Search results for: Grey prediction model

Authors: Qiming Zhang, Youda Ye, Qinxue Jiang

Abstract:

Accurate prediction of external flowfield and aero-heating at the wall of hypersonic vehicle is very crucial for the design of aircrafts. Unstructured/hybrid meshes have more powerful advantages than structured meshes in terms of pre-processing, parallel computing and mesh adaptation, so it is imperative to develop high-resolution numerical methods for the calculation of aerothermal environment on unstructured/hybrid meshes. The inviscid flux scheme is one of the most important factors affecting the accuracy of unstructured/ hybrid mesh heat flux calculation. Here, a new hybrid flux scheme is developed and the approach of interface type selection is proposed: i.e. 1) using the exact Riemann scheme solution to calculate the flux on the faces parallel to the wall; 2) employing Sterger-Warming (S-W) scheme to improve the stability of the numerical scheme in other interfaces. The results of the heat flux fit the one observed experimentally and have little dependence on grids, which show great application prospect in unstructured/ hybrid mesh.

Keywords: aero-heating prediction, computational fluid dynamics, hybrid meshes, hybrid schemes

Procedia PDF Downloads 224

Authors: Farzad Hosseini Hossein Abadi, Cristina Prieto Sierra, Cesar Álvarez Díaz

Abstract:

Predicting streamflow accurately in flashy catchments prone to floods is a major research and operational challenge in hydrological modeling. Recent advancements in deep learning, particularly Long Short-Term Memory (LSTM) networks, have shown to be promising in achieving accurate hydrological predictions at daily and hourly time scales. In this work, a multi-timescale LSTM (MTS-LSTM) network was applied to the context of regional hydrological predictions at an hourly time scale in flashy catchments. The case study includes 40 catchments allocated in the Basque Country, north of Spain. We explore the impact of hyperparameters on the performance of streamflow predictions given by regional deep learning models through systematic hyperparameter tuning - where optimal regional values for different catchments are identified. The results show that predictions are highly accurate, with Nash-Sutcliffe (NSE) and Kling-Gupta (KGE) metrics values as high as 0.98 and 0.97, respectively. A principal component analysis reveals that a hyperparameter related to the length of the input sequence contributes most significantly to the prediction performance. The findings suggest that input sequence lengths have a crucial impact on the model prediction performance. Moreover, employing catchment-scale analysis reveals distinct sequence lengths for individual basins, highlighting the necessity of customizing this hyperparameter based on each catchment’s characteristics. This aligns with well known “uniqueness of the place” paradigm. In prior research, tuning the length of the input sequence of LSTMs has received limited focus in the field of streamflow prediction. Initially it was set to 365 days to capture a full annual water cycle. Later, performing limited systematic hyper-tuning using grid search, revealed a modification to 270 days. However, despite the significance of this hyperparameter in hydrological predictions, usually studies have overlooked its tuning and fixed it to 365 days. This study, employing a simultaneous systematic hyperparameter tuning approach, emphasizes the critical role of input sequence length as an influential hyperparameter in configuring LSTMs for regional streamflow prediction. Proper tuning of this hyperparameter is essential for achieving accurate hourly predictions using deep learning models.

Keywords: LSTMs, streamflow, hyperparameters, hydrology

Procedia PDF Downloads 41

Authors: Rehan Waheed, Abdul Shakoor

Abstract:

Distortion produced during welding of thin metal plates is a problem in many industries. The purpose of this research was to study distortion produced during welding in 2mm Mild Steel plate by simulating the welding process using Finite Element Analysis. Simulation of welding process requires a couple field transient analyses. At first a transient thermal analysis is performed and the temperature obtained from thermal analysis is used as input in structural analysis to find distortion. An actual weld sample is prepared and the weld distortion produced is measured. The simulated and actual results were in quite agreement with each other and it has been found that there is profound deflection at center of plate. Temperature dependent material properties play significant role in prediction of weld distortion. The results of this research can be used for prediction and control of weld distortion in large steel structures by changing different weld parameters.

Keywords: welding simulation, FEA, welding distortion, temperature dependent mechanical properties

Procedia PDF Downloads 379

Authors: Abdelkader Hocine, Abdelhakim Maizia

Abstract:

The exponential growth of reinforced fibers composite materials use has prompted researchers to step up their work on the prediction of their reliability. Owing to differences between the properties of the materials used for the composite, the manufacturing processes, the load combinations and types of environment, the prediction of the reliability of composite materials has become a primary task. Through failure criteria, TSAI-WU and the maximum stress, the reliability of multilayer tubular structures under pressure is the subject of this paper, where the failure probability of is estimated by the method of Monte Carlo.

