Search results for: Gaussian Conditional Random Field

Authors: Badreddine Chemali, Boualem Tiliouine

Abstract:

This article presents the main results of a numerical investigation on the uncertainty of dynamic response of structures with statistically correlated random damping Gamma distributed. A computational method based on a Linear Statistical Model (LSM) is implemented to predict second order statistics for the response of a typical industrial building structure. The significance of random damping with correlated parameters and its implications on the sensitivity of structural peak response in the neighborhood of a resonant frequency are discussed in light of considerable ranges of damping uncertainties and correlation coefficients. The results are compared to those generated using Monte Carlo simulation techniques. The numerical results obtained show the importance of damping uncertainty and statistical correlation of damping coefficients when obtaining accurate probabilistic estimates of dynamic response of structures. Furthermore, the effectiveness of the LSM model to efficiently predict uncertainty propagation for structural dynamic problems with correlated damping parameters is demonstrated.

Keywords: correlated random damping, linear statistical model, Monte Carlo simulation, uncertainty of dynamic response

Procedia PDF Downloads 280

Authors: Atinkut Atinafu Yilma, Eyob Messele Sefene

Abstract:

Anomaly detection is one of the essential mechanisms to control and reduce production loss, especially in today's smart manufacturing. Quick anomaly detection aids in reducing the cost of production by minimizing the possibility of producing defective products. However, developing an anomaly detection model that can rapidly detect a production change is challenging. This paper proposes Gated Recurrent Unit (GRU) combined with Random Forest (RF) to detect anomalies in the production process in real-time quickly. The GRU is used as a feature detector, and RF as a classifier using the input features from GRU. The model was tested using various synthesis and real-world datasets against benchmark methods. The results show that the proposed GRU-RF outperforms the benchmark methods with the shortest time taken to detect anomalies in the production process. Based on the investigation from the study, this proposed model can eliminate or reduce unnecessary production costs and bring a competitive advantage to manufacturing industries.

Keywords: anomaly detection, multivariate time series data, smart manufacturing, gated recurrent unit network, random forest

Procedia PDF Downloads 118

Authors: Nawang Chhunid, Gagnesh Kumar

Abstract:

On-chip memories consume a significant portion of the overall die space and power in modern microprocessors. On-chip caches depend on Static Random-Access Memory (SRAM) cells and scaling of technology occurring as per Moore’s law. Unfortunately, the scaling is affecting stability, performance, and leakage power which will become major problems for future SRAMs in aggressive nanoscale technologies due to increasing device mismatch and variations. 3T1D Dynamic Random-Access Memory (DRAM) cell is a non-destructive read DRAM cell with three transistors and a gated diode. In 3T1D DRAM cell gated diode (D1) acts as a storage device and also as an amplifier, which leads to fast read access. Due to its high tolerance to process variation, high density, and low cost of memory as compared to 6T SRAM cell, it is universally used by the advanced microprocessor for on chip data and program memory. In the present paper, it has been shown that 3T1D DRAM cell can perform better in terms of fast read access as compared to 6T, 4T, 3T SRAM cells, respectively.

Keywords: DRAM Cell, Read Access Time, Retention Time, Average Power dissipation

Procedia PDF Downloads 313

Authors: V. Saccà, A. Sarica, F. Novellino, S. Barone, T. Tallarico, E. Filippelli, A. Granata, P. Valentino, A. Quattrone

Abstract:

The work aim was to evaluate how well Random Forest (RF) and Support Vector Machine (SVM) algorithms could support the early diagnosis of Multiple Sclerosis (MS) from resting-state functional connectivity data. In particular, we wanted to explore the ability in distinguishing between controls and patients of mean signals extracted from ICA components corresponding to 15 well-known networks. Eighteen patients with early-MS (mean-age 37.42±8.11, 9 females) were recruited according to McDonald and Polman, and matched for demographic variables with 19 healthy controls (mean-age 37.55±14.76, 10 females). MRI was acquired by a 3T scanner with 8-channel head coil: (a)whole-brain T1-weighted; (b)conventional T2-weighted; (c)resting-state functional MRI (rsFMRI), 200 volumes. Estimated total lesion load (ml) and number of lesions were calculated using LST-toolbox from the corrected T1 and FLAIR. All rsFMRIs were pre-processed using tools from the FMRIB's Software Library as follows: (1) discarding of the first 5 volumes to remove T1 equilibrium effects, (2) skull-stripping of images, (3) motion and slice-time correction, (4) denoising with high-pass temporal filter (128s), (5) spatial smoothing with a Gaussian kernel of FWHM 8mm. No statistical significant differences (t-test, p < 0.05) were found between the two groups in the mean Euclidian distance and the mean Euler angle. WM and CSF signal together with 6 motion parameters were regressed out from the time series. We applied an independent component analysis (ICA) with the GIFT-toolbox using the Infomax approach with number of components=21. Fifteen mean components were visually identified by two experts. The resulting z-score maps were thresholded and binarized to extract the mean signal of the 15 networks for each subject. Statistical and machine learning analysis were then conducted on this dataset composed of 37 rows (subjects) and 15 features (mean signal in the network) with R language. The dataset was randomly splitted into training (75%) and test sets and two different classifiers were trained: RF and RBF-SVM. We used the intrinsic feature selection of RF, based on the Gini index, and recursive feature elimination (rfe) for the SVM, to obtain a rank of the most predictive variables. Thus, we built two new classifiers only on the most important features and we evaluated the accuracies (with and without feature selection) on test-set. The classifiers, trained on all the features, showed very poor accuracies on training (RF:58.62%, SVM:65.52%) and test sets (RF:62.5%, SVM:50%). Interestingly, when feature selection by RF and rfe-SVM were performed, the most important variable was the sensori-motor network I in both cases. Indeed, with only this network, RF and SVM classifiers reached an accuracy of 87.5% on test-set. More interestingly, the only misclassified patient resulted to have the lowest value of lesion volume. We showed that, with two different classification algorithms and feature selection approaches, the best discriminant network between controls and early MS, was the sensori-motor I. Similar importance values were obtained for the sensori-motor II, cerebellum and working memory networks. These findings, in according to the early manifestation of motor/sensorial deficits in MS, could represent an encouraging step toward the translation to the clinical diagnosis and prognosis.

