Search results for: Grey prediction model

Authors: Suraj Mehrotra

Abstract:

The stock market is a volatile, bustling marketplace that is a cornerstone of economics. It defines whether companies are successful or in spiral. A thorough understanding of it is important - many companies have whole divisions dedicated to analysis of both their stock and of rivaling companies. Linking the world of finance and artificial intelligence (AI), especially the stock market, has been a relatively recent development. Predicting how stocks will do considering all external factors and previous data has always been a human task. With the help of AI, however, machine learning models can help us make more complete predictions in financial trends. Taking a look at the stock market specifically, predicting the open, closing, high, and low prices for the next day is very hard to do. Machine learning makes this task a lot easier. A model that builds upon itself that takes in external factors as weights can predict trends far into the future. When used effectively, new doors can be opened up in the business and finance world, and companies can make better and more complete decisions. This paper explores the various techniques used in the prediction of stock prices, from traditional statistical methods to deep learning and neural networks based approaches, among other methods. It provides a detailed analysis of the techniques and also explores the challenges in predictive analysis. For the accuracy of the testing set, taking a look at four different models - linear regression, neural network, decision tree, and naïve Bayes - on the different stocks, Apple, Google, Tesla, Amazon, United Healthcare, Exxon Mobil, J.P. Morgan & Chase, and Johnson & Johnson, the naïve Bayes model and linear regression models worked best. For the testing set, the naïve Bayes model had the highest accuracy along with the linear regression model, followed by the neural network model and then the decision tree model. The training set had similar results except for the fact that the decision tree model was perfect with complete accuracy in its predictions, which makes sense. This means that the decision tree model likely overfitted the training set when used for the testing set.

Keywords: machine learning, testing set, artificial intelligence, stock analysis

Procedia PDF Downloads 96

Authors: Bharatendra Rai

Abstract:

Predictive data analysis and modeling involving machine learning techniques become challenging in presence of too many explanatory variables or features. Presence of too many features in machine learning is known to not only cause algorithms to slow down, but they can also lead to decrease in model prediction accuracy. This study involves housing dataset with 79 quantitative and qualitative features that describe various aspects people consider while buying a new house. Boruta algorithm that supports feature selection using a wrapper approach build around random forest is used in this study. This feature selection process leads to 49 confirmed features which are then used for developing predictive random forest models. The study also explores five different data partitioning ratios and their impact on model accuracy are captured using coefficient of determination (r-square) and root mean square error (rsme).

Keywords: housing data, feature selection, random forest, Boruta algorithm, root mean square error

Procedia PDF Downloads 324

Authors: Ju-young Hwang, Hyo-Gyoung Kwak, Hong Jae Yim

Abstract:

This paper introduces a numerical analysis method for reinforced-concrete (RC) structures exposed to fire and compares the result with experimental results. The proposed analysis method for RC structure under the high temperature consists of two procedures. First step is to decide the temperature distribution across the section through the heat transfer analysis by using the time-temperature curve. After determination of the temperature distribution, the nonlinear analysis is followed. By considering material and geometrical non-linearity with the temperature distribution, nonlinear analysis predicts the behavior of RC structure under the fire by the exposed time. The proposed method is validated by the comparison with the experimental results. Finally, Prediction model to describe the status of after-cooling concrete can also be introduced based on the results of additional experiment. The product of this study is expected to be embedded for smart structure monitoring system against fire in u-City.

Keywords: RC structures, heat transfer analysis, nonlinear analysis, after-cooling concrete model

Procedia PDF Downloads 369

Authors: Kuo-Wei Liao, Jessica Gitomarsono

Abstract:

Bridge reliability against natural hazards such as floods or earthquakes is an interdisciplinary problem that involves a wide range of knowledge. Moreover, due to the global climate change, engineers have to design a structure against the multi-hazard threats. Currently, few of the practical design guideline has included such concept. The bridge foundation in Taiwan often does not have a uniform width. However, few of the researches have focused on safety evaluation of a bridge with a complex pier. Investigation of the scouring depth under such situation is very important. Thus, this study first focuses on investigating and improving the scour prediction formula for a bridge with complicated foundation via experiments and artificial intelligence. Secondly, a probabilistic design procedure is proposed using the established prediction formula for practical engineers under the multi-hazard attacks.

