Search results for: spatio-temporal prediction

Authors: Artur Krukowski, Emmanouela Vogiatzaki

Abstract:

The article presents an ongoing work in research projects such as SCAN4RECO or ARCH, both funded by the European Commission under Horizon 2020 program. The former one concerns multimodal and multispectral scanning of Cultural Heritage assets for their digitization and conservation via spatiotemporal reconstruction and 3D printing, while the latter one aims to better preserve areas of cultural heritage from hazards and risks. It co-creates tools that would help pilot cities to save cultural heritage from the effects of climate change. It develops a disaster risk management framework for assessing and improving the resilience of historic areas to climate change and natural hazards. Tools and methodologies are designed for local authorities and practitioners, urban population, as well as national and international expert communities, aiding authorities in knowledge-aware decision making. In this article we focus on 3D modelling of object geometry using primarily photogrammetric methods to achieve very high model accuracy using consumer types of devices, attractive both to professions and hobbyists alike.

Keywords: 3D modelling, UAS, cultural heritage, preservation

Procedia PDF Downloads 123

Authors: Uma Maheshwari V., Rajanikanth Aluvalu, Kumar Gautam

Abstract:

The COVID-19 disease is a highly contagious viral infection with major worldwide health implications. The global economy suffers as a result of COVID. The spread of this pandemic disease can be slowed if positive patients are found early. COVID-19 disease prediction is beneficial for identifying patients' health problems that are at risk for COVID. Deep learning and machine learning algorithms for COVID prediction using X-rays have the potential to be extremely useful in solving the scarcity of doctors and clinicians in remote places. In this paper, a convolutional neural network (CNN) with deep layers is presented for recognizing COVID-19 patients using real-world datasets. We gathered around 6000 X-ray scan images from various sources and split them into two categories: normal and COVID-impacted. Our model examines chest X-ray images to recognize such patients. Because X-rays are commonly available and affordable, our findings show that X-ray analysis is effective in COVID diagnosis. The predictions performed well, with an average accuracy of 99% on training photographs and 88% on X-ray test images.

Keywords: deep CNN, COVID–19 analysis, feature extraction, feature map, accuracy

Procedia PDF Downloads 81

Authors: Seung Hwan Park, Cheng-Sool Park, Jun Seok Kim, Youngji Yoo, Daewoong An, Jun-Geol Baek

Abstract:

Depending on the big data analysis becomes important, yield prediction using data from the semiconductor process is essential. In general, yield prediction and analysis of the causes of the failure are closely related. The purpose of this study is to analyze pattern affects the final test results using a die map based clustering. Many researches have been conducted using die data from the semiconductor test process. However, analysis has limitation as the test data is less directly related to the final test results. Therefore, this study proposes a framework for analysis through clustering using more detailed data than existing die data. This study consists of three phases. In the first phase, die map is created through fail bit data in each sub-area of die. In the second phase, clustering using map data is performed. And the third stage is to find patterns that affect final test result. Finally, the proposed three steps are applied to actual industrial data and experimental results showed the potential field application.

Keywords: die-map clustering, feature extraction, pattern recognition, semiconductor manufacturing process

Procedia PDF Downloads 406

Authors: J. Balaraju, M. Govinda Raj, C. S. N. Murthy

Abstract:

Every industry is constantly looking for enhancement of its day to day production and productivity. This can be possible only by maintaining the men and machinery at its adequate level. Prediction of performance characteristics plays an important role in performance evaluation of the equipment. Analytical and statistical approaches will take a bit more time to solve complex problems such as performance estimations as compared with software-based approaches. Keeping this in view the present study deals with an Artificial Neural Network (ANN) modelling of a Load-Haul-Dump (LHD) machine to predict the performance characteristics such as reliability, availability and preventive maintenance (PM). A feed-forward-back-propagation ANN technique has been used to model the Levenberg-Marquardt (LM) training algorithm. The performance characteristics were computed using Isograph Reliability Workbench 13.0 software. These computed values were validated using predicted output responses of ANN models. Further, recommendations are given to the industry based on the performed analysis for improvement of equipment performance.

Keywords: load-haul-dump, LHD, artificial neural network, ANN, performance, reliability, availability, preventive maintenance

Procedia PDF Downloads 151

Authors: Mohamed Aly, Aliaa Rehan Youssef, Emad Sawerees, Mounir Guirgis

Abstract:

Relevance: Osteoarthritis (OA) is the most common degenerative disease seen in all populations. It causes disability and substantial socioeconomic burden. Evidence supports that exercise are the most effective conservative treatment for patients with OA. Therapists experience and clinical judgment play major role in exercise prescription and scientific evidence for this regard is lacking. The development of clinical prediction rules to identify patients who are most likely benefit from exercise may help solving this dilemma. Purpose: This study investigated whether body mass index and functional ability at baseline can predict patients’ response to a selected exercise program. Approach: Fifty-six patients, aged 35 to 65 years, completed an exercise program consisting of open kinetic chain strengthening and passive stretching exercises. The program was given for 3 sessions per week, 45 minutes per session, for 6 weeks Evaluation: At baseline and post treatment, pain severity was assessed using the numerical pain rating scale, whereas functional ability was being assessed by step test (ST), time up and go test (TUG) and 50 feet time walk test (50 FTW). After completing the program, global rate of change (GROC) score of greater than 4 was used to categorize patients as successful and non-successful. Thirty-eight patients (68%) had successful response to the intervention. Logistic regression showed that BMI and 50 FTW test were the only significant predictors. Based on the results, patients with BMI less than 34.71 kg/m2 and 50 FTW test less than 25.64 sec are 68% to 89% more likely to benefit from the exercise program. Conclusions: Clinicians should consider the described strengthening and flexibility exercise program for patents with BMI less than 34.7 Kg/m2 and 50 FTW faster than 25.6 seconds. The validity of these predictors should be investigated for other exercise.