Keywords: feature selection, machine learning, multiple sclerosis, random forest, support vector machine

Procedia PDF Downloads 240

Authors: I. M. L. Nadeesha Jayaweera, Adao Alex Trindade

Abstract:

In choosing a candidate model in likelihood-based modeling via an information criterion, the practitioner is often faced with the difficult task of deciding just how far up the ranked list to look. Motivated by this pragmatic necessity, we construct an uncertainty band for a generalized (model selection) information criterion (GIC), defined as a criterion for which the limit in probability is identical to that of the normalized log-likelihood. This includes common special cases such as AIC & BIC. The method starts from the asymptotic normality of the GIC for the joint distribution of the candidate models in an independent and identically distributed (IID) data framework and proceeds by deriving the (asymptotically) exact distribution of the minimum. The calculation of an upper quantile for its distribution then involves the computation of multivariate Gaussian integrals, which is amenable to efficient implementation via the R package "mvtnorm". The performance of the methodology is tested on simulated data by checking the coverage probability of nominal upper quantiles and compared to the bootstrap. Both methods give coverages close to nominal for large samples, but the bootstrap is two orders of magnitude slower. The methodology is subsequently extended to two other commonly used model structures: regression and time series. In the regression case, we derive the corresponding asymptotically exact distribution of the minimum GIC invoking Lindeberg-Feller type conditions for triangular arrays and are thus able to similarly calculate upper quantiles for its distribution via multivariate Gaussian integration. The bootstrap once again provides a default competing procedure, and we find that similar comparison performance metrics hold as for the IID case. The time series case is complicated by far more intricate asymptotic regime for the joint distribution of the model GIC statistics. Under a Gaussian likelihood, the default in most packages, one needs to derive the limiting distribution of a normalized quadratic form for a realization from a stationary series. Under conditions on the process satisfied by ARMA models, a multivariate normal limit is once again achieved. The bootstrap can, however, be employed for its computation, whence we are once again in the multivariate Gaussian integration paradigm for upper quantile evaluation. Comparisons of this bootstrap-aided semi-exact method with the full-blown bootstrap once again reveal a similar performance but faster computation speeds. One of the most difficult problems in contemporary statistical methodological research is to be able to account for the extra variability introduced by model selection uncertainty, the so-called post-model selection inference (PMSI). We explore ways in which the GIC uncertainty band can be inverted to make inferences on the parameters. This is being attempted in the IID case by pivoting the CDF of the asymptotically exact distribution of the minimum GIC. For inference one parameter at a time and a small number of candidate models, this works well, whence the attained PMSI confidence intervals are wider than the MLE-based Wald, as expected.

Keywords: model selection inference, generalized information criteria, post model selection, Asymptotic Theory

Procedia PDF Downloads 89

Authors: H. R. Goshayeshi, M. Mansori, M. Ahmady, M. Zhaloyi

Abstract:

This paper presents the result of an experimental investigation regarding the use of Fe2O3 nanoparticles added to Kerosene as a working fluid, under magnetic field for Copper Oscillating Heat pipe with inclination angle of 0°(horizontal), 15°, 30°, 45°, 60°, 75°, and 90° (vertical). The following were examined; measure the temperature distribution and heat transfer rate on Oscillating Heat Pipe (OHP), with magnetic field under different angles. Results showed that the addition of Fe2O3 nanoparticles under magnetic field improved thermal performance of OHP especially in 75°.

