Search results for: nonparametric geographically weighted regression
2912 A Modified Decoupled Semi-Analytical Approach Based On SBFEM for Solving 2D Elastodynamic Problems
Authors: M. Fakharian, M. I. Khodakarami
Abstract:
In this paper, a new trend for improvement in semi-analytical method based on scale boundaries in order to solve the 2D elastodynamic problems is provided. In this regard, only the boundaries of the problem domain discretization are by specific sub-parametric elements. Mapping functions are uses as a class of higher-order Lagrange polynomials, special shape functions, Gauss-Lobatto -Legendre numerical integration, and the integral form of the weighted residual method, the matrix is diagonal coefficients in the equations of elastodynamic issues. Differences between study conducted and prior research in this paper is in geometry production procedure of the interpolation function and integration of the different is selected. Validity and accuracy of the present method are fully demonstrated through two benchmark problems which are successfully modeled using a few numbers of DOFs. The numerical results agree very well with the analytical solutions and the results from other numerical methods.Keywords: 2D elastodynamic problems, lagrange polynomials, G-L-Lquadrature, decoupled SBFEM
Procedia PDF Downloads 4362911 Impacts of Aquaculture Farms on the Mangroves Forests of Sundarbans, India (2010-2018): Temporal Changes of NDVI
Authors: Sandeep Thakur, Ismail Mondal, Phani Bhusan Ghosh, Papita Das, Tarun Kumar De
Abstract:
Sundarbans Reserve forest of India has been undergoing major transformations in the recent past owing to population pressure and related changes. This has brought about major changes in the spatial landscape of the region especially in the western parts. This study attempts to assess the impacts of the Landcover changes on the mangrove habitats. Time series imageries of Landsat were used to analyze the Normalized Differential Vegetation Index (NDVI) patterns over the western parts of Indian Sundarbans forest in order to assess the heath of the mangroves in the region. The images were subjected to Land use Land cover (LULC) classification using sub-pixel classification techniques in ERDAS Imagine software and the changes were mapped. The spatial proliferation of aquaculture farms during the study period was also mapped. A multivariate regression analysis was carried out between the obtained NDVI values and the LULC classes. Similarly, the observed meteorological data sets (time series rainfall and minimum and maximum temperature) were also statistically correlated for regression. The study demonstrated the application of NDVI in assessing the environmental status of mangroves as the relationship between the changes in the environmental variables and the remote sensing based indices felicitate an efficient evaluation of environmental variables, which can be used in the coastal zone monitoring and development processes.Keywords: aquaculture farms, LULC, Mangrove, NDVI
Procedia PDF Downloads 1732910 Methodology to Achieve Non-Cooperative Target Identification Using High Resolution Range Profiles
Authors: Olga Hernán-Vega, Patricia López-Rodríguez, David Escot-Bocanegra, Raúl Fernández-Recio, Ignacio Bravo
Abstract:
Non-Cooperative Target Identification has become a key research domain in the Defense industry since it provides the ability to recognize targets at long distance and under any weather condition. High Resolution Range Profiles, one-dimensional radar images where the reflectivity of a target is projected onto the radar line of sight, are widely used for identification of flying targets. According to that, to face this problem, an approach to Non-Cooperative Target Identification based on the exploitation of Singular Value Decomposition to a matrix of range profiles is presented. Target Identification based on one-dimensional radar images compares a collection of profiles of a given target, namely test set, with the profiles included in a pre-loaded database, namely training set. The classification is improved by using Singular Value Decomposition since it allows to model each aircraft as a subspace and to accomplish recognition in a transformed domain where the main features are easier to extract hence, reducing unwanted information such as noise. Singular Value Decomposition permits to define a signal subspace which contain the highest percentage of the energy, and a noise subspace which will be discarded. This way, only the valuable information of each target is used in the recognition process. The identification algorithm is based on finding the target that minimizes the angle between subspaces and takes place in a transformed domain. Two metrics, F1 and F2, based on Singular Value Decomposition are accomplished in the identification process. In the case of F2, the angle is weighted, since the top vectors set the importance in the contribution to the formation of a target signal, on the contrary F1 simply shows the evolution of the unweighted angle. In order to have a wide database or radar signatures and evaluate the performance, range profiles are obtained through numerical simulation of seven civil aircraft at defined trajectories taken from an actual measurement. Taking into account the nature of the datasets, the main drawback of using simulated profiles instead of actual measured profiles is that the former implies an ideal identification scenario, since measured profiles suffer from noise, clutter and other unwanted information and simulated profiles don't. In this case, the test and training samples have similar nature and usually a similar high signal-to-noise ratio, so as to assess the feasibility of the approach, the addition of noise has been considered before the creation of the test set. The identification results applying the unweighted and weighted metrics are analysed for demonstrating which algorithm provides the best robustness against noise in an actual possible scenario. So as to confirm the validity of the methodology, identification experiments of profiles coming from electromagnetic simulations are conducted, revealing promising results. Considering the dissimilarities between the test and training sets when noise is added, the recognition performance has been improved when weighting is applied. Future experiments with larger sets are expected to be conducted with the aim of finally using actual profiles as test sets in a real hostile situation.Keywords: HRRP, NCTI, simulated/synthetic database, SVD