Keywords: clinical prediction rule, knee osteoarthritis, physical therapy exercises, validity

Procedia PDF Downloads 425

Authors: Sukhbir Singh

Abstract:

This paper describes the modeling of novel solar air collector (NSAC) system by using artificial neural network (ANN) model. The objective of the study is to demonstrate the application of the ANN model to predict the performance of the NSAC with acetamide as a phase change material (PCM) storage. Input data set consist of time, solar intensity and ambient temperature wherever as outlet air temperature of NSAC was considered as output. Experiments were conducted between 9.00 and 24.00 h in June and July 2014 underneath the prevailing atmospheric condition of Kurukshetra (city of the India). After that, experimental results were utilized to train the back propagation neural network (BPNN) to predict the outlet air temperature of NSAC. The results of proposed algorithm show that the BPNN is effective tool for the prediction of responses. The BPNN predicted results are 99% in agreement with the experimental results.

Keywords: Evacuated tube solar air collector, Artificial neural network, Phase change material, solar air collector

Procedia PDF Downloads 122

Authors: Jan Henrik Wosnitza

Abstract:

The logistic regression has developed into a standard approach for estimating conditional probabilities in a wide range of applications including credit risk prediction. The article at hand contributes to the current literature on logistic regression fourfold: First, it is demonstrated that the binary logistic regression automatically meets its model assumptions under very general conditions. This result explains, at least in part, the logistic regression's popularity. Second, the requirement of homoscedasticity in the context of binary logistic regression is theoretically substantiated. The variances among the groups of defaulted and non-defaulted obligors have to be the same across the level of the aggregated default indicators in order to achieve linear logits. Third, this article sheds some light on the question why nonlinear logits might be superior to linear logits in case of a small amount of data. Fourth, an innovative methodology for estimating correlations between obligor-specific log-odds is proposed. In order to crystallize the key ideas, this paper focuses on the example of credit risk prediction. However, the results presented in this paper can easily be transferred to any other field of application.

Keywords: correlation, credit risk estimation, default correlation, homoscedasticity, logistic regression, nonlinear logistic regression

Procedia PDF Downloads 427

Authors: Mohammad Reza Dahmardeh Ghaleno, Mohammad Nohtani, Saeedeh Khaledi

Abstract:

Hydrological models are applied to simulation and prediction floods in watersheds. WetSpa is a distributed, continuous and physically model with daily or hourly time step that explains of precipitation, runoff and evapotranspiration processes for both simple and complex contexts. This model uses a modified rational method for runoff calculation. In this model, runoff is routed along the flow path using Diffusion-Wave Equation which depend on the slope, velocity and flow route characteristics. Garmabrood watershed located in Mazandaran province in Iran and passing over coordinates 53° 10´ 55" to 53° 38´ 20" E and 36° 06´ 45" to 36° 25´ 30"N. The area of the catchment is about 1133 km2 and elevations in the catchment range from 213 to 3136 m at the outlet, with average slope of 25.77 %. Results of the simulations show a good agreement between calculated and measured hydrographs at the outlet of the basin. Drawing upon Nash-Sutcliffe Model Efficiency Coefficient for calibration periodic model estimated daily hydrographs and maximum flow rate with an accuracy up to 61% and 83.17 % respectively.

Keywords: watershed simulation, WetSpa, runoff, flood prediction

Procedia PDF Downloads 338

Authors: Misuk Kim, Seokho Kang, Jehyuk Lee, Hyunchang Cho, Sungzoon Cho

Abstract:

