Search results for: defect prediction
Commenced in January 2007
Frequency: Monthly
Edition: International
Paper Count: 2569

Search results for: defect prediction

2059 Prediction of Dubai Financial Market Stocks Movement Using K-Nearest Neighbor and Support Vector Regression

Authors: Abdulla D. Alblooshi

Abstract:

The stock market is a representation of human behavior and psychology, such as fear, greed, and discipline. Those are manifested in the form of price movements during the trading sessions. Therefore, predicting the stock movement and prices is a challenging effort. However, those trading sessions produce a large amount of data that can be utilized to train an AI agent for the purpose of predicting the stock movement. Predicting the stock market price action will be advantageous. In this paper, the stock movement data of three DFM listed stocks are studied using historical price movements and technical indicators value and used to train an agent using KNN and SVM methods to predict the future price movement. MATLAB Toolbox and a simple script is written to process and classify the information and output the prediction. It will also compare the different learning methods and parameters s using metrics like RMSE, MAE, and R².

Keywords: KNN, ANN, style, SVM, stocks, technical indicators, RSI, MACD, moving averages, RMSE, MAE

Procedia PDF Downloads 149
2058 Neuronal Networks for the Study of the Effects of Cosmic Rays on Climate Variations

Authors: Jossitt Williams Vargas Cruz, Aura Jazmín Pérez Ríos

Abstract:

The variations of solar dynamics have become a relevant topic of study due to the effects of climate changes generated on the earth. One of the most disconcerting aspects is the variability that the sun has on the climate is the role played by sunspots (extra-atmospheric variable) in the modulation of the Cosmic Rays CR (extra-atmospheric variable). CRs influence the earth's climate by affecting cloud formation (atmospheric variable), and solar cycle influence is associated with the presence of solar storms, and the magnetic activity is greater, resulting in less CR entering the earth's atmosphere. The different methods of climate prediction in Colombia do not take into account the extra-atmospheric variables. Therefore, correlations between atmospheric and extra-atmospheric variables were studied in order to implement a Python code based on neural networks to make the prediction of the extra-atmospheric variable with the highest correlation.

Keywords: correlations, cosmic rays, sun, sunspots and variations.

Procedia PDF Downloads 50
2057 A Wall Law for Two-Phase Turbulent Boundary Layers

Authors: Dhahri Maher, Aouinet Hana

Abstract:

The presence of bubbles in the boundary layer introduces corrections into the log law, which must be taken into account. In this work, a logarithmic wall law was presented for bubbly two phase flows. The wall law presented in this work was based on the postulation of additional turbulent viscosity associated with bubble wakes in the boundary layer. The presented wall law contained empirical constant accounting both for shear induced turbulence interaction and for non-linearity of bubble. This constant was deduced from experimental data. The wall friction prediction achieved with the wall law was compared to the experimental data, in the case of a turbulent boundary layer developing on a vertical flat plate in the presence of millimetric bubbles. A very good agreement between experimental and numerical wall friction prediction was verified. The agreement was especially noticeable for the low void fraction when bubble induced turbulence plays a significant role.

Keywords: bubbly flows, log law, boundary layer, CFD

Procedia PDF Downloads 258
2056 Learning Dynamic Representations of Nodes in Temporally Variant Graphs

Authors: Sandra Mitrovic, Gaurav Singh

Abstract:

In many industries, including telecommunications, churn prediction has been a topic of active research. A lot of attention has been drawn on devising the most informative features, and this area of research has gained even more focus with spread of (social) network analytics. The call detail records (CDRs) have been used to construct customer networks and extract potentially useful features. However, to the best of our knowledge, no studies including network features have yet proposed a generic way of representing network information. Instead, ad-hoc and dataset dependent solutions have been suggested. In this work, we build upon a recently presented method (node2vec) to obtain representations for nodes in observed network. The proposed approach is generic and applicable to any network and domain. Unlike node2vec, which assumes a static network, we consider a dynamic and time-evolving network. To account for this, we propose an approach that constructs the feature representation of each node by generating its node2vec representations at different timestamps, concatenating them and finally compressing using an auto-encoder-like method in order to retain reasonably long and informative feature vectors. We test the proposed method on churn prediction task in telco domain. To predict churners at timestamp ts+1, we construct training and testing datasets consisting of feature vectors from time intervals [t1, ts-1] and [t2, ts] respectively, and use traditional supervised classification models like SVM and Logistic Regression. Observed results show the effectiveness of proposed approach as compared to ad-hoc feature selection based approaches and static node2vec.

Keywords: churn prediction, dynamic networks, node2vec, auto-encoders

Procedia PDF Downloads 293
2055 Artificial Intelligence Methods in Estimating the Minimum Miscibility Pressure Required for Gas Flooding

Authors: Emad A. Mohammed

Abstract:

Utilizing the capabilities of Data Mining and Artificial Intelligence in the prediction of the minimum miscibility pressure (MMP) required for multi-contact miscible (MCM) displacement of reservoir petroleum by hydrocarbon gas flooding using Fuzzy Logic models and Artificial Neural Network models will help a lot in giving accurate results. The factors affecting the (MMP) as it is proved from the literature and from the dataset are as follows: XC2-6: Intermediate composition in the oil-containing C2-6, CO2 and H2S, in mole %, XC1: Amount of methane in the oil (%),T: Temperature (°C), MwC7+: Molecular weight of C7+ (g/mol), YC2+: Mole percent of C2+ composition in injected gas (%), MwC2+: Molecular weight of C2+ in injected gas. Fuzzy Logic and Neural Networks have been used widely in prediction and classification, with relatively high accuracy, in different fields of study. It is well known that the Fuzzy Inference system can handle uncertainty within the inputs such as in our case. The results of this work showed that our proposed models perform better with higher performance indices than other emprical correlations.