Procedia PDF Downloads 3482909 Perceived Effects of Work-Family Balance on Employee’s Job Satisfaction among Extension Agents in Southwest Nigeria
Authors: B. G. Abiona, A. A. Onaseso, T. D. Odetayo, J. Yila, O. E. Fapojuwo, K. G. Adeosun
Abstract:
This study determines the perceived effects of work-family balance on employees’ job satisfaction among Extension Agents in the Agricultural Development Programme (ADP) in southwest Nigeria. A multistage sampling technique was used to select 256 respondents for the study. Data on personal characteristics, work-family balance domain, and job satisfaction were collected. The collected data were analysed using descriptive statistics, Chi-square, Pearson Product Moment Correlation (PPMC), multiple linear regression, and Student T-test. Results revealed that the mean age of the respondents was 40 years; the majority (59.3%) of the respondents were male, and slightly above half (51.6%) of the respondents had MSc as their highest academic qualification. Findings revealed that turnover intention (x ̅ = 3.20) and work-role conflict (x ̅ = 3.06) were the major perceived work-family balance domain in the studied areas. Further, the result showed that the respondents have a high (79%) level of job satisfaction. Multiple linear regression revealed that job involvement (ß=0.167, p<0.01) and work-role conflict (ß= -0.221, p<0.05) contributed significantly to employees’ level of job satisfaction. The results of the Student T-test revealed a significant difference in the perceived work-family balance domain (t = 0.43, p<0.05) between the two studied areas. The study concluded that work-role conflict among employees causes work-family imbalance and, therefore, negatively affects employees’ job satisfaction. The definition of job design among the respondents that will create a balance between work and family is highly recommended.Keywords: work-life, conflict, job satisfaction, extension agent
Procedia PDF Downloads 872908 Foreign Investment, Technological Diffusion and Competiveness of Exports: A Case for Textile Industry in Pakistan
Authors: Syed Toqueer Akhter, Muhammad Awais
Abstract:
Pakistan is a country which is gifted by naturally abundant resources these resources are a pioneer towards a prospect and developed country. Pakistan is the fourth largest exporter of the textile in the world and with the passage of time the competitiveness of these exports is subject to a decline. With a lot of International players in the textile world like China, Bangladesh, India, and Sri Lanka, Pakistan needs to put up a lot of effort to compete with these countries. This research paper would determine the impact of Foreign Direct Investment upon technological diffusion and that how significantly it may be affecting on export performance of the country. It would also demonstrate that with the increase in Foreign Direct Investment, technological diffusion, strong property rights, and using different policy tools, export competitiveness of the country could be improved. The research has been carried out using time series data from 1995 to 2013 and the results have been estimated by using competing Econometrics modes such as Robust regression and Generalized least squares so that to consolidate the impact of the Foreign Investments and Technological diffusion upon export competitiveness comprehensively. Distributed Lag model has also been used to encompass the lagged effect of policy tools variables used by the government. Model estimates entail that 'FDI' and 'Technological Diffusion' do have a significant impact on the competitiveness of the exports of Pakistan. It may also be inferred that competitiveness of Textile Sector requires integrated policy framework, primarily including the reduction in interest rates, providing subsides, and manufacturing of value added products.Keywords: high technology export, robust regression, patents, technological diffusion, export competitiveness
Procedia PDF Downloads 4932907 An Improved Face Recognition Algorithm Using Histogram-Based Features in Spatial and Frequency Domains
Authors: Qiu Chen, Koji Kotani, Feifei Lee, Tadahiro Ohmi
Abstract:
In this paper, we propose an improved face recognition algorithm using histogram-based features in spatial and frequency domains. For adding spatial information of the face to improve recognition performance, a region-division (RD) method is utilized. The facial area is firstly divided into several regions, then feature vectors of each facial part are generated by Binary Vector Quantization (BVQ) histogram using DCT coefficients in low frequency domains, as well as Local Binary Pattern (LBP) histogram in spatial domain. Recognition results with different regions are first obtained separately and then fused by weighted averaging. Publicly available ORL database is used for the evaluation of our proposed algorithm, which is consisted of 40 subjects with 10 images per subject containing variations in lighting, posing, and expressions. It is demonstrated that face recognition using RD method can achieve much higher recognition rate.Keywords: binary vector quantization (BVQ), DCT coefficients, face recognition, local binary patterns (LBP)
Procedia PDF Downloads 3442906 Forced Vibration of an Auxetic Cylindrical Shell Containing Fluid Under the Influence of Shock Load
Authors: Korosh Khorshidi
Abstract:
Due to the increasing use of different materials, such as auxetic structures, it is necessary to investigate mechanical phenomena, such as vibration, in structures made of these types of materials. This paper examines the forced vibrations of a three-layer cylindrical shell containing inviscid fluid under shock load. All three layers are made of aluminum, and the central layer is made of a re-entrant honeycomb cell structure. Using high-order shear deformation theories (HSDT) and Hamilton’s principle, the governing equations of the system have been extracted and solved by the Galerkin weighted residual method. The outputs of the Abaqus finite element software are used to validate the results. The system is investigated with both simple and clamped support conditions. Finally, this study investigates the influence of the geometrical parameters of the shell and the auxetic structure, as well as the type, intensity, duration, and location of the load, and the effect of the fluid on the dynamic and time responses.Keywords: force vibration, cylindrical shell, auxetic structure, inviscid fluid