Keywords: copper oscillating heat pipe, Fe2O3, magnetic field, inclination angles

Procedia PDF Downloads 365

Authors: Nordila Ahmad, Thamer Mohammad, Bruce W. Melville, Zuliziana Suif

Abstract:

Current methods for predicting local scour at wide bridge piers, were developed on the basis of laboratory studies and very limited scour prediction were tested with field data. Laboratory wide pier scour equation from previous findings with field data were presented. A wide range of field data were used and it consists of both live-bed and clear-water scour. A method for assessing the quality of the data was developed and applied to the data set. Three other wide pier-scour equations from the literature were used to compare the performance of each predictive method. The best-performing scour equation were analyzed using statistical analysis. Comparisons of computed and observed scour depths indicate that the equation from the previous publication produced the smallest discrepancy ratio and RMSE value when compared with the large amount of laboratory and field data.

Keywords: field data, local scour, scour equation, wide piers

Procedia PDF Downloads 414

Authors: Ahmed Nour El Islam Ayad, Tahar Rouibah, Wafa Krika, Houari Boudjella, Larab Moulay, Farid Benhamida, Selma Benmoussa

Abstract:

The purpose of this study is to evaluate the electromagnetic field of an underground cable of very high voltage perforated by nail. The aim of this work shows a numerical simulation of the electromagnetic field of 400 kV line after perforation through a ferrous nail in four positions for the pinch pin at different distances. From results for a longitudinal section, we observe and evaluate the distribution and the variation of the electromagnetic field in the cable and the earth. When the nail approaches the underground power cable, the distribution of the magnetic field changes and takes several forms, the magnetic field increase and become very important when the nail breaks the metal screen and will produce a significant leak of the electric field, characterized by a large electric arc and or electric discharge to earth and then a fault in the electrical network. These electromagnetic analysis results help to detect defects in underground cables.

Keywords: underground, electromagnetic, nail, defect

Procedia PDF Downloads 231

Authors: Adel Kara, Abdelhafid Bayadi, Hocine Terrab

Abstract:

This paper presents a study of electric field distribution along of 72 kV polymeric outdoor insulators with broken sheds. Different cases of damaged insulators are modeled and both of clean and polluted cases. By 3D finite element analysis using the software package COMSOL Multiphysics 4.3b. The obtained results of potential and the electrical field distribution around insulators by 3D simulation proved that finite element computations is useful tool for studying insulation electrical field distribution.

Keywords: electric field distributions, insulator, broken sheds, potential distributions

Procedia PDF Downloads 512

Authors: Aijuka Nicholas

Abstract:

A research study was undertaken to characterize the aquifers and identify the potential groundwater recharge zones in the Kagandi district. Quantitative characterization of hydraulic conductivities of aquifers is of fundamental importance to the study of groundwater flow and contaminant transport in aquifers. A conditional approach is used to represent the spatial variability of hydraulic conductivity. Briefly, it involves using qualitative and quantitative geologic borehole-log data to generate a three-dimensional (3D) hydraulic conductivity distribution, which is then adjusted through calibration of a 3D groundwater flow model using pumping-test data and historic hydraulic data. The approach consists of several steps. The study area was divided into five sub-watersheds on the basis of artificial drainage divides. A digital terrain model (DTM) was developed using Arc GIS to determine the general drainage pattern of Kagandi watershed. Hydrologic characterization involved the determination of the various hydraulic properties of the aquifers. Potential groundwater recharge zones were identified by integrating various thematic maps pertaining to the digital elevation model, land use, and drainage pattern in Arc GIS and Sufer golden software. The study demonstrates the potential of GIS in delineating groundwater recharge zones and that the developed methodology will be applicable to other watersheds in Uganda.

Keywords: aquifers, Arc GIS, groundwater recharge, recharge zones

Procedia PDF Downloads 147

Authors: Ja-Keoung Koo, Kensuke Nakamura, Hyohun Kim, Dongwha Shin, Yeonseok Kim, Ji-Su Ahn, Byung-Woo Hong

Abstract:

The machine learning techniques based on a convolutional neural network (CNN) have been actively developed and successfully applied to a variety of image analysis tasks including reconstruction, noise reduction, resolution enhancement, segmentation, motion estimation, object recognition. The classical visual information processing that ranges from low level tasks to high level ones has been widely developed in the deep learning framework. It is generally considered as a challenging problem to derive visual interpretation from high dimensional imagery data. A CNN is a class of feed-forward artificial neural network that usually consists of deep layers the connections of which are established by a series of non-linear operations. The CNN architecture is known to be shift invariant due to its shared weights and translation invariance characteristics. However, it is often computationally intractable to optimize the network in particular with a large number of convolution layers due to a large number of unknowns to be optimized with respect to the training set that is generally required to be large enough to effectively generalize the model under consideration. It is also necessary to limit the size of convolution kernels due to the computational expense despite of the recent development of effective parallel processing machinery, which leads to the use of the constantly small size of the convolution kernels throughout the deep CNN architecture. However, it is often desired to consider different scales in the analysis of visual features at different layers in the network. Thus, we propose a CNN model where different sizes of the convolution kernels are applied at each layer based on the random projection. We apply random filters with varying sizes and associate the filter responses with scalar weights that correspond to the standard deviation of the random filters. We are allowed to use large number of random filters with the cost of one scalar unknown for each filter. The computational cost in the back-propagation procedure does not increase with the larger size of the filters even though the additional computational cost is required in the computation of convolution in the feed-forward procedure. The use of random kernels with varying sizes allows to effectively analyze image features at multiple scales leading to a better generalization. The robustness and effectiveness of the proposed CNN based on random kernels are demonstrated by numerical experiments where the quantitative comparison of the well-known CNN architectures and our models that simply replace the convolution kernels with the random filters is performed. The experimental results indicate that our model achieves better performance with less number of unknown weights. The proposed algorithm has a high potential in the application of a variety of visual tasks based on the CNN framework. Acknowledgement—This work was supported by the MISP (Ministry of Science and ICT), Korea, under the National Program for Excellence in SW (20170001000011001) supervised by IITP, and NRF-2014R1A2A1A11051941, NRF2017R1A2B4006023.