Keywords: bridge, reliability, multi-hazards, scour

Procedia PDF Downloads 375

Authors: Etienne Provencal, David L. St-Pierre

Abstract:

A facility exploiting only electronic gambling machines (EGMs) opened in 2007 in Quebec City, Canada under the name of Salons de Jeux du Québec (SdjQ). This facility is one of the first worldwide to rely on that business model. This paper models the performance of such EGMs. The interest from a managerial point of view is to identify the variables that can be controlled or influenced so that a comprehensive model can help improve the overall performance of the business. The EGM individual performance model contains eight different variables under study (Game Title, Progressive jackpot, Bonus Round, Minimum Coin-in, Maximum Coin-in, Denomination, Slant Top and Position). Using data from Quebec City’s SdjQ, a linear regression analysis explains 90.80% of the EGM performance. Moreover, results show a behavior slightly different than that of a casino. The addition of GameTitle as a factor to predict the EGM performance is one of the main contributions of this paper. The choice of the game (GameTitle) is very important. Games having better position do not have significantly better performance than games located elsewhere on the gaming floor. Progressive jackpots have a positive and significant effect on the individual performance of EGMs. The impact of BonusRound on the dependent variable is significant but negative. The effect of Denomination is significant but weakly negative. As expected, the Language of an EGMS does not impact its individual performance. This paper highlights some possible improvements by indicating which features are performing well. Recommendations are given to increase the performance of the EGMs performance.

Keywords: EGM, linear regression, model prediction, slot operations

Procedia PDF Downloads 257

Authors: Benjamin Leiby, Darryl Ahner

Abstract:

This study demonstrates an alternative stochastic imputation approach for large datasets when preferred commercial packages struggle to iterate due to numerical problems. A large country conflict dataset motivates the search to impute missing values well over a common threshold of 20% missingness. The methodology capitalizes on correlation while using model residuals to provide the uncertainty in estimating unknown values. Examination of the methodology provides insight toward choosing linear or nonlinear modeling terms. Static tolerances common in most packages are replaced with tailorable tolerances that exploit residuals to fit each data element. The methodology evaluation includes observing computation time, model fit, and the comparison of known values to replaced values created through imputation. Overall, the country conflict dataset illustrates promise with modeling first-order interactions while presenting a need for further refinement that mimics predictive mean matching.

Keywords: correlation, country conflict, imputation, stochastic regression

Procedia PDF Downloads 120

Authors: Andreas Helwig, John Bell, Wangmo

Abstract:

Hybrid energy storage systems (HESS) are gaining popularity for grid energy storage (ESS) driven by the increasingly dynamic nature of energy demands, requiring both high energy and high power density. Particularly the ability of energy storage systems via inverters to respond to increasing fluctuation in energy demands, the combination of lithium Iron Phosphate (LFP) battery and supercapacitor (SC) is a particular example of complex electro-chemical devices that may provide benefit to each other for pulse width modulated DC to AC inverter application. This is due to SC’s ability to respond to instantaneous, high-current demands and batteries' long-term energy delivery. However, there is a knowledge gap on the current sharing mechanism within a HESS supplying a load powered by high-frequency pulse-width modulation (PWM) switching to understand the mechanism of aging in such HESS. This paper investigates the prediction of current utilizing various equivalent circuits for SC to investigate sharing between battery and SC in MATLAB/Simulink simulation environment. The findings predict a significant reduction of battery current when the battery is used in a hybrid combination with a supercapacitor as compared to a battery-only model. The impact of PWM inverter carrier switching frequency on current requirements was analyzed between 500Hz and 31kHz. While no clear trend emerged, models predicted optimal frequencies for minimized current needs.

Keywords: hybrid energy storage, carrier frequency, PWM switching, equivalent circuit models

Procedia PDF Downloads 28

Authors: Zane Turner, Kevin Labille, Susan Gauch

Abstract:

Sentiment analysis is a broad and expanding field that aims to extract and classify opinions from textual data. Lexicon-based approaches are based on the use of a sentiment lexicon, i.e., a list of words each mapped to a sentiment score, to rate the sentiment of a text chunk. Our work focuses on predicting stock price change using a sentiment lexicon built from financial conference call logs. We present a method to generate a sentiment lexicon based upon an existing probabilistic approach. By using a domain-specific lexicon, we outperform traditional techniques and demonstrate that domain-specific sentiment lexicons provide higher accuracy than generic sentiment lexicons when predicting stock price change.

Keywords: computational finance, sentiment analysis, sentiment lexicon, stock movement prediction

Procedia PDF Downloads 128

Authors: Zane Turner, Kevin Labille, Susan Gauch

Abstract:

Sentiment analysis is a broad and expanding field that aims to extract and classify opinions from textual data. Lexicon-based approaches are based on the use of a sentiment lexicon, i.e., a list of words each mapped to a sentiment score, to rate the sentiment of a text chunk. Our work focuses on predicting stock price change using a sentiment lexicon built from financial conference call logs. We introduce a method to generate a sentiment lexicon based upon an existing probabilistic approach. By using a domain-specific lexicon, we outperform traditional techniques and demonstrate that domain-specific sentiment lexicons provide higher accuracy than generic sentiment lexicons when predicting stock price change.