Keywords: MMP, gas flooding, artificial intelligence, correlation

Procedia PDF Downloads 122
2054 Experimental Research of Canine Mandibular Defect Construction with the Controlled Meshy Titanium Alloy Scaffold Fabricated by Electron Beam Melting Combined with BMSCs-Encapsulating Chitosan Hydrogel

Authors: Wang Hong, Liu Chang Kui, Zhao Bing Jing, Hu Min

Abstract:

Objection We observed the repairment effection of canine mandibular defect with meshy Ti6Al4V scaffold fabricated by electron beam melting (EBM) combined with bone marrow mesenchymal stem cells (BMMSCs) encapsulated in chitosan hydrogel. Method Meshy titanium scaffolds were prepared by EBM of commercial Ti6Al4V power. The length of scaffolds was 24 mm, the width was 5 mm and height was 8mm. The pore size and porosity were evaluated by scanning electron microscopy (SEM). Chitosan /Bio-Oss hydrogel was prepared by chitosan, β- sodium glycerophosphate and Bio-Oss power. BMMSCs were harvested from canine iliac crests. BMMSCs were seeded in titanium scaffolds and encapsulated in Chitosan /Bio-Oss hydrogel. The validity of BMMSCs was evaluated by cell count kit-8 (CCK-8). The osteogenic differentiation ability was evaluated by alkaline phosphatase (ALP) activity and gene expression of OC, OPN and CoⅠ. Combination were performed by injecting BMMSCs/ Chitosan /Bio-Oss hydrogel into the meshy Ti6Al4V scaffolds and solidified. 24 mm long box-shaped bone defects were made at the mid-portion of mandible of adult beagles. The defects were randomly filled with BMMSCs/ Chitosan/Bio-Oss + titanium, Chitosan /Bio-Oss+titanium, titanium alone. Autogenous iliac crests graft as control group in 3 beagles. Radionuclide bone imaging was used to monitor the new bone tissue at 2, 4, 8 and 12 weeks after surgery. CT examination was made on the surgery day and 4 weeks, 12 weeks and 24 weeks after surgery. The animals were sacrificed in 4, 12 and 24 weeks after surgery. The bone formation were evaluated by histology and micro-CT. Results: The pores of the scaffolds was interconnected, the pore size was about 1 mm, the average porosity was about 76%. The pore size of the hydrogel was 50-200μm and the average porosity was approximately 90%. The hydrogel were solidified under the condition of 37℃in 10 minutes. The validity and the osteogenic differentiation ability of BMSCs were not affected by titanium scaffolds and hydrogel. Radionuclide bone imaging shown an increasing tendency of the revascularization and bone regeneration was observed in all the groups at 2, 4, 8 weeks after operation, and there were no changes at 12weeks.The tendency was more obvious in the BMMSCs/ Chitosan/Bio-Oss +titanium group and autogenous group. CT, Micro-CT and histology shown that new bone formed increasingly with the time extend. There were more new bone regenerated in BMMSCs/ Chitosan /Bio-Oss + titanium group and autogenous group than the other two groups. At 24 weeks, the autogenous group was achieved bone union. The BMSCs/ Chitosan /Bio-Oss group was seen extensive new bone formed around the scaffolds and more new bone inside of the central pores of scaffolds than Chitosan /Bio-Oss + titanium group and titanium group. The difference was significantly. Conclusion: The titanium scaffolds fabricated by EBM had controlled porous structure, good bone conduction and biocompatibility. Chitosan /Bio-Oss hydrogel had injectable plasticity, thermosensitive property and good biocompatibility. The meshy Ti6Al4V scaffold produced by EBM combined BMSCs encapsulated in chitosan hydrogel had good capacity on mandibular bone defect repair.

Keywords: mandibular reconstruction, tissue engineering, electron beam melting, titanium alloy

Procedia PDF Downloads 418
2053 Time Series Modelling and Prediction of River Runoff: Case Study of Karkheh River, Iran

Authors: Karim Hamidi Machekposhti, Hossein Sedghi, Abdolrasoul Telvari, Hossein Babazadeh

Abstract:

Rainfall and runoff phenomenon is a chaotic and complex outcome of nature which requires sophisticated modelling and simulation methods for explanation and use. Time Series modelling allows runoff data analysis and can be used as forecasting tool. In the paper attempt is made to model river runoff data and predict the future behavioural pattern of river based on annual past observations of annual river runoff. The river runoff analysis and predict are done using ARIMA model. For evaluating the efficiency of prediction to hydrological events such as rainfall, runoff and etc., we use the statistical formulae applicable. The good agreement between predicted and observation river runoff coefficient of determination (R2) display that the ARIMA (4,1,1) is the suitable model for predicting Karkheh River runoff at Iran.