In semiconductor manufacturing, virtual metrology (VM) refers to methods to predict properties of a wafer based on machine parameters and sensor data of the production equipment, without performing the (costly) physical measurement of the wafer properties (Wikipedia). Additional benefits include avoidance of human bias and identification of important factors affecting the quality of the process which allow improving the process quality in the future. It is however rare to find VM applied to other areas of manufacturing. In this work, we propose to use VM to copper clad laminate (CCL) manufacturing. CCL is a core element of a printed circuit board (PCB) which is used in smartphones, tablets, digital cameras, and laptop computers. The manufacturing of CCL consists of three processes: Treating, lay-up, and pressing. Treating, the most important process among the three, puts resin on glass cloth, heat up in a drying oven, then produces prepreg for lay-up process. In this process, three important quality factors are inspected: Treated weight (T/W), Minimum Viscosity (M/V), and Gel Time (G/T). They are manually inspected, incurring heavy cost in terms of time and money, which makes it a good candidate for VM application. We developed prediction models of the three quality factors T/W, M/V, and G/T, respectively, with process variables, raw material, and environment variables. The actual process data was obtained from a CCL manufacturer. A variety of variable selection methods and learning algorithms were employed to find the best prediction model. We obtained prediction models of M/V and G/T with a high enough accuracy. They also provided us with information on “important” predictor variables, some of which the process engineers had been already aware and the rest of which they had not. They were quite excited to find new insights that the model revealed and set out to do further analysis on them to gain process control implications. T/W did not turn out to be possible to predict with a reasonable accuracy with given factors. The very fact indicates that the factors currently monitored may not affect T/W, thus an effort has to be made to find other factors which are not currently monitored in order to understand the process better and improve the quality of it. In conclusion, VM application to CCL’s treating process was quite successful. The newly built quality prediction model allowed one to reduce the cost associated with actual metrology as well as reveal some insights on the factors affecting the important quality factors and on the level of our less than perfect understanding of the treating process.

Keywords: copper clad laminate, predictive modeling, quality control, virtual metrology

Procedia PDF Downloads 351

Authors: Ammar Alali, Mahmoud Abughaban

Abstract:

Cost reduction and drilling optimization is the goal of many drilling operators. Historically, stuck pipe incidents were a major segment of non-productive time (NPT) associated costs. Traditionally, stuck pipe problems are part of the operations and solved post-sticking. However, the real key to savings and success is in predicting the stuck pipe incidents and avoiding the conditions leading to its occurrences. Previous attempts in stuck-pipe predictions have neglected the local geology of the problem. The proposed predictive tool utilizes geophysical data processing techniques and Machine Learning (ML) algorithms to predict drilling activities events in real-time using surface drilling data with minimum computational power. The method combines two types of analysis: (1) real-time prediction, and (2) cause analysis. Real-time prediction aggregates the input data, including historical drilling surface data, geological formation tops, and petrophysical data, from wells within the same field. The input data are then flattened per the geological formation and stacked per stuck-pipe incidents. The algorithm uses two physical methods (stacking and flattening) to filter any noise in the signature and create a robust pre-determined pilot that adheres to the local geology. Once the drilling operation starts, the Wellsite Information Transfer Standard Markup Language (WITSML) live surface data are fed into a matrix and aggregated in a similar frequency as the pre-determined signature. Then, the matrix is correlated with the pre-determined stuck-pipe signature for this field, in real-time. The correlation used is a machine learning Correlation-based Feature Selection (CFS) algorithm, which selects relevant features from the class and identifying redundant features. The correlation output is interpreted as a probability curve of stuck pipe incidents prediction in real-time. Once this probability passes a fixed-threshold defined by the user, the other component, cause analysis, alerts the user of the expected incident based on set pre-determined signatures. A set of recommendations will be provided to reduce the associated risk. The validation process involved feeding of historical drilling data as live-stream, mimicking actual drilling conditions, of an onshore oil field. Pre-determined signatures were created for three problematic geological formations in this field prior. Three wells were processed as case studies, and the stuck-pipe incidents were predicted successfully, with an accuracy of 76%. This accuracy of detection could have resulted in around 50% reduction in NPT, equivalent to 9% cost saving in comparison with offset wells. The prediction of stuck pipe problem requires a method to capture geological, geophysical and drilling data, and recognize the indicators of this issue at a field and geological formation level. This paper illustrates the efficiency and the robustness of the proposed cross-disciplinary approach in its ability to produce such signatures and predicting this NPT event.

Keywords: drilling optimization, hazard prediction, machine learning, stuck pipe

Procedia PDF Downloads 232

Authors: Subhamita Chakraborty, Shubhabrata Datta, Sujay Kumar Mukherjea, Partha Protim Chattopadhyay

Abstract:

Manufacturing of multiphase high strength steel in hot strip mill have drawn significant attention due to the possibility of forming low temperature transformation product of austenite under continuous cooling condition. In such endeavor, reliable prediction of temperature profile of hot strip coil is essential in order to accesses the evolution of microstructure at different location of hot strip coil, on the basis of corresponding Continuous Cooling Transformation (CCT) diagram. Temperature distribution profile of the hot strip coil has been determined by using finite volume method (FVM) vis-à-vis finite difference method (FDM). It has been demonstrated that FVM offer greater computational reliability in estimation of contact pressure distribution and hence the temperature distribution for curved and irregular profiles, owing to the flexibility in selection of grid geometry and discrete point position, Moreover, use of finite volume concept allows enforcing the conservation of mass, momentum and energy, leading to enhanced accuracy of prediction.

