Search results for: probability estimation
2452 Non-Linear Regression Modeling for Composite Distributions
Authors: Mostafa Aminzadeh, Min Deng
Abstract:
Modeling loss data is an important part of actuarial science. Actuaries use models to predict future losses and manage financial risk, which can be beneficial for marketing purposes. In the insurance industry, small claims happen frequently while large claims are rare. Traditional distributions such as Normal, Exponential, and inverse-Gaussian are not suitable for describing insurance data, which often show skewness and fat tails. Several authors have studied classical and Bayesian inference for parameters of composite distributions, such as Exponential-Pareto, Weibull-Pareto, and Inverse Gamma-Pareto. These models separate small to moderate losses from large losses using a threshold parameter. This research introduces a computational approach using a nonlinear regression model for loss data that relies on multiple predictors. Simulation studies were conducted to assess the accuracy of the proposed estimation method. The simulations confirmed that the proposed method provides precise estimates for regression parameters. It's important to note that this approach can be applied to datasets if goodness-of-fit tests confirm that the composite distribution under study fits the data well. To demonstrate the computations, a real data set from the insurance industry is analyzed. A Mathematica code uses the Fisher information algorithm as an iteration method to obtain the maximum likelihood estimation (MLE) of regression parameters.Keywords: maximum likelihood estimation, fisher scoring method, non-linear regression models, composite distributions
Procedia PDF Downloads 72451 A Semiparametric Approach to Estimate the Mode of Continuous Multivariate Data
Authors: Tiee-Jian Wu, Chih-Yuan Hsu
Abstract:
Mode estimation is an important task, because it has applications to data from a wide variety of sources. We propose a semi-parametric approach to estimate the mode of an unknown continuous multivariate density function. Our approach is based on a weighted average of a parametric density estimate using the Box-Cox transform and a non-parametric kernel density estimate. Our semi-parametric mode estimate improves both the parametric- and non-parametric- mode estimates. Specifically, our mode estimate solves the non-consistency problem of parametric mode estimates (at large sample sizes) and reduces the variability of non-parametric mode estimates (at small sample sizes). The performance of our method at practical sample sizes is demonstrated by simulation examples and two real examples from the fields of climatology and image recognition.Keywords: Box-Cox transform, density estimation, mode seeking, semiparametric method
Procedia PDF Downloads 2762450 GIS Application in Surface Runoff Estimation for Upper Klang River Basin, Malaysia
Authors: Suzana Ramli, Wardah Tahir
Abstract:
Estimation of surface runoff depth is a vital part in any rainfall-runoff modeling. It leads to stream flow calculation and later predicts flood occurrences. GIS (Geographic Information System) is an advanced and opposite tool used in simulating hydrological model due to its realistic application on topography. The paper discusses on calculation of surface runoff depth for two selected events by using GIS with Curve Number method for Upper Klang River basin. GIS enables maps intersection between soil type and land use that later produces curve number map. The results show good correlation between simulated and observed values with more than 0.7 of R2. Acceptable performance of statistical measurements namely mean error, absolute mean error, RMSE, and bias are also deduced in the paper.Keywords: surface runoff, geographic information system, curve number method, environment
Procedia PDF Downloads 2732449 Challenges for IoT Adoption in India: A Study Based on Foresight Analysis for 2025
Authors: Shruti Chopra, Vikas Rao Vadi
Abstract:
In the era of the digital world, the Internet of Things (IoT) has been receiving significant attention. Its ubiquitous connectivity between humans, machines to machines (M2M) and machines to humans provides it a potential to transform the society and establish an ecosystem to serve new dimensions to the economy of the country. Thereby, this study has attempted to identify the challenges that seem prevalent in IoT adoption in India through the literature survey. Further, the data has been collected by taking the opinions of experts to conduct the foresight analysis and it has been analyzed with the help of scenario planning process – Micmac, Mactor, Multipol, and Smic-Prob. As a methodology, the study has identified the relationship between variables through variable analysis using Micmac and actor analysis using Mactor, this paper has attempted to generate the entire field of possibilities in terms of hypotheses and construct various scenarios through Multipol. And lastly, the findings of the study include final scenarios that are selected using Smic-Prob by assigning the probability to all the scenarios (including the conditional probability). This study may help the practitioners and policymakers to remove the obstacles to successfully implement the IoT in India.Keywords: Internet of Thing (IoT), foresight analysis, scenario planning, challenges, policymaking
Procedia PDF Downloads 1372448 Nonparametric Sieve Estimation with Dependent Data: Application to Deep Neural Networks
Authors: Chad Brown
Abstract:
This paper establishes general conditions for the convergence rates of nonparametric sieve estimators with dependent data. We present two key results: one for nonstationary data and another for stationary mixing data. Previous theoretical results often lack practical applicability to deep neural networks (DNNs). Using these conditions, we derive convergence rates for DNN sieve estimators in nonparametric regression settings with both nonstationary and stationary mixing data. The DNN architectures considered adhere to current industry standards, featuring fully connected feedforward networks with rectified linear unit activation functions, unbounded weights, and a width and depth that grows with sample size.Keywords: sieve extremum estimates, nonparametric estimation, deep learning, neural networks, rectified linear unit, nonstationary processes