Keywords: time series modelling, ARIMA model, river runoff, Karkheh River, CLS method

Procedia PDF Downloads 316
2052 Ensemble-Based SVM Classification Approach for miRNA Prediction

Authors: Sondos M. Hammad, Sherin M. ElGokhy, Mahmoud M. Fahmy, Elsayed A. Sallam

Abstract:

In this paper, an ensemble-based Support Vector Machine (SVM) classification approach is proposed. It is used for miRNA prediction. Three problems, commonly associated with previous approaches, are alleviated. These problems arise due to impose assumptions on the secondary structural of premiRNA, imbalance between the numbers of the laboratory checked miRNAs and the pseudo-hairpins, and finally using a training data set that does not consider all the varieties of samples in different species. We aggregate the predicted outputs of three well-known SVM classifiers; namely, Triplet-SVM, Virgo and Mirident, weighted by their variant features without any structural assumptions. An additional SVM layer is used in aggregating the final output. The proposed approach is trained and then tested with balanced data sets. The results of the proposed approach outperform the three base classifiers. Improved values for the metrics of 88.88% f-score, 92.73% accuracy, 90.64% precision, 96.64% specificity, 87.2% sensitivity, and the area under the ROC curve is 0.91 are achieved.

Keywords: MiRNAs, SVM classification, ensemble algorithm, assumption problem, imbalance data

Procedia PDF Downloads 318
2051 Study of the Use of Artificial Neural Networks in Islamic Finance

Authors: Kaoutar Abbahaddou, Mohammed Salah Chiadmi

Abstract:

The need to find a relevant way to predict the next-day price of a stock index is a real concern for many financial stakeholders and researchers. We have known across years the proliferation of several methods. Nevertheless, among all these methods, the most controversial one is a machine learning algorithm that claims to be reliable, namely neural networks. Thus, the purpose of this article is to study the prediction power of neural networks in the particular case of Islamic finance as it is an under-looked area. In this article, we will first briefly present a review of the literature regarding neural networks and Islamic finance. Next, we present the architecture and principles of artificial neural networks most commonly used in finance. Then, we will show its empirical application on two Islamic stock indexes. The accuracy rate would be used to measure the performance of the algorithm in predicting the right price the next day. As a result, we can conclude that artificial neural networks are a reliable method to predict the next-day price for Islamic indices as it is claimed for conventional ones.

Keywords: Islamic finance, stock price prediction, artificial neural networks, machine learning

Procedia PDF Downloads 204
2050 CD133 and CD44 - Stem Cell Markers for Prediction of Clinically Aggressive Form of Colorectal Cancer

Authors: Ognen Kostovski, Svetozar Antovic, Rubens Jovanovic, Irena Kostovska, Nikola Jankulovski

Abstract:

Introduction:Colorectal carcinoma (CRC) is one of the most common malignancies in the world. The cancer stem cell (CSC) markers are associated with aggressive cancer types and poor prognosis. The aim of study was to determine whether the expression of colorectal cancer stem cell markers CD133 and CD44 could be significant in prediction of clinically aggressive form of CRC. Materials and methods: Our study included ninety patients (n=90) with CRC. Patients were divided into two subgroups: with metatstatic CRC and non-metastatic CRC. Tumor samples were analyzed with standard histopathological methods, than was performed immunohistochemical analysis with monoclonal antibodies against CD133 and CD44 stem cell markers. Results: High coexpression of CD133 and CD44 was observed in 71.4% of patients with metastatic disease, compared to 37.9% in patients without metastases. Discordant expression of both markers was found in 8% of the subgroup with metastatic CRC, and in 13.4% of the subgroup without metastatic CRC. Statistical analyses showed a significant association of increased expression of CD133 and CD44 with the disease stage, T - category and N - nodal status. With multiple regression analysis the stage of disease was designate as a factor with the greatest statistically significant influence on expression of CD133 (p <0.0001) and CD44 (p <0.0001). Conclusion: Our results suggest that the coexpression of CD133 and CD44 have an important role in prediction of clinically aggressive form of CRC. Both stem cell markers can be routinely implemented in standard pathohistological diagnostics and can be useful markers for pre-therapeutic oncology screening.

Keywords: colorectal carcinoma, stem cells, CD133+, CD44+

Procedia PDF Downloads 124
2049 Prediction of Bubbly Plume Characteristics Using the Self-Similarity Model

Authors: Li Chen, Alex Skvortsov, Chris Norwood

Abstract:

Gas releasing into water can be found in for many industrial situations. This process results in the formation of bubbles and acoustic emission which depends upon the bubble characteristics. If the bubble creation rates (bubble volume flow rate) are of interest, an inverse method has to be used based on the measurement of acoustic emission. However, there will be sound attenuation through the bubbly plume which will influence the measurement and should be taken into consideration in the model. The sound transmission through the bubbly plume depends on the characteristics of the bubbly plume, such as the shape and the bubble distributions. In this study, the bubbly plume shape is modelled using a self-similarity model, which has been normally applied for a single phase buoyant plume. The prediction is compared with the experimental data. It has been found the model can be applied to a buoyant plume of gas-liquid mixture. The influence of the gas flow rate and discharge nozzle size is studied.

Keywords: bubbly plume, buoyant plume, bubble acoustics, self-similarity model

Procedia PDF Downloads 264
2048 Intelligent Prediction of Breast Cancer Severity

Authors: Wahab Ali, Oyebade K. Oyedotun, Adnan Khashman

Abstract:

Breast cancer remains a threat to the woman’s world in view of survival rates, it early diagnosis and mortality statistics. So far, research has shown that many survivors of breast cancer cases are in the ones with early diagnosis. Breast cancer is usually categorized into stages which indicates its severity and corresponding survival rates for patients. Investigations show that the farther into the stages before diagnosis the lesser the chance of survival; hence the early diagnosis of breast cancer becomes imperative, and consequently the application of novel technologies to achieving this. Over the year, mammograms have used in the diagnosis of breast cancer, but the inconclusive deductions made from such scans lead to either false negative cases where cancer patients may be left untreated or false positive where unnecessary biopsies are carried out. This paper presents the application of artificial neural networks in the prediction of severity of breast tumour (whether benign or malignant) using mammography reports and other factors that are related to breast cancer.