Keywords: deep learning, convolutional neural network, random kernel, random projection, dimensionality reduction, object recognition

Procedia PDF Downloads 290

Authors: Chin-Chih Chang

Abstract:

Many manufacturing systems suffer failures due to complex degradation processes and various environment conditions such as random shocks. Consider an operating system is subject to random shocks and works at random times for successive jobs. When successive jobs often result in production losses and performance deterioration, it would be better to do maintenance or replacement at a planned time. A preventive replacement (PR) policy is presented to replace the system before a failure occurs at a continuous time T. In such a policy, the failure characteristics of the system are designed as follows. Each job would cause a random amount of additive damage to the system, and the system fails when the cumulative damage has exceeded a failure threshold. Suppose that the deteriorating system suffers one of the two types of shocks with age-dependent probabilities: type-I (minor) shock is rectified by a minimal repair, or type-II (catastrophic) shock causes the system to fail. A corrective replacement (CR) is performed immediately when the system fails. In summary, a generalized maintenance model to scheduling replacement plan for an operating system is presented below. PR is carried out at time T, whereas CR is carried out when any type-II shock occurs and the total damage exceeded a failure level. The main objective is to determine the optimal continuous schedule time of preventive replacement through minimizing the mean cost rate function. The existence and uniqueness of optimal replacement policy are derived analytically. It can be seen that the present model is a generalization of the previous models, and the policy with preventive replacement outperforms the one without preventive replacement.

Keywords: preventive replacement, working time, cumulative damage model, minimal repair, imperfect maintenance, optimization

Procedia PDF Downloads 363

Authors: Brahim Mahfoud

Abstract:

A three-dimensional (3D) numerical technique is used to investigate the possibility of reducing the price of manufacturing some silicon-based devices, particularly those in which minor temperature gradients can significantly reduce performance. The silicon melt under the magnetic field produces Lorentz force, which can effectively suppress the flow which is caused by temperature gradients. This might allow some silicon-based products, such as solar cells, to be manufactured using a less pure, and hence less expensive. The thermocapillary effect of the silicon melt flow in thin annular pools subjected to an externally induced magnetic field was observed. The results reveal that with a strong enough magnetic field, isothermal lines change form and become concentric circles. As the amplitude of the magnetic field (Ha) grows, the azimuthal velocity and temperature at the free surface reduce, and the asymmetric 3D flow becomes axisymmetric steady when Ha surpasses a threshold value.

Keywords: magnetic field, manufacturing, silicon melt, thermocapillary

Procedia PDF Downloads 84

Authors: B. Raghu, Shashi Vemuri, Ch. Sreenivasa Rao

Abstract:

The survey on pesticide use pattern was carried out by interviewing farmers growing chill in open fields and poly houses based on the questionnaire prepared to assess their knowledge and practices on crop cultivation, general awareness on pesticide recommendations and use. Education levels of poly house farmers are high compared to open field farmers, where 57.14% poly house farmers are high school educated, whereas 35% open field farmers are illiterates. Majority farmers use nursery of 35 days and grow in <0.5 acre poly house in summer and rabi and < 1 acre in open field during kharif. Awareness on pesticide related issues is varying among poly house and open field farmers with some commonality, where 28.57% poly house farmers know about recommended pesticides while only 10% open field farmers are aware of this issue. However, in general, all farmers contact pesticide dealer for recommendations, poly house farmers prefer to contact scientists (35.71%) and open field farmers prefer to contact agricultural officers (33.33). Most farmers are unaware about pesticide classification and toxicity symbols on packing. Farmers are aware about endosulfan ban, but only 21.42% poly house and 11.66% open field farmers know about ban of monocrotofos on vegetables. Very few farmers know about pesticide residues and related issues, but know washing helps to reduce contamination.