Procedia PDF Downloads 402905 Predictor Factors for Treatment Failure among Patients on Second Line Antiretroviral Therapy
Authors: Mohd. A. M. Rahim, Yahaya Hassan, Mathumalar L. Fahrni
Abstract:
Second line antiretroviral therapy (ART) regimen is used when patients fail their first line regimen. There are many factors such as non-adherence, drug resistance as well as virological and immunological failure that lead to second line highly active antiretroviral therapy (HAART) regimen treatment failure. This study was aimed at determining predictor factors to treatment failure with second line HAART and analyzing median survival time. An observational, retrospective study was conducted in Sungai Buloh Hospital (HSB) to assess current status of HIV patients treated with second line HAART regimen. Convenience sampling was used and 104 patients were included based on the study’s inclusion and exclusion criteria. Data was collected for six months i.e. from July until December 2013. Data was then analysed using SPSS version 18. Kaplan-Meier and Cox regression analyses were used to measure median survival times and predictor factors for treatment failure. The study population consisted mainly of male subjects, aged 30-45 years, who were heterosexual, and had HIV infection for less than 6 years. The most common second line HAART regimen given was lopinavir/ritonavir (LPV/r)-based combination. Kaplan-Meier analysis showed that patients on LPV/r demonstrated longer median survival times than patients on indinavir/ritonavir (IDV/r) based combination (p<0.001). The commonest reason for a treatment to fail with second line HAART was non-adherence. Based on Cox regression analysis, other predictor factors for treatment failure with second line HAART regimen were age and mode of HIV transmission.Keywords: adherence, antiretroviral therapy, second line, treatment failure
Procedia PDF Downloads 2552904 Satellite LiDAR-Based Digital Terrain Model Correction using Gaussian Process Regression
Authors: Keisuke Takahata, Hiroshi Suetsugu
Abstract:
Forest height is an important parameter for forest biomass estimation, and precise elevation data is essential for accurate forest height estimation. There are several globally or nationally available digital elevation models (DEMs) like SRTM and ASTER. However, its accuracy is reported to be low particularly in mountainous areas where there are closed canopy or steep slope. Recently, space-borne LiDAR, such as the Global Ecosystem Dynamics Investigation (GEDI), have started to provide sparse but accurate ground elevation and canopy height estimates. Several studies have reported the high degree of accuracy in their elevation products on their exact footprints, while it is not clear how this sparse information can be used for wider area. In this study, we developed a digital terrain model correction algorithm by spatially interpolating the difference between existing DEMs and GEDI elevation products by using Gaussian Process (GP) regression model. The result shows that our GP-based methodology can reduce the mean bias of the elevation data from 3.7m to 0.3m when we use airborne LiDAR-derived elevation information as ground truth. Our algorithm is also capable of quantifying the elevation data uncertainty, which is critical requirement for biomass inventory. Upcoming satellite-LiDAR missions, like MOLI (Multi-footprint Observation Lidar and Imager), are expected to contribute to the more accurate digital terrain model generation.Keywords: digital terrain model, satellite LiDAR, gaussian processes, uncertainty quantification
Procedia PDF Downloads 1712903 Trajectories of Depression Anxiety and Stress among Breast Cancer Patients: Assessment at First Year of Diagnosis
Authors: Jyoti Srivastava, Sandhya S. Kaushik, Mallika Tewari, Hari S. Shukla
Abstract:
Little information is available about the development of psychological well being over time among women who have been undergoing treatment for breast cancer. The aim of this study was to identify the trajectories of depression anxiety and stress among women with early-stage breast cancer. Of the 48 Indian women with newly diagnosed early-stage breast cancer recruited from surgical oncology unit, 39 completed an interview and were assessed for depression anxiety and stress (Depression Anxiety Stress Scale-DASS 21) before their first course of chemotherapy (baseline) and follow up interviews at 3, 6 and 9 months thereafter. Growth mixture modeling was used to identify distinct trajectories of Depression Anxiety and Stress symptoms. Logistic Regression analysis was used to evaluate the characteristics of women in distinct groups. Most women showed mild to moderate level of depression and anxiety (68%) while normal to mild level of stress (71%). But one in 11 women was chronically anxious (9%) and depressed (9%). Young age, having a partner, shorter education and receiving chemotherapy but not radiotherapy might characterize women whose psychological symptoms remain strong nine months after diagnosis. By looking beyond the mean, it was found that several socio-demographic and treatment factors characterized the women whose depression, anxiety and stress level remained severe even nine months after diagnosis. The results suggest that support provided to cancer patients should have a special focus on a relatively small group of patient most in need.Keywords: psychological well being, growth mixture modeling, logistic regression analysis, socio-demographic factors
Procedia PDF Downloads 1422902 A Packet Loss Probability Estimation Filter Using Most Recent Finite Traffic Measurements
Authors: Pyung Soo Kim, Eung Hyuk Lee, Mun Suck Jang
Abstract:
A packet loss probability (PLP) estimation filter with finite memory structure is proposed to estimate the packet rate mean and variance of the input traffic process in real-time while removing undesired system and measurement noises. The proposed PLP estimation filter is developed under a weighted least square criterion using only the finite traffic measurements on the most recent window. The proposed PLP estimation filter is shown to have several inherent properties such as unbiasedness, deadbeat, robustness. A guideline for choosing appropriate window length is described since it can affect significantly the estimation performance. Using computer simulations, the proposed PLP estimation filter is shown to be superior to the Kalman filter for the temporarily uncertain system. One possible explanation for this is that the proposed PLP estimation filter can have greater convergence time of a filtered estimate as the window length M decreases.Keywords: packet loss probability estimation, finite memory filter, infinite memory filter, Kalman filter