Keywords: breast cancer, intelligent classification, neural networks, mammography

Procedia PDF Downloads 465
2047 In vitro Modeling of Aniridia-Related Keratopathy by the Use of Crispr/Cas9 on Limbal Epithelial Cells and Rescue

Authors: Daniel Aberdam

Abstract:

Haploinsufficiency of PAX6 in humans is the main cause of congenital aniridia, a rare eye disease characterized by reduced visual acuity. Patients have also progressive disorders including cataract, glaucoma and corneal abnormalities making their condition very challenging to manage. Aniridia-related keratopathy (ARK), caused by a combination of factors including limbal stem-cell deficiency, impaired healing response, abnormal differentiation, and infiltration of conjunctival cells onto the corneal surface, affects up to 95% of patients. It usually begins in the first decade of life resulting in recurrent corneal erosions, sub-epithelial fibrosis with corneal decompensation and opacification. Unfortunately, current treatment options for aniridia patients are currently limited. Although animal models partially recapitulate this disease, there is no in vitro cellular model of AKT needed for drug/therapeutic tools screening and validation. We used genome editing (CRISPR/Cas9 technology) to introduce a nonsense mutation found in patients into one allele of the PAX6 gene into limbal stem cells. Resulting mutated clones, expressing half of the amount of PAX6 protein and thus representative of haploinsufficiency were further characterized. Sequencing analysis showed that no off-target mutations were induced. The mutated cells displayed reduced cell proliferation and cell migration but enhanced cell adhesion. Known PAX6 targets expression was also reduced. Remarkably, addition of soluble recombinant PAX6 protein into the culture medium was sufficient to activate endogenous PAX6 gene and, as a consequence, rescue the phenotype. It strongly suggests that our in vitro model recapitulates well the epithelial defect and becomes a powerful tool to identify drugs that could rescue the corneal defect in patients. Furthermore, we demonstrate that the homeotic transcription factor Pax6 is able to be uptake naturally by recipient cells to function into the nucleus.

Keywords: Pax6, crispr/cas9, limbal stem cells, aniridia, gene therapy

Procedia PDF Downloads 185
2046 Computational Study and Wear Prediction of Steam Turbine Blade with Titanium-Nitride Coating Deposited by Physical Vapor Deposition Method

Authors: Karuna Tuchinda, Sasithon Bland

Abstract:

This work investigates the wear of a steam turbine blade coated with titanium nitride (TiN), and compares to the wear of uncoated blades. The coating is deposited on by physical vapor deposition (PVD) method. The working conditions of the blade were simulated and surface temperature and pressure values as well as flow velocity and flow direction were obtained. This data was used in the finite element wear model developed here in order to predict the wear of the blade. The wear mechanisms considered are erosive wear due to particle impingement and fluid jet, and fatigue wear due to repeated impingement of particles and fluid jet. Results show that the life of the TiN-coated blade is approximately 1.76 times longer than the life of the uncoated one.

Keywords: physical vapour deposition, steam turbine blade, titanium-based coating, wear prediction

Procedia PDF Downloads 344
2045 Prediction of Solanum Lycopersicum Genome Encoded microRNAs Targeting Tomato Spotted Wilt Virus

Authors: Muhammad Shahzad Iqbal, Zobia Sarwar, Salah-ud-Din

Abstract:

Tomato spotted wilt virus (TSWV) belongs to the genus Tospoviruses (family Bunyaviridae). It is one of the most devastating pathogens of tomato (Solanum Lycopersicum) and heavily damages the crop yield each year around the globe. In this study, we retrieved 329 mature miRNA sequences from two microRNA databases (miRBase and miRSoldb) and checked the putative target sites in the downloaded-genome sequence of TSWV. A consensus of three miRNA target prediction tools (RNA22, miRanda and psRNATarget) was used to screen the false-positive microRNAs targeting sites in the TSWV genome. These tools calculated different target sites by calculating minimum free energy (mfe), site-complementarity, minimum folding energy and other microRNA-mRNA binding factors. R language was used to plot the predicted target-site data. All the genes having possible target sites for different miRNAs were screened by building a consensus table. Out of these 329 mature miRNAs predicted by three algorithms, only eight miRNAs met all the criteria/threshold specifications. MC-Fold and MC-Sym were used to predict three-dimensional structures of miRNAs and further analyzed in USCF chimera to visualize the structural and conformational changes before and after microRNA-mRNA interactions. The results of the current study show that the predicted eight miRNAs could further be evaluated by in vitro experiments to develop TSWV-resistant transgenic tomato plants in the future.

Keywords: tomato spotted wild virus (TSWV), Solanum lycopersicum, plant virus, miRNAs, microRNA target prediction, mRNA

Procedia PDF Downloads 126
2044 Analysing the Behaviour of Local Hurst Exponent and Lyapunov Exponent for Prediction of Market Crashes

Authors: Shreemoyee Sarkar, Vikhyat Chadha

Abstract:

In this paper, the local fractal properties and chaotic properties of financial time series are investigated by calculating two exponents, the Local Hurst Exponent: LHE and Lyapunov Exponent in a moving time window of a financial series.y. For the purpose of this paper, the Dow Jones Industrial Average (DIJA) and S&P 500, two of the major indices of United States have been considered. The behaviour of the above-mentioned exponents prior to some major crashes (1998 and 2008 crashes in S&P 500 and 2002 and 2008 crashes in DIJA) is discussed. Also, the optimal length of the window for obtaining the best possible results is decided. Based on the outcomes of the above, an attempt is made to predict the crashes and accuracy of such an algorithm is decided.

