Search results for: damage prediction models

Authors: Agnieszka A. Malinowska, R. Hejmanowski

Abstract:

A number of European cities are strongly affected by ground movements caused by anthropogenic activities or post-anthropogenic metamorphosis. Those are mainly water pumping, current mining operation, the collapse of post-mining underground voids or mining-induced earthquakes. These activities lead to large and small-scale ground displacements and a ground ruptures. The ground movements occurring in urban areas could considerably affect stability and safety of structures and infrastructures. The complexity of the ground deformation phenomenon in relation to the structures and infrastructures vulnerability leads to considerable constraints in assessing the threat of those objects. However, the increase of access to the free software and satellite data could pave the way for developing new methods and strategies for environmental risk mitigation and management. Open source geographical information systems (OS GIS), may support data integration, management, and risk analysis. Lately, developed methods based on fuzzy logic and experts methods for buildings and infrastructure damage risk assessment could be integrated into OS GIS. Those methods were verified base on back analysis proving their accuracy. Moreover, those methods could be supported by ground displacement observation. Based on freely available data from European Space Agency and free software, ground deformation could be estimated. The main innovation presented in the paper is the application of open source software (OS GIS) for integration developed models and assessment of the threat of urban areas. Those approaches will be reinforced by analysis of ground movement based on free satellite data. Those data would support the verification of ground movement prediction models. Moreover, satellite data will enable our mapping of ground deformation in urbanized areas. Developed models and methods have been implemented in one of the urban areas hazarded by underground mining activity. Vulnerability maps supported by satellite ground movement observation would mitigate the hazards of land displacements in urban areas close to mines.

Keywords: fuzzy logic, open source geographic information science (OS GIS), risk assessment on urbanized areas, satellite interferometry (InSAR)

Procedia PDF Downloads 147

Authors: M. Heydari Vini

Abstract:

There is a complicated relation between effective input parameters of cold rolling and output rolling force and exit thickness of strips.in many mathematical models, the effect of some rolling parameters have been ignored and the outputs have not a desirable accuracy. In the other hand, there is a special relation among input thickness of strips,the width of the strips,rolling speeds,mandrill tensions and the required exit thickness of strips with rolling force and the real exit thickness of the rolled strip. First of all, in this paper the effective parameters of cold rolling process modeled using an artificial neural network according to the optimum network achieved by using a written program in MATLAB,it has been shown that the prediction of rolling stand parameters with different properties and new dimensions attained from prior rolled strips by an artificial neural network is applicable.

Keywords: cold rolling, artificial neural networks, rolling force, real rolled thickness of strips

Procedia PDF Downloads 483

Authors: Said Alshukri, Mazhar Hussain Malik

Abstract:

Green hydrogen is hydrogen produced using renewable energy sources. In the last few years, Oman aimed to reduce its dependency on fossil fuels. Recently, the hydrogen economy has become a global trend, and many countries have started to investigate the feasibility of implementing this sector. Oman created an alliance to establish the policy and rules for this sector. With motivation coming from both global and local interest in green hydrogen, this paper investigates the potential of producing hydrogen from wind and solar energies in three different locations in Oman, namely Duqm, Salalah, and Sohar. By using machine learning-based software “WEKA” and local metrological data, the project was designed to figure out which location has the highest wind and solar energy potential. First, various supervised models were tested to obtain their prediction accuracy, and it was found that the Random Forest (RF) model has the best prediction performance. The RF model was applied to 2021 metrological data for each location, and the results indicated that Duqm has the highest wind and solar energy potential. The system of one wind turbine in Duqm can produce 8335 MWh/year, which could be utilized in the water electrolysis process to produce 88847 kg of hydrogen mass, while a solar system consisting of 2820 solar cells is estimated to produce 1666.223 MWh/ year which is capable of producing 177591 kg of hydrogen mass.

Keywords: green hydrogen, machine learning, wind and solar energies, WEKA, supervised models, random forest

Procedia PDF Downloads 54

Authors: Sonia Sassi, Mostapha Tarfaoui, Hamza Benyahia

Abstract:

Composite materials are increasingly being used as a substitute for metallic materials in many technological applications like aeronautics, aerospace, marine and civil engineering applications. For composite materials, the thermomechanical response evolves with the strain rate. The energy balance equation for anisotropic, elastic materials includes heat source terms that govern the conversion of some of the kinetic work into heat. The remainder contributes to the stored energy creating the damage process in the composite material. In this paper, we investigate the bulk thermomechanical behavior of adhesively-bonded composite assemblies to quantitatively asses the temperature rise which accompanies adiabatic deformations. In particular, adhesively bonded joints in glass/vinylester composite material are subjected to in-plane dynamic loads under a range of strain rates. Dynamic thermomechanical behavior of this material is investigated using compression Split Hopkinson Pressure Bars (SHPB) coupled with a high speed infrared camera and a high speed camera to measure in real time the dynamic behavior, the damage kinetic and the temperature variation in the material. The interest of using high speed IR camera is in order to view in real time the evolution of heat dissipation in the material when damage occurs. But, this technique does not produce thermal values in correlation with the stress-strain curves of composite material because of its high time response in comparison with the dynamic test time. For this reason, the authors revisit the application of specific thermocouples placed on the surface of the material to ensure the real thermal measurements under dynamic loading using small thermocouples. Experiments with dynamically loaded material show that the thermocouples record temperatures values with a short typical rise time as a result of the conversion of kinetic work into heat during compression test. This results show that small thermocouples can be used to provide an important complement to other noncontact techniques such as the high speed infrared camera. Significant temperature rise was observed in in-plane compression tests especially under high strain rates. During the tests, it has been noticed that sudden temperature rise occur when macroscopic damage occur. This rise in temperature is linked to the rate of damage. The more serve the damage is, a higher localized temperature is detected. This shows the strong relationship between the occurrence of damage and induced heat dissipation. For the case of the in plane tests, the damage takes place more abruptly as the strain rate is increased. The difference observed in the obtained thermomechanical response in plane compression is explained only by the difference in the damage process being active during the compression tests. In this study, we highlighted the dependence of the thermomechanical response on the strain rate of bonded specimens. The effect of heat dissipation of this material cannot hence be ignored and should be taken into account when defining damage models during impact loading.

Keywords: adhesively-bonded composite joints, damage, dynamic compression tests, energy balance, heat dissipation, SHPB, thermomechanical behavior

Procedia PDF Downloads 195

Authors: Shani Brathwaite, Deborah Villarroel-Lamb

Abstract:

Wave run-up may be defined as the time-varying position of the landward extent of the water’s edge, measured vertically from the mean water level position. The hydrodynamics of the swash zone and the accurate prediction of maximum wave run-up, play a critical role in the study of coastal engineering. The understanding of these processes is necessary for the modeling of sediment transport, beach recovery and the design and maintenance of coastal engineering structures. However, due to the complex nature of the swash zone, there remains a lack of detailed knowledge in this area. Particularly, there has been found to be insufficient consideration of bed porosity and ultimately infiltration/exfiltration processes, in the development of wave run-up models. Theoretically, there should be an inverse relationship between maximum wave run-up and beach porosity. The greater the rate of infiltration during an event, associated with a larger bed porosity, the lower the magnitude of the maximum wave run-up. Additionally, most models have been developed using data collected on North American or Australian beaches and may have limitations when used for operational forecasting in Trinidad. This paper aims to assess the influence and significance of infiltration and exfiltration processes on wave run-up magnitudes within the swash zone. It also seeks to pay particular attention to how well various empirical formulae can predict maximum run-up on contrasting beaches in Trinidad. Traditional surveying techniques will be used to collect wave run-up and cross-sectional data on various beaches. Wave data from wave gauges and wave models will be used as well as porosity measurements collected using a double ring infiltrometer. The relationship between maximum wave run-up and differing physical parameters will be investigated using correlation analyses. These physical parameters comprise wave and beach characteristics such as wave height, wave direction, period, beach slope, the magnitude of wave setup, and beach porosity. Most parameterizations to determine the maximum wave run-up are described using differing parameters and do not always have a good predictive capability. This study seeks to improve the formulation of wave run-up by using the aforementioned parameters to generate a formulation with a special focus on the influence of infiltration/exfiltration processes. This will further contribute to the improvement of the prediction of sediment transport, beach recovery and design of coastal engineering structures in Trinidad.

Keywords: beach porosity, empirical models, infiltration, swash, wave run-up

Procedia PDF Downloads 336

Authors: Assia Galleze, Abdurrahim Kocyigit, Nacira Cherif, Nidel Benhalilou, Nabila Attal, Chafia Touil Boukkoffa, Rachida Raache

Abstract:

Introduction and aims: Chemotherapeutic agents used to inhibit cell division and reduce tumor growth, increase reactive oxygen species levels, which contributes to their genotoxicity [1]. The comet assay is an inexpensive and rapid method to detect the damage at cellular levels and has been used in various cancer populations undergoing chemotherapy [2,3]. The present study aim to assess the oxidative stress and the genotoxicity induced by chemotherapy by the determination of plasma malondialdehyde (MDA) level, protein carbonyl (PC) content, superoxide dismutase (SOD) activity and lymphocyte DNA damage in Algerian children with lymphoma. Materials and Methods: For our study, we selected thirty children with lymphoma treated in university hospital of Beni Messous, Algeria, and fifty unrelated subjects as controls, after obtaining the informed consent in accordance with the Declaration of Helsinki (1964). Plasma levels of MDA, PC and SOD activity were spectrophotometrically measured, while DNA damage was assessed by alkaline comet assay in peripheral blood leukocytes. Results and Discussion: Plasma MDA, PC levels and lymphocyte DNA damage, were found to be significantly higher in lymphoma patients than in controls (p < 0.001). Whereas, SOD activity in lymphoma patients was significantly lower than in healthy controls (p < 0.001). There were significant positive correlations between DNA damage, MDA and PC in patients (r = 0.96, p < 0.001, r = 0.97, p < 0.001, respectively), and negative correlation with SOD (r = 0.87, p < 0.01). Conclusion and Perspective: Our results indicated that, leukocytes DNA damage and oxidative stress were significantly higher in lymphoma patients, suggesting that the direct effect of chemotherapy and the alteration of the redox balance may influence oxidative/antioxidative status.