Keywords: simulation, modeling, thermal analysis, coil cooling, contact pressure, finite volume method

Procedia PDF Downloads 473

Authors: M.Rüştü Karaman, İsmail İşeri, Kadir Saltalı, A.Reşit Brohi, Ayhan Horuz, Mümin Dizman

Abstract:

Considerable relations has recently been given to the environmental hazardous caused by agricultural chemicals such as excess fertilizers. In this study, a neural network approach was investigated in the prediction of potential nitrate pollution across different land-use patterns by using a feedforward multilayered computer model of artificial neural network (ANN) with proper training. Periodical concentrations of some anions, especially nitrate (NO3-), and cations were also detected in drainage waters collected from the drain pipes placed in irrigated tomato field, unirrigated wheat field, fallow and pasture lands. The soil samples were collected from the irrigated tomato field and unirrigated wheat field on a grid system with 20 m x 20 m intervals. Site specific nitrate concentrations in the soil samples were measured for ANN based simulation of nitrate leaching potential from the land profiles. In the application of ANN model, a multi layered feedforward was evaluated, and data sets regarding with training, validation and testing containing the measured soil nitrate values were estimated based on spatial variability. As a result of the testing values, while the optimal structures of 2-15-1 was obtained (R2= 0.96, P < 0.01) for unirrigated field, the optimal structures of 2-10-1 was obtained (R2= 0.96, P < 0.01) for irrigated field. The results showed that the ANN model could be successfully used in prediction of the potential leaching levels of nitrate, based on different land use patterns. However, for the most suitable results, the model should be calibrated by training according to different NN structures depending on site specific soil parameters and varied agricultural managements.

Keywords: artificial intelligence, ANN, drainage water, nitrate pollution

Procedia PDF Downloads 311

Authors: Amin Salighehdar, Ziwen Ye, Mingzhe Liu, Ionut Florescu, Alan F. Blumberg

Abstract:

Storm surge is an abnormal water level caused by a storm. Accurate prediction of a storm surge is a challenging problem. Researchers developed various ensemble modeling techniques to combine several individual forecasts to produce an overall presumably better forecast. There exist some simple ensemble modeling techniques in literature. For instance, Model Output Statistics (MOS), and running mean-bias removal are widely used techniques in storm surge prediction domain. However, these methods have some drawbacks. For instance, MOS is based on multiple linear regression and it needs a long period of training data. To overcome the shortcomings of these simple methods, researchers propose some advanced methods. For instance, ENSURF (Ensemble SURge Forecast) is a multi-model application for sea level forecast. This application creates a better forecast of sea level using a combination of several instances of the Bayesian Model Averaging (BMA). An ensemble dressing method is based on identifying best member forecast and using it for prediction. Our contribution in this paper can be summarized as follows. First, we investigate whether the ensemble models perform better than any single forecast. Therefore, we need to identify the single best forecast. We present a methodology based on a simple Bayesian selection method to select the best single forecast. Second, we present several new and simple ways to construct ensemble models. We use correlation and standard deviation as weights in combining different forecast models. Third, we use these ensembles and compare with several existing models in literature to forecast storm surge level. We then investigate whether developing a complex ensemble model is indeed needed. To achieve this goal, we use a simple average (one of the simplest and widely used ensemble model) as benchmark. Predicting the peak level of Surge during a storm as well as the precise time at which this peak level takes place is crucial, thus we develop a statistical platform to compare the performance of various ensemble methods. This statistical analysis is based on root mean square error of the ensemble forecast during the testing period and on the magnitude and timing of the forecasted peak surge compared to the actual time and peak. In this work, we analyze four hurricanes: hurricanes Irene and Lee in 2011, hurricane Sandy in 2012, and hurricane Joaquin in 2015. Since hurricane Irene developed at the end of August 2011 and hurricane Lee started just after Irene at the beginning of September 2011, in this study we consider them as a single contiguous hurricane event. The data set used for this study is generated by the New York Harbor Observing and Prediction System (NYHOPS). We find that even the simplest possible way of creating an ensemble produces results superior to any single forecast. We also show that the ensemble models we propose generally have better performance compared to the simple average ensemble technique.

Keywords: Bayesian learning, ensemble model, statistical analysis, storm surge prediction

Procedia PDF Downloads 309

Authors: Tea Poklepović, Zdravka Aljinović, Branka Marasović

Abstract:

Due to the importance of yield curve and its estimation it is inevitable to have valid methods for yield curve forecasting in cases when there are scarce issues of securities and/or week trade on a secondary market. Therefore in this paper, after the estimation of weekly yield curves on Croatian financial market from October 2011 to August 2012 using Nelson-Siegel and Svensson models, yield curves are forecasted using Vector auto-regressive model and Neural networks. In general, it can be concluded that both forecasting methods have good prediction abilities where forecasting of yield curves based on Nelson Siegel estimation model give better results in sense of lower Mean Squared Error than forecasting based on Svensson model Also, in this case Neural networks provide slightly better results. Finally, it can be concluded that most appropriate way of yield curve prediction is neural networks using Nelson-Siegel estimation of yield curves.