Keywords: computational finance, sentiment analysis, sentiment lexicon, stock movement prediction

Procedia PDF Downloads 170

Authors: Debesh R. Roy

Abstract:

The fundamental issue in understanding the origin and growth mechanism of nanomaterials, from a fundamental unit is a big challenging problem to the scientists. Recently, an immense attention is generated to the researchers for prediction of exceptionally stable atomic cluster units as the building units for future smart materials. The present study is a systematic investigation on the stability and electronic properties of a series of bimetallic (semiconductor-alkaline earth) clusters, viz., BxMg3 (x=1-5) is performed, in search for exceptional and/ or unusual stable motifs. A very popular hybrid exchange-correlation functional, B3LYP as proposed by A. D. Becke along with a higher basis set, viz., 6-31+G[d,p] is employed for this purpose under the density functional formalism. The magic stability among the concerned clusters is explained using the jellium model. It is evident from the present study that the magic stability of B4Mg3 cluster arises due to the jellium shell closure.

Keywords: atomic clusters, density functional theory, jellium model, magic clusters, smart nanomaterials

Procedia PDF Downloads 530

Authors: Ali Nabavi, Farimah Safari, Mohammad Kashkooli, Sara Sadat Nabavizadeh, Hossein Molavi Vardanjani

Abstract:

Cognitive impairment presents a significant and increasing health concern as populations age. Environmental risk factors such as heavy metal exposure are suspected contributors, but their specific roles remain incompletely understood. Machine learning offers a promising approach to integrate multi-factorial data and improve the prediction of cognitive outcomes. This study aimed to develop and validate machine learning models to predict early risk of cognitive impairment by incorporating demographic, clinical, and biomarker data, including measures of heavy metal exposure. A retrospective analysis was conducted using 2011-2014 National Health and Nutrition Examination Survey (NHANES) data. The dataset included participants aged 20 years and older who underwent cognitive testing. Variables encompassed demographic information, medical history, lifestyle factors, and biomarkers such as blood and urine levels of lead, cadmium, manganese, and other metals. Machine learning algorithms were trained on 90% of the data and evaluated on the remaining 10%, with performance assessed through metrics such as accuracy, area under curve (AUC), and sensitivity. Analysis included 2,933 participants. The stacking ensemble model demonstrated the highest predictive performance, achieving an AUC of 0.778 and a sensitivity of 0.879 on the test dataset. Key predictors included age, gender, hypertension, education level, urinary cadmium, and blood manganese levels. The findings indicate that machine learning can effectively predict the risk of cognitive impairment using a comprehensive set of clinical and environmental exposure data. Incorporating biomarkers of heavy metal exposure improved prediction accuracy and highlighted the role of environmental factors in cognitive decline. Further prospective studies are recommended to validate the models and assess their utility over time.

Keywords: cognitive impairment, heavy metal exposure, predictive models, aging

Procedia PDF Downloads 4

Authors: Dorota Witkowska, Paweł Gosek, Lukasz Swiecicki, Wojciech Jernajczyk, Bruce J. West, Miroslaw Latka

Abstract:

In clinical practice, the selection of an antidepressant often degrades to lengthy trial-and-error. In this work we employ a normalized wavelet power of alpha waves as a biomarker of antidepressant treatment response. This novel EEG metric takes into account both non-stationarity and intersubject variability of alpha waves. We recorded resting, 19-channel EEG (closed eyes) in 22 inpatients suffering from unipolar (UD, n=10) or bipolar (BD, n=12) depression. The EEG measurement was done at the end of the short washout period which followed previously unsuccessful pharmacotherapy. The normalized alpha wavelet power of 11 responders was markedly different than that of 11 nonresponders at several, mostly temporoparietal sites. Using the prediction of treatment response based on the normalized alpha wavelet power, we achieved 81.8% sensitivity and 81.8% specificity for channel T4.

Keywords: alpha waves, antidepressant, treatment outcome, wavelet

Procedia PDF Downloads 316

Authors: Nikolaos Simantiris, Markos Avlonitis

Abstract:

This work builds a simulation platform, modeling the spatial diffusion of the invasive species Callinectes sapidus (blue crab) as a random walk, incorporating also generation, fatality, and fishing rates modeling the time evolution of its population. Antinioti lagoon in West Greece was used as a testbed for applying the simulation model. Field measurements from June 2020 to June 2021 on the lagoon’s setting, bathymetry, and blue crab juveniles provided the initial population simulation of blue crabs, as well as biological parameters from the current literature were used to calibrate simulation parameters. The scope of this study is to render the authors able to predict the evolution of the blue crab population in confined environments of the Ionian Islands region in West Greece. The first result of the simulation experiments shows the possibility for a robust prediction for blue crab population evolution in the Antinioti lagoon.