Keywords: local hurst exponent, lyapunov exponent, market crash prediction, time series chaos, time series local fractal properties

Procedia PDF Downloads 128
2043 A Reinforcement Learning Approach for Evaluation of Real-Time Disaster Relief Demand and Network Condition

Authors: Ali Nadi, Ali Edrissi

Abstract:

Relief demand and transportation links availability is the essential information that is needed for every natural disaster operation. This information is not in hand once a disaster strikes. Relief demand and network condition has been evaluated based on prediction method in related works. Nevertheless, prediction seems to be over or under estimated due to uncertainties and may lead to a failure operation. Therefore, in this paper a stochastic programming model is proposed to evaluate real-time relief demand and network condition at the onset of a natural disaster. To address the time sensitivity of the emergency response, the proposed model uses reinforcement learning for optimization of the total relief assessment time. The proposed model is tested on a real size network problem. The simulation results indicate that the proposed model performs well in the case of collecting real-time information.

Keywords: disaster management, real-time demand, reinforcement learning, relief demand

Procedia PDF Downloads 280
2042 Crime Prevention with Artificial Intelligence

Authors: Mehrnoosh Abouzari, Shahrokh Sahraei

Abstract:

Today, with the increase in quantity and quality and variety of crimes, the discussion of crime prevention has faced a serious challenge that human resources alone and with traditional methods will not be effective. One of the developments in the modern world is the presence of artificial intelligence in various fields, including criminal law. In fact, the use of artificial intelligence in criminal investigations and fighting crime is a necessity in today's world. The use of artificial intelligence is far beyond and even separate from other technologies in the struggle against crime. Second, its application in criminal science is different from the discussion of prevention and it comes to the prediction of crime. Crime prevention in terms of the three factors of the offender, the offender and the victim, following a change in the conditions of the three factors, based on the perception of the criminal being wise, and therefore increasing the cost and risk of crime for him in order to desist from delinquency or to make the victim aware of self-care and possibility of exposing him to danger or making it difficult to commit crimes. While the presence of artificial intelligence in the field of combating crime and social damage and dangers, like an all-seeing eye, regardless of time and place, it sees the future and predicts the occurrence of a possible crime, thus prevent the occurrence of crimes. The purpose of this article is to collect and analyze the studies conducted on the use of artificial intelligence in predicting and preventing crime. How capable is this technology in predicting crime and preventing it? The results have shown that the artificial intelligence technologies in use are capable of predicting and preventing crime and can find patterns in the data set. find large ones in a much more efficient way than humans. In crime prediction and prevention, the term artificial intelligence can be used to refer to the increasing use of technologies that apply algorithms to large sets of data to assist or replace police. The use of artificial intelligence in our debate is in predicting and preventing crime, including predicting the time and place of future criminal activities, effective identification of patterns and accurate prediction of future behavior through data mining, machine learning and deep learning, and data analysis, and also the use of neural networks. Because the knowledge of criminologists can provide insight into risk factors for criminal behavior, among other issues, computer scientists can match this knowledge with the datasets that artificial intelligence uses to inform them.

Keywords: artificial intelligence, criminology, crime, prevention, prediction

Procedia PDF Downloads 61
2041 Design of a Small and Medium Enterprise Growth Prediction Model Based on Web Mining

Authors: Yiea Funk Te, Daniel Mueller, Irena Pletikosa Cvijikj

Abstract:

Small and medium enterprises (SMEs) play an important role in the economy of many countries. When the overall world economy is considered, SMEs represent 95% of all businesses in the world, accounting for 66% of the total employment. Existing studies show that the current business environment is characterized as highly turbulent and strongly influenced by modern information and communication technologies, thus forcing SMEs to experience more severe challenges in maintaining their existence and expanding their business. To support SMEs at improving their competitiveness, researchers recently turned their focus on applying data mining techniques to build risk and growth prediction models. However, data used to assess risk and growth indicators is primarily obtained via questionnaires, which is very laborious and time-consuming, or is provided by financial institutes, thus highly sensitive to privacy issues. Recently, web mining (WM) has emerged as a new approach towards obtaining valuable insights in the business world. WM enables automatic and large scale collection and analysis of potentially valuable data from various online platforms, including companies’ websites. While WM methods have been frequently studied to anticipate growth of sales volume for e-commerce platforms, their application for assessment of SME risk and growth indicators is still scarce. Considering that a vast proportion of SMEs own a website, WM bears a great potential in revealing valuable information hidden in SME websites, which can further be used to understand SME risk and growth indicators, as well as to enhance current SME risk and growth prediction models. This study aims at developing an automated system to collect business-relevant data from the Web and predict future growth trends of SMEs by means of WM and data mining techniques. The envisioned system should serve as an 'early recognition system' for future growth opportunities. In an initial step, we examine how structured and semi-structured Web data in governmental or SME websites can be used to explain the success of SMEs. WM methods are applied to extract Web data in a form of additional input features for the growth prediction model. The data on SMEs provided by a large Swiss insurance company is used as ground truth data (i.e. growth-labeled data) to train the growth prediction model. Different machine learning classification algorithms such as the Support Vector Machine, Random Forest and Artificial Neural Network are applied and compared, with the goal to optimize the prediction performance. The results are compared to those from previous studies, in order to assess the contribution of growth indicators retrieved from the Web for increasing the predictive power of the model.