Keywords: composite, design, monte carlo, tubular structure, reliability

Procedia PDF Downloads 446

Authors: Abobaker Mohammed Qasem Farhan, Shangming Yang, Mohammed Al-Nehari

Abstract:

Pneumonia is a kind of lung disease that creates congestion in the chest. Such pneumonic conditions lead to loss of life of the severity of high congestion. Pneumonic lung disease is caused by viral pneumonia, bacterial pneumonia, or Covidi-19 induced pneumonia. The early prediction and classification of such lung diseases help to reduce the mortality rate. We propose the automatic Computer-Aided Diagnosis (CAD) system in this paper using the deep learning approach. The proposed CAD system takes input from raw computerized tomography (CT) scans of the patient's chest and automatically predicts disease classification. We designed the Hybrid Deep Learning Algorithm (HDLA) to improve accuracy and reduce processing requirements. The raw CT scans have pre-processed first to enhance their quality for further analysis. We then applied a hybrid model that consists of automatic feature extraction and classification. We propose the robust 2D Convolutional Neural Network (CNN) model to extract the automatic features from the pre-processed CT image. This CNN model assures feature learning with extremely effective 1D feature extraction for each input CT image. The outcome of the 2D CNN model is then normalized using the Min-Max technique. The second step of the proposed hybrid model is related to training and classification using different classifiers. The simulation outcomes using the publically available dataset prove the robustness and efficiency of the proposed model compared to state-of-art algorithms.

Keywords: CT scan, Covid-19, deep learning, image processing, lung disease classification

Procedia PDF Downloads 139

Authors: Junhai Liao, Yansong Shen, Aibing Yu

Abstract:

A 3D numerical model is developed to simulate the complicated in-furnace combustion phenomena in the lower part of an ironmaking blast furnace (BF) while using pulverized coal injection (PCI) technology to reduce the consumption of relatively expensive coke. The computational domain covers blowpipe-tuyere-raceway-coke bed in the BF. The model is validated against experimental data in terms of gaseous compositions and coal burnout. Parameters, such as coal properties and some key operational variables, play an important role on the performance of coal combustion. Their diverse effects on different combustion characteristics are examined in the domain, in terms of gas compositions, temperature, and burnout. The heat generated by the combustion of upgraded Victorian brown coal is able to meet the heating requirement of a BF, hence making upgraded brown coal injected into BF possible. It is evidenced that the model is suitable to investigate the mechanism of the PCI operation in a BF. Prediction results provide scientific insights to optimize and control of the PCI operation. This model cuts the cost to investigate and understand the comprehensive combustion phenomena of upgraded Victorian brown coal in a full-scale BF.

Keywords: blast furnace, numerical study, pulverized coal injection, Victorian brown coal

Procedia PDF Downloads 231

Authors: Suk-Hyun Yu, Heeyong Kwon

Abstract:

Recently PM-10 has become a social and global issue. It is one of major air pollutants which affect human health. Therefore, it needs to be forecasted rapidly and precisely. However, PM-10 comes from various emission sources, and its level of concentration is largely dependent on meteorological and geographical factors of local and global region, so the forecasting of PM-10 concentration is very difficult. Neural network model can be used in the case. But, there are few cases of high concentration PM-10. It makes the learning of the neural network model difficult. In this paper, we suggest a simple input balancing method when the data distribution is uneven. It is based on the probability of appearance of the data. Experimental results show that the input balancing makes the neural networks’ learning easy and improves the forecasting rates.

Keywords: artificial intelligence, air quality prediction, neural networks, pattern recognition, PM-10

Procedia PDF Downloads 220

Authors: Siham G. Farag

Abstract:

The main objective of this paper is to provide a new methodology for road safety assessment in Oman through the development of suitable accident prediction models. GLM technique with Poisson or NBR using SAS package was carried out to develop these models. The paper utilized the accidents data of 31 un-signalized T-intersections during three years. Five goodness-of-fit measures were used to assess the overall quality of the developed models. Two types of models were developed separately; the flow-based models including only traffic exposure functions, and the full models containing both exposure functions and other significant geometry and traffic variables. The results show that, traffic exposure functions produced much better fit to the accident data. The most effective geometric variables were major-road mean speed, minor-road 85th percentile speed, major-road lane width, distance to the nearest junction, and right-turn curb radius. The developed models can be used for intersection treatment or upgrading and specify the appropriate design parameters of T- intersections. Finally, the models presented in this thesis reflect the intersection conditions in Oman and could represent the typical conditions in several countries in the middle east area, especially gulf countries.

Keywords: accidents prediction models (APMs), generalized linear model (GLM), T-intersections, Oman

Procedia PDF Downloads 257

Authors: Ayliana Dharmawan, Heng Yong Sheng, Zhang Xiaojin, Tan Thai Lian

Abstract:

To facilitate discharge planning, doctors are presently required to assign an Estimated Discharge Date (EDD) for each patient admitted to the hospital. This assignment of the EDD is largely based on the doctor’s judgment. This can be difficult for cases which are complex or relatively new to the doctor. It is hypothesized that a data-driven approach would be able to facilitate the doctors to make accurate estimations of the discharge date. Making use of routinely collected data on inpatient discharges between January 2013 and May 2016, a predictive model was developed using machine learning techniques to predict the Length of Stay (and hence the EDD) of inpatients, at the point of admission. The predictive performance of the model was compared to that of the clinicians using accuracy measures. Overall, the best performing model was found to be able to predict EDD with an accuracy improvement in Average Squared Error (ASE) by -38% as compared to the first EDD determined by the present method. It was found that important predictors of the EDD include the provisional diagnosis code, patient’s age, attending doctor at admission, medical specialty at admission, accommodation type, and the mean length of stay of the patient in the past year. The predictive model can be used as a tool to accurately predict the EDD.