Keywords: antinioti lagoon, blue crab, stochastic simulation, random walk

Procedia PDF Downloads 231

Authors: Joonas Pääkkönen

Abstract:

In sports, individuals and teams are typically interested in final rankings. Final results, such as times or distances, dictate these rankings, also known as places. Places can be further associated with ordered random variables, commonly referred to as order statistics. In this work, we introduce a simple, yet accurate order statistical ordinal regression function that predicts relay race places with changeover-times. We call this function the Fenton-Wilkinson Order Statistics model. This model is built on the following educated assumption: individual leg-times follow log-normal distributions. Moreover, our key idea is to utilize Fenton-Wilkinson approximations of changeover-times alongside an estimator for the total number of teams as in the notorious German tank problem. This original place regression function is sigmoidal and thus correctly predicts the existence of a small number of elite teams that significantly outperform the rest of the teams. Our model also describes how place increases linearly with changeover-time at the inflection point of the log-normal distribution function. With real-world data from Jukola 2019, a massive orienteering relay race, the model is shown to be highly accurate even when the size of the training set is only 5% of the whole data set. Numerical results also show that our model exhibits smaller place prediction root-mean-square-errors than linear regression, mord regression and Gaussian process regression.

Keywords: Fenton-Wilkinson approximation, German tank problem, log-normal distribution, order statistics, ordinal regression, orienteering, sports analytics, sports modeling

Procedia PDF Downloads 125

Authors: Umit Duru

Abstract:

The Soil and Water Assessment Tool (SWAT) was tested for prediction of water balance and sediment yield in the Ankara gauged basin, Turkey. The overall objective of this study was to evaluate the performance and applicability of the SWAT in this region of Turkey. Thirteen years of monthly stream flow, and suspended sediment, data were used for calibration and validation. This research assessed model performance based on differences between observed and predicted suspended sediment yield during calibration (1987-1996) and validation (1982-1984) periods. Statistical comparisons of suspended sediment produced values for NSE (Nash Sutcliffe efficiency), RE (relative error), and R² (coefficient of determination), of 0.81, -1.55, and 0.93, respectively, during the calibration period, and NSE, RE (%), and R² of 0.77, -2.61, and 0.87, respectively, during the validation period. Based on the analyses, SWAT satisfactorily simulated observed hydrology and sediment yields and can be used as a tool in decision making for water resources planning and management in the basin.

Keywords: calibration, GIS, sediment yield, SWAT, validation

Procedia PDF Downloads 283

Authors: Sadia Ilyas, Hyunjung Kim, Rajiv R. Srivastava

Abstract:

Current work has attempted to establish the linkages between circular bio-economy and recycling of copper and gold from urban mine by applying microbial activities instead of the smelter and chemical technologies. Thereafter, based on the potential of microbial approaches and research hypothesis, the structural model has been tested for a significance level of 99%, which is supported by the corresponding standardization co-efficient values. A prediction model applied to determine the recycling impact on circular bio-economy indicates to re-circulate 51,833 tons of copper and 58 tons of gold by 2030 for the production of virgin metals/raw-materials, while recycling rate of the accumulated e-waste remains to be 20%. This restoration volume of copper and gold through the microbial activities corresponds to mitigate 174 million kg CO₂ emissions and 24 million m³ water consumption if compared with the primary production activities. The study potentially opens a new window for environmentally-friendly biotechnological recycling of e-waste urban mine under the umbrella concept of circular bio-economy.

Keywords: urban mining, biobleaching, circular bio-economy, environmental impact

Procedia PDF Downloads 158

Authors: Arslan Murtaza

Abstract:

Model Driven Architecture (MDA) is technique presented by OMG (Object Management Group) for software development in which different models are proposed and converted them into code. The main plan is to identify task by using PIM (Platform Independent Model) and transform it into PSM (Platform Specific Model) and then converted into code. In this review paper describes some challenges and issues that are faced in MDA, type and transformation of models (e.g. CIM, PIM and PSM), and evaluation of MDA-based methodologies.