Procedia PDF Downloads 282447 Statistical Correlation between Ply Mechanical Properties of Composite and Its Effect on Structure Reliability
Authors: S. Zhang, L. Zhang, X. Chen
Abstract:
Due to the large uncertainty on the mechanical properties of FRP (fibre reinforced plastic), the reliability evaluation of FRP structures are currently receiving much attention in industry. However, possible statistical correlation between ply mechanical properties has been so far overlooked, and they are mostly assumed to be independent random variables. In this study, the statistical correlation between ply mechanical properties of uni-directional and plain weave composite is firstly analyzed by a combination of Monte-Carlo simulation and finite element modeling of the FRP unit cell. Large linear correlation coefficients between the in-plane mechanical properties are observed, and the correlation coefficients are heavily dependent on the uncertainty of the fibre volume ratio. It is also observed that the correlation coefficients related to Poisson’s ratio are negative while others are positive. To experimentally achieve the statistical correlation coefficients between in-plane mechanical properties of FRP, all concerned in-plane mechanical properties of the same specimen needs to be known. In-plane shear modulus of FRP is experimentally derived by the approach suggested in the ASTM standard D5379M. Tensile tests are conducted using the same specimens used for the shear test, and due to non-uniform tensile deformation a modification factor is derived by a finite element modeling. Digital image correlation is adopted to characterize the specimen non-uniform deformation. The preliminary experimental results show a good agreement with the numerical analysis on the statistical correlation. Then, failure probability of laminate plates is calculated in cases considering and not considering the statistical correlation, using the Monte-Carlo and Markov Chain Monte-Carlo methods, respectively. The results highlight the importance of accounting for the statistical correlation between ply mechanical properties to achieve accurate failure probability of laminate plates. Furthermore, it is found that for the multi-layer laminate plate, the statistical correlation between the ply elastic properties significantly affects the laminate reliability while the effect of statistical correlation between the ply strength is minimal.Keywords: failure probability, FRP, reliability, statistical correlation
Procedia PDF Downloads 1542446 Time of Week Intensity Estimation from Interval Censored Data with Application to Police Patrol Planning
Authors: Jiahao Tian, Michael D. Porter
Abstract:
Law enforcement agencies are tasked with crime prevention and crime reduction under limited resources. Having an accurate temporal estimate of the crime rate would be valuable to achieve such a goal. However, estimation is usually complicated by the interval-censored nature of crime data. We cast the problem of intensity estimation as a Poisson regression using an EM algorithm to estimate the parameters. Two special penalties are added that provide smoothness over the time of day and day of the week. This approach presented here provides accurate intensity estimates and can also uncover day-of-week clusters that share the same intensity patterns. Anticipating where and when crimes might occur is a key element to successful policing strategies. However, this task is complicated by the presence of interval-censored data. The censored data refers to the type of data that the event time is only known to lie within an interval instead of being observed exactly. This type of data is prevailing in the field of criminology because of the absence of victims for certain types of crime. Despite its importance, the research in temporal analysis of crime has lagged behind the spatial component. Inspired by the success of solving crime-related problems with a statistical approach, we propose a statistical model for the temporal intensity estimation of crime with censored data. The model is built on Poisson regression and has special penalty terms added to the likelihood. An EM algorithm was derived to obtain maximum likelihood estimates, and the resulting model shows superior performance to the competing model. Our research is in line with the smart policing initiative (SPI) proposed by the Bureau Justice of Assistance (BJA) as an effort to support law enforcement agencies in building evidence-based, data-driven law enforcement tactics. The goal is to identify strategic approaches that are effective in crime prevention and reduction. In our case, we allow agencies to deploy their resources for a relatively short period of time to achieve the maximum level of crime reduction. By analyzing a particular area within cities where data are available, our proposed approach could not only provide an accurate estimate of intensities for the time unit considered but a time-variation crime incidence pattern. Both will be helpful in the allocation of limited resources by either improving the existing patrol plan with the understanding of the discovery of the day of week cluster or supporting extra resources available.Keywords: cluster detection, EM algorithm, interval censoring, intensity estimation
Procedia PDF Downloads 612445 An Efficient Fundamental Matrix Estimation for Moving Object Detection
Authors: Yeongyu Choi, Ju H. Park, S. M. Lee, Ho-Youl Jung
Abstract:
In this paper, an improved method for estimating fundamental matrix is proposed. The method is applied effectively to monocular camera based moving object detection. The method consists of corner points detection, moving object’s motion estimation and fundamental matrix calculation. The corner points are obtained by using Harris corner detector, motions of moving objects is calculated from pyramidal Lucas-Kanade optical flow algorithm. Through epipolar geometry analysis using RANSAC, the fundamental matrix is calculated. In this method, we have improved the performances of moving object detection by using two threshold values that determine inlier or outlier. Through the simulations, we compare the performances with varying the two threshold values.Keywords: corner detection, optical flow, epipolar geometry, RANSAC
Procedia PDF Downloads 3962444 Cyber Security Enhancement via Software Defined Pseudo-Random Private IP Address Hopping
Authors: Andre Slonopas, Zona Kostic, Warren Thompson
Abstract:
Obfuscation is one of the most useful tools to prevent network compromise. Previous research focused on the obfuscation of the network communications between external-facing edge devices. This work proposes the use of two edge devices, external and internal facing, which communicate via private IPv4 addresses in a software-defined pseudo-random IP hopping. This methodology does not require additional IP addresses and/or resources to implement. Statistical analyses demonstrate that the hopping surface must be at least 1e3 IP addresses in size with a broad standard deviation to minimize the possibility of coincidence of monitored and communication IPs. The probability of breaking the hopping algorithm requires a collection of at least 1e6 samples, which for large hopping surfaces will take years to collect. The probability of dropped packets is controlled via memory buffers and the frequency of hops and can be reduced to levels acceptable for video streaming. This methodology provides an impenetrable layer of security ideal for information and supervisory control and data acquisition systems.Keywords: moving target defense, cybersecurity, network security, hopping randomization, software defined network, network security theory
Procedia PDF Downloads 1752443 Cycle Number Estimation Method on Fatigue Crack Initiation Using Voronoi Tessellation and the Tanaka Mura Model
Authors: Mohammad Ridzwan Bin Abd Rahim, Siegfried Schmauder, Yupiter HP Manurung, Peter Binkele, Meor Iqram B. Meor Ahmad, Kiarash Dogahe
Abstract:
This paper deals with the short crack initiation of the material P91 under cyclic loading at two different temperatures, concluded with the estimation of the short crack initiation Wöhler (S/N) curve. An artificial but representative model microstructure was generated using Voronoi tessellation and the Finite Element Method, and the non-uniform stress distribution was calculated accordingly afterward. The number of cycles needed for crack initiation is estimated on the basis of the stress distribution in the model by applying the physically-based Tanaka-Mura model. Initial results show that the number of cycles to generate crack initiation is strongly correlated with temperature.Keywords: short crack initiation, P91, Wöhler curve, Voronoi tessellation, Tanaka-Mura model
Procedia PDF Downloads 952442 Residual Lifetime Estimation for Weibull Distribution by Fusing Expert Judgements and Censored Data
Authors: Xiang Jia, Zhijun Cheng
Abstract:
The residual lifetime of a product is the operation time between the current time and the time point when the failure happens. The residual lifetime estimation is rather important in reliability analysis. To predict the residual lifetime, it is necessary to assume or verify a particular distribution that the lifetime of the product follows. And the two-parameter Weibull distribution is frequently adopted to describe the lifetime in reliability engineering. Due to the time constraint and cost reduction, a life testing experiment is usually terminated before all the units have failed. Then the censored data is usually collected. In addition, other information could also be obtained for reliability analysis. The expert judgements are considered as it is common that the experts could present some useful information concerning the reliability. Therefore, the residual lifetime is estimated for Weibull distribution by fusing the censored data and expert judgements in this paper. First, the closed-forms concerning the point estimate and confidence interval for the residual lifetime under the Weibull distribution are both presented. Next, the expert judgements are regarded as the prior information and how to determine the prior distribution of Weibull parameters is developed. For completeness, the cases that there is only one, and there are more than two expert judgements are both focused on. Further, the posterior distribution of Weibull parameters is derived. Considering that it is difficult to derive the posterior distribution of residual lifetime, a sample-based method is proposed to generate the posterior samples of Weibull parameters based on the Monte Carlo Markov Chain (MCMC) method. And these samples are used to obtain the Bayes estimation and credible interval for the residual lifetime. Finally, an illustrative example is discussed to show the application. It demonstrates that the proposed method is rather simple, satisfactory, and robust.Keywords: expert judgements, information fusion, residual lifetime, Weibull distribution
Procedia PDF Downloads 1342441 Effective Dose and Size Specific Dose Estimation with and without Tube Current Modulation for Thoracic Computed Tomography Examinations: A Phantom Study
Authors: S. Gharbi, S. Labidi, M. Mars, M. Chelli, F. Ladeb
Abstract:
The purpose of this study is to reduce radiation dose for chest CT examination by including Tube Current Modulation (TCM) to a standard CT protocol. A scan of an anthropomorphic male Alderson phantom was performed on a 128-slice scanner. The estimation of effective dose (ED) in both scans with and without mAs modulation was done via multiplication of Dose Length Product (DLP) to a conversion factor. Results were compared to those measured with a CT-Expo software. The size specific dose estimation (SSDE) values were obtained by multiplication of the volume CT dose index (CTDIvol) with a conversion size factor related to the phantom’s effective diameter. Objective assessment of image quality was performed with Signal to Noise Ratio (SNR) measurements in phantom. SPSS software was used for data analysis. Results showed including CARE Dose 4D; ED was lowered by 48.35% and 51.51% using DLP and CT-expo, respectively. In addition, ED ranges between 7.01 mSv and 6.6 mSv in case of standard protocol, while it ranges between 3.62 mSv and 3.2 mSv with TCM. Similar results are found for SSDE; dose was higher without TCM of 16.25 mGy and was lower by 48.8% including TCM. The SNR values calculated were significantly different (p=0.03<0.05). The highest one is measured on images acquired with TCM and reconstructed with Filtered back projection (FBP). In conclusion, this study proves the potential of TCM technique in SSDE and ED reduction and in conserving image quality with high diagnostic reference level for thoracic CT examinations.Keywords: anthropomorphic phantom, computed tomography, CT-expo, radiation dose
Procedia PDF Downloads 2092440 Constructing the Joint Mean-Variance Regions for Univariate and Bivariate Normal Distributions: Approach Based on the Measure of Cumulative Distribution Functions
Authors: Valerii Dashuk
Abstract:
The usage of the confidence intervals in economics and econometrics is widespread. To be able to investigate a random variable more thoroughly, joint tests are applied. One of such examples is joint mean-variance test. A new approach for testing such hypotheses and constructing confidence sets is introduced. Exploring both the value of the random variable and its deviation with the help of this technique allows checking simultaneously the shift and the probability of that shift (i.e., portfolio risks). Another application is based on the normal distribution, which is fully defined by mean and variance, therefore could be tested using the introduced approach. This method is based on the difference of probability density functions. The starting point is two sets of normal distribution parameters that should be compared (whether they may be considered as identical with given significance level). Then the absolute difference in probabilities at each 'point' of the domain of these distributions is calculated. This measure is transformed to a function of cumulative distribution functions and compared to the critical values. Critical values table was designed from the simulations. The approach was compared with the other techniques for the univariate case. It differs qualitatively and quantitatively in easiness of implementation, computation speed, accuracy of the critical region (theoretical vs. real significance level). Stable results when working with outliers and non-normal distributions, as well as scaling possibilities, are also strong sides of the method. The main advantage of this approach is the possibility to extend it to infinite-dimension case, which was not possible in the most of the previous works. At the moment expansion to 2-dimensional state is done and it allows to test jointly up to 5 parameters. Therefore the derived technique is equivalent to classic tests in standard situations but gives more efficient alternatives in nonstandard problems and on big amounts of data.Keywords: confidence set, cumulative distribution function, hypotheses testing, normal distribution, probability density function
Procedia PDF Downloads 1692439 Infrastructure Change Monitoring Using Multitemporal Multispectral Satellite Images
Authors: U. Datta
Abstract:
The main objective of this study is to find a suitable approach to monitor the land infrastructure growth over a period of time using multispectral satellite images. Bi-temporal change detection method is unable to indicate the continuous change occurring over a long period of time. To achieve this objective, the approach used here estimates a statistical model from series of multispectral image data over a long period of time, assuming there is no considerable change during that time period and then compare it with the multispectral image data obtained at a later time. The change is estimated pixel-wise. Statistical composite hypothesis technique is used for estimating pixel based change detection in a defined region. The generalized likelihood ratio test (GLRT) is used to detect the changed pixel from probabilistic estimated model of the corresponding pixel. The changed pixel is detected assuming that the images have been co-registered prior to estimation. To minimize error due to co-registration, 8-neighborhood pixels around the pixel under test are also considered. The multispectral images from Sentinel-2 and Landsat-8 from 2015 to 2018 are used for this purpose. There are different challenges in this method. First and foremost challenge is to get quite a large number of datasets for multivariate distribution modelling. A large number of images are always discarded due to cloud coverage. Due to imperfect modelling there will be high probability of false alarm. Overall conclusion that can be drawn from this work is that the probabilistic method described in this paper has given some promising results, which need to be pursued further.Keywords: co-registration, GLRT, infrastructure growth, multispectral, multitemporal, pixel-based change detection
Procedia PDF Downloads 1262438 Design Flood Estimation in Satluj Basin-Challenges for Sunni Dam Hydro Electric Project, Himachal Pradesh-India
Authors: Navneet Kalia, Lalit Mohan Verma, Vinay Guleria
Abstract:
Introduction: Design Flood studies are essential for effective planning and functioning of water resource projects. Design flood estimation for Sunni Dam Hydro Electric Project located in State of Himachal Pradesh, India, on the river Satluj, was a big challenge in view of the river flowing in the Himalayan region from Tibet to India, having a large catchment area of varying topography, climate, and vegetation. No Discharge data was available for the part of the river in Tibet, whereas, for India, it was available only at Khab, Rampur, and Luhri. The estimation of Design Flood using standard methods was not possible. This challenge was met using two different approaches for upper (snow-fed) and lower (rainfed) catchment using Flood Frequency Approach and Hydro-metrological approach. i) For catchment up to Khab Gauging site (Sub-Catchment, C1), Flood Frequency approach was used. Around 90% of the catchment area (46300 sqkm) up to Khab is snow-fed which lies above 4200m. In view of the predominant area being snow-fed area, 1 in 10000 years return period flood estimated using Flood Frequency analysis at Khab was considered as Probable Maximum Flood (PMF). The flood peaks were taken from daily observed discharges at Khab, which were increased by 10% to make them instantaneous. Design Flood of 4184 cumec thus obtained was considered as PMF at Khab. ii) For catchment between Khab and Sunni Dam (Sub-Catchment, C2), Hydro-metrological approach was used. This method is based upon the catchment response to the rainfall pattern observed (Probable Maximum Precipitation - PMP) in a particular catchment area. The design flood computation mainly involves the estimation of a design storm hyetograph and derivation of the catchment response function. A unit hydrograph is assumed to represent the response of the entire catchment area to a unit rainfall. The main advantage of the hydro-metrological approach is that it gives a complete flood hydrograph which allows us to make a realistic determination of its moderation effect while passing through a reservoir or a river reach. These studies were carried out to derive PMF for the catchment area between Khab and Sunni Dam site using a 1-day and 2-day PMP values of 232 and 416 cm respectively. The PMF so obtained was 12920.60 cumec. Final Result: As the Catchment area up to Sunni Dam has been divided into 2 sub-catchments, the Flood Hydrograph for the Catchment C1 has been routed through the connecting channel reach (River Satluj) using Muskingum method and accordingly, the Design Flood was computed after adding the routed flood ordinates with flood ordinates of catchment C2. The total Design Flood (i.e. 2-Day PMF) with a peak of 15473 cumec was obtained. Conclusion: Even though, several factors are relevant while deciding the method to be used for design flood estimation, data availability and the purpose of study are the most important factors. Since, generally, we cannot wait for the hydrological data of adequate quality and quantity to be available, flood estimation has to be done using whatever data is available. Depending upon the type of data available for a particular catchment, the method to be used is to be selected.Keywords: design flood, design storm, flood frequency, PMF, PMP, unit hydrograph
Procedia PDF Downloads 3162437 Volume Estimation of Trees: An Exploratory Study on Rosewood Logging Within Forest Transition and Savannah Ecological Zones of Ghana
Authors: Albert Kwabena Osei Konadu
Abstract:
One of the endemic forest species of the savannah transition zones enlisted by the Convention of International Treaty for Endangered Species (CITES) in Appendix II is the Rosewood, also known as Pterocarpus erinaceus or Krayie. Its economic viability has made it increasingly popular and in high demand. Ghana’s forest resource management regime for these ecozones is mainly on conservation and very little on resource utilization. Consequently, commercial logging management standards are at teething stage and not fully developed, leading to a deficiency in the monitoring of logging operations and quantification of harvested trees volumes. Tree information form (TIF); a volume estimation and tracking regime, has proven to be an effective sustainable management tool for regulating timber resource extraction in the high forest zones of the country. This work aims to generate TIF that can track and capture requisite parameters to accurately estimate the volume of harvested rosewood within forest savannah transition zones. Tree information forms were created on three scenarios of individual billets, stacked billets and conveying vessel basis. The study was limited by the usage of regulators assigned volume as benchmark and also fraught with potential volume measurement error in the stacked billet scenario due to the existence of spaces within packed billets. These TIFs were field-tested to deduce the most viable option for the tracking and estimation of harvested volumes of rosewood using the smallian and cubic volume estimation formula. Overall, four districts were covered with individual billets, stacked billets and conveying vessel scenarios registering mean volumes of 25.83m3,45.08m3 and 32.6m3, respectively. These adduced volumes were validated by benchmarking to assigned volumes of the Forestry Commission of Ghana and known standard volumes of conveying vessels. The results did indicate an underestimation of extracted volumes under the quotas regime, a situation that could lead to unintended overexploitation of the species. The research revealed conveying vessels route is the most viable volume estimation and tracking regime for the sustainable management of the Pterocarpous erinaceus species as it provided a more practical volume estimate and data extraction protocol.Keywords: cubic volume formula, smallian volume formula, pterocarpus erinaceus, tree information form, forest transition and savannah zones, harvested tree volume
Procedia PDF Downloads 322436 Applications of Analytical Probabilistic Approach in Urban Stormwater Modeling in New Zealand
Authors: Asaad Y. Shamseldin
Abstract:
Analytical probabilistic approach is an innovative approach for urban stormwater modeling. It can provide information about the long-term performance of a stormwater management facility without being computationally very demanding. This paper explores the application of the analytical probabilistic approach in New Zealand. The paper presents the results of a case study aimed at development of an objective way of identifying what constitutes a rainfall storm event and the estimation of the corresponding statistical properties of storms using two selected automatic rainfall stations located in the Auckland region in New Zealand. The storm identification and the estimation of the storm statistical properties are regarded as the first step in the development of the analytical probabilistic models. The paper provides a recommendation about the definition of the storm inter-event time to be used in conjunction with the analytical probabilistic approach.Keywords: hydrology, rainfall storm, storm inter-event time, New Zealand, stormwater management