Keywords: inpatient, estimated discharge date, EDD, prediction, data-driven

Procedia PDF Downloads 160

Authors: M. Sirhan, S. Bekhor, A. Sidess

Abstract:

In-service pavements deteriorate with time due to traffic wheel loads, environment, and climate conditions. Pavement deterioration leads to a reduction in their serviceability and structural behavior. Consequently, proper maintenance and rehabilitation (M&R) are necessary actions to keep the in-service pavement network at the desired level of serviceability. Due to resource and financial constraints, the pavement management system (PMS) prioritizes roads most in need of maintenance and rehabilitation action. It recommends a suitable action for each pavement based on the performance and surface condition of each road in the network. The pavement performance and condition are usually quantified and evaluated by different types of roughness-based and stress-based indices. Examples of such indices are Pavement Serviceability Index (PSI), Pavement Serviceability Ratio (PSR), Mean Panel Rating (MPR), Pavement Condition Rating (PCR), Ride Number (RN), Profile Index (PI), International Roughness Index (IRI), and Pavement Condition Index (PCI). PCI is commonly used in PMS as an indicator of the extent of the distresses on the pavement surface. PCI values range between 0 and 100; where 0 and 100 represent a highly deteriorated pavement and a newly constructed pavement, respectively. The PCI value is a function of distress type, severity, and density (measured as a percentage of the total pavement area). PCI is usually calculated iteratively using the 'Paver' program developed by the US Army Corps. The use of soft computing techniques, especially Artificial Neural Network (ANN), has become increasingly popular in the modeling of engineering problems. ANN techniques have successfully modeled the performance of the in-service pavements, due to its efficiency in predicting and solving non-linear relationships and dealing with an uncertain large amount of data. Typical regression models, which require a pre-defined relationship, can be replaced by ANN, which was found to be an appropriate tool for predicting the different pavement performance indices versus different factors as well. Subsequently, the objective of the presented study is to develop and train an ANN model that predicts the PCI values. The model’s input consists of percentage areas of 11 different damage types; alligator cracking, swelling, rutting, block cracking, longitudinal/transverse cracking, edge cracking, shoving, raveling, potholes, patching, and lane drop off, at three severity levels (low, medium, high) for each. The developed model was trained using 536,000 samples and tested on 134,000 samples. The samples were collected and prepared by The National Transport Infrastructure Company. The predicted results yielded satisfactory compliance with field measurements. The proposed model predicted PCI values with relatively low standard deviations, suggesting that it could be incorporated into the PMS for PCI determination. It is worth mentioning that the most influencing variables for PCI prediction are damages related to alligator cracking, swelling, rutting, and potholes.

Keywords: artificial neural networks, computer programming, pavement condition index, pavement management, performance prediction

Procedia PDF Downloads 124

Authors: Shun-Qi Zhang, Shu-Yang Zhang, Min Chen

Abstract:

Applying strong electric field on piezoelectric actuators, on one hand very significant electroelastic material nonlinear effects will occur, on the other hand piezo plates and shells may undergo large displacements and rotations. In order to give a precise prediction of piezolaminated smart structures under large electric field, this paper develops a finite element (FE) model accounting for both electroelastic material nonlinearity and geometric nonlinearity with large rotations based on the first order shear deformation (FSOD) hypothesis. The proposed FE model is applied to analyze a piezolaminated semicircular shell structure.

Keywords: smart structures, piezolamintes, material nonlinearity, strong electric field

Procedia PDF Downloads 411

Authors: Joseph Fitoussi, Mohammadali Shirinbayan, Abbas Tcharkhtchi

Abstract:

Due to material flow during processing, short fiber reinforced composites structures obtained by injection or compression molding generally present strong spatial microstructure variation. On the other hand, quasi-static, dynamic, and fatigue behavior of these materials are highly dependent on microstructure parameters such as fiber orientation distribution. Indeed, because of complex damage mechanisms, SFRC structures design is a key challenge for safety and reliability. In this paper, we propose a micromechanical model allowing prediction of damage behavior of real structures as a function of microstructure spatial distribution. To this aim, a statistical damage criterion including strain rate and fatigue effect at the local scale is introduced into a Mori and Tanaka model. A critical local damage state is identified, allowing fatigue life prediction. Moreover, the multi-scale model is coupled with an experimental intrinsic link between damage under monotonic loading and fatigue life in order to build an abacus giving Tsai-Wu failure criterion parameters as a function of microstructure and targeted fatigue life. On the other hand, the micromechanical damage model gives access to the evolution of the anisotropic stiffness tensor of SFRC submitted to complex thermomechanical loading, including quasi-static, dynamic, and cyclic loading with temperature and amplitude variations. Then, the latter is used to fill out microstructure dependent material cards in finite element analysis for design optimization in the case of complex loading history. The proposed methodology is illustrated in the case of a real automotive component made of sheet molding compound (PSA 3008 tailgate). The obtained results emphasize how the proposed micromechanical methodology opens a new path for the automotive industry to lighten vehicle bodies and thereby save energy and reduce gas emission.