Keywords: OMG, model driven rrchitecture (MDA), computation independent model (CIM), platform independent model (PIM), platform specific model(PSM), MDA-based methodologies

Procedia PDF Downloads 459

Authors: Afroditi Zamanidou, Dionysios Giannakopoulos, Konstantinos Manolitsis

Abstract:

A notable amount of electrical energy demand in many countries worldwide is used to cover public energy demand for road, square and other public spaces’ lighting. Renewable energy can contribute in a significant way to the electrical energy demand coverage for public lighting. This paper focuses on the sizing and design of a hybrid energy system (HES) exploiting the solar-wind energy potential to meet the electrical energy needs of lighting roads, squares and other public spaces. Moreover, the proposed HES provides coverage of the electrical energy demand for a Wi-Fi hotspot and a charging hotspot for the end-users. Alongside the sizing of the energy production system of the proposed HES, in order to ensure a reliable supply without interruptions, a storage system is added and sized. Multiple scenarios of energy consumption are assumed and applied in order to optimize the sizing of the energy production system and the energy storage system. A database with meteorological prediction data for 51 areas in Greece is developed in order to assess the possible deployment of the proposed HES. Since there are detailed meteorological prediction data for all 51 areas under investigation, the use of these data is evaluated, comparing them to real meteorological data. The meteorological prediction data are exploited to form three hourly production profiles for each area for every month of the year; minimum, average and maximum energy production. The energy production profiles are combined with the energy consumption scenarios and the sizing results of the energy production system and the energy storage system are extracted and presented for every area. Finally, the economic performance of the proposed HES in terms of Levelized cost of energy is estimated by calculating and assessing construction, operation and maintenance costs.

Keywords: energy production system sizing, Greece’s deployment potential, meteorological prediction data, wind-solar hybrid energy system, levelized cost of energy

Procedia PDF Downloads 156

Authors: Tugba Bayoglu

Abstract:

Aerodynamic parameter estimation is very crucial in missile design phase, since accurate high fidelity aerodynamic model is required for designing high performance and robust control system, developing high fidelity flight simulations and verification of computational and wind tunnel test results. However, in literature, there is not enough missile aerodynamic parameter identification study for three main reasons: (1) most air to air missiles cannot fly with constant speed, (2) missile flight test number and flight duration are much less than that of fixed wing aircraft, (3) variation of the missile aerodynamic parameters with respect to Mach number is higher than that of fixed wing aircraft. In addition to these challenges, identification of aerodynamic parameters for high wind angles by using classical estimation techniques brings another difficulty in the estimation process. The reason for this, most of the estimation techniques require employing polynomials or splines to model the behavior of the aerodynamics. However, for the missiles with a large variation of aerodynamic parameters with respect to flight variables, the order of the proposed model increases, which brings computational burden and complexity. Therefore, in this study, it is aimed to solve nonlinear aerodynamic parameter identification problem for a supersonic air to air missile by using Artificial Neural Networks. The method proposed will be tested by using simulated data which will be generated with a six degree of freedom missile model, involving a nonlinear aerodynamic database. The data will be corrupted by adding noise to the measurement model. Then, by using the flight variables and measurements, the parameters will be estimated. Finally, the prediction accuracy will be investigated.

Keywords: air to air missile, artificial neural networks, open loop simulation, parameter identification

Procedia PDF Downloads 281

Authors: Aadityaa Singla

Abstract:

The big five personality traits are as follows: openness, conscientiousness, extraversion, agreeableness, and neuroticism. In order to get an insight into their personality, many flocks to these categories, which each have different meanings/characteristics. This information is important not only to individuals but also to career professionals and psychologists who can use this information for candidate assessment or job recruitment. The links between AI and psychology have been well studied in cognitive science, but it is still a rather novel development. It is possible for various AI classification models to accurately predict a personality question via ten input questions. This would contrast with the hundred questions that normal humans have to answer to gain a complete picture of their five personality traits. In order to approach this problem, various AI classification models were used on a dataset to predict what a user may answer. From there, the model's prediction was compared to its actual response. Normally, there are five answer choices (a 20% chance of correct guess), and the models exceed that value to different degrees, proving their significance. By utilizing an MLP classifier, decision tree, linear model, and K-nearest neighbors, they were able to obtain a test accuracy of 86.643, 54.625, 47.875, and 52.125, respectively. These approaches display that there is potential in the future for more nuanced predictions to be made regarding personality.

Keywords: machine learning, personally, big five personality traits, cognitive science

Procedia PDF Downloads 147

Authors: Xiaoli Zhang, Xiongfei Li, Yuncong Feng

Abstract:

ROC curves, as a widely used evaluating tool in machine learning field, are the tradeoff of true positive rate and negative rate. However, they are blamed for ignoring some vital information in the evaluation process, such as the amount of information about the target that each instance carries, predicted score given by each classification model to each instance. Hence, in this paper, a new classification performance method is proposed by extending the Receiver Operator Characteristic (ROC) curves to 3D space, which is denoted as 3D ROC Histogram. In the histogram, the

Keywords: classification, performance evaluation, receiver operating characteristic histogram, hardness prediction

Procedia PDF Downloads 315

Authors: Çiğdem Bakır, Mecit Yüzkat

Abstract:

With the increasing emphasis on water quality worldwide, the search for and expanding the market for new and intelligent monitoring systems has increased. The current method is the laboratory process, where samples are taken from bodies of water, and tests are carried out in laboratories. This method is time-consuming, a waste of manpower, and uneconomical. To solve this problem, we used machine learning methods to detect water pollution in our study. We created decision trees with the Orange3 software we used in our study and tried to determine all the factors that cause water pollution. An automatic prediction model based on water quality was developed by taking many model inputs such as water temperature, pH, transparency, conductivity, dissolved oxygen, and ammonia nitrogen with machine learning methods. The proposed approach consists of three stages: preprocessing of the data used, feature detection, and classification. We tried to determine the success of our study with different accuracy metrics and the results. We presented it comparatively. In addition, we achieved approximately 98% success with the decision tree.

Keywords: decision tree, water quality, water pollution, machine learning

Procedia PDF Downloads 83

Authors: Quentin C.P. Bourgogne, Vanessa Bouchart, Pierre Chevrier, Emmanuel Dattoli

Abstract:

This study presents an experimental and theoretical work conducted on a PolyPhenylene Sulfide reinforced with 40%wt of short glass fibers (PPS GF40) and its matrix. Thermoplastics are widely used in the automotive industry to lightweight automotive parts. The replacement of metallic parts by thermoplastics is reaching under-the-hood parts, near the engine. In this area, the parts are subjected to high temperatures and are immersed in cooling liquid. This liquid is composed of water and glycol and can affect the mechanical properties of the composite. The aim of this work was thus to quantify the evolution of mechanical properties of the thermoplastic composite, as a function of temperature and liquid aging effects, in order to develop a reliable design of parts. An experimental campaign in the tensile mode was carried out at different temperatures and for various glycol proportions in the cooling liquid, for monotonic and cyclic loadings on a neat and a reinforced PPS. The results of these tests allowed to highlight some of the main physical phenomena occurring during these solicitations under tough hydro-thermal conditions. Indeed, the performed tests showed that temperature and liquid cooling aging can affect the mechanical behavior of the material in several ways. The more the cooling liquid contains water, the more the mechanical behavior is affected. It was observed that PPS showed a higher sensitivity to absorption than to chemical aggressiveness of the cooling liquid, explaining this dominant sensitivity. Two kinds of behaviors were noted: an elasto-plastic type under the glass transition temperature and a visco-pseudo-plastic one above it. It was also shown that viscosity is the leading phenomenon above the glass transition temperature for the PPS and could also be important under this temperature, mostly under cyclic conditions and when the stress rate is low. Finally, it was observed that soliciting this composite at high temperatures is decreasing the advantages of the presence of fibers. A new phenomenological model was then built to take into account these experimental observations. This new model allowed the prediction of the evolution of mechanical properties as a function of the loading environment, with a reduced number of parameters compared to precedent studies. It was also shown that the presented approach enables the description and the prediction of the mechanical response with very good accuracy (2% of average error at worst), over a wide range of hydrothermal conditions. A temperature-humidity equivalence principle was underlined for the PPS, allowing the consideration of aging effects within the proposed model. Then, a limit of improvement of the reachable accuracy was determinate for all models using this set of data by the application of an artificial intelligence-based model allowing a comparison between artificial intelligence-based models and phenomenological based ones.

Keywords: aging, analytical modeling, mechanical testing, polymer matrix composites, sequential model, thermomechanical

Procedia PDF Downloads 117

Authors: Baladitya Swaika, Rahul Khatry

Abstract:

Computer Adaptive Tests (CATs) is one of the most efficient ways for testing the cognitive abilities of students. CATs are based on Item Response Theory (IRT) which is based on item selection and ability estimation using statistical methods of maximum information selection/selection from posterior and maximum-likelihood (ML)/maximum a posteriori (MAP) estimators respectively. This study aims at combining both classical and Bayesian approaches to IRT to create a dataset which is then fed to a neural network which automates the process of ability estimation and then comparing it to traditional CAT models designed using IRT. This study uses python as the base coding language, pymc for statistical modelling of the IRT and scikit-learn for neural network implementations. On creation of the model and on comparison, it is found that the Neural Network based model performs 7-10% worse than the IRT model for score estimations. Although performing poorly, compared to the IRT model, the neural network model can be beneficially used in back-ends for reducing time complexity as the IRT model would have to re-calculate the ability every-time it gets a request whereas the prediction from a neural network could be done in a single step for an existing trained Regressor. This study also proposes a new kind of framework whereby the neural network model could be used to incorporate feature sets, other than the normal IRT feature set and use a neural network’s capacity of learning unknown functions to give rise to better CAT models. Categorical features like test type, etc. could be learnt and incorporated in IRT functions with the help of techniques like logistic regression and can be used to learn functions and expressed as models which may not be trivial to be expressed via equations. This kind of a framework, when implemented would be highly advantageous in psychometrics and cognitive assessments. This study gives a brief overview as to how neural networks can be used in adaptive testing, not only by reducing time-complexity but also by being able to incorporate newer and better datasets which would eventually lead to higher quality testing.