Keywords: chemotherapy, comet assay, DNA damage, lymphoma

Procedia PDF Downloads 112

Authors: Yan Cheng, Yijun Shao, James Rudolph, Charlene R. Weir, Beth Sahlmann, Qing Zeng-Treitler

Abstract:

Supervised predictive models require labeled data for training purposes. Complete and accurate labeled data, i.e., a ‘gold standard’, is not always available, and imperfectly labeled data may need to serve as an alternative. An important question is if the accuracy of the labeled data creates a performance ceiling for the trained model. In this study, we trained several models to recognize the presence of delirium in clinical documents using data with annotations that are not completely accurate (i.e., weakly-supervised learning). In the external evaluation, the support vector machine model with a linear kernel performed best, achieving an area under the curve of 89.3% and accuracy of 88%, surpassing the 80% accuracy of the training sample. We then generated a set of simulated data and carried out a series of experiments which demonstrated that models trained on imperfect data can (but do not always) outperform the accuracy of the training data, e.g., the area under the curve for some models is higher than 80% when trained on the data with an error rate of 40%. Our experiments also showed that the error resistance of linear modeling is associated with larger sample size, error type, and linearity of the data (all p-values < 0.001). In conclusion, this study sheds light on the usefulness of imperfect data in clinical research via weakly-supervised learning.

Keywords: weakly-supervised learning, support vector machine, prediction, delirium, simulation

Procedia PDF Downloads 175

Authors: Noha Nagy, Hoda Mokhtar, Mohamed El Sherkawi

Abstract:

The popularity of workflow delegation models and the increasing number of workflow provenance-aware systems motivate the need for finding more strict delegation models. Such models combine different approaches for enhanced security and respecting workflow privacy. Although modern enterprises seek conformance to workflow constraints to ensure correctness of their work, these constraints pose a threat to security, because these constraints can be good seeds for attacking privacy even in secure models. This paper introduces a comprehensive Workflow Delegation Model (WFDM) that utilizes provenance and workflow constraints to prevent malicious delegate from attacking workflow privacy as well as extending the delegation functionalities. In addition, we argue the need for exploiting workflow constraints to improve workflow security models.

Keywords: workflow delegation models, secure workflow, workflow privacy, workflow provenance

Procedia PDF Downloads 312

Authors: Surita Maini, Sanjay Dhanka

Abstract:

Machine learning (ML) involves developing algorithms and statistical models that enable computers to learn and make predictions or decisions based on data without being explicitly programmed. Because of its unlimited abilities ML is gaining popularity in medical sectors; Medical Imaging, Electronic Health Records, Genomic Data Analysis, Wearable Devices, Disease Outbreak Prediction, Disease Diagnosis, etc. In the last few decades, many researchers have tried to diagnose Breast Cancer (BC) using ML, because early detection of any disease can save millions of lives. Working in this direction, the authors have proposed a hybrid ML technique RBF SVM, to predict the BC in earlier the stage. The proposed method is implemented on the Breast Cancer UCI ML dataset with 569 instances and 32 attributes. The authors recorded performance metrics of the proposed model i.e., Accuracy 98.24%, Sensitivity 98.67%, Specificity 97.43%, F1 Score 98.67%, Precision 98.67%, and run time 0.044769 seconds. The proposed method is validated by K-Fold cross-validation.

Keywords: breast cancer, support vector classifier, machine learning, hyper parameter tunning

Procedia PDF Downloads 53

Authors: Mahesh K. Chudasama, Harit K. Raval

Abstract:

3-roller conical bending process is widely used in the industries for manufacturing of conical sections and shells. It involves static as well dynamic bending stages. Analytical models for prediction of bending force during static as well as dynamic bending stage are available in the literature. In this paper, bending forces required for static bending stage and dynamic bending stages have been compared using the analytical models. It is concluded that force required for dynamic bending is very less as compared to the bending force required during the static bending stage.