Keywords: short fiber reinforced composite, structural design, damage, micromechanical modelling, fatigue, strain rate effect

Procedia PDF Downloads 94

Authors: Ju Peng Poh, Jun Yu Charles Lee, Jonathan Chew Hoe Khoo

Abstract:

The emergence of digital twin technology, a digital replica of physical world, has improved the real-time access to data from sensors about the performance of buildings. This digital transformation has opened up many opportunities to improve the management of the building by using the data collected to help monitor consumption patterns and energy leakages. One example is the integration of predictive models for anomaly detection. In this paper, we use the GAM (Generalised Additive Model) for the anomaly detection of Air Handling Units (AHU) power consumption pattern. There is ample research work on the use of GAM for the prediction of power consumption at the office building and nation-wide level. However, there is limited illustration of its anomaly detection capabilities, prescriptive analytics case study, and its integration with the latest development of digital twin technology. In this paper, we applied the general GAM modelling framework on the historical data of the AHU power consumption and cooling load of the building between Jan 2018 to Aug 2019 from an education campus in Singapore to train prediction models that, in turn, yield predicted values and ranges. The historical data are seamlessly extracted from the digital twin for modelling purposes. We enhanced the utility of the GAM model by using it to power a real-time anomaly detection system based on the forward predicted ranges. The magnitude of deviation from the upper and lower bounds of the uncertainty intervals is used to inform and identify anomalous data points, all based on historical data, without explicit intervention from domain experts. Notwithstanding, the domain expert fits in through an optional feedback loop through which iterative data cleansing is performed. After an anomalously high or low level of power consumption detected, a set of rule-based conditions are evaluated in real-time to help determine the next course of action for the facilities manager. The performance of GAM is then compared with other approaches to evaluate its effectiveness. Lastly, we discuss the successfully deployment of this approach for the detection of anomalous power consumption pattern and illustrated with real-world use cases.

Keywords: anomaly detection, digital twin, generalised additive model, GAM, power consumption, supervised learning

Procedia PDF Downloads 138

Authors: Ning Chang, Zelong Yuan, Yunpeng Wang, Jianchun Wang

Abstract:

Large eddy simulation (LES) has been extensively used in the investigation of turbulence. LES calculates the grid-resolved large-scale motions and leaves small scales modeled by sublfilterscale (SFS) models. Among the existing SFS models, the deconvolution model has been used successfully in the LES of the engineering flows and geophysical flows. Despite the wide application of deconvolution models, the effects of subfilter scale dynamics and filter anisotropy on the accuracy of SFS modeling have not been investigated in depth. The results of LES are highly sensitive to the selection of filters and the anisotropy of the grid, which has been overlooked in previous research. In the current study, two critical aspects of LES are investigated. Firstly, we analyze the influence of sub-filter scale (SFS) dynamics on the accuracy of direct deconvolution models (DDM) at varying filter-to-grid ratios (FGR) in isotropic turbulence. An array of invertible filters are employed, encompassing Gaussian, Helmholtz I and II, Butterworth, Chebyshev I and II, Cauchy, Pao, and rapidly decaying filters. The significance of FGR becomes evident, as it acts as a pivotal factor in error control for precise SFS stress prediction. When FGR is set to 1, the DDM models cannot accurately reconstruct the SFS stress due to the insufficient resolution of SFS dynamics. Notably, prediction capabilities are enhanced at an FGR of 2, resulting in accurate SFS stress reconstruction, except for cases involving Helmholtz I and II filters. A remarkable precision close to 100% is achieved at an FGR of 4 for all DDM models. Additionally, the further exploration extends to the filter anisotropy to address its impact on the SFS dynamics and LES accuracy. By employing dynamic Smagorinsky model (DSM), dynamic mixed model (DMM), and direct deconvolution model (DDM) with the anisotropic filter, aspect ratios (AR) ranging from 1 to 16 in LES filters are evaluated. The findings highlight the DDM's proficiency in accurately predicting SFS stresses under highly anisotropic filtering conditions. High correlation coefficients exceeding 90% are observed in the a priori study for the DDM's reconstructed SFS stresses, surpassing those of the DSM and DMM models. However, these correlations tend to decrease as lter anisotropy increases. In the a posteriori studies, the DDM model consistently outperforms the DSM and DMM models across various turbulence statistics, encompassing velocity spectra, probability density functions related to vorticity, SFS energy flux, velocity increments, strain-rate tensors, and SFS stress. It is observed that as filter anisotropy intensify, the results of DSM and DMM become worse, while the DDM continues to deliver satisfactory results across all filter-anisotropy scenarios. The findings emphasize the DDM framework's potential as a valuable tool for advancing the development of sophisticated SFS models for LES of turbulence.

Keywords: deconvolution model, large eddy simulation, subfilter scale modeling, turbulence

Procedia PDF Downloads 62

Authors: Florin Leon

Abstract:

This paper describes a simulator of traffic scenarios tailored to facilitate autonomous driving model training for urban environments. With the rising prominence of self-driving vehicles, the need for diverse datasets is very important. The proposed simulator provides a flexible framework that allows the generation of custom scenarios needed for the validation and enhancement of trajectory prediction algorithms. Its controlled yet dynamic environment addresses the challenges associated with real-world data acquisition and ensures adaptability to diverse driving scenarios. By providing an adaptable solution for scenario creation and algorithm testing, this tool proves to be a valuable resource for advancing autonomous driving technology that aims to ensure safe and efficient self-driving vehicles.