Keywords: computer adaptive tests, item response theory, machine learning, neural networks

Procedia PDF Downloads 176

Authors: Hesham Abd Elkhalek, Sherif M. Hafez, Yasser M. El Fahham

Abstract:

Allocating limited budget to maintain bridge networks and selecting effective maintenance strategies for each bridge represent challenging tasks for maintenance managers and decision makers. In Egypt, bridges are continuously deteriorating. In many cases, maintenance works are performed due to user complaints. The objective of this paper is to develop a practical and reliable framework to manage the maintenance, repair, and rehabilitation (MR&R) activities of Bridges network considering performance and budget limits. The model solves an optimization problem that maximizes the average condition of the entire network given the limited available budget using Genetic Algorithm (GA). The framework contains bridge inventory, condition assessment, repair cost calculation, deterioration prediction, and maintenance optimization. The developed model takes into account multiple parameters including serviceability requirements, budget allocation, element importance on structural safety and serviceability, bridge impact on network, and traffic. A questionnaire is conducted to complete the research scope. The proposed model is implemented in software, which provides a friendly user interface. The framework provides a multi-year maintenance plan for the entire network for up to five years. A case study of ten bridges is presented to validate and test the proposed model with data collected from Transportation Authorities in Egypt. Different scenarios are presented. The results are reasonable, feasible and within acceptable domain.

Keywords: bridge management systems (BMS), cost optimization condition assessment, fund allocation, Markov chain

Procedia PDF Downloads 292

Authors: Dhruv Sharma, Lynne Blair, Stephen Clune

Abstract:

Later life loneliness is a social issue that is increasing alongside an upward global population trend. As a society, one way that we have responded to this social challenge is through developing non-pharmacological interventions such as befriending services, activity clubs, meet-ups, etc. Through a systematic literature review, this paper suggests that currently there is an underrepresentation of radical innovation, and underutilization of digital technologies in developing loneliness interventions for older adults. This paper examines intervention studies that were published in English language, within peer reviewed journals between January 2005 and December 2014 across 4 electronic databases. In addition to academic databases, interventions found in grey literature in the form of websites, blogs, and Twitter were also included in the overall review. This approach yielded 129 interventions that were included in the study. A systematic approach allowed the minimization of any bias dictating the selection of interventions to study. A coding strategy based on a pattern analysis approach was devised to be able to compare and contrast the loneliness interventions. Firstly, interventions were categorized on the basis of their objective to identify whether they were preventative, supportive, or remedial in nature. Secondly, depending on their scope, they were categorized as one-to-one, community-based, or group based. It was also ascertained whether interventions represented an improvement, an incremental innovation, a major advance or a radical departure, in comparison to the most basic form of a loneliness intervention. Finally, interventions were also assessed on the basis of the extent to which they utilized digital technologies. Individual visualizations representing the four levels of coding were created for each intervention, followed by an aggregated visual to facilitate analysis. To keep the inquiry within scope and to present a coherent view of the findings, the analysis was primarily concerned the level of innovation, and the use of digital technologies. This analysis highlights a weak but positive correlation between the level of innovation and the use of digital technologies in designing and deploying loneliness interventions, and also emphasizes how certain existing interventions could be tweaked to enable their migration from representing incremental innovation to radical innovation for example. This analysis also points out the value of including grey literature, especially from Twitter, in systematic literature reviews to get a contemporary view of latest work in the area under investigation.

Keywords: ageing, loneliness, innovation, digital

Procedia PDF Downloads 124

Authors: Yazan Al-Kofahi, Jamal Alqawasmi.

Abstract:

In this study, a comprehensive literature review (SLR) was conducted, with the main goal of assessing the existing literature about how artificial intelligence (AI), machine learning (ML), deep learning (DL) models are used in sustainable architecture applications and issues including thermal comfort satisfaction, energy efficiency, cost prediction and many others issues. For this reason, the search strategy was initiated by using different databases, including Scopus, Springer and Google Scholar. The inclusion criteria were used by two research strings related to DL, ML and sustainable architecture. Moreover, the timeframe for the inclusion of the papers was open, even though most of the papers were conducted in the previous four years. As a paper filtration strategy, conferences and books were excluded from database search results. Using these inclusion and exclusion criteria, the search was conducted, and a sample of 59 papers was selected as the final included papers in the analysis. The data extraction phase was basically to extract the needed data from these papers, which were analyzed and correlated. The results of this SLR showed that there are many applications of ML and DL in Sustainable buildings, and that this topic is currently trendy. It was found that most of the papers focused their discussions on addressing Environmental Sustainability issues and factors using machine learning predictive models, with a particular emphasis on the use of Decision Tree algorithms. Moreover, it was found that the Random Forest repressor demonstrates strong performance across all feature selection groups in terms of cost prediction of the building as a machine-learning predictive model.