Keywords: open field, pesticide usage, polyhouses, residues survey

Procedia PDF Downloads 468

Authors: Valeria Bondarenko

Abstract:

We proposed algorithms for: estimation of parameters fBm (volatility and Hurst exponent) and for the approximation of random time series by functional of fBm. We proved the consistency of the estimators, which constitute the above algorithms, and proved the optimal forecast of approximated time series. The adequacy of estimation algorithms, approximation, and forecasting is proved by numerical experiment. During the process of creating software, the system has been created, which is displayed by the hierarchical structure. The comparative analysis of proposed algorithms with the other methods gives evidence of the advantage of approximation method. The results can be used to develop methods for the analysis and modeling of time series describing the economic, physical, biological and other processes.

Keywords: mathematical model, random process, Wiener process, fractional Brownian motion

Procedia PDF Downloads 358

Authors: Samir Bentata, Fatima Bendahma

Abstract:

We have numerically investigated the effect of Aluminium concentration on the the laser wavelength of random trimer barrier AlxGa1-xAs superlattices (RTBSL). Such systems consist of two different structures randomly distributed along the growth direction, with the additional constraint that the barriers of one kind appear in triply. An explicit formula is given for evaluating the transmission coefficient of superlattices (SL's) with intentional correlated disorder. The method is based on Airy function formalism and the transfer-matrix technique. We discuss the impact of the Aluminium concentration associate to the structure profile on the laser wavelengths.

Keywords: superlattices, correlated disorder, transmission coefficient, laser wavelength

Procedia PDF Downloads 337

Authors: Sarah Beaver, Renee Bryce

Abstract:

Audiograms detect hearing impairment, but missing values pose problems. This work explores imputations in an attempt to improve accuracy. This work implements Linear Regression, Lasso, Linear Support Vector Regression, Bayesian Ridge, K Nearest Neighbors (KNN), and Random Forest machine learning techniques to impute audiogram frequencies ranging from 125Hz to 8000Hz. The data contains patients who had or were candidates for cochlear implants. Accuracy is compared across two different Nested Cross-Validation k values. Over 4000 audiograms were used from 800 unique patients. Additionally, training on data combines and compares left and right ear audiograms versus single ear side audiograms. The accuracy achieved using Root Mean Square Error (RMSE) values for the best models for Random Forest ranges from 4.74 to 6.37. The R\textsuperscript{2} values for the best models for Random Forest ranges from .91 to .96. The accuracy achieved using RMSE values for the best models for KNN ranges from 5.00 to 7.72. The R\textsuperscript{2} values for the best models for KNN ranges from .89 to .95. The best imputation models received R\textsuperscript{2} between .89 to .96 and RMSE values less than 8dB. We also show that the accuracy of classification predictive models performed better with our best imputation models versus constant imputations by a two percent increase.

Keywords: machine learning, audiograms, data imputations, single imputations

Procedia PDF Downloads 82

Authors: Fawaz Abdulmalek

Abstract:

The two-stage flowshop assembly scheduling problem is considered in this paper. There are more than one parallel machines at stage one and an assembly machine at stage two. The jobs will be processed into the flowshop based on Johnson rule and two extensions of Johnson rule. A simulation model of the two-stage flowshop is constructed where both machines at stage one are subject to random failures. Three simulation experiments will be conducted to test the effect of the three job ranking rules on the makespan. Johnson Largest heuristic outperformed both Johnson rule and Johnson Smallest heuristic for two performed experiments for all scenarios where each experiments having five scenarios.

Keywords: flowshop scheduling, random failures, johnson rule, simulation

Procedia PDF Downloads 339

Authors: Hu Ding, Kai Liu, Guoan Tang

Abstract:

The Chinese Loess Plateau suffers from serious gully erosion induced by natural and human causes. Gully features detection including gully-affected area and its two dimension parameters (length, width, area et al.), is a significant task not only for researchers but also for policy-makers. This study aims at gully-affected area detection in three catchments of Chinese Loess Plateau, which were selected in Changwu, Ansai, and Suide by using unmanned aerial vehicle (UAV). The methodology includes a sequence of UAV data generation, image segmentation, feature calculation and selection, and random forest classification. Two experiments were conducted to investigate the influences of segmentation strategy and feature selection. Results showed that vertical and horizontal root-mean-square errors were below 0.5 and 0.2 m, respectively, which were ideal for the Loess Plateau region. The segmentation strategy adopted in this paper, which considers the topographic information, and optimal parameter combination can improve the segmentation results. Besides, the overall extraction accuracy in Changwu, Ansai, and Suide achieved was 84.62%, 86.46%, and 93.06%, respectively, which indicated that the proposed method for detecting gully-affected area is more objective and effective than traditional methods. This study demonstrated that UAV can bridge the gap between field measurement and satellite-based remote sensing, obtaining a balance in resolution and efficiency for catchment-scale gully erosion research.