Keywords: Nelson-Siegel Model, neural networks, Svensson Model, vector autoregressive model, yield curve

Procedia PDF Downloads 337

Authors: Prateeksha Mahamallik, Anjali Pal

Abstract:

In the present study, Co(II)-adsolubilized surfactant modified alumina (SMA) was prepared, and methylene blue (MB) degradation was carried out on Co-SMA surface by visible light photo-Fenton process. The entire reaction proceeded on solid surface as MB was embedded on Co-SMA surface. The reaction followed zero order kinetics. Response surface methodology (RSM) and artificial neural network (ANN) were used for modeling the decolorization of MB by photo-Fenton process as a function of dose of Co-SMA (10, 20 and 30 g/L), initial concentration of MB (10, 20 and 30 mg/L), concentration of H2O2 (174.4, 348.8 and 523.2 mM) and reaction time (30, 45 and 60 min). The prediction capabilities of both the methodologies (RSM and ANN) were compared on the basis of correlation coefficient (R2), root mean square error (RMSE), standard error of prediction (SEP), relative percent deviation (RPD). Due to lower value of RMSE (1.27), SEP (2.06) and RPD (1.17) and higher value of R2 (0.9966), ANN was proved to be more accurate than RSM in order to predict decolorization efficiency.

Keywords: adsolubilization, artificial neural network, methylene blue, photo-fenton process, response surface methodology

Procedia PDF Downloads 254

Authors: Moustafa Osman

Abstract:

Modeling of air pollutants from the accidental release is performed for quantifying the impact of industrial facilities into the ambient air. The mathematical methods are requiring for the prediction of the accidental scenario in probability of failure-safe mode and analysis consequences to quantify the environmental damage upon human health. The initial statement of mitigation plan is supporting implementation during production and maintenance periods. In a number of mathematical methods, the flow rate at which gaseous and liquid pollutants might be accidentally released is determined from various types in term of point, line and area sources. These emissions are integrated meteorological conditions in simplified stability parameters to compare dispersion coefficients from non-continuous air pollution plumes. The differences are reflected in concentrations levels and greenhouse effect to transport the parcel load in both urban and rural areas. This research reveals that the elevation effect nearby buildings with other structure is higher 5 times more than open terrains. These results are agreed with Sutton suggestion for dispersion coefficients in different stability classes.

Keywords: air pollutants, dispersion modeling, GIS, health effect, urban planning

Procedia PDF Downloads 375

Authors: Sanja Pfeifer, Nataša Šarlija, Marina Jeger, Ana Bilandžić

Abstract:

The purpose of this study is to explore the different facets of growth among micro, small and medium-sized firms in Croatia and to analyze the differences between models designed for all micro, small and medium-sized firms and those in creative industries. Three growth prediction models were designed and tested using the growth of sales, employment and assets of the company as dependent variables. The key drivers of sales growth are: prudent use of cash, industry affiliation and higher share of intangible assets. Growth of assets depends on retained profits, internal and external sources of financing, as well as industry affiliation. Growth in employment is closely related to sources of financing, in particular, debt and it occurs less frequently than growth in sales and assets. The findings confirm the assumption that growth strategies of small and medium-sized enterprises (SMEs) in creative industries have specific differences in comparison to SMEs in general. Interestingly, only 2.2% of growing enterprises achieve growth in employment, assets and sales simultaneously.

Keywords: creative industries, growth prediction model, growth determinants, growth measures

Procedia PDF Downloads 332

Authors: Babak Bahri, Fatemeh Yassaee Meybodi, Changiz Eslahchi

Abstract:

In the pursuit of effective cancer therapies, the exploration of combinatorial drug regimens is crucial to leverage synergistic interactions between drugs, thereby improving treatment efficacy and overcoming drug resistance. However, identifying synergistic drug pairs poses challenges due to the vast combinatorial space and limitations of experimental approaches. This study introduces ClusterSyn, a machine learning (ML)-powered framework for classifying anti-cancer drug synergy scores. ClusterSyn employs a two-step approach involving drug clustering and synergy score prediction using a fully connected deep neural network. For each cell line in the training dataset, a drug graph is constructed, with nodes representing drugs and edge weights denoting synergy scores between drug pairs. Drugs are clustered using the Markov clustering (MCL) algorithm, and vectors representing the similarity of drug pairs to each cluster are input into the deep neural network for synergy score prediction (synergy or antagonism). Clustering results demonstrate effective grouping of drugs based on synergy scores, aligning similar synergy profiles. Subsequently, neural network predictions and synergy scores of the two drugs on others within their clusters are used to predict the synergy score of the considered drug pair. This approach facilitates comparative analysis with clustering and regression-based methods, revealing the superior performance of ClusterSyn over state-of-the-art methods like DeepSynergy and DeepDDS on diverse datasets such as Oniel and Almanac. The results highlight the remarkable potential of ClusterSyn as a versatile tool for predicting anti-cancer drug synergy scores.

Keywords: drug synergy, clustering, prediction, machine learning., deep learning

Procedia PDF Downloads 81

Authors: Deepika Christopher, Garima Anand

Abstract:

To determine the best model for churn prediction in the telecom industry, this paper compares 11 machine learning algorithms, namely Logistic Regression, Support Vector Machine, Random Forest, Decision Tree, XGBoost, LightGBM, Cat Boost, AdaBoost, Extra Trees, Deep Neural Network, and Hybrid Model (MLPClassifier). It also aims to pinpoint the top three factors that lead to customer churn and conducts customer segmentation to identify vulnerable groups. According to the data, the Logistic Regression model performs the best, with an F1 score of 0.6215, 81.76% accuracy, 68.95% precision, and 56.57% recall. The top three attributes that cause churn are found to be tenure, Internet Service Fiber optic, and Internet Service DSL; conversely, the top three models in this article that perform the best are Logistic Regression, Deep Neural Network, and AdaBoost. The K means algorithm is applied to establish and analyze four different customer clusters. This study has effectively identified customers that are at risk of churn and may be utilized to develop and execute strategies that lower customer attrition.