Keywords: machine learning, deep learning, artificial intelligence, sustainable building

Procedia PDF Downloads 67

Authors: Farhad Alizadeh, Alireza Faregh Gharamaleki, Mojtaba Jalilzadeh, Houshang Gholami, Ali Akhoundzadeh

Abstract:

This study presented hybrid pre-processing approach along with a conceptual model to enhance the accuracy of river discharge prediction. In order to achieve this goal, Ensemble Empirical Mode Decomposition algorithm (EEMD), Discrete Wavelet Transform (DWT) and Mutual Information (MI) were employed as a hybrid pre-processing approach conjugated to Least Square Support Vector Machine (LSSVM). A conceptual strategy namely multi-station model was developed to forecast the Souris River discharge more accurately. The strategy used herein was capable of covering uncertainties and complexities of river discharge modeling. DWT and EEMD was coupled, and the feature selection was performed for decomposed sub-series using MI to be employed in multi-station model. In the proposed feature selection method, some useless sub-series were omitted to achieve better performance. Results approved efficiency of the proposed DWT-EEMD-MI approach to improve accuracy of multi-station modeling strategies.

Keywords: river stage-discharge process, LSSVM, discrete wavelet transform, Ensemble Empirical Decomposition Mode, multi-station modeling

Procedia PDF Downloads 175

Authors: S. Girish, N. Ajay

Abstract:

Permeation properties have been widely used to quantify durability characteristics of concrete for assessing long term performance and sustainability. The processes of deterioration in concrete are mediated largely by water. There is a strong interest in finding a better way of assessing the material properties of concrete in terms of durability. Water sorptivity is a useful single material property which can be one of the measures of durability useful in service life planning and prediction, especially in severe environmental conditions. This paper presents the results of the comparative study of sorptivity of Self-Compacting Concrete (SCC) with conventionally vibrated concrete. SCC is a new, special type of concrete mixture, characterized by high resistance to segregation that can flow through intricate geometrical configuration in the presence of reinforcement, under its own mass, without vibration and compaction. SCC mixes were developed for the paste contents of 0.38, 0.41 and 0.43 with fly ash as the filler for different cement contents ranging from 300 to 450 kg/m3. The study shows better performance by SCC in terms of capillary absorption. The sorptivity value decreased as the volume of paste increased. The use of higher paste content in SCC can make the concrete robust with better densification of the micro-structure, improving the durability and making the concrete more sustainable with improved long term performance. The sorptivity based on secondary absorption can be effectively used as a durability index to predict the time duration required for the ingress of water to penetrate the concrete, which has practical significance.

Keywords: self-compacting concrete, service life prediction, sorptivity, volume of paste

Procedia PDF Downloads 322

Authors: Mikiyas Adugna

Abstract:

Effort estimation is among the activities carried out in software development processes. An accurate model of estimation leads to project success. The method of agile effort estimation is a complex task because of the dynamic nature of software development. Researchers are still conducting studies on agile effort estimation to enhance prediction accuracy. Due to these reasons, we investigated and proposed a model on LASSO and Elastic Net regression to enhance estimation accuracy. The proposed model has major components: preprocessing, train-test split, training with default parameters, and cross-validation. During the preprocessing phase, the entire dataset is normalized. After normalization, a train-test split is performed on the dataset, setting training at 80% and testing set to 20%. We chose two different phases for training the two algorithms (Elastic Net and LASSO) regression following the train-test-split. In the first phase, the two algorithms are trained using their default parameters and evaluated on the testing data. In the second phase, the grid search technique (the grid is used to search for tuning and select optimum parameters) and 5-fold cross-validation to get the final trained model. Finally, the final trained model is evaluated using the testing set. The experimental work is applied to the agile story point dataset of 21 software projects collected from six firms. The results show that both Elastic Net and LASSO regression outperformed the compared ones. Compared to the proposed algorithms, LASSO regression achieved better predictive performance and has acquired PRED (8%) and PRED (25%) results of 100.0, MMRE of 0.0491, MMER of 0.0551, MdMRE of 0.0593, MdMER of 0.063, and MSE of 0.0007. The result implies LASSO regression algorithm trained model is the most acceptable, and higher estimation performance exists in the literature.

Keywords: agile software development, effort estimation, elastic net regression, LASSO

Procedia PDF Downloads 72