Keywords: analytical modeling, cone frustum, dynamic bending, static bending

Procedia PDF Downloads 287

Authors: Uduak Umoh, Imo Eyoh, Emmauel Nyoho

Abstract:

This paper compares fuzzy-machine learning algorithms such as Support Vector Machine (SVM), and K-Nearest Neighbor (KNN) for the predicting cases of fire outbreak. The paper uses the fire outbreak dataset with three features (Temperature, Smoke, and Flame). The data is pre-processed using Interval Type-2 Fuzzy Logic (IT2FL) algorithm. Min-Max Normalization and Principal Component Analysis (PCA) are used to predict feature labels in the dataset, normalize the dataset, and select relevant features respectively. The output of the pre-processing is a dataset with two principal components (PC1 and PC2). The pre-processed dataset is then used in the training of the aforementioned machine learning models. K-fold (with K=10) cross-validation method is used to evaluate the performance of the models using the matrices – ROC (Receiver Operating Curve), Specificity, and Sensitivity. The model is also tested with 20% of the dataset. The validation result shows KNN is the better model for fire outbreak detection with an ROC value of 0.99878, followed by SVM with an ROC value of 0.99753.

Keywords: Machine Learning Algorithms , Interval Type-2 Fuzzy Logic, Fire Outbreak, Support Vector Machine, K-Nearest Neighbour, Principal Component Analysis

Procedia PDF Downloads 157

Authors: Elfatih M. Abdel-Rahman, Tobias Landmann, Richard Kyalo, George Ong’amo, Bruno Le Ru

Abstract:

Maize (Zea mays L.) is a major staple food crop in Africa, particularly in the eastern region of the continent. The maize growing area in Africa spans over 25 million ha and 84% of rural households in Africa cultivate maize mainly as a means to generate food and income. Average maize yields in Sub Saharan Africa are 1.4 t/ha as compared to global average of 2.5–3.9 t/ha due to biotic and abiotic constraints. Amongst the biotic production constraints in Africa, stem borers are the most injurious. In East Africa, yield losses due to stem borers are currently estimated between 12% to 40% of the total production. The objective of the present study was therefore to predict stem borer larvae density in maize fields using RapidEye reflectance data and generalized linear models (GLMs). RapidEye images were captured for a test site in Kenya (Machakos) in January and in February 2015. Stem borer larva numbers were modeled using GLMs assuming Poisson (Po) and negative binomial (NB) distributions with error with log arithmetic link. Root mean square error (RMSE) and ratio prediction to deviation (RPD) statistics were employed to assess the models performance using a leave one-out cross-validation approach. Results showed that NB models outperformed Po ones in all study sites. RMSE and RPD ranged between 0.95 and 2.70, and between 2.39 and 6.81, respectively. Overall, all models performed similar when used the January and the February image data. We conclude that reflectance data from RapidEye data can be used to estimate stem borer larvae density. The developed models could to improve decision making regarding controlling maize stem borers using various integrated pest management (IPM) protocols.

Keywords: maize, stem borers, density, RapidEye, GLM

Procedia PDF Downloads 480

Authors: Shogo Kato, Daisuke Okamoto, Satoko Tsuru, Yoshinori Iizuka, Ryoko Shimono

Abstract:

Healthcare safety has been perceived important. It is essential to prevent troubles in healthcare processes for healthcare safety. Trouble prevention is based on trouble prediction using accumulated knowledge on processes, troubles, and countermeasures. However, information on troubles has not been accumulated in hospitals in the appropriate structure, and it has not been utilized effectively to prevent troubles. In the previous study, though a detailed knowledge acquisition process for trouble prediction was proposed, the knowledgebase for countermeasures was not involved. In this paper, we aim to propose the structure of the knowledgebase for countermeasures in the knowledge acquisition process for trouble prediction in healthcare process. We first design the structure of countermeasures and propose the knowledge representation form on countermeasures. Then, we evaluate the validity of the proposal, by applying it into an actual hospital.

Keywords: trouble prevention, knowledge structure, structured knowledge, reusable knowledge

Procedia PDF Downloads 350

Authors: Youcef Faci, Ahmed Mebtouche, Badredine Maalem

Abstract:

n the present work, an experimental study is carried out using acoustic emission and DIC techniques to analyze the damage of open hole woven composite carbon/epoxy under solicitations. Damage mechanisms were identified based on acoustic emission parameters such as amplitude, energy, and cumulative account. The findings of the AE measurement were successfully identified by digital image correlation (DIC) measurements. The evolution value of bolt angle inclination during tensile tests was studied and analyzed. Consequently, the relationship between the bolt inclination angles during tensile tests associated with failure modes of fastened joints of composite materials is determined. Moreover, there is an interaction between laminate pattern, laminate thickness, fastener size and type, surface strain concentrations, and out-of-plane displacement. Conclusions are supported by microscopic visualizations of the composite specimen.