Keywords: attrition, retention, predictive modeling, customer segmentation, telecommunications

Procedia PDF Downloads 58

Authors: Housein Deli, Loui Al-Shrouf, Hammoud Al Joumaa, Mohieddine Jelali

Abstract:

When forming metallic materials, fluctuations in material properties, process conditions, and wear lead to deviations in the component geometry. Several hundred features sometimes need to be measured, especially in the case of functional and safety-relevant components. These can only be measured offline due to the large number of features and the accuracy requirements. The risk of producing components outside the tolerances is minimized but not eliminated by the statistical evaluation of process capability and control measurements. The inspection intervals are based on the acceptable risk and are at the expense of productivity but remain reactive and, in some cases, considerably delayed. Due to the considerable progress made in the field of condition monitoring and measurement technology, permanently installed sensor systems in combination with machine learning and artificial intelligence, in particular, offer the potential to independently derive forecasts for component geometry and thus eliminate the risk of defective products - actively and preventively. The reliability of forecasts depends on the quality, completeness, and timeliness of the data. Measuring all geometric characteristics is neither sensible nor technically possible. This paper, therefore, uses the example of car seat rail production to discuss the necessary first step of feature selection and reduction by correlation analysis, as otherwise, it would not be possible to forecast components in real-time and inline. Four different car seat rails with an average of 130 features were selected and measured using a coordinate measuring machine (CMM). The run of such measuring programs alone takes up to 20 minutes. In practice, this results in the risk of faulty production of at least 2000 components that have to be sorted or scrapped if the measurement results are negative. Over a period of 2 months, all measurement data (> 200 measurements/ variant) was collected and evaluated using correlation analysis. As part of this study, the number of characteristics to be measured for all 6 car seat rail variants was reduced by over 80%. Specifically, direct correlations for almost 100 characteristics were proven for an average of 125 characteristics for 4 different products. A further 10 features correlate via indirect relationships so that the number of features required for a prediction could be reduced to less than 20. A correlation factor >0.8 was assumed for all correlations.

Keywords: long-term SHM, condition monitoring, machine learning, correlation analysis, component prediction, wear prediction, regressions analysis

Procedia PDF Downloads 50

Authors: Xia Chen, Yulan Wang

Abstract:

purpose: To compare the accuracy of Haigis, SRK/T, T2, Holladay 1, Hoffer Q, Barrett Universal II, Emmetropia Verifying Optical (EVO) and Kane for intraocular lens power calculation in patients with axial length (AL) ≥ 28 mm. Methods: In this retrospective single-center study, 50 eyes of 41 patients with AL ≥ 28 mm that underwent uneventful cataract surgery were enrolled. The actual postoperative refractive results were compared to the predicted refraction calculated with different formulas (Haigis, SRK/T, T2, Holladay 1, Hoffer Q, Barrett Universal II, EVO and Kane). The mean absolute prediction errors (MAE) 1 month postoperatively were compared. Results: The MAE of different formulas were as follows: Haigis (0.509), SRK/T (0.705), T2 (0.999), Holladay 1 (0.714), Hoffer Q (0.583), Barrett Universal II (0.552), EVO (0.463) and Kane (0.441). No significant difference was found among the different formulas (P = .122). The Kane and EVO formulas achieved the lowest level of mean prediction error (PE) and median absolute error (MedAE) (p < 0.05). Conclusion: The Kane and EVO formulas had a better success rate than others in predicting IOL power in high myopic eyes with AL longer than 28 mm in this study.

Keywords: cataract, power calculation formulas, intraocular lens, long axial length

Procedia PDF Downloads 87

Authors: Alexander Vandesompele, Joni Dambre

Abstract:

The diversity in dendritic arborization, as first illustrated by Santiago Ramon y Cajal, has always suggested a role for dendrites in the functionality of neurons. In the past decades, thanks to new recording techniques and optical stimulation methods, it has become clear that dendrites are not merely passive electrical components. They are observed to integrate inputs in a non-linear fashion and actively participate in computations. Regardless, in simulations of neural networks dendritic structure and functionality are often overlooked. Especially in a machine learning context, when designing artificial neural networks, point neuron models such as the leaky-integrate-and-fire (LIF) model are dominant. These models mimic the integration of inputs at the neuron soma, and ignore the existence of dendrites. In this work, the LIF point neuron model is extended with a simple form of dendritic computation. This gives the LIF neuron increased capacity to discriminate spatiotemporal input sequences, a dendritic functionality as observed in another study. Simulations of the spiking neurons are performed using the Bindsnet framework. In the common LIF model, incoming synapses are independent. Here, we introduce a dependency between incoming synapses such that the post-synaptic impact of a spike is not only determined by the weight of the synapse, but also by the activity of other synapses. This is a form of short term plasticity where synapses are potentiated or depressed by the preceding activity of neighbouring synapses. This is a straightforward way to prevent inputs from simply summing linearly at the soma. To implement this, each pair of synapses on a neuron is assigned a variable,representing the synaptic relation. This variable determines the magnitude ofthe short term plasticity. These variables can be chosen randomly or, more interestingly, can be learned using a form of Hebbian learning. We use Spike-Time-Dependent-Plasticity (STDP), commonly used to learn synaptic strength magnitudes. If all neurons in a layer receive the same input, they tend to learn the same through STDP. Adding inhibitory connections between the neurons creates a winner-take-all (WTA) network. This causes the different neurons to learn different input sequences. To illustrate the impact of the proposed dendritic mechanism, even without learning, we attach five input neurons to two output neurons. One output neuron isa regular LIF neuron, the other output neuron is a LIF neuron with dendritic relationships. Then, the five input neurons are allowed to fire in a particular order. The membrane potentials are reset and subsequently the five input neurons are fired in the reversed order. As the regular LIF neuron linearly integrates its inputs at the soma, the membrane potential response to both sequences is similar in magnitude. In the other output neuron, due to the dendritic mechanism, the membrane potential response is different for both sequences. Hence, the dendritic mechanism improves the neuron’s capacity for discriminating spa-tiotemporal sequences. Dendritic computations improve LIF neurons even if the relationships between synapses are established randomly. Ideally however, a learning rule is used to improve the dendritic relationships based on input data. It is possible to learn synaptic strength with STDP, to make a neuron more sensitive to its input. Similarly, it is possible to learn dendritic relationships with STDP, to make the neuron more sensitive to spatiotemporal input sequences. Feeding structured data to a WTA network with dendritic computation leads to a significantly higher number of discriminated input patterns. Without the dendritic computation, output neurons are less specific and may, for instance, be activated by a sequence in reverse order.

Keywords: dendritic computation, spiking neural networks, point neuron model

Procedia PDF Downloads 134

Authors: Ming Wei

Abstract:

Over the past two decades, Location Based Service (LBS) data have been increasingly applied to urban and transportation studies due to their comprehensiveness and consistency. However, compared to other LBS data including mobile phone data, GPS and social networking platforms, smart card data collected from public transport users have arguably yet to be fully exploited in urban systems analysis. By using five weekdays of passenger travel transaction data taken from go card – Southeast Queensland’s transit smart card – this paper analyses the spatiotemporal distribution of passenger movement with regard to the land use patterns in Brisbane. Work and residential places for public transport commuters were identified after extracting journeys-to-work patterns. Our results show that the locations of the workplaces identified from the go card data and residential suburbs are largely consistent with those that were marked in the land use map. However, the intensity for some residential locations in terms of population or commuter densities do not match well between the map and those derived from the go card data. This indicates that the misalignment between residential areas and workplaces to a certain extent, shedding light on how enhancements to service management and infrastructure expansion might be undertaken.

Keywords: big data, smart card data, travel pattern, land use

Procedia PDF Downloads 286

Authors: Y. Khulief, S. Bashmal, S. Said, D. Al-Otaibi, K. Mansour

Abstract:

The prediction of flow rates at which the vibration-induced instability takes place in tubular heat exchangers due to cross-flow is of major importance to the performance and service life of such equipment. In this paper, the semi-analytical model for square tube arrays was extended and utilized to study the triangular tube patterns. A laboratory test rig with instrumented test section is used to measure the fluidelastic coefficients to be used for tuning the mathematical model. The test section can be made of any bundle pattern. In this study, two test sections were constructed for both the normal triangular and the rotated triangular tube arrays. The developed scheme is utilized in predicting the onset of flow-induced instability in the two triangular tube arrays. The results are compared to those obtained for two other bundle configurations. The results of the four different tube patterns are viewed in the light of TEMA predictions. The comparison demonstrated that TEMA guidelines are more conservative in all configurations considered

Keywords: fluid-structure interaction, cross-flow, heat exchangers,

Procedia PDF Downloads 278

Authors: Heba M. Wagih, Hoda M. O. Mokhtar

Abstract:

Social Network has recently played a significant role in both scientific and social communities. The growing adoption of social network applications has been a relevant source of information nowadays. Due to its popularity, several research trends are emerged to service the huge volume of users including, Location-Based Social Networks (LBSN), Recommendation Systems, Sentiment Analysis Applications, and many others. LBSNs applications are among the highly demanded applications that do not focus only on analyzing the spatiotemporal positions in a given raw trajectory but also on understanding the semantics behind the dynamics of the moving object. LBSNs are possible means of predicting human mobility based on users social ties as well as their spatial preferences. LBSNs rely on the efficient representation of users’ trajectories. Hence, traditional raw trajectory information is no longer convenient. In our research, we focus on studying human behavior trajectory which is the major pillar in location recommendation systems. In this paper, we propose an ontology design patterns with their underlying description logics to efficiently annotate human behavior trajectories.