Keywords: autonomous driving, car simulator, machine learning, model training, urban simulation environment

Procedia PDF Downloads 38

Authors: Man Fung Ho, Lap So, Jiaqi Zhang, Yuheng Zhao, Huiyang Lu, Tat Shing Choi, K. Y. Michael Wong

Abstract:

Nowadays, a tremendous amount of data is available in the transportation system, enabling the development of various machine learning approaches to make short-term latency predictions. A natural question is then the choice of relevant information to enable accurate predictions. Using traffic data collected from the Taiwan Freeway System, we consider the prediction of short-term latency of a freeway segment with a length of 17 km covering 5 measurement points, each collecting vehicle-by-vehicle data through the electronic toll collection system. The processed data include the past latencies of the freeway segment with different time lags, the traffic conditions of the individual segments (the accumulations, the traffic fluxes, the entrance and exit rates), the total accumulations, and the weekday latency profiles obtained by Gaussian process regression of past data. We arrive at several important conclusions about how data should be refined to obtain accurate predictions, which have implications for future system-wide latency predictions. (1) We find that the prediction of median latency is much more accurate and meaningful than the prediction of average latency, as the latter is plagued by outliers. This is verified by machine-learning prediction using XGBoost that yields a 35% improvement in the mean square error of the 5-minute averaged latencies. (2) We find that the median latency of the segment 15 minutes ago is a very good baseline for performance comparison, and we have evidence that further improvement is achieved by machine learning approaches such as XGBoost and Long Short-Term Memory (LSTM). (3) By analyzing the feature importance score in XGBoost and calculating the mutual information between the inputs and the latencies to be predicted, we identify a sequence of inputs ranked in importance. It confirms that the past latencies are most informative of the predicted latencies, followed by the total accumulation, whereas inputs such as the entrance and exit rates are uninformative. It also confirms that the inputs are much less informative of the average latencies than the median latencies. (4) For predicting the latencies of segments composed of two or three sub-segments, summing up the predicted latencies of each sub-segment is more accurate than the one-step prediction of the whole segment, especially with the latency prediction of the downstream sub-segments trained to anticipate latencies several minutes ahead. The duration of the anticipation time is an increasing function of the traveling time of the upstream segment. The above findings have important implications to predicting the full set of latencies among the various locations in the freeway system.

Keywords: data refinement, machine learning, mutual information, short-term latency prediction

Procedia PDF Downloads 160

Authors: Chisomo Patrick Kumbuyo, Katsuyuki Shimizu, Hiroshi Yasuda, Yoshinobu Kitamura

Abstract:

This study deals with a way of predicting Malawi rainfall from global sea surface temperature (SST) using a simple multiple regression model. Monthly rainfall data from nine stations in Malawi grouped into two zones on the basis of inter-station rainfall correlations were used in the study. Zone 1 consisted of Karonga and Nkhatabay stations, located in northern Malawi; and Zone 2 consisted of Bolero, located in northern Malawi; Kasungu, Dedza, Salima, located in central Malawi; Mangochi, Makoka and Ngabu stations located in southern Malawi. Links between Malawi rainfall and SST based on statistical correlations were evaluated and significant results selected as predictors for the regression models. The predictors for Zone 1 model were identified from the Atlantic, Indian and Pacific oceans while those for Zone 2 were identified from the Pacific Ocean. The correlation between the fit of predicted and observed rainfall values of the models were satisfactory with r=0.81 and 0.54 for Zone 1 and 2 respectively (significant at less than 99.99%). The results of the models are in agreement with other findings that suggest that SST anomalies in the Atlantic, Indian and Pacific oceans have an influence on the rainfall patterns of Southern Africa.

Keywords: Malawi rainfall, forecast model, predictors, SST

Procedia PDF Downloads 373

Authors: Sudha T., Naveen C.

Abstract:

Dengue is a serious public health issue that causes significant annual economic and welfare burdens on nations. However, enhanced optimization techniques and quantitative modeling approaches can predict the incidence of dengue. By advocating for a data-driven approach, public health officials can make informed decisions, thereby improving the overall effectiveness of sudden disease outbreak control efforts. The National Oceanic and Atmospheric Administration and the Centers for Disease Control and Prevention are two of the U.S. Federal Government agencies from which this study uses environmental data. Based on environmental data that describe changes in temperature, precipitation, vegetation, and other factors known to affect dengue incidence, many predictive models are constructed that use different machine learning methods to estimate weekly dengue cases. The first step involves preparing the data, which includes handling outliers and missing values to make sure the data is prepared for subsequent processing and the creation of an accurate forecasting model. In the second phase, multiple feature selection procedures are applied using various machine learning models and optimization techniques. During the third phase of the research, machine learning models like the Huber Regressor, Support Vector Machine, Gradient Boosting Regressor (GBR), and Support Vector Regressor (SVR) are compared with several optimization techniques for feature selection, such as Harmony Search and Genetic Algorithm. In the fourth stage, the model's performance is evaluated using Mean Square Error (MSE), Mean Absolute Error (MAE), and Root Mean Square Error (RMSE) as assistance. Selecting an optimization strategy with the least number of errors, lowest price, biggest productivity, or maximum potential results is the goal. In a variety of industries, including engineering, science, management, mathematics, finance, and medicine, optimization is widely employed. An effective optimization method based on harmony search and an integrated genetic algorithm is introduced for input feature selection, and it shows an important improvement in the model's predictive accuracy. The predictive models with Huber Regressor as the foundation perform the best for optimization and also prediction.