Keywords: tensile test, damage, acoustic emission, digital image correlation

Procedia PDF Downloads 52

Authors: Sophia Shi

Abstract:

Acute kidney injury (AKI) is the sudden onset of kidney damage in which the kidneys cannot filter waste from the blood, requiring emergency hospitalization. AKI patient mortality rate is high in the ICU and is virtually impossible for doctors to predict because it is so unexpected. Currently, there is no hybrid model predicting AKI that takes advantage of two types of data. De-identified patient data from the MIMIC-III database and de-identified kidney images and corresponding patient records from the Beijing Hospital of the Ministry of Health were collected. Using data features including serum creatinine among others, two numeric models using MIMIC and Beijing Hospital data were built, and with the hospital ultrasounds, an image-only model was built. Convolutional neural networks (CNN) were used, VGG and Resnet for numeric data and Resnet for image data, and they were combined into a hybrid model by concatenating feature maps of both types of models to create a new input. This input enters another CNN block and then two fully connected layers, ending in a binary output after running through Softmax and additional code. The hybrid model successfully predicted AKI and the highest AUROC of the model was 0.953, achieving an accuracy of 90% and F1-score of 0.91. This model can be implemented into urgent clinical settings such as the ICU and aid doctors by assessing the risk of AKI shortly after the patient’s admission to the ICU, so that doctors can take preventative measures and diminish mortality risks and severe kidney damage.

Keywords: Acute kidney injury, Convolutional neural network, Hybrid deep learning, Patient record data, ResNet, Ultrasound kidney images, VGG

Procedia PDF Downloads 113

Authors: Jimeng Shi, Mahek Jain, Giri Narasimhan

Abstract:

Time Series Forecasting (TSF) is used to predict the target variables at a future time point based on the learning from previous time points. To keep the problem tractable, learning methods use data from a fixed-length window in the past as an explicit input. In this paper, we study how the performance of predictive models changes as a function of different look-back window sizes and different amounts of time to predict the future. We also consider the performance of the recent attention-based Transformer models, which have had good success in the image processing and natural language processing domains. In all, we compare four different deep learning methods (RNN, LSTM, GRU, and Transformer) along with a baseline method. The dataset (hourly) we used is the Beijing Air Quality Dataset from the UCI website, which includes a multivariate time series of many factors measured on an hourly basis for a period of 5 years (2010-14). For each model, we also report on the relationship between the performance and the look-back window sizes and the number of predicted time points into the future. Our experiments suggest that Transformer models have the best performance with the lowest Mean Average Errors (MAE = 14.599, 23.273) and Root Mean Square Errors (RSME = 23.573, 38.131) for most of our single-step and multi-steps predictions. The best size for the look-back window to predict 1 hour into the future appears to be one day, while 2 or 4 days perform the best to predict 3 hours into the future.

Keywords: air quality prediction, deep learning algorithms, time series forecasting, look-back window

Procedia PDF Downloads 138

Authors: Oluwaponmile David Alao

Abstract:

Due to an increase in the death rate as a result of heart attack. There is need to develop a system that can be useful in the diagnosis of the disease at the medical centre. This system will help in preventing misdiagnosis that may occur from the medical practitioner or the physicians. In this research work, heart disease dataset obtained from UCI repository has been used to develop an intelligent prediction diagnosis system. The system is modeled on a feedforwad neural network and trained with back propagation neural network. A recognition rate of 86% is obtained from the testing of the network.

Keywords: heart disease, artificial neural network, diagnosis, prediction system

Procedia PDF Downloads 429

Authors: Sun-Young Jang, Sung-Ah Kim, Dongyoun Shin

Abstract:

The Intelligent transportation system is essential to build smarter cities. Machine learning based transportation prediction could be highly promising approach by delivering invisible aspect visible. In this context, this research aims to make a prototype model that predicts transportation network by using big data and machine learning technology. In detail, among urban transportation systems this research chooses bus system.  The research problem that existing headway model cannot response dynamic transportation conditions. Thus, bus delay problem is often occurred. To overcome this problem, a prediction model is presented to fine patterns of bus delay by using a machine learning implementing the following data sets; traffics, weathers, and bus statues. This research presents a flexible headway model to predict bus delay and analyze the result. The prototyping model is composed by real-time data of buses. The data are gathered through public data portals and real time Application Program Interface (API) by the government. These data are fundamental resources to organize interval pattern models of bus operations as traffic environment factors (road speeds, station conditions, weathers, and bus information of operating in real-time). The prototyping model is designed by the machine learning tool (RapidMiner Studio) and conducted tests for bus delays prediction. This research presents experiments to increase prediction accuracy for bus headway by analyzing the urban big data. The big data analysis is important to predict the future and to find correlations by processing huge amount of data. Therefore, based on the analysis method, this research represents an effective use of the machine learning and urban big data to understand urban dynamics.

Keywords: big data, machine learning, smart city, social cost, transportation network

Procedia PDF Downloads 238

Authors: Mohamed Arbi Khlifi, Badr M. Alshammari

Abstract:

This paper discusses the general methods to saturation in the steady-state, two axis (d & q) frame models of synchronous machines. In particular, the important role of the magnetic coupling between the d-q axes (cross-magnetizing phenomenon), is demonstrated. For that purpose, distinct methods of saturation modeling of dumper synchronous machine with cross-saturation are identified, and detailed models synthesis in d-q axes. A number of models are given in the final developed form. The procedure and the novel models are verified by a critical application to prove the validity of the method and the equivalence between all developed models is reported. Advantages of some of the models over the existing ones and their applicability are discussed.