Keywords: data mining, SME growth, success factors, web mining

Procedia PDF Downloads 244
2040 Dissolved Oxygen Prediction Using Support Vector Machine

Authors: Sorayya Malek, Mogeeb Mosleh, Sharifah M. Syed

Abstract:

In this study, Support Vector Machine (SVM) technique was applied to predict the dichotomized value of Dissolved oxygen (DO) from two freshwater lakes namely Chini and Bera Lake (Malaysia). Data sample contained 11 parameters for water quality features from year 2005 until 2009. All data parameters were used to predicate the dissolved oxygen concentration which was dichotomized into 3 different levels (High, Medium, and Low). The input parameters were ranked, and forward selection method was applied to determine the optimum parameters that yield the lowest errors, and highest accuracy. Initial results showed that pH, water temperature, and conductivity are the most important parameters that significantly affect the predication of DO. Then, SVM model was applied using the Anova kernel with those parameters yielded 74% accuracy rate. We concluded that using SVM models to predicate the DO is feasible, and using dichotomized value of DO yields higher prediction accuracy than using precise DO value.

Keywords: dissolved oxygen, water quality, predication DO, support vector machine

Procedia PDF Downloads 266
2039 Forecasting Stock Indexes Using Bayesian Additive Regression Tree

Authors: Darren Zou

Abstract:

Forecasting the stock market is a very challenging task. Various economic indicators such as GDP, exchange rates, interest rates, and unemployment have a substantial impact on the stock market. Time series models are the traditional methods used to predict stock market changes. In this paper, a machine learning method, Bayesian Additive Regression Tree (BART) is used in predicting stock market indexes based on multiple economic indicators. BART can be used to model heterogeneous treatment effects, and thereby works well when models are misspecified. It also has the capability to handle non-linear main effects and multi-way interactions without much input from financial analysts. In this research, BART is proposed to provide a reliable prediction on day-to-day stock market activities. By comparing the analysis results from BART and with time series method, BART can perform well and has better prediction capability than the traditional methods.

Keywords: BART, Bayesian, predict, stock

Procedia PDF Downloads 103
2038 Analysis of Ancient Bone DNA Samples From Excavations at St Peter’s Burial Ground, Blackburn

Authors: Shakhawan K. Mawlood, Catriona Pickard, Benjamin Pickard

Abstract:

In summer 2015 the remains of 800 children are among 1,967 bodies were exhumed by archaeologists at St Peter's Burial Ground in Blackburn, Lancashire. One hundred samples from these 19th century ancient bones were selected for DNA analysis. These comprised samples biased for those which prior osteological evidence indicated a potential for microbial infection by Mycobacterium tuberculosis (causing tuberculosis, TB) or Treponema pallidum (causing Syphilis) species, as well a random selection of other bones for which visual inspection suggested good preservation (and, therefore, likely DNA retrieval).They were subject to polymerase chain reaction (PCR) assays aimed at detecting traces of DNA from infecting mycobacteria, with the purpose both of confirming the palaeopathological diagnosis of tuberculosis and determining in individual cases whether disease and death was due to M. tuberculosis or other reasons. Our secondary goal was to determine sex determination and age prediction. The results demonstrated that extraction of vast majority ancient bones DNA samples succeeded.

Keywords: ancient bone, DNA, tuberculosis, age prediction

Procedia PDF Downloads 70
2037 Heat Transfer Studies for LNG Vaporization During Underwater LNG Releases

Authors: S. Naveen, V. Sivasubramanian

Abstract:

A modeling theory is proposed to consider the vaporization of LNG during its contact with water following its release from an underwater source. The spillage of LNG underwater can lead to a decrease in the surface temperature of water and subsequent freezing. This can in turn affect the heat flux distribution from the released LNG onto the water surrounding it. The available models predict the rate of vaporization considering the surface of contact as a solid wall, and considering the entire phenomena as a solid-liquid operation. This assumption greatly under-predicted the overall heat transfer on LNG water interface. The vaporization flux would first decrease during the film boiling, followed by an increase during the transition boiling and a steady decrease during the nucleate boiling. A superheat theory is introduced to enhance the accuracy in the prediction of the heat transfer between LNG and water. The work suggests that considering the superheat theory can greatly enhance the prediction of LNG vaporization on underwater releases and also help improve the study of overall thermodynamics.

Keywords: evaporation rate, heat transfer, LNG vaporization, underwater LNG release

Procedia PDF Downloads 416
2036 Prediction Study of the Structural, Elastic and Electronic Properties of the Parent and Martensitic Phases of Nonferrous Ti, Zr, and Hf Pure Metals

Authors: Tayeb Chihi, Messaoud Fatmi

Abstract:

We present calculations of the structural, elastic and electronic properties of nonferrous Ti, Zr, and Hf pure metals in both parent and martensite phases in bcc and hcp structures respectively. They are based on the generalized gradient approximation (GGA) within the density functional theory (DFT). The shear modulus, Young's modulus and Poisson's ratio for Ti, Zr, and Hf metals have were calculated and compared with the corresponding experimental values. Using elastic constants obtained from calculations GGA, the bulk modulus along the crystallographic axes of single crystals was calculated. This is in good agreement with experiment for Ti and Zr, whereas the hcp structure for Hf is a prediction. At zero temperature and zero pressure, the bcc crystal structure is found to be mechanically unstable for Ti, Zr, and Hf. In our calculations the hcp structures is correctly found to be stable at the equilibrium volume. In the electronic density of states (DOS), the smaller n(EF) is, the more stable the compound is. Therefore, in agreement with the results obtained from the total energy minimum.