Procedia PDF Downloads 6662901 Stock Prediction and Portfolio Optimization Thesis
Authors: Deniz Peksen
Abstract:
This thesis aims to predict trend movement of closing price of stock and to maximize portfolio by utilizing the predictions. In this context, the study aims to define a stock portfolio strategy from models created by using Logistic Regression, Gradient Boosting and Random Forest. Recently, predicting the trend of stock price has gained a significance role in making buy and sell decisions and generating returns with investment strategies formed by machine learning basis decisions. There are plenty of studies in the literature on the prediction of stock prices in capital markets using machine learning methods but most of them focus on closing prices instead of the direction of price trend. Our study differs from literature in terms of target definition. Ours is a classification problem which is focusing on the market trend in next 20 trading days. To predict trend direction, fourteen years of data were used for training. Following three years were used for validation. Finally, last three years were used for testing. Training data are between 2002-06-18 and 2016-12-30 Validation data are between 2017-01-02 and 2019-12-31 Testing data are between 2020-01-02 and 2022-03-17 We determine Hold Stock Portfolio, Best Stock Portfolio and USD-TRY Exchange rate as benchmarks which we should outperform. We compared our machine learning basis portfolio return on test data with return of Hold Stock Portfolio, Best Stock Portfolio and USD-TRY Exchange rate. We assessed our model performance with the help of roc-auc score and lift charts. We use logistic regression, Gradient Boosting and Random Forest with grid search approach to fine-tune hyper-parameters. As a result of the empirical study, the existence of uptrend and downtrend of five stocks could not be predicted by the models. When we use these predictions to define buy and sell decisions in order to generate model-based-portfolio, model-based-portfolio fails in test dataset. It was found that Model-based buy and sell decisions generated a stock portfolio strategy whose returns can not outperform non-model portfolio strategies on test dataset. We found that any effort for predicting the trend which is formulated on stock price is a challenge. We found same results as Random Walk Theory claims which says that stock price or price changes are unpredictable. Our model iterations failed on test dataset. Although, we built up several good models on validation dataset, we failed on test dataset. We implemented Random Forest, Gradient Boosting and Logistic Regression. We discovered that complex models did not provide advantage or additional performance while comparing them with Logistic Regression. More complexity did not lead us to reach better performance. Using a complex model is not an answer to figure out the stock-related prediction problem. Our approach was to predict the trend instead of the price. This approach converted our problem into classification. However, this label approach does not lead us to solve the stock prediction problem and deny or refute the accuracy of the Random Walk Theory for the stock price.Keywords: stock prediction, portfolio optimization, data science, machine learning
Procedia PDF Downloads 752900 A Data-Driven Monitoring Technique Using Combined Anomaly Detectors
Authors: Fouzi Harrou, Ying Sun, Sofiane Khadraoui
Abstract:
Anomaly detection based on Principal Component Analysis (PCA) was studied intensively and largely applied to multivariate processes with highly cross-correlated process variables. Monitoring metrics such as the Hotelling's T2 and the Q statistics are usually used in PCA-based monitoring to elucidate the pattern variations in the principal and residual subspaces, respectively. However, these metrics are ill suited to detect small faults. In this paper, the Exponentially Weighted Moving Average (EWMA) based on the Q and T statistics, T2-EWMA and Q-EWMA, were developed for detecting faults in the process mean. The performance of the proposed methods was compared with that of the conventional PCA-based fault detection method using synthetic data. The results clearly show the benefit and the effectiveness of the proposed methods over the conventional PCA method, especially for detecting small faults in highly correlated multivariate data.Keywords: data-driven method, process control, anomaly detection, dimensionality reduction
Procedia PDF Downloads 2932899 The Effect of Multi-Stakeholder Extension Services towards Crop Choice and Farmer's Income, the Case of the Arc High Value Crop Programme
Authors: Joseph Sello Kau, Elias Mashayamombe, Brian Washington Madinkana, Cynthia Ngwane
Abstract:
This paper presents the results for the statistical (stepwise linear regression and multiple regression) analyses, carried out on a number of crops in order to evaluate how the decision for crop choice affect the level of farm income generated by the farmers participating in the High Value Crop production (referred to as the HVC). The goal of the HVC is to encourage farmers cultivate fruit crops. The farmers received planting material from different extension agencies, together with other complementary packages such as fertilizer, garden tools, water tanks etc. During the surveys, it was discovered that a significant number of farmers were cultivating traditional crops even when their plot sizes were small. Traditional crops are competing for resources with high value crops. The results of the analyses show that farmers cultivating fruit crops, maize and potatoes were generating high income than those cultivating spinach and cabbage. High farm income is associated with plot size, access to social grants and gender. Choice for a crop is influenced by the availability of planting material and the market potential for the crop. Extension agencies providing the planting materials stand a good chance of having farmers follow their directives. As a recommendation, for the farmers to cultivate more of the HVCs, the ARC must intensify provision of fruit trees.Keywords: farm income, nature of extension services, type of crops cultivated, fruit crops, cabbage, maize, potato and spinach
Procedia PDF Downloads 3152898 A Spatial Perspective on the Metallized Combustion Aspect of Rockets