Keywords: cross-magnetizing, models synthesis, synchronous machine, saturated modeling, state-space vectors

Procedia PDF Downloads 433

Authors: Vikrant Gupta, Amrit Goswami

Abstract:

The fixed income market forms the basis of the modern financial market. All other assets in financial markets derive their value from the bond market. Owing to its over-the-counter nature, corporate bonds have relatively less data publicly available and thus is researched upon far less compared to Equities. Bond price prediction is a complex financial time series forecasting problem and is considered very crucial in the domain of finance. The bond prices are highly volatile and full of noise which makes it very difficult for traditional statistical time-series models to capture the complexity in series patterns which leads to inefficient forecasts. To overcome the inefficiencies of statistical models, various machine learning techniques were initially used in the literature for more accurate forecasting of time-series. However, simple machine learning methods such as linear regression, support vectors, random forests fail to provide efficient results when tested on highly complex sequences such as stock prices and bond prices. hence to capture these intricate sequence patterns, various deep learning-based methodologies have been discussed in the literature. In this study, a recurrent neural network-based deep learning model using long short term networks for prediction of corporate bond prices has been discussed. Long Short Term networks (LSTM) have been widely used in the literature for various sequence learning tasks in various domains such as machine translation, speech recognition, etc. In recent years, various studies have discussed the effectiveness of LSTMs in forecasting complex time-series sequences and have shown promising results when compared to other methodologies. LSTMs are a special kind of recurrent neural networks which are capable of learning long term dependencies due to its memory function which traditional neural networks fail to capture. In this study, a simple LSTM, Stacked LSTM and a Masked LSTM based model has been discussed with respect to varying input sequences (three days, seven days and 14 days). In order to facilitate faster learning and to gradually decompose the complexity of bond price sequence, an Empirical Mode Decomposition (EMD) has been used, which has resulted in accuracy improvement of the standalone LSTM model. With a variety of Technical Indicators and EMD decomposed time series, Masked LSTM outperformed the other two counterparts in terms of prediction accuracy. To benchmark the proposed model, the results have been compared with traditional time series models (ARIMA), shallow neural networks and above discussed three different LSTM models. In summary, our results show that the use of LSTM models provide more accurate results and should be explored more within the asset management industry.

Keywords: bond prices, long short-term memory, time series forecasting, empirical mode decomposition

Procedia PDF Downloads 116

Authors: JingWei Yu, Hong Yang Yu

Abstract:

At present, the increasingly serious air pollution in various cities of China has made people pay more attention to the air quality index(hereinafter referred to as AQI) of their living areas. To face this situation, it is of great significance to predict air pollution in heavily polluted areas. In this paper, based on the time series model of LSTM, a spatiotemporal prediction model of PM2.5 concentration in Mianyang, Sichuan Province, is established. The model fully considers the temporal variability and spatial distribution characteristics of PM2.5 concentration. The spatial correlation of air quality at different locations is based on the Air quality status of other nearby monitoring stations, including AQI and meteorological data to predict the air quality of a monitoring station. The experimental results show that the method has good prediction accuracy that the fitting degree with the actual measured data reaches more than 0.7, which can be applied to the modeling and prediction of the spatial and temporal distribution of regional PM2.5 concentration.

Keywords: LSTM, PM2.5, neural networks, spatio-temporal prediction

Procedia PDF Downloads 111

Authors: Rami El-Hajj Mohamad, Mahmoud Skafi, Ali Massoud Haidar

Abstract:

Several meteorological parameters were used for the prediction of monthly average daily global solar radiation on horizontal using recurrent neural networks (RNNs). Climatological data and measures, mainly air temperature, humidity, sunshine duration, and wind speed between 1995 and 2007 were used to design and validate a feed forward and recurrent neural network based prediction systems. In this paper we present our reference system based on a feed-forward multilayer perceptron (MLP) as well as the proposed approach based on an RNN model. The obtained results were promising and comparable to those obtained by other existing empirical and neural models. The experimental results showed the advantage of RNNs over simple MLPs when we deal with time series solar radiation predictions based on daily climatological data.

Keywords: recurrent neural networks, global solar radiation, multi-layer perceptron, gradient, root mean square error

Procedia PDF Downloads 421

Authors: Shahram Jamali, Samira Hamed

Abstract:

One of the open issues in Random Early Detection (RED) algorithm is how to set its parameters to reach high performance for the dynamic conditions of the network. Although original RED uses fixed values for its parameters, this paper follows a model-based approach to upgrade performance of the RED algorithm. It models the routers queue behavior by using the Markov model and uses this model to predict future conditions of the queue. This prediction helps the proposed algorithm to make some tunings over RED's parameters and provide efficiency and better performance. Widespread packet level simulations confirm that the proposed algorithm, called Markov-RED, outperforms RED and FARED in terms of queue stability, bottleneck utilization and dropped packets count.