Keywords: Ti, Zr, Hf, pure metals, transformation, energy

Procedia PDF Downloads 330
2035 Prediction of Terrorist Activities in Nigeria using Bayesian Neural Network with Heterogeneous Transfer Functions

Authors: Tayo P. Ogundunmade, Adedayo A. Adepoju

Abstract:

Terrorist attacks in liberal democracies bring about a few pessimistic results, for example, sabotaged public support in the governments they target, disturbing the peace of a protected environment underwritten by the state, and a limitation of individuals from adding to the advancement of the country, among others. Hence, seeking for techniques to understand the different factors involved in terrorism and how to deal with those factors in order to completely stop or reduce terrorist activities is the topmost priority of the government in every country. This research aim is to develop an efficient deep learning-based predictive model for the prediction of future terrorist activities in Nigeria, addressing low-quality prediction accuracy problems associated with the existing solution methods. The proposed predictive AI-based model as a counterterrorism tool will be useful by governments and law enforcement agencies to protect the lives of individuals in society and to improve the quality of life in general. A Heterogeneous Bayesian Neural Network (HETBNN) model was derived with Gaussian error normal distribution. Three primary transfer functions (HOTTFs), as well as two derived transfer functions (HETTFs) arising from the convolution of the HOTTFs, are namely; Symmetric Saturated Linear transfer function (SATLINS ), Hyperbolic Tangent transfer function (TANH), Hyperbolic Tangent sigmoid transfer function (TANSIG), Symmetric Saturated Linear and Hyperbolic Tangent transfer function (SATLINS-TANH) and Symmetric Saturated Linear and Hyperbolic Tangent Sigmoid transfer function (SATLINS-TANSIG). Data on the Terrorist activities in Nigeria gathered through questionnaires for the purpose of this study were used. Mean Square Error (MSE), Mean Absolute Error (MAE) and Test Error are the forecast prediction criteria. The results showed that the HETFs performed better in terms of prediction and factors associated with terrorist activities in Nigeria were determined. The proposed predictive deep learning-based model will be useful to governments and law enforcement agencies as an effective counterterrorism mechanism to understand the parameters of terrorism and to design strategies to deal with terrorism before an incident actually happens and potentially causes the loss of precious lives. The proposed predictive AI-based model will reduce the chances of terrorist activities and is particularly helpful for security agencies to predict future terrorist activities.

Keywords: activation functions, Bayesian neural network, mean square error, test error, terrorism

Procedia PDF Downloads 142
2034 Epidemiology of Congenital Heart Defects in Kazakhstan: Data from Unified National Electronic Healthcare System 2014-2020

Authors: Dmitriy Syssoyev, Aslan Seitkamzin, Natalya Lim, Kamilla Mussina, Abduzhappar Gaipov, Dimitri Poddighe, Dinara Galiyeva

Abstract:

Background: Data on the epidemiology of congenital heart defects (CHD) in Kazakhstan is scarce. Therefore, the aim of this study was to describe the incidence, prevalence and all-cause mortality of patients with CHD in Kazakhstan, using national large-scale registry data from the Unified National Electronic Healthcare System (UNEHS) for the period of 2014-2020. Methods: In this retrospective cohort study, the included data pertained to all patients diagnosed with CHD in Kazakhstan and registered in UNEHS between January 2014 and December 2020. CHD was defined based on International Classification of Diseases 10th Revision (ICD-10) codes Q20-Q26. Incidence, prevalence, and all-cause mortality rates were calculated per 100,000 population. Survival analysis was performed using Cox proportional hazards regression modeling and the Kaplan-Meier method. Results: In total, 66,512 patients were identified. Among them, 59,534 (89.5%) were diagnosed with a single CHD, while 6,978 (10.5%) had more than two CHDs. The median age at diagnosis was 0.08 years (interquartile range (IQR) 0.01 – 0.66) for people with multiple CHD types and 0.39 years (IQR 0.04 – 8.38) for those with a single CHD type. The most common CHD types were atrial septal defect (ASD) and ventricular septal defect (VSD), accounting for 25.8% and 21.2% of single CHD cases, respectively. The most common multiple types of CHD were ASD with VSD (23.4%), ASD with patent ductus arteriosus (PDA) (19.5%), and VSD with PDA (17.7%). The incidence rate of CHD decreased from 64.6 to 47.1 cases per 100,000 population among men and from 68.7 to 42.4 among women. The prevalence rose from 66.1 to 334.1 cases per 100,000 population among men and from 70.8 to 328.7 among women. Mortality rates showed a slight increase from 3.5 to 4.7 deaths per 100,000 in men and from 2.9 to 3.7 in women. Median follow-up was 5.21 years (IQR 2.47 – 11.69). Male sex (HR 1.60, 95% CI 1.45 - 1.77), having multiple CHDs (HR 2.45, 95% CI 2.01 - 2.97), and living in a rural area (HR 1.32, 95% CI 1.19 - 1.47) were associated with a higher risk of all-cause mortality. Conclusion: The incidence of CHD in Kazakhstan has shown a moderate decrease between 2014 and 2020, while prevalence and mortality have increased. Male sex, multiple CHD types, and rural residence were significantly associated with a higher risk of all-cause mortality.