Procedia PDF Downloads 3342435 On the Optimality of Blocked Main Effects Plans
Authors: Rita SahaRay, Ganesh Dutta
Abstract:
In this article, experimental situations are considered where a main effects plan is to be used to study m two-level factors using n runs which are partitioned into b blocks, not necessarily of same size. Assuming the block sizes to be even for all blocks, for the case n ≡ 2 (mod 4), optimal designs are obtained with respect to type 1 and type 2 optimality criteria in the class of designs providing estimation of all main effects orthogonal to the block effects. In practice, such orthogonal estimation of main effects is often a desirable condition. In the wider class of all available m two level even sized blocked main effects plans, where the factors do not occur at high and low levels equally often in each block, E-optimal designs are also characterized. Simple construction methods based on Hadamard matrices and Kronecker product for these optimal designs are presented.Keywords: design matrix, Hadamard matrix, Kronecker product, type 1 criteria, type 2 criteria
Procedia PDF Downloads 3582434 Estimation of Stress-Strength Parameter for Burr Type XII Distribution Based on Progressive Type-II Censoring
Authors: A. M. Abd-Elfattah, M. H. Abu-Moussa
Abstract:
In this paper, the estimation of stress-strength parameter R = P(Y < X) is considered when X; Y the strength and stress respectively are two independent random variables of Burr Type XII distribution. The samples taken for X and Y are progressively censoring of type II. The maximum likelihood estimator (MLE) of R is obtained when the common parameter is unknown. But when the common parameter is known the MLE, uniformly minimum variance unbiased estimator (UMVUE) and the Bayes estimator of R = P(Y < X) are obtained. The exact condence interval of R based on MLE is obtained. The performance of the proposed estimators is compared using the computer simulation.Keywords: Burr Type XII distribution, progressive type-II censoring, stress-strength model, unbiased estimator, maximum-likelihood estimator, uniformly minimum variance unbiased estimator, confidence intervals, Bayes estimator
Procedia PDF Downloads 4502433 Estimation of the External Force for a Co-Manipulation Task Using the Drive Chain Robot
Authors: Sylvain Devie, Pierre-Philippe Robet, Yannick Aoustin, Maxime Gautier
Abstract:
The aim of this paper is to show that the observation of the external effort and the sensor-less control of a system is limited by the mechanical system. First, the model of a one-joint robot with a prismatic joint is presented. Based on this model, two different procedures were performed in order to identify the mechanical parameters of the system and observe the external effort applied on it. Experiments have proven that the accuracy of the force observer, based on the DC motor current, is limited by the mechanics of the robot. The sensor-less control will be limited by the accuracy in estimation of the mechanical parameters and by the maximum static friction force, that is the minimum force which can be observed in this case. The consequence of this limitation is that industrial robots without specific design are not well adapted to perform sensor-less precision tasks. Finally, an efficient control law is presented for high effort applications.Keywords: control, identification, robot, co-manipulation, sensor-less
Procedia PDF Downloads 1512432 Organizational Innovations of the 20th Century as High Tech of the 21st: Evidence from Patent Data
Authors: Valery Yakubovich, Shuping wu
Abstract:
Organization theorists have long claimed that organizational innovations are nontechnological, in part because they are unpatentable. The claim rests on the assumption that organizational innovations are abstract ideas embodied in persons and contexts rather than in context-free practical tools. However, over the last three decades, organizational knowledge has been increasingly embodied in digital tools which, in principle, can be patented. To provide the first empirical evidence regarding the patentability of organizational innovations, we trained two machine learning algorithms to identify a population of 205,434 patent applications for organizational technologies (OrgTech) and, among them, 141,285 applications that use organizational innovations accumulated over the 20th century. Our event history analysis of the probability of patenting an OrgTech invention shows that ideas from organizational innovations decrease the probability of patent allowance unless they describe a practical tool. We conclude that the present-day digital transformation places organizational innovations in the realm of high tech and turns the debate about organizational technologies into the challenge of designing practical organizational tools that embody big ideas about organizing. We outline an agenda for patent-based research on OrgTech as an emerging phenomenon.Keywords: organizational innovation, organizational technology, high tech, patents, machine learning
Procedia PDF Downloads 1152431 Results of EPR Dosimetry Study of Population Residing in the Vicinity of the Uranium Mines and Uranium Processing Plant
Authors: K. Zhumadilov, P. Kazymbet, A. Ivannikov, M. Bakhtin, A. Akylbekov, K. Kadyrzhanov, A. Morzabayev, M. Hoshi
Abstract:
The aim of the study is to evaluate the possible excess of dose received by uranium processing plant workers. The possible excess of dose of workers was evaluated with comparison with population pool (Stepnogorsk) and control pool (Astana city). The measured teeth samples were extracted according to medical indications. In total, twenty-seven tooth enamel samples were analyzed from the residents of Stepnogorsk city (180 km from Astana city, Kazakhstan). About 6 tooth samples were collected from the workers of uranium processing plant. The results of tooth enamel dose estimation show us small influence of working conditions to workers, the maximum excess dose is less than 100 mGy. This is pilot study of EPR dose estimation and for a final conclusion additional sample is required.Keywords: EPR dose, workers, uranium mines, tooth samples