Keywords: human behavior trajectory, location-based social network, ontology, social network

Procedia PDF Downloads 453

Authors: M. R. Dahmardeh Ghaleno, M. Nohtani, S. Khaledi

Abstract:

Flood simulation and prediction is one of the most active research areas in surface water management. WetSpa is a distributed, continuous, and physical model with daily or hourly time step that explains precipitation, runoff, and evapotranspiration processes for both simple and complex contexts. This model uses a modified rational method for runoff calculation. In this model, runoff is routed along the flow path using Diffusion-Wave equation which depends on the slope, velocity, and flow route characteristics. Golestan Dam Basin is located in Golestan province in Iran and it is passing over coordinates 55° 16´ 50" to 56° 4´ 25" E and 37° 19´ 39" to 37° 49´ 28"N. The area of the catchment is about 224 km², and elevations in the catchment range from 414 to 2856 m at the outlet, with average slope of 29.78%. Results of the simulations show a good agreement between calculated and measured hydrographs at the outlet of the basin. Drawing upon Nash-Sutcliffe model efficiency coefficient for calibration periodic model estimated daily hydrographs and maximum flow rate with an accuracy up to 59% and 80.18%, respectively.

Keywords: watershed simulation, WetSpa, stream flow, flood prediction

Procedia PDF Downloads 244

Authors: Firas M. Tuaimah, Huda M. Abdul Abbas

Abstract:

Accurate Short Term Load Forecasting (STLF) is essential for a variety of decision making processes. However, forecasting accuracy can drop due to the presence of uncertainty in the operation of energy systems or unexpected behavior of exogenous variables. Interval Type 2 Fuzzy Logic System (IT2 FLS), with additional degrees of freedom, gives an excellent tool for handling uncertainties and it improved the prediction accuracy. The training data used in this study covers the period from January 1, 2012 to February 1, 2012 for winter season and the period from July 1, 2012 to August 1, 2012 for summer season. The actual load forecasting period starts from January 22, till 28, 2012 for winter model and from July 22 till 28, 2012 for summer model. The real data for Iraqi power system which belongs to the Ministry of Electricity.

Keywords: short term load forecasting, prediction interval, type 2 fuzzy logic systems, electric, computer systems engineering

Procedia PDF Downloads 398

Authors: Reza Zakerinejad

Abstract:

Gully erosion is a serious problem that threading the sustainability of agricultural area and rangeland and water in a large part of Iran. This type of water erosion is the main source of sedimentation in many catchment areas in the north of Iran. Since in many national assessment approaches just qualitative models were applied the aim of this study is to predict the spatial distribution of gully erosion processes by means of detail terrain analysis and GIS -based logistic regression in the loess deposition in a case study in the Golestan Province. This study the DEM with 25 meter result ion from ASTER data has been used. The Landsat ETM data have been used to mapping of land use. The TreeNet model as a stochastic modeling was applied to prediction the susceptible area for gully erosion. In this model ROC we have set 20 % of data as learning and 20 % as learning data. Therefore, applying the GIS and satellite image analysis techniques has been used to derive the input information for these stochastic models. The result of this study showed a high accurate map of potential for gully erosion.

Keywords: TreeNet model, terrain analysis, Golestan Province, Iran

Procedia PDF Downloads 537

Authors: Yu Bingqing

Abstract:

Research on the meteorological observation data of conventional meteorological stations in Jiangnan area from 2001 to 2020 and digital elevation DEM, the "golden section" comfort index calculation method was used to refine the spatial estimation of climate comfort in Jiangnan area under undulating terrain on the Gis platform, and its spatiotemporal distribution characteristics in the region were analyzed. The results can provide reference for the development and utilization of climate resources in Jiangnan area.The results show that: ① there is a significant spatial difference between winter and summer climate comfort from low latitude to high latitude. ②There is a significant trend of decreasing climate comfort from low altitude to high altitude in winter, but the opposite is true in summer. ③There is a trend of decreasing climate comfort from offshore to inland in winter, but the difference is not significant in summer. The climate comfort level in the natural lake area is higher in summer than in the surrounding areas, but not in winter. ⑤ In winter and summer, altitude has the greatest influence on the difference in comfort level.

Keywords: vernacular courtyards, thermal environment, depth-to-height ratio, climate adaptability，Southeast China

Procedia PDF Downloads 59

Authors: Lidija R. Jevrić, Sanja O. Podunavac-Kuzmanović, Strahinja Z. Kovačević

Abstract:

The present study deals with the selection of the most suitable quantitative structure-retention relationship (QSRR) models which should be used in prediction of the retention behavior of basic, neutral, acidic and phenolic pesticides which belong to different classes: fungicides, herbicides, metabolites, insecticides and plant growth regulators. Sum of ranking differences (SRD) approach can give a different point of view on selection of the most consistent QSRR model. SRD approach can be applied not only for ranking of the QSRR models, but also for detection of similarity or dissimilarity among them. Applying the SRD analysis, the most similar models can be found easily. In this study, selection of the best model was carried out on the basis of the reference ranking (“golden standard”) which was defined as the row average values of logarithm of retention time (logtr) defined by high performance liquid chromatography (HPLC). Also, SRD analysis based on experimental logtr values as reference ranking revealed similar grouping of the established QSRR models already obtained by hierarchical cluster analysis (HCA).

Keywords: chemometrics, chromatography, pesticides, sum of ranking differences

Procedia PDF Downloads 375