Authors: Chitresh Prasad, Arvind Ramesh, Aditya Virkar, Karan Dholkaria, Vinayak Malhotra
Abstract:
Solid Propellant Rocket is a rocket that utilises a combination of a solid Oxidizer and a solid Fuel. Success in Solid Rocket Motor design and development depends significantly on knowledge of burning rate behaviour of the selected solid propellant under all motor operating conditions and design limit conditions. Most Solid Motor Rockets consist of the Main Engine, along with multiple Boosters that provide an additional thrust to the space-bound vehicle. Though widely used, they have been eclipsed by Liquid Propellant Rockets, because of their better performance characteristics. The addition of a catalyst such as Iron Oxide, on the other hand, can drastically enhance the performance of a Solid Rocket. This scientific investigation tries to emulate the working of a Solid Rocket using Sparklers and Energized Candles, with a central Energized Candle acting as the Main Engine and surrounding Sparklers acting as the Booster. The Energized Candle is made of Paraffin Wax, with Magnesium filings embedded in it’s wick. The Sparkler is made up of 45% Barium Nitrate, 35% Iron, 9% Aluminium, 10% Dextrin and the remaining composition consists of Boric Acid. The Magnesium in the Energized Candle, and the combination of Iron and Aluminium in the Sparkler, act as catalysts and enhance the burn rates of both materials. This combustion of Metallized Propellants has an influence over the regression rate of the subject candle. The experimental parameters explored here are Separation Distance, Systematically varying Configuration and Layout Symmetry. The major performance parameter under observation is the Regression Rate of the Energized Candle. The rate of regression is significantly affected by the orientation and configuration of the sparklers, which usually act as heat sources for the energized candle. The Overall Efficiency of any engine is factorised by the thermal and propulsive efficiencies. Numerous efforts have been made to improve one or the other. This investigation focuses on the Orientation of Rocket Motor Design to maximize their Overall Efficiency. The primary objective is to analyse the Flame Spread Rate variations of the energized candle, which resembles the solid rocket propellant used in the first stage of rocket operation thereby affecting the Specific Impulse values in a Rocket, which in turn have a deciding impact on their Time of Flight. Another objective of this research venture is to determine the effectiveness of the key controlling parameters explored. This investigation also emulates the exhaust gas interactions of the Solid Rocket through concurrent ignition of the Energized Candle and Sparklers, and their behaviour is analysed. Modern space programmes intend to explore the universe outside our solar system. To accomplish these goals, it is necessary to design a launch vehicle which is capable of providing incessant propulsion along with better efficiency for vast durations. The main motivation of this study is to enhance Rocket performance and their Overall Efficiency through better designing and optimization techniques, which will play a crucial role in this human conquest for knowledge.Keywords: design modifications, improving overall efficiency, metallized combustion, regression rate variations
Procedia PDF Downloads 1712897 Machine Learning Approach for Stress Detection Using Wireless Physical Activity Tracker
Authors: B. Padmaja, V. V. Rama Prasad, K. V. N. Sunitha, E. Krishna Rao Patro
Abstract:
Stress is a psychological condition that reduces the quality of sleep and affects every facet of life. Constant exposure to stress is detrimental not only for mind but also body. Nevertheless, to cope with stress, one should first identify it. This paper provides an effective method for the cognitive stress level detection by using data provided from a physical activity tracker device Fitbit. This device gathers people’s daily activities of food, weight, sleep, heart rate, and physical activities. In this paper, four major stressors like physical activities, sleep patterns, working hours and change in heart rate are used to assess the stress levels of individuals. The main motive of this system is to use machine learning approach in stress detection with the help of Smartphone sensor technology. Individually, the effect of each stressor is evaluated using logistic regression and then combined model is built and assessed using variants of ordinal logistic regression models like logit, probit and complementary log-log. Then the quality of each model is evaluated using Akaike Information Criterion (AIC) and probit is assessed as the more suitable model for our dataset. This system is experimented and evaluated in a real time environment by taking data from adults working in IT and other sectors in India. The novelty of this work lies in the fact that stress detection system should be less invasive as possible for the users.Keywords: physical activity tracker, sleep pattern, working hours, heart rate, smartphone sensor
Procedia PDF Downloads 2492896 Performance and Limitations of Likelihood Based Information Criteria and Leave-One-Out Cross-Validation Approximation Methods
Authors: M. A. C. S. Sampath Fernando, James M. Curran, Renate Meyer
Abstract:
Model assessment, in the Bayesian context, involves evaluation of the goodness-of-fit and the comparison of several alternative candidate models for predictive accuracy and improvements. In posterior predictive checks, the data simulated under the fitted model is compared with the actual data. Predictive model accuracy is estimated using information criteria such as the Akaike information criterion (AIC), the Bayesian information criterion (BIC), the Deviance information criterion (DIC), and the Watanabe-Akaike information criterion (WAIC). The goal of an information criterion is to obtain an unbiased measure of out-of-sample prediction error. Since posterior checks use the data twice; once for model estimation and once for testing, a bias correction which penalises the model complexity is incorporated in these criteria. Cross-validation (CV) is another method used for examining out-of-sample prediction accuracy. Leave-one-out cross-validation (LOO-CV) is the most computationally expensive variant among the other CV methods, as it fits as many models as the number of observations. Importance sampling (IS), truncated importance sampling (TIS) and Pareto-smoothed importance sampling (PSIS) are generally used as approximations to the exact LOO-CV and utilise the existing MCMC results avoiding expensive computational issues. The reciprocals of the predictive densities calculated over posterior draws for each observation are treated as the raw importance weights. These are in turn used to calculate the approximate LOO-CV of the observation as a weighted average of posterior densities. In IS-LOO, the raw weights are directly used. In contrast, the larger weights are replaced by their modified truncated weights in calculating TIS-LOO and PSIS-LOO. Although, information criteria and LOO-CV are unable to reflect the goodness-of-fit in absolute sense, the differences can be used to measure the relative performance of the models of interest. However, the use of these measures is only valid under specific circumstances. This study has developed 11 models using normal, log-normal, gamma, and student’s t distributions to improve the PCR stutter prediction with forensic data. These models are comprised of four with profile-wide variances, four with locus specific variances, and three which are two-component mixture models. The mean stutter ratio in each model is modeled as a locus specific simple linear regression against a feature of the alleles under study known as the longest uninterrupted sequence (LUS). The use of AIC, BIC, DIC, and WAIC in model comparison has some practical limitations. Even though, IS-LOO, TIS-LOO, and PSIS-LOO are considered to be approximations of the exact LOO-CV, the study observed some drastic deviations in the results. However, there are some interesting relationships among the logarithms of pointwise predictive densities (lppd) calculated under WAIC and the LOO approximation methods. The estimated overall lppd is a relative measure that reflects the overall goodness-of-fit of the model. Parallel log-likelihood profiles for the models conditional on equal posterior variances in lppds were observed. This study illustrates the limitations of the information criteria in practical model comparison problems. In addition, the relationships among LOO-CV approximation methods and WAIC with their limitations are discussed. Finally, useful recommendations that may help in practical model comparisons with these methods are provided.Keywords: cross-validation, importance sampling, information criteria, predictive accuracy
Procedia PDF Downloads 3852895 Organic Farming Profitability: Evidence from South Korea
Authors: Saem Lee, Thanh Nguyen, Hio-Jung Shin, Thomas Koellner
Abstract:
Land-use management has an influence on the provision of ecosystem service in dynamic, agricultural landscapes. Agricultural land use is important for maintaining the productivity and sustainability of agricultural ecosystems. However, in Korea, intensive farming activities in this highland agricultural zone, the upper stream of Soyang has led to contaminated soil caused by over-use pesticides and fertilizers. This has led to decrease in water and soil quality, which has consequences for ecosystem services and human wellbeing. Conventional farming has still high percentage in this area and there is no special measure to prevent low water quality caused by farming activities. Therefore, the adoption of environmentally friendly farming has been considered one of the alternatives that lead to improved water quality and increase in biomass production. Concurrently, farm households with environmentally friendly farming have occupied still low rates. Therefore, our research involved a farm household survey spanning conventional farming, the farm in transition and organic farming in Soyang watershed. Another purpose of our research was to compare economic advantage of the farmers adopting environmentally friendly farming and non-adaptors and to investigate the different factors by logistic regression analysis with socio-economic and benefit-cost ratio variables. The results found that farmers with environmentally friendly farming tended to be younger than conventional farming and farmer in transition. They are similar in terms of gender which was predominately male. Farmers with environmentally friendly farming were more educated and had less farming experience than conventional farming and farmer in transition. Based on the benefit-cost analysis, total costs that farm in transition farmers spent for one year are about two times as much as the sum of costs in environmentally friendly farming. The benefit of organic farmers was assessed with 2,800 KRW per household per year. In logistic regression, the factors having statistical significance are subsidy and district, residence period and benefit-cost ratio. And district and residence period have the negative impact on the practice of environmentally friendly farming techniques. The results of our research make a valuable contribution to provide important information to describe Korean policy-making for agricultural and water management and to consider potential approaches to policy that would substantiate ways beneficial for sustainable resource management.Keywords: organic farming, logistic regression, profitability, agricultural land-use
Procedia PDF Downloads 3962894 Laboratory Findings as Predictors of St2 and NT-Probnp Elevations in Heart Failure Clinic, National Cardiovascular Centre Harapan Kita, Indonesia
Authors: B. B. Siswanto, A. Halimi, K. M. H. J. Tandayu, C. Abdillah, F. Nanda , E. Chandra
Abstract:
Nowadays, modern cardiac biomarkers, such as ST2 and NT-proBNP, have important roles in predicting morbidity and mortality in heart failure patients. Abnormalities of serum electrolytes, sepsis or infection, and deteriorating renal function will worsen the conditions of patients with heart failure. It is intriguing to know whether cardiac biomarkers elevations are affected by laboratory findings in heart failure patients. We recruited 65 patients from the heart failure clinic in NCVC Harapan Kita in 2014-2015. All of them have consented for laboratory examination, including cardiac biomarkers. The findings were recorded in our Research and Development Centre and analyzed using linear regression to find whether there is a relationship between laboratory findings (sodium, potassium, creatinine, and leukocytes) and ST2 or NT-proBNP. From 65 patients, 26.9% of them are female, and 73.1% are male, 69.4% patients classified as NYHA I-II and 31.6% as NYHA III-IV. The mean age is 55.7+11.4 years old; mean sodium level is 136.1+6.5 mmol/l; mean potassium level is 4.7+1.9 mmol/l; mean leukocyte count is 9184.7+3622.4 /ul; mean creatinine level is 1.2+0.5 mg/dl. From linear regression logistics, the relationship between NT-proBNP and sodium level (p<0.001), as well as leukocyte count (p=0.002) are significant, while NT-proBNP and potassium level (p=0.05), as well as creatinine level (p=0.534) are not significant. The relationship between ST2 and sodium level (p=0.501), potassium level (p=0.76), leukocyte level (p=0.897), and creatinine level (p=0.817) are not significant. To conclude, laboratory findings are more sensitive in predicting NT-proBNP elevation than ST2 elevation. Larger studies are needed to prove that NT-proBNP correlation with laboratory findings is more superior than ST2.Keywords: heart failure, laboratory, NT-proBNP, ST2