Keywords: deep learning model, dengue fever, prediction, optimization

Procedia PDF Downloads 44

Authors: Jan-Peter Mund, Christian Kind

Abstract:

In view of the ongoing climate change and global warming, fires along railways in Germany are occurring more frequently, with sometimes massive consequences for railway operations and affected railroad infrastructure. In the absence of systematic studies within the infrastructure network of German Rail, little is known about the causes of such embankment fires. Since a further increase in these hazards is to be expected in the near future, there is a need for a sound knowledge of triggers and drivers for embankment fires as well as methodical knowledge of prediction tools. Two predictable future trends speak for the increasing relevance of the topic: through the intensification of the use of rail for passenger and freight transport (e.g..: doubling of annual passenger numbers by 2030, compared to 2019), there will be more rail traffic and also more maintenance and construction work on the railways. This research project approach uses satellite data to identify historical embankment fires along rail network infrastructure. The team links data from these fires with infrastructure and weather data and trains a machine-learning model with the aim of predicting fire hazards on sections of the track. Companies reflect on the results and use them on a pilot basis in precautionary measures.

Keywords: embankment fires, railway maintenance, machine learning, remote sensing, VIIRS data

Procedia PDF Downloads 79

Authors: Imad Eddine Charif, Wafaa Benchouk, Sidi Mohamed Mekelleche

Abstract:

The regioselectivity of a series of 16 1,3-dipolar cycloaddition reactions of nitrile oxides with 2(5H)-furanones has been analysed by means of global and local electrophilic and nucleophilic reactivity indices using density functional theory at the B3LYP level together with the 6-31G(d) basis set. The local electrophilicity and nucleophilicity indices, based on Fukui and Parr functions, have been calculated for the terminal sites, namely the C1 and O3 atoms of the 1,3-dipole and the C4 and C5 atoms of the dipolarophile. These local indices were calculated using both Mulliken and natural charges and spin densities. The results obtained show that the C5 atom of the 2(5H)-furanones is the most electrophilic site whereas the O3 atom of the nitrile oxides is the most nucleophilic centre. It turns out that the experimental regioselectivity is correctly reproduced, indicating that both Fukui- and Parr-based indices are efficient tools for the prediction of the regiochemistry of the studied reactions and could be used for the prediction of newly designed reactions of the same kind.

Keywords: 1, 3-dipolar cycloaddition, density functional theory, nitrile oxides, regioselectivity, reactivity indices

Procedia PDF Downloads 155

Authors: Subhadip Biswas, Shivendra Maurya, Satish Chandra, Indrajit Ghosh

Abstract:

Use of speed prediction models sometimes appears as a feasible alternative to laborious field measurement particularly, in case when field data cannot fulfill designer’s requirements. However, developing speed models is a challenging task specifically in the context of developing countries like India where vehicles with diverse static and dynamic characteristics use the same right of way without any segregation. Here the traffic composition plays a significant role in determining the vehicular speed. The present research was carried out to examine the effects of traffic volume and its composition on vehicular speed under mixed traffic conditions. Classified traffic volume and speed data were collected from different geometrically identical six lane divided arterials in New Delhi. Based on these field data, speed prediction models were developed for individual vehicle category adopting Kriging approximation technique, an alternative for commonly used regression. These models are validated with the data set kept aside earlier for validation purpose. The predicted speeds showed a great deal of agreement with the observed values and also the model outperforms all other existing speed models. Finally, the proposed models were utilized to evaluate the effect of traffic volume and its composition on speed.

Keywords: speed, Kriging, arterial, traffic volume

Procedia PDF Downloads 340

Authors: Zunaira Zaman, David Bohannon

Abstract:

This study explores the application of machine learning (ML) for detecting security vulnerabilities in source code. The research aims to assist organizations with large application portfolios and limited security testing capabilities in prioritizing security activities. ML-based approaches offer benefits such as increased confidence scores, false positives and negatives tuning, and automated feedback. The initial approach using natural language processing techniques to extract features achieved 86% accuracy during the training phase but suffered from overfitting and performed poorly on unseen datasets during testing. To address these issues, the study proposes using the abstract syntax tree (AST) for Java and C++ codebases to capture code semantics and structure and generate path-context representations for each function. The Code2Vec model architecture is used to learn distributed representations of source code snippets for training a machine-learning classifier for vulnerability prediction. The study evaluates the performance of the proposed methodology using two datasets and compares the results with existing approaches. The Devign dataset yielded 60% accuracy in predicting vulnerable code snippets and helped resist overfitting, while the Juliet Test Suite predicted specific vulnerabilities such as OS-Command Injection, Cryptographic, and Cross-Site Scripting vulnerabilities. The Code2Vec model achieved 75% accuracy and a 98% recall rate in predicting OS-Command Injection vulnerabilities. The study concludes that even partial AST representations of source code can be useful for vulnerability prediction. The approach has the potential for automated intelligent analysis of source code, including vulnerability prediction on unseen source code. State-of-the-art models using natural language processing techniques and CNN models with ensemble modelling techniques did not generalize well on unseen data and faced overfitting issues. However, predicting vulnerabilities in source code using machine learning poses challenges such as high dimensionality and complexity of source code, imbalanced datasets, and identifying specific types of vulnerabilities. Future work will address these challenges and expand the scope of the research.