Procedia PDF Downloads 4012430 A Method to Determine Cutting Force Coefficients in Turning Using Mechanistic Approach
Authors: T. C. Bera, A. Bansal, D. Nema
Abstract:
During performing turning operation, cutting force plays a significant role in metal cutting process affecting tool-work piece deflection, vibration and eventually part quality. The present research work aims to develop a mechanistic cutting force model and to study the mechanistic constants used in the force model in case of turning operation. The proposed model can be used for the reliable and accurate estimation of the cutting forces establishing relationship of various force components (cutting force and feed force) with uncut chip thickness. The accurate estimation of cutting force is required to improve thin-walled part accuracy by controlling the tool-work piece deflection induced surface errors and tool-work piece vibration.Keywords: turning, cutting forces, cutting constants, uncut chip thickness
Procedia PDF Downloads 5152429 Use of Dendrochronology in Estimation of Creep Velocity and Its Dependence on the Bulk Density of Soils
Authors: Mohammad Amjad Sabir, Ishtiaq Khan, Shahid Ali, Umar Shabbir, Aneel Ahmad
Abstract:
Creep, being the main silt contributor to the rivers, is a slow, downhill flow of soils. The creep velocity is measured in millimeters to a couple of centimeters per year and is determined with the help of tilt caused by creep in the vertical objects and needs at least ten years to get a reliable creep velocity. This project was devised to calculate creep velocity using dendrochronology and looking for the difference of creep velocity registered by different trees on the same slope. It was concluded that dendrochronology provides a very reliable procedure of creep velocity estimation if ‘J’ shaped trees are studied for their horizontal movement and age. The age of these trees was measured using tree coring, and the horizontal movement was measured with a conventional tape. Using this procedure it does not require decades and additionally the data reveals the creep velocity for up to 150 years and even more instead of just a decade. It was also concluded that the creep velocity does not only depend on bulk density of soil hence no pronounced effect of bulk density was detected.Keywords: creep velocity, Galiyat, Pakistan, dendrochronology, Nagri Bala
Procedia PDF Downloads 3022428 Determinants of Income Diversification among Support Zone Communities of National Parks in Nigeria
Authors: Daniel Etim Jacob, Samuel Onadeko, Edem A. Eniang, Imaobong Ufot Nelson
Abstract:
This paper examined determinants of income diversification among households in support zones communities of national parks in Nigeria. This involved the use household data collected through questionnaires administered randomly among 1009 household heads in the study area. The data obtained were analyzed using probability and non-probability statistical analysis such as regression and analysis of variance to test for mean difference between parks. The result obtained indicates that majority of the household heads were male (92.57%0, between the age class of 21 – 40 years (44.90%), had non-formal education (38.16%), were farmers (65.21%), owned land (95.44%), with a household size of 1 – 5 (36.67%) and an annual income range of ₦401,000 - ₦600,000 (24.58%). Mean Simpson index of diversity showed a general low (0.375) level of income diversification among the households. Income, age, off-farm dependence, education, household size and occupation where significant (p<0.01) factors that affected households’ income diversification. The study recommends improvement in the existing infrastructures and social capital in the communities as avenues to improve the livelihood and ensure positive conservation behaviors in the study area.Keywords: income diversification, protected area, livelihood, poverty, Nigeria
Procedia PDF Downloads 1352427 A Generalized Family of Estimators for Estimation of Unknown Population Variance in Simple Random Sampling
Authors: Saba Riaz, Syed A. Hussain
Abstract:
This paper is addressing the estimation method of the unknown population variance of the variable of interest. A new generalized class of estimators of the finite population variance has been suggested using the auxiliary information. To improve the precision of the proposed class, known population variance of the auxiliary variable has been used. Mathematical expressions for the biases and the asymptotic variances of the suggested class are derived under large sample approximation. Theoretical and numerical comparisons are made to investigate the performances of the proposed class of estimators. The empirical study reveals that the suggested class of estimators performs better than the usual estimator, classical ratio estimator, classical product estimator and classical linear regression estimator. It has also been found that the suggested class of estimators is also more efficient than some recently published estimators.Keywords: study variable, auxiliary variable, finite population variance, bias, asymptotic variance, percent relative efficiency
Procedia PDF Downloads 2172426 Off-Line Text-Independent Arabic Writer Identification Using Optimum Codebooks
Authors: Ahmed Abdullah Ahmed
Abstract:
The task of recognizing the writer of a handwritten text has been an attractive research problem in the document analysis and recognition community with applications in handwriting forensics, paleography, document examination and handwriting recognition. This research presents an automatic method for writer recognition from digitized images of unconstrained writings. Although a great effort has been made by previous studies to come out with various methods, their performances, especially in terms of accuracy, are fallen short, and room for improvements is still wide open. The proposed technique employs optimal codebook based writer characterization where each writing sample is represented by a set of features computed from two codebooks, beginning and ending. Unlike most of the classical codebook based approaches which segment the writing into graphemes, this study is based on fragmenting a particular area of writing which are beginning and ending strokes. The proposed method starting with contour detection to extract significant information from the handwriting and the curve fragmentation is then employed to categorize the handwriting into Beginning and Ending zones into small fragments. The similar fragments of beginning strokes are grouped together to create Beginning cluster, and similarly, the ending strokes are grouped to create the ending cluster. These two clusters lead to the development of two codebooks (beginning and ending) by choosing the center of every similar fragments group. Writings under study are then represented by computing the probability of occurrence of codebook patterns. The probability distribution is used to characterize each writer. Two writings are then compared by computing distances between their respective probability distribution. The evaluations carried out on ICFHR standard dataset of 206 writers using Beginning and Ending codebooks separately. Finally, the Ending codebook achieved the highest identification rate of 98.23%, which is the best result so far on ICFHR dataset.Keywords: off-line text-independent writer identification, feature extraction, codebook, fragments
Procedia PDF Downloads 5062425 Parameter Estimation with Uncertainty and Sensitivity Analysis for the SARS Outbreak in Hong Kong
Authors: Afia Naheed, Manmohan Singh, David Lucy
Abstract:
This work is based on a mathematical as well as statistical study of an SEIJTR deterministic model for the interpretation of transmission of severe acute respiratory syndrome (SARS). Based on the SARS epidemic in 2003, the parameters are estimated using Runge-Kutta (Dormand-Prince pairs) and least squares methods. Possible graphical and numerical techniques are used to validate the estimates. Then effect of the model parameters on the dynamics of the disease is examined using sensitivity and uncertainty analysis. Sensitivity and uncertainty analytical techniques are used in order to analyze the affect of the uncertainty in the obtained parameter estimates and to determine which parameters have the largest impact on controlling the disease dynamics.Keywords: infectious disease, severe acute respiratory syndrome (SARS), parameter estimation, sensitivity analysis, uncertainty analysis, Runge-Kutta methods, Levenberg-Marquardt method
Procedia PDF Downloads 3492424 Evaluating Accuracy of Foetal Weight Estimation by Clinicians in Christian Medical College Hospital, India and Its Correlation to Actual Birth Weight: A Clinical Audit
Authors: Aarati Susan Mathew, Radhika Narendra Patel, Jiji Mathew
Abstract:
A retrospective study conducted at Christian Medical College (CMC) Teaching Hospital, Vellore, India on 14th August 2014 to assess the accuracy of clinically estimated foetal weight upon labour admission. Estimating foetal weight is a crucial factor in assessing maternal and foetal complications during and after labour. Medical notes of ninety-eight postnatal women who fulfilled the inclusion criteria were studied to evaluate the correlation between their recorded Estimated Foetal Weight (EFW) on admission and actual birth weight (ABW) of the newborn after delivery. Data concerning maternal and foetal demographics was also noted. Accuracy was determined by absolute percentage error and proportion of estimates within 10% of ABW. Actual birth weights ranged from 950-4080g. A strong positive correlation between EFW and ABW (r=0.904) was noted. Term deliveries (≥40 weeks) in the normal weight range (2500-4000g) had a 59.5% estimation accuracy (n=74) compared to pre-term (<40 weeks) with an estimation accuracy of 0% (n=2). Out of the term deliveries, macrosomic babies (>4000g) were underestimated by 25% (n=3) and low birthweight (LBW) babies were overestimated by 12.7% (n=9). Registrars who estimated foetal weight were accurate in babies within normal weight ranges. However, there needs to be an improvement in predicting weight of macrosomic and LBW foetuses. We have suggested the use of an amended version of the Johnson’s formula for the Indian population for improvement and a need to re-audit once implemented.Keywords: clinical palpation, estimated foetal weight, pregnancy, India, Johnson’s formula
Procedia PDF Downloads 3592423 Copula Markov Switching Multifractal Models for Forecasting Value-at-Risk
Authors: Giriraj Achari, Malay Bhattacharyya
Abstract:
In this paper, the effectiveness of Copula Markov Switching Multifractal (MSM) models at forecasting Value-at-Risk of a two-stock portfolio is studied. The innovations are allowed to be drawn from distributions that can capture skewness and leptokurtosis, which are well documented empirical characteristics observed in financial returns. The candidate distributions considered for this purpose are Johnson-SU, Pearson Type-IV and α-Stable distributions. The two univariate marginal distributions are combined using the Student-t copula. The estimation of all parameters is performed by Maximum Likelihood Estimation. Finally, the models are compared in terms of accurate Value-at-Risk (VaR) forecasts using tests of unconditional coverage and independence. It is found that Copula-MSM-models with leptokurtic innovation distributions perform slightly better than Copula-MSM model with Normal innovations. Copula-MSM models, in general, produce better VaR forecasts as compared to traditional methods like Historical Simulation method, Variance-Covariance approach and Copula-Generalized Autoregressive Conditional Heteroscedasticity (Copula-GARCH) models.Keywords: Copula, Markov Switching, multifractal, value-at-risk
Procedia PDF Downloads 158