Keywords: active queue management, RED, Markov model, random early detection algorithm

Procedia PDF Downloads 520

Authors: Sofia Stoica

Abstract:

In this paper, we use historical data to predict the stock price of a tech company. To this end, we use a dataset consisting of the stock prices in the past five years of ten major tech companies – Adobe, Amazon, Apple, Facebook, Google, Microsoft, Netflix, Oracle, Salesforce, and Tesla. We experimented with a variety of models– a linear regressor model, K nearest Neighbors (KNN), a sequential neural network – and algorithms - Multiplicative Weight Update, and AdaBoost. We found that the sequential neural network performed the best, with a testing error of 0.18%. Interestingly, the linear model performed the second best with a testing error of 0.73%. These results show that using historical data is enough to obtain high accuracies, and a simple algorithm like linear regression has a performance similar to more sophisticated models while taking less time and resources to implement.

Keywords: finance, machine learning, opening price, stock market

Procedia PDF Downloads 153

Authors: Sadaf Sahar, Usman Qamar, Sadaf Ayaz

Abstract:

In the software development lifecycle, the quality prediction techniques hold a prime importance in order to minimize future design errors and expensive maintenance. There are many techniques proposed by various researchers, but with the increasing complexity of the software lifecycle model, it is crucial to develop a flexible system which can cater for the factors which in result have an impact on the quality of the end product. These factors include properties of the software development process and the product along with its operation conditions. In this paper, a neural network (perceptron) based software quality prediction technique is proposed. Using this technique, the stakeholders can predict the quality of the resulting software during the early phases of the lifecycle saving time and resources on future elimination of design errors and costly maintenance. This technique can be brought into practical use using successful training.

Keywords: software quality, fuzzy logic, perception, prediction

Procedia PDF Downloads 299

Authors: S. Siddharth, Saravana Kumar

Abstract:

All Metros across the world tend to have a large number of bridges and there have been concerns about the safety of these bridges. As the traffic in most cities in India is heterogeneous, Trucks and Heavy vehicles traverse on our roads on an everyday basis this will lead to structural damage on the long run. All bridges are designed with a maximum Load limit and this limit is seldom checked. We have hence come up with an idea to check the load of all the vehicles entering the bridge and block the bridge with barricades if the vehicle surpasses the maximum load , this is done to catch hold of the perpetrators. By doing this we can avoid further structural damage and also provide an effective way to enforce the law. If our solution is put in place structural damage and accidents would be reduced to a great deal and it would also make the law enforcement job easier.

Keywords: heterogeneous, structural, load, law, heavy, vehicles

Procedia PDF Downloads 421

Authors: Ahmed G. Mahgoub, Dahlia H. Hafez, Mostafa A. Abu Kiefa

Abstract:

The Cone Penetration Test (CPT) is a common in-situ test which generally investigates a much greater volume of soil more quickly than possible from sampling and laboratory tests. Therefore, it has the potential to realize both cost savings and assessment of soil properties rapidly and continuously. The principle objective of this paper is to demonstrate the feasibility and efficiency of using artificial neural networks (ANNs) to predict the soil angle of internal friction (Φ) and the soil modulus of elasticity (E) from CPT results considering the uncertainties and non-linearities of the soil. In addition, ANNs are used to study the influence of different parameters and recommend which parameters should be included as input parameters to improve the prediction. Neural networks discover relationships in the input data sets through the iterative presentation of the data and intrinsic mapping characteristics of neural topologies. General Regression Neural Network (GRNN) is one of the powerful neural network architectures which is utilized in this study. A large amount of field and experimental data including CPT results, plate load tests, direct shear box, grain size distribution and calculated data of overburden pressure was obtained from a large project in the United Arab Emirates. This data was used for the training and the validation of the neural network. A comparison was made between the obtained results from the ANN's approach, and some common traditional correlations that predict Φ and E from CPT results with respect to the actual results of the collected data. The results show that the ANN is a very powerful tool. Very good agreement was obtained between estimated results from ANN and actual measured results with comparison to other correlations available in the literature. The study recommends some easily available parameters that should be included in the estimation of the soil properties to improve the prediction models. It is shown that the use of friction ration in the estimation of Φ and the use of fines content in the estimation of E considerable improve the prediction models.