Procedia PDF Downloads 3332893 Use of RAPD and ISSR Markers in Detection of Genetic Variation among Colletotrichum falcatum Went Isolates from South Gujarat India
Authors: Prittesh Patel, Rushabh Shah, Krishnamurthy Ramar, Vakulbhushan Bhaskar
Abstract:
The present research work aims at finding genetic differences in the genomes of sugarcane red rot isolates Colletotrichum falcatum Went using Random Amplified Polymorphic DNA (RAPD) and interspersed simple sequence repeat (ISSR) molecular markers. Ten isolates of C. falcatum isolated from different red rot infected sugarcane cultivars stalk were used in present study. The amplified bands were scored across the lanes obtained in 15 RAPD primes and 21 ISSR primes successfully. The data were analysed using NTSYSpc 2.2 software. The results showed 80.6% and 68.07% polymorphism in RPAD and ISSR analysis respectively. Based on the RAPD analysis, ten genotypes were grouped into two major clusters at a cut-off value of 0.75. Geographically distant C. falcatum isolate cfGAN from south Gujarat had a level of similarity with Coimbatore isolate cf8436 presented on separate clade of bootstrapped dendrograms. First and second cluster consisted of five and three isolates respectively, indicating the close relation among them. The 21 ISSR primers produced 119 distinct and scorable loci in that 38 were monomorphic. The number of scorable loci for each primer varied from 2 (ISSR822) to 8 (ISSR807, ISSR823 and ISSR15) with an average of 5.66 loci per primer. Primer ISSR835 amplified the highest number of bands (57), while only 16 bands were obtained by primers ISSR822. Four primers namely ISSR830, ISSR845, ISSR4 and ISSR15 showed the highest value of percentage of polymorphism (100%). The results indicated that both of the marker systems RAPD and ISSR, individually can be effectively used in determination of genetic relationship among C falcatum accessions collected from different parts of south Gujarat.Keywords: Colletotrichum falcatum, ISSR, RAPD, Red Rot
Procedia PDF Downloads 3572892 Deep Learning for Qualitative and Quantitative Grain Quality Analysis Using Hyperspectral Imaging
Authors: Ole-Christian Galbo Engstrøm, Erik Schou Dreier, Birthe Møller Jespersen, Kim Steenstrup Pedersen
Abstract:
Grain quality analysis is a multi-parameterized problem that includes a variety of qualitative and quantitative parameters such as grain type classification, damage type classification, and nutrient regression. Currently, these parameters require human inspection, a multitude of instruments employing a variety of sensor technologies, and predictive model types or destructive and slow chemical analysis. This paper investigates the feasibility of applying near-infrared hyperspectral imaging (NIR-HSI) to grain quality analysis. For this study two datasets of NIR hyperspectral images in the wavelength range of 900 nm - 1700 nm have been used. Both datasets contain images of sparsely and densely packed grain kernels. The first dataset contains ~87,000 image crops of bulk wheat samples from 63 harvests where protein value has been determined by the FOSS Infratec NOVA which is the golden industry standard for protein content estimation in bulk samples of cereal grain. The second dataset consists of ~28,000 image crops of bulk grain kernels from seven different wheat varieties and a single rye variety. In the first dataset, protein regression analysis is the problem to solve while variety classification analysis is the problem to solve in the second dataset. Deep convolutional neural networks (CNNs) have the potential to utilize spatio-spectral correlations within a hyperspectral image to simultaneously estimate the qualitative and quantitative parameters. CNNs can autonomously derive meaningful representations of the input data reducing the need for advanced preprocessing techniques required for classical chemometric model types such as artificial neural networks (ANNs) and partial least-squares regression (PLS-R). A comparison between different CNN architectures utilizing 2D and 3D convolution is conducted. These results are compared to the performance of ANNs and PLS-R. Additionally, a variety of preprocessing techniques from image analysis and chemometrics are tested. These include centering, scaling, standard normal variate (SNV), Savitzky-Golay (SG) filtering, and detrending. The results indicate that the combination of NIR-HSI and CNNs has the potential to be the foundation for an automatic system unifying qualitative and quantitative grain quality analysis within a single sensor technology and predictive model type.Keywords: deep learning, grain analysis, hyperspectral imaging, preprocessing techniques
Procedia PDF Downloads 912891 Travel Delay and Modal Split Analysis: A Case Study
Authors: H. S. Sathish, H. S. Jagadeesh, Skanda Kumar
Abstract:
Journey time and delay study is used to evaluate the quality of service, the travel time and study can also be used to evaluate the quality of traffic movement along the route and to determine the location types and extent of traffic delays. Components of delay are boarding and alighting, issue of tickets, other causes and distance between each stops. This study investigates the total journey time required to travel along the stretch and the influence the delays. The route starts from Kempegowda Bus Station to Yelahanka Satellite Station of Bangalore City. The length of the stretch is 16.5 km. Modal split analysis has been done for this stretch. This stretch has elevated highway connecting to Bangalore International Airport and the extension of metro transit stretch. From the regression analysis of total journey time it is affected by delay due to boarding and alighting moderately, Delay due to issue of tickets affects the journey time to a higher extent. Some of the delay factors affecting significantly the journey time are evident from F-test at 10 percent level of confidence. Along this stretch work trips are more prevalent as indicated by O-D study. Modal shift analysis indicates about 70 percent of commuters are ready to shift from current system to Metro Rail System. Metro Rail System carries maximum number of trips compared to private mode. Hence Metro is a highly viable choice of mode for Bangalore Metropolitan City.Keywords: delay, journey time, modal choice, regression analysis
