR) technology has been identified as a potential replacement for the gas compression system of refrigeration due to its environmental friendliness and high level of efficiency. This technology utilizes... more
Magnetic refrigeration (MR) technology has been identified as a potential replacement for the gas compression system of refrigeration due to its environmental friendliness and high level of efficiency. This technology utilizes manganite-based materials as magnetic refrigerants due to the dependence of magnetic properties as well as relative cooling power (RCP) of this class of materials on the concentration and nature of the dopants. Quantifying the effect of dopants on RCP of manganite-based materials requires a long experimental procedures and techniques that are costly and time-consuming. In order to circumvent these challenges, we propose a model, based on support vector regression (SVR), which quickly estimates the RCP of doped manganite-based materials with high level of accuracy using crystal lattice constants as descriptors. The accuracy and ease with which the proposed SVR-based model estimates RCP of doped manganite-based materials is very promising and effective in designing MR system of desired RCP.