Keywords: angle of internal friction, cone penetrating test, general regression neural network, soil modulus of elasticity

Procedia PDF Downloads 403

Authors: Golnush Masghati-Amoli, Paul Chin

Abstract:

Over the past recent years, with the rapid increases in data availability and computing power, Machine Learning (ML) techniques have been called on in a range of different industries for their strong predictive capability. However, the use of Machine Learning in commercial banking has been limited due to a special challenge imposed by numerous regulations that require lenders to be able to explain their analytic models, not only to regulators but often to consumers. In other words, although Machine Leaning techniques enable better prediction with a higher level of accuracy, in comparison with other industries, they are adopted less frequently in commercial banking especially for scoring purposes. This is due to the fact that Machine Learning techniques are often considered as a black box and fail to provide information on why a certain risk score is given to a customer. In order to bridge this gap between the explain-ability and performance of Machine Learning techniques, a Hybrid Model is developed at Dun and Bradstreet that is focused on blending Machine Learning algorithms with traditional approaches such as scorecards. The Hybrid Model maximizes efficiency of traditional scorecards by merging its practical benefits, such as explain-ability and the ability to input domain knowledge, with the deep insights of Machine Learning techniques which can uncover patterns scorecard approaches cannot. First, through development of Machine Learning models, engineered features and latent variables and feature interactions that demonstrate high information value in the prediction of customer risk are identified. Then, these features are employed to introduce observed non-linear relationships between the explanatory and dependent variables into traditional scorecards. Moreover, instead of directly computing the Weight of Evidence (WoE) from good and bad data points, the Hybrid Model tries to match the score distribution generated by a Machine Learning algorithm, which ends up providing an estimate of the WoE for each bin. This capability helps to build powerful scorecards with sparse cases that cannot be achieved with traditional approaches. The proposed Hybrid Model is tested on different portfolios where a significant gap is observed between the performance of traditional scorecards and Machine Learning models. The result of analysis shows that Hybrid Model can improve the performance of traditional scorecards by introducing non-linear relationships between explanatory and target variables from Machine Learning models into traditional scorecards. Also, it is observed that in some scenarios the Hybrid Model can be almost as predictive as the Machine Learning techniques while being as transparent as traditional scorecards. Therefore, it is concluded that, with the use of Hybrid Model, Machine Learning algorithms can be used in the commercial banking industry without being concerned with difficulties in explaining the models for regulatory purposes.

Keywords: machine learning algorithms, scorecard, commercial banking, consumer risk, feature engineering

Procedia PDF Downloads 116

Authors: I. A Tijani, Y. F Wu, C.W. Lim

Abstract:

Concrete Damaged Plasticity Model (CDPM) is capable of modeling the stress-strain behavior of confined concrete. Nevertheless, the accuracy of the model largely depends on its parameters. To date, most research works mainly focus on the identification and modification of the parameters for fiber reinforced polymer (FRP) confined concrete prior to damage. And, it has been established that the FRP-strengthened concrete behaves differently to FRP-repaired concrete. This paper presents a modified plastic damage model within the context of the CDPM in ABAQUS for modelling of a uniformly FRP-confined repaired concrete under monotonic loading. The proposed model includes infliction damage, elastic stiffness, yield criterion and strain hardening rule. The distinct feature of damaged concrete is elastic stiffness reduction; this is included in the model. Meanwhile, the test results were obtained from a physical testing of repaired concrete. The dilation model is expressed as a function of the lateral stiffness of the FRP-jacket. The finite element predictions are shown to be in close agreement with the obtained test results of the repaired concrete. It was observed from the study that with necessary modifications, finite element method is capable of modeling FRP-repaired concrete structures.

Keywords: Concrete, FRP, Damage, Repairing, Plasticity, and Finite element method

Procedia PDF Downloads 121

Authors: Victor Bodell, Lukas Ekstrom, Somayeh Aghanavesi

Abstract:

Fuel consumption (FC) is one of the key factors in determining expenses of operating a heavy-duty vehicle. A customer may therefore request an estimate of the FC of a desired vehicle. The modular design of heavy-duty vehicles allows their construction by specifying the building blocks, such as gear box, engine and chassis type. If the combination of building blocks is unprecedented, it is unfeasible to measure the FC, since this would first r equire the construction of the vehicle. This paper proposes a machine learning approach to predict FC. This study uses around 40,000 vehicles specific and o perational e nvironmental c onditions i nformation, such as road slopes and driver profiles. A ll v ehicles h ave d iesel engines and a mileage of more than 20,000 km. The data is used to investigate the accuracy of machine learning algorithms Linear regression (LR), K-nearest neighbor (KNN) and Artificial n eural n etworks (ANN) in predicting fuel consumption for heavy-duty vehicles. Performance of the algorithms is evaluated by reporting the prediction error on both simulated data and operational measurements. The performance of the algorithms is compared using nested cross-validation and statistical hypothesis testing. The statistical evaluation procedure finds that ANNs have the lowest prediction error compared to LR and KNN in estimating fuel consumption on both simulated and operational data. The models have a mean relative prediction error of 0.3% on simulated data, and 4.2% on operational data.

Keywords: artificial neural networks, fuel consumption, friedman test, machine learning, statistical hypothesis testing

Procedia PDF Downloads 155