Keywords: unmanned aerial vehicle (UAV), object-analysis image analysis, gully erosion, gully-affected area, Loess Plateau, random forest

Procedia PDF Downloads 218

Authors: Lule Basha, Eralda Gjika

Abstract:

This study is focused on analyzing climate change in Albania and its potential effects on cereal yields. Initially, monthly temperature and rainfalls in Albania were studied for the period 1960-2021. Climacteric variables are important variables when trying to model cereal yield behavior, especially when significant changes in weather conditions are observed. For this purpose, in the second part of the study, linear and nonlinear models explaining cereal yield are constructed for the same period, 1960-2021. The multiple linear regression analysis and lasso regression method are applied to the data between cereal yield and each independent variable: average temperature, average rainfall, fertilizer consumption, arable land, land under cereal production, and nitrous oxide emissions. In our regression model, heteroscedasticity is not observed, data follow a normal distribution, and there is a low correlation between factors, so we do not have the problem of multicollinearity. Machine-learning methods, such as random forest, are used to predict cereal yield responses to climacteric and other variables. Random Forest showed high accuracy compared to the other statistical models in the prediction of cereal yield. We found that changes in average temperature negatively affect cereal yield. The coefficients of fertilizer consumption, arable land, and land under cereal production are positively affecting production. Our results show that the Random Forest method is an effective and versatile machine-learning method for cereal yield prediction compared to the other two methods.

Keywords: cereal yield, climate change, machine learning, multiple regression model, random forest

Procedia PDF Downloads 91

Authors: David F. Nettleton, Elodie Bugnicourt, Christian Wasiak, Alejandro Rosales

Abstract:

In this presentation, preliminary results are given for the modeling and calibration of two different industrial winding MIMO (Multiple Input Multiple Output) processes using machine learning techniques. In contrast to previous approaches which have typically used ‘black-box’ linear statistical methods together with a definition of the mechanical behavior of the process, we use non-linear machine learning algorithms together with a ‘white-box’ rule induction technique to create a supervised model of the fitting error between the expected and real force measures. The final objective is to build a precise model of the winding process in order to control de-tension of the material being wound in the first case, and the friction of the material passing through the die, in the second case. Case 1, Tension Control of a Winding Process. A plastic web is unwound from a first reel, goes over a traction reel and is rewound on a third reel. The objectives are: (i) to train a model to predict the web tension and (ii) calibration to find the input values which result in a given tension. Case 2, Friction Force Control of a Micro-Pullwinding Process. A core+resin passes through a first die, then two winding units wind an outer layer around the core, and a final pass through a second die. The objectives are: (i) to train a model to predict the friction on die2; (ii) calibration to find the input values which result in a given friction on die2. Different machine learning approaches are tested to build models, Kernel Ridge Regression, Support Vector Regression (with a Radial Basis Function Kernel) and MPART (Rule Induction with continuous value as output). As a previous step, the MPART rule induction algorithm was used to build an explicative model of the error (the difference between expected and real friction on die2). The modeling of the error behavior using explicative rules is used to help improve the overall process model. Once the models are built, the inputs are calibrated by generating Gaussian random numbers for each input (taking into account its mean and standard deviation) and comparing the output to a target (desired) output until a closest fit is found. The results of empirical testing show that a high precision is obtained for the trained models and for the calibration process. The learning step is the slowest part of the process (max. 5 minutes for this data), but this can be done offline just once. The calibration step is much faster and in under one minute obtained a precision error of less than 1x10-3 for both outputs. To summarize, in the present work two processes have been modeled and calibrated. A fast processing time and high precision has been achieved, which can be further improved by using heuristics to guide the Gaussian calibration. Error behavior has been modeled to help improve the overall process understanding. This has relevance for the quick optimal set up of many different industrial processes which use a pull-winding type process to manufacture fibre reinforced plastic parts. Acknowledgements to the Openmind project which is funded by Horizon 2020 European Union funding for Research & Innovation, Grant Agreement number 680820

Keywords: data model, machine learning, industrial winding, calibration

Procedia PDF Downloads 241

Authors: Ali S. Gargoum

Abstract:

Graphical modeling plays an important role in providing efficient probability calculations in high dimensional problems (computational efficiency). In this paper, we address one of such problems where we discuss fragmenting puff models and some distributional assumptions concerning models for the instantaneous, emission readings and for the fragmenting process. A graphical representation in terms of a junction tree of the conditional probability breakdown of puffs and puff fragments is proposed.

Keywords: graphical models, influence diagrams, junction trees, Bayesian nets

Procedia PDF Downloads 396

Authors: Nurliani, Ida Rosada

Abstract:

The national rice consumption keeps increasing along with raising income of the households and the rapid growth of population. However, food availability, particularly rice, is limited. Impacts of rice-field conversion have run cumulatively, as we can see on potential losses of rice and crops production, as well as work opportunity that keeps increasing year-by-year. Therefore, it requires policy recommendation to control rice-field conversion through economic, social, and ecological approaches. The research was a survey method intended to: (1) Identify internal factors; quality and productivity of the land as the cause of land conversion, (2) Identify external factors of land conversion, value of the rice-field and the competitor’s land, workforce absorption, and regulation, as well as (3) Formulate strategies in controlling rice-field conversion. Population of the research was farmers who applied land conversion at Pangkep Regency, South Sulawesi. Samples were determined using the incidental sampling method. Data analysis used productivity analysis, land quality analysis, total economic value analysis, and SWOT analysis. Results of the research showed that the quality of rice-field was low as well as productivity of the grains (unhulled-rice). So that, average productivity of the grains and quality of rice-field were low as well. Total economic value of rice-field was lower than the economic value of the embankment. Workforce absorption value on rice-field was higher than on the embankment. Strategies in controlling such rice-field conversion can be done by increasing rice-field productivity, improving land quality, applying cultivation technique of specific location, improving the irrigation lines, and socializing regulation and sanction about the transfer of land use.