Keywords: code embeddings, neural networks, natural language processing, OS command injection, software security, code properties

Procedia PDF Downloads 93

Authors: Christian Neunzig, Simon Fahle, Jürgen Schulz, Matthias Möller, Bernd Kuhlenkötter

Abstract:

Digitalisation in production technology is a driver for the application of machine learning methods. Through the application of predictive quality, the great potential for saving necessary quality control can be exploited through the data-based prediction of product quality and states. However, the serial use of machine learning applications is often prevented by various problems. Fluctuations occur in real production data sets, which are reflected in trends and systematic shifts over time. To counteract these problems, data preprocessing includes rule-based data cleaning, the application of dimensionality reduction techniques, and the identification of comparable data subsets to extract stable features. Successful process control of the target variables aims to centre the measured values around a mean and minimise variance. Competitive leaders claim to have mastered their processes. As a result, much of the real data has a relatively low variance. For the training of prediction models, the highest possible generalisability is required, which is at least made more difficult by this data availability. The implementation of a machine learning application can be interpreted as a production process. The CRoss Industry Standard Process for Data Mining (CRISP-DM) is a process model with six phases that describes the life cycle of data science. As in any process, the costs to eliminate errors increase significantly with each advancing process phase. For the quality prediction of hydraulic test steps of directional control valves, the question arises in the initial phase whether a regression or a classification is more suitable. In the context of this work, the initial phase of the CRISP-DM, the business understanding, is critically compared for the use case at Bosch Rexroth with regard to regression and classification. The use of cross-process production data along the value chain of hydraulic valves is a promising approach to predict the quality characteristics of workpieces. Suitable methods for leakage volume flow regression and classification for inspection decision are applied. Impressively, classification is clearly superior to regression and achieves promising accuracies.

Keywords: classification, CRISP-DM, machine learning, predictive quality, regression

Procedia PDF Downloads 132

Authors: Yan Zhang

Abstract:

Predictive maintenance is a technique to predict when an in-service machine will fail so that maintenance can be planned in advance. Analytics-driven predictive maintenance is gaining increasing attention in many industries such as manufacturing, utilities, aerospace, etc., along with the emerging demand of Internet of Things (IoT) applications and the maturity of technologies that support Big Data storage and processing. This study aims to build an end-to-end analytics solution that includes both real-time machine condition monitoring and machine learning based predictive analytics capabilities. The goal is to showcase a general predictive maintenance solution architecture, which suggests how the data generated from field machines can be collected, transmitted, stored, and analyzed. We use a publicly available aircraft engine run-to-failure dataset to illustrate the streaming analytics component and the batch failure prediction component. We outline the contributions of this study from four aspects. First, we compare the predictive maintenance problems from the view of the traditional reliability centered maintenance field, and from the view of the IoT applications. When evolving to the IoT era, predictive maintenance has shifted its focus from ensuring reliable machine operations to improve production/maintenance efficiency via any maintenance related tasks. It covers a variety of topics, including but not limited to: failure prediction, fault forecasting, failure detection and diagnosis, and recommendation of maintenance actions after failure. Second, we review the state-of-art technologies that enable a machine/device to transmit data all the way through the Cloud for storage and advanced analytics. These technologies vary drastically mainly based on the power source and functionality of the devices. For example, a consumer machine such as an elevator uses completely different data transmission protocols comparing to the sensor units in an environmental sensor network. The former may transfer data into the Cloud via WiFi directly. The latter usually uses radio communication inherent the network, and the data is stored in a staging data node before it can be transmitted into the Cloud when necessary. Third, we illustrate show to formulate a machine learning problem to predict machine fault/failures. By showing a step-by-step process of data labeling, feature engineering, model construction and evaluation, we share following experiences: (1) what are the specific data quality issues that have crucial impact on predictive maintenance use cases; (2) how to train and evaluate a model when training data contains inter-dependent records. Four, we review the tools available to build such a data pipeline that digests the data and produce insights. We show the tools we use including data injection, streaming data processing, machine learning model training, and the tool that coordinates/schedules different jobs. In addition, we show the visualization tool that creates rich data visualizations for both real-time insights and prediction results. To conclude, there are two key takeaways from this study. (1) It summarizes the landscape and challenges of predictive maintenance applications. (2) It takes an example in aerospace with publicly available data to illustrate each component in the proposed data pipeline and showcases how the solution can be deployed as a live demo.

Keywords: Internet of Things, machine learning, predictive maintenance, streaming data

Procedia PDF Downloads 375

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 167

Authors: Lojain Suliman, Xinrong Liu, Xiaohan Zhou

Abstract:

Since most tunnels are built in crowded metropolitan settings, the excavation process must take place in highly condensed locations, including high-density cities. In this way, the tunnels are typically located close together, which leads to more interaction between the parallel existing tunnels, and this, in turn, leads to more settlement. This research presents an examination of the impact of a large-scale tunnel excavation on two forms of settlement: surface settlement and settlement surrounding the tunnel. Additionally, research has been done on the properties of interactions between two and three parallel tunnels. The settlement has been evaluated using three primary techniques: theoretical modeling, numerical simulation, and data monitoring. Additionally, a parametric investigation on how distance affects the settlement characteristic for parallel tunnels with short distances has been completed. Additionally, it has been observed that the sequence of excavation has an impact on the behavior of settlements. Nevertheless, a comparison of the model test and numerical simulation yields significant agreement in terms of settlement trend and value. Additionally, when compared to the FEM study, the suggested analytical solution exhibits reduced sensitivity in the settlement prediction. For example, the settlement of the small tunnel diameter does not appear clearly on the settlement curve, while it is notable in the FEM analysis. It is advised, however, that additional studies be conducted in the future employing analytical solutions for settlement prediction for parallel tunnels.