Keywords: congenital heart defects (CHD), epidemiology, incidence, Kazakhstan, mortality, prevalence

Procedia PDF Downloads 64
2033 Statistical Assessment of Models for Determination of Soil–Water Characteristic Curves of Sand Soils

Authors: S. J. Matlan, M. Mukhlisin, M. R. Taha

Abstract:

Characterization of the engineering behavior of unsaturated soil is dependent on the soil-water characteristic curve (SWCC), a graphical representation of the relationship between water content or degree of saturation and soil suction. A reasonable description of the SWCC is thus important for the accurate prediction of unsaturated soil parameters. The measurement procedures for determining the SWCC, however, are difficult, expensive, and time-consuming. During the past few decades, researchers have laid a major focus on developing empirical equations for predicting the SWCC, with a large number of empirical models suggested. One of the most crucial questions is how precisely existing equations can represent the SWCC. As different models have different ranges of capability, it is essential to evaluate the precision of the SWCC models used for each particular soil type for better SWCC estimation. It is expected that better estimation of SWCC would be achieved via a thorough statistical analysis of its distribution within a particular soil class. With this in view, a statistical analysis was conducted in order to evaluate the reliability of the SWCC prediction models against laboratory measurement. Optimization techniques were used to obtain the best-fit of the model parameters in four forms of SWCC equation, using laboratory data for relatively coarse-textured (i.e., sandy) soil. The four most prominent SWCCs were evaluated and computed for each sample. The result shows that the Brooks and Corey model is the most consistent in describing the SWCC for sand soil type. The Brooks and Corey model prediction also exhibit compatibility with samples ranging from low to high soil water content in which subjected to the samples that evaluated in this study.

Keywords: soil-water characteristic curve (SWCC), statistical analysis, unsaturated soil, geotechnical engineering

Procedia PDF Downloads 317
2032 Predicting the Human Impact of Natural Onset Disasters Using Pattern Recognition Techniques and Rule Based Clustering

Authors: Sara Hasani

Abstract:

This research focuses on natural sudden onset disasters characterised as ‘occurring with little or no warning and often cause excessive injuries far surpassing the national response capacities’. Based on the panel analysis of the historic record of 4,252 natural onset disasters between 1980 to 2015, a predictive method was developed to predict the human impact of the disaster (fatality, injured, homeless) with less than 3% of errors. The geographical dispersion of the disasters includes every country where the data were available and cross-examined from various humanitarian sources. The records were then filtered into 4252 records of the disasters where the five predictive variables (disaster type, HDI, DRI, population, and population density) were clearly stated. The procedure was designed based on a combination of pattern recognition techniques and rule-based clustering for prediction and discrimination analysis to validate the results further. The result indicates that there is a relationship between the disaster human impact and the five socio-economic characteristics of the affected country mentioned above. As a result, a framework was put forward, which could predict the disaster’s human impact based on their severity rank in the early hours of disaster strike. The predictions in this model were outlined in two worst and best-case scenarios, which respectively inform the lower range and higher range of the prediction. A necessity to develop the predictive framework can be highlighted by noticing that despite the existing research in literature, a framework for predicting the human impact and estimating the needs at the time of the disaster is yet to be developed. This can further be used to allocate the resources at the response phase of the disaster where the data is scarce.

Keywords: disaster management, natural disaster, pattern recognition, prediction

Procedia PDF Downloads 136
2031 Refitting Equations for Peak Ground Acceleration in Light of the PF-L Database

Authors: Matevž Breška, Iztok Peruš, Vlado Stankovski

Abstract:

Systematic overview of existing Ground Motion Prediction Equations (GMPEs) has been published by Douglas. The number of earthquake recordings that have been used for fitting these equations has increased in the past decades. The current PF-L database contains 3550 recordings. Since the GMPEs frequently model the peak ground acceleration (PGA) the goal of the present study was to refit a selection of 44 of the existing equation models for PGA in light of the latest data. The algorithm Levenberg-Marquardt was used for fitting the coefficients of the equations and the results are evaluated both quantitatively by presenting the root mean squared error (RMSE) and qualitatively by drawing graphs of the five best fitted equations. The RMSE was found to be as low as 0.08 for the best equation models. The newly estimated coefficients vary from the values published in the original works.

Keywords: Ground Motion Prediction Equations, Levenberg-Marquardt algorithm, refitting PF-L database, peak ground acceleration

Procedia PDF Downloads 432
2030 The Role of Psychological Factors in Prediction Academic Performance of Students

Authors: Hadi Molaei, Yasavoli Davoud, Keshavarz, Mozhde Poordana

Abstract:

The present study aimed was to prediction the academic performance based on academic motivation, self-efficacy and Resiliency in the students. The present study was descriptive and correlational. Population of the study consisted of all students in Arak schools in year 1393-94. For this purpose, the number of 304 schools students in Arak was selected using multi-stage cluster sampling. They all questionnaires, self-efficacy, Resiliency and academic motivation Questionnaire completed. Data were analyzed using Pearson correlation and multiple regressions. Pearson correlation showed academic motivation, self-efficacy, and Resiliency with academic performance had a positive and significant relationship. In addition, multiple regression analysis showed that the academic motivation, self-efficacy and Resiliency were predicted academic performance. Based on the findings could be conclude that in order to increase the academic performance and further progress of students must provide the ground to strengthen academic motivation, self-efficacy and Resiliency act on them.

Keywords: academic motivation, self-efficacy, resiliency, academic performance

Procedia PDF Downloads 461