Keywords: land conversion, quality of rice-field, productivity, land economic value.

Procedia PDF Downloads 275

Authors: Jadon Matthiasa, Cindy Donga, Ali Al Jibouria, Hsin Kuo

Abstract:

The environmental impact of emissions from the Covanta Waste-to-Energy facility in Burnaby, BC, was comprehensively evaluated, focusing on the dispersion of air pollutants and the subsequent assessment of heavy metal contamination in surrounding soils. A Gaussian Plume Model, implemented in MATLAB, was utilized to simulate the dispersion of key pollutants to understand their atmospheric behaviour and potential deposition patterns. The MATLAB code developed for this study enhanced the accuracy of pollutant concentration predictions and provided capabilities for visualizing pollutant dispersion in 3D plots. Furthermore, the code could predict the maximum concentration of pollutants at ground level, eliminating the need to use the Ranchoux model for predictions. Complementing the modelling approach, empirical soil sampling and analysis were conducted to evaluate heavy metal concentrations in the vicinity of the facility. This integrated methodology underscored the importance of computational modelling in air pollution assessment and highlighted the necessity of soil analysis to obtain a holistic understanding of environmental impacts. The findings emphasized the effectiveness of current emissions controls while advocating for ongoing monitoring to safeguard public health and environmental integrity.

Keywords: air emissions, Gaussian Plume Model, MATLAB, soil contamination, air pollution monitoring, waste-to-energy, pollutant dispersion visualization, heavy metal analysis, environmental impact assessment, emission control effectiveness

Procedia PDF Downloads 16

Authors: Rongli Gai, Zhiyuan Chang

Abstract:

At this stage, in view of various situations in the interpolation process, most researchers use self-adaptation to adjust the interpolation process, which is also one of the current and future research hotspots in the field of CNC machining. In the interpolation process, according to the overview of the spline curve interpolation algorithm, the adaptive analysis is carried out from the factors affecting the interpolation process. The adaptive operation is reflected in various aspects, such as speed, parameters, errors, nodes, feed rates, random Period, sensitive point, step size, curvature, adaptive segmentation, adaptive optimization, etc. This paper will analyze and summarize the research of adaptive imputation in the direction of the above factors affecting imputation.

Keywords: adaptive algorithm, CNC machining, interpolation constraints, spline curve interpolation

Procedia PDF Downloads 205

Authors: A. Harras, A. Tsuji, K. Terada

Abstract:

Tracking of moving people has gained a matter of great importance due to rapid technological advancements in the field of computer vision. The objective of this study is to design a motion based detection and tracking multiple walking pedestrians randomly in different directions. In our proposed method, Gaussian mixture model (GMM) is used to determine moving persons in image sequences. It reacts to changes that take place in the scene like different illumination; moving objects start and stop often, etc. Background noise in the scene is eliminated through applying morphological operations and the motions of tracked people which is determined by using the Kalman filter. The Kalman filter is applied to predict the tracked location in each frame and to determine the likelihood of each detection. We used a benchmark data set for the evaluation based on a side wall stationary camera. The actual scenes from the data set are taken on a street including up to eight people in front of the camera in different two scenes, the duration is 53 and 35 seconds, respectively. In the case of walking pedestrians in close proximity, the proposed method has achieved the detection ratio of 87%, and the tracking ratio is 77 % successfully. When they are deferred from each other, the detection ratio is increased to 90% and the tracking ratio is also increased to 79%.

Keywords: automatic detection, tracking, pedestrians, counting

Procedia PDF Downloads 257

Authors: Faruk Guven, Nurtekin Erkmen, Samet Aktas, Cengiz Taskin

Abstract:

The aim of this study was to determine effects of field sizes on technical parameters of small-sided games in football players. Eight amateur football players (27.23±3.08 years, heigth: 171.01±5.36 cm, body weigth: 66.86±4.54 kg, sports experience: 12.88±3.28 years) performed 4-a-side small-sided games (SSG) with different field sizes. In SSGs, field sizes were 30 x 40 m and 26 mx24 m. SSGs was conducted as a series of 3 bouts of 6 min with 5 min recovery durations. All SSGs were video recorded using two digital video camcorder positioned on a tripot. Shoot on taget, passes, succesful passes, unsuccesful passes, dripling, tackle, possession in SSGs were counted by Mathball Match Analysis System. The effects of bouts on technical score were examined separately using a Friedman’s test. Mann Whitney U test was applied to analyse differences between field sizes. There were no significant differences in shoots on target, total pass, successful pass, tackle, interception, possession between bouts in 30x40 m field size (p>0.05). Unsuccessful pass in bout 3 for 30x40 m field size was lower than bout 1 and bout 2 (p<0.05) and dripling in bout 3 was lower than bout 2 (p<0.05). There was no significant difference in technical actions between bouts for 26x34 m field size (p>0.05). Shoot on target in SSG with 26 x 34 m field size was higher than SSG with 30x40 m field size (p<0.05). Unsuccessful pass for 26x34 m field size in bout 3 was higher than SSG with 30x40 m field size (p<0.05). There was no significant difference in technical actions between field sizes (p>0.05). In conclusion; in this study demonstrates that technical actions in a-4-side SSG are not influenced by different field sizes (for 30x40 m and 26x34 m field sizes). This consequence is same for both total SSG time and each bout. Dripling and unsuccessful pass decrease in bout 3 during SSG in 30 x 40 m field size.

Keywords: small-sided games, football, technical actions, sport science

Procedia PDF Downloads 552

Authors: Sudhir Kumar Singh, Debashish Chakravarty

Abstract:

Slope stability analysis is an important aspect in the field of geotechnical engineering. It is also important from safety, and economic point of view as any slope failure leads to loss of valuable lives and damage to property worth millions. This paper aims at mitigating the risk of slope failure by studying the effect of different joint sets on the stability of mine pit slopes under the influence of various external factors, namely degree of saturation, rainfall intensity, and seismic coefficients. Supervised machine learning approach has been utilized for making accurate and reliable predictions regarding the stability of slopes based on the value of Factor of Safety. Numerous cases have been studied for analyzing the stability of slopes using the popular Finite Element Method, and the data thus obtained has been used as training data for the supervised machine learning models. The input data has been trained on different supervised machine learning models, namely Random Forest, Decision Tree, Support vector Machine, and XGBoost. Distinct test data that is not present in training data has been used for measuring the performance and accuracy of different models. Although all models have performed well on the test dataset but Random Forest stands out from others due to its high accuracy of greater than 95%, thus helping us by providing a valuable tool at our disposition which is neither computationally expensive nor time consuming and in good accordance with the numerical analysis result.

Keywords: finite element method, geotechnical engineering, machine learning, slope stability

Procedia PDF Downloads 101

Authors: L. Giraudet, O. Simonetti, G. de Tournadre, N. Dumelié, B. Clarenc, F. Reisdorffer

Abstract:

In this paper we intend to give a comprehensive view of the saturation misbehavior of thin film transistors (TFTs) based on disordered semiconductors, such as most organic TFTs, and its link to the field activation of the mobility. Experimental evidence of the field activation of the mobility is given for disordered semiconductor based TFTs, when reducing the gate length. Saturation misbehavior is observed simultaneously. Advanced transport models have been implemented in a quasi-2D numerical TFT simulation software. From the numerical simulations it is clearly established that field activation of the mobility alone cannot explain the saturation misbehavior. Evidence is given that high longitudinal field gradient at the drain end of the channel is responsible for an excess charge accumulation, preventing saturation. The two combined effects allow reproducing the experimental output characteristics of short channel TFTs, with S-shaped characteristics and saturation failure.

Keywords: mobility field activation, numerical simulation, OTFT, saturation failure

Procedia PDF Downloads 520

Authors: Kinjal Trivedi, Ramesh V. Upadhyay

Abstract:

Magnetic fluid as a nanolubricant is a most recent field of study due to its unusual properties that can be tuned by applying a magnetic field. In present work, four ball tester has been used to investigate the tribological properties of the magnetic fluid having a 4 wt% of nanoparticles. The structural characterization of fluid shows crystallite size of particle is 11.7 nm and particles are nearly spherical in nature. The magnetic characterization shows the fluid saturation magnetization is 2.2 kA/m. The magnetic field applied using permanent strip magnet (0 to 1.6 mT) on the faces of the lock nut and fixing a solenoid (0 to 50 mT) around a shaft, such that shaft rotates freely. The magnetic flux line for both the systems analyzed using finite elemental analysis. The coefficient of friction increases with the application of magnetic field using permanent strip magnet compared to zero field value. While for the solenoid, it decreases at 20 mT. The wear scar diameter is lower for 1.1 mT and 20 mT when the magnetic field applied using permanent strip magnet and solenoid, respectively. The coefficient of friction and wear scar reduced by 29 % and 7 % at 20 mT using solenoid. The worn surface analysis carried out using Scanning Electron Microscope and Atomic Force Microscope to understand the wear mechanism. The results are explained on the basis of structure formation in a magnetic fluid upon application of magnetic field. It is concluded that the tribological properties of magnetic fluid depend on magnetic field and its applied direction.

Keywords: four ball tester, magnetic fluid, nanolubricant, tribology

Procedia PDF Downloads 235