Keywords: settlement, FEM, analytical solution, parallel tunnels

Procedia PDF Downloads 18

Authors: Hary Aprianto Wijaya Siahaan, Bayu Edo Pratama

Abstract:

Sea fishery's potential to become one of the nation's assets which very contributed to Indonesia's economy. This fishery potential not in spite of the availability of the chlorophyll in the territorial waters of Indonesia. The research was conducted using three methods, namely: statistics, comparative and analytical. The data used include MODIS sea temperature data imaging results in Aqua satellite with a resolution of 4 km in 2002-2015, MODIS data of chlorophyll-a imaging results in Aqua satellite with a resolution of 4 km in 2002-2015, and Imaging results data ASCAT on MetOp and NOAA satellites with 27 km resolution in 2002-2015. The results of the processing of the data show that the incidence of upwelling in the south of East Java Sea began to happen in June identified with sea surface temperature anomaly below normal, the mass of the air that moves from the East to the West, and chlorophyll-a concentrations are high. In July the region upwelling events are increasingly expanding towards the West and reached its peak in August. Chlorophyll-a concentration prediction using multiple linear regression equations demonstrate excellent results to chlorophyll-a concentrations prediction in 2002 until 2015 with the correlation of predicted chlorophyll-a concentration indicate a value of 0.8 and 0.3 with RMSE value. On the chlorophyll-a concentration prediction in 2016 indicate good results despite a decline in the value of the correlation, where the correlation of predicted chlorophyll-a concentration in the year 2016 indicate a value 0.6, but showed improvement in RMSE values with 0.2.

Keywords: satellite, sea surface temperature, upwelling, wind stress

Procedia PDF Downloads 148

Authors: Leah Ning

Abstract:

This paper discusses the development of a machine learning algorithm that accurately detects metastatic breast cancer (cancer has spread elsewhere from its origin part) in selected images that come from pathology scans of lymph node sections. Being able to develop an accurate artificial intelligence (AI) algorithm would help significantly in breast cancer diagnosis since manual examination of lymph node scans is both tedious and oftentimes highly subjective. The usage of AI in the diagnosis process provides a much more straightforward, reliable, and efficient method for medical professionals and would enable faster diagnosis and, therefore, more immediate treatment. The overall approach used was to train a convolution neural network (CNN) based on a set of pathology scan data and use the trained model to binarily classify if a new scan were benign or malignant, outputting a 0 or a 1, respectively. The final model’s prediction accuracy is very high, with 100% for the train set and over 70% for the test set. Being able to have such high accuracy using an AI model is monumental in regard to medical pathology and cancer detection. Having AI as a new tool capable of quick detection will significantly help medical professionals and patients suffering from cancer.

Keywords: breast cancer detection, AI, machine learning, algorithm

Procedia PDF Downloads 81

Authors: Abdelrahman Alghazali, Youssef Kassem, Hüseyin Çamur, Ozan Erenay

Abstract:

Savonius is a drag type vertical axis wind turbine. Savonius wind turbines have a low cut-in speed and can operate at low wind speed. This makes it suitable for electricity or mechanical generation in low-power applications such as individual domestic installations. Therefore, the primary purpose of this work was to investigate the relationship between the type of Savonius rotor and the torque and mechanical power generated. And it was to illustrate how the type of rotor might play an important role in the prediction of mechanical power of wind turbine powered car. The main purpose of this paper is to predict and investigate the aerodynamic effects by means of velocity analysis on the performance of a wind turbine powered car by converting the wind energy into mechanical energy to overcome load that rotates the main shaft. The predicted results based on theoretical analysis were compared with experimental results obtained from literature. The percentage of error between the two was approximately around 20%. Prediction of the torque was done at a wind speed of 4 m/s, and an angular velocity of 130 RPM according to meteorological statistics in Northern Cyprus.

Keywords: mechanical power, torque, Savonius rotor, wind car

Procedia PDF Downloads 318

Authors: Dariush Jafari, Seyed Ali Jafari

Abstract:

The recommended limit for cadmium concentration in potable water is less than 0.005 mg/L. A continuous biosorption process using indigenous red seaweed, Gracilaria corticata, was performed to remove cadmium from the potable water. The process was conducted under fixed conditions and the breakthrough curves were achieved for three consecutive sorption-desorption cycles. A modeling based on Artificial Neural Network (ANN) was employed to fit the experimental breakthrough data. In addition, a simplified semi empirical model, Thomas, was employed for this purpose. It was found that ANN well described the experimental data (R2>0.99) while the Thomas prediction were a bit less successful with R2>0.97. The adjusted design parameters using the nonlinear form of Thomas model was in a good agreement with the experimentally obtained ones. The results approve the capability of ANN to predict the cadmium concentration in potable water.

Keywords: ANN, biosorption, cadmium, packed-bed, potable water

Procedia PDF Downloads 414