Procedia PDF Downloads 4902890 Passenger Flow Characteristics of Seoul Metropolitan Subway Network
Authors: Kang Won Lee, Jung Won Lee
Abstract:
Characterizing the network flow is of fundamental importance to understand the complex dynamics of networks. And passenger flow characteristics of the subway network are very relevant for an effective transportation management in urban cities. In this study, passenger flow of Seoul metropolitan subway network is investigated and characterized through statistical analysis. Traditional betweenness centrality measure considers only topological structure of the network and ignores the transportation factors. This paper proposes a weighted betweenness centrality measure that incorporates monthly passenger flow volume. We apply the proposed measure on the Seoul metropolitan subway network involving 493 stations and 16 lines. Several interesting insights about the network are derived from the new measures. Using Kolmogorov-Smirnov test, we also find out that monthly passenger flow between any two stations follows a power-law distribution and other traffic characteristics such as congestion level and throughflow traffic follow exponential distribution.Keywords: betweenness centrality, correlation coefficient, power-law distribution, Korea traffic DB
Procedia PDF Downloads 2842889 Farmers’ Access to Agricultural Extension Services Delivery Systems: Evidence from a Field Study in India
Authors: Ankit Nagar, Dinesh Kumar Nauriyal, Sukhpal Singh
Abstract:
This paper examines the key determinants of farmers’ access to agricultural extension services, sources of agricultural extension services preferred and accessed by the farmers. An ordered logistic regression model was used to analyse the data of the 360 sample households based on a primary survey conducted in western Uttar Pradesh, India. The study finds that farmers' decision to engage in the agricultural extension programme is significantly influenced by factors such as education level, gender, farming experience, social group, group membership, farm size, credit access, awareness about the extension scheme, farmers' perception, and distance from extension sources. The most intriguing finding of this study is that the progressive farmers, which have long been regarded as a major source of knowledge diffusion, are the most distrusted sources of information as they are suspected of withholding vital information from potential beneficiaries. The positive relationship between farm size and ‘Access’ underlines that the extension services should revisit their strategies for targeting more marginal and small farmers constituting over 85 percent of the agricultural households by incorporating their priorities in their outreach programs. The study suggests that marginal and small farmers' productive potential could still be greatly augmented by the appropriate technology, advisory services, guidance, and improved market access. Also, the perception of poor quality of the public extension services can be corrected by initiatives aimed at building up extension workers' capacity.Keywords: agriculture, access, extension services, ordered logistic regression
Procedia PDF Downloads 2062888 The Role of Attachment Styles, Gender Schemas, Sexual Self Schemas, and Body Exposures During Sexual Activity in Sexual Function, Marital Satisfaction, and Sexual Self-Esteem
Authors: Hossein Shareh, Farhad Seifi
Abstract:
The present study was to examine the role of attachment styles, gender schemas, sexual-self schemas, and body image during sexual activity in sexual function, marital satisfaction, and sexual self-esteem. The sampling method was among married women who were living in Mashhad; a snowball selected 765 people. Questionnaires and measures of adult attachment style (AAS), Bem Sex Role Inventory (BSRI), sexual self-schema (SSS), body exposure during sexual activity questionnaire (BESAQ), sexual function female inventory (FSFI), a short form of sexual self-esteem (SSEI-W-SF) and marital satisfaction (Enrich) were completed by participants. Data analysis using Pearson correlation and hierarchical regression and case analysis was performed by SPSS-19 software. The results showed that there is a significant correlation (P <0.05) between attachment and sexual function (r=0.342), marital satisfaction (r=0.351) and sexual self-esteem (r =0.292). A correlation (P <0.05) was observed between sexual schema (r=0.342) and sexual esteem (r=0.31). A meaningful correlation (P <0.05) exists between gender stereotypes and sexual function (r=0.352). There was a significant inverse correlation (P <0.05) between body image and their performance during sexual activity (r=0.41). There is no significant relationship between gender schemas, sexual schemas, body image, and marital satisfaction, and no relation was found between gender schemas, body image, and sexual self-esteem. Also, the result of the regression showed that attachment styles, gender schemas, sexual self- schemas, and body exposures during sexual activity are predictable in sexual function, and marital satisfaction can be predicted by attachment style and gender schema. Somewhat, sexual self-esteem can be expected by attachment style and gender schemas.Keywords: attachment styles, gender and sexual schemas, body image, sexual function, marital satisfaction, sexual self-esteem
Procedia PDF Downloads 302887 A Three Elements Vector Valued Structure’s Ultimate Strength-Strong Motion-Intensity Measure
Authors: A. Nicknam, N. Eftekhari, A. Mazarei, M. Ganjvar
Abstract:
This article presents an alternative collapse capacity intensity measure in the three elements form which is influenced by the spectral ordinates at periods longer than that of the first mode period at near and far source sites. A parameter, denoted by β, is defined by which the spectral ordinate effects, up to the effective period (2T_1), on the intensity measure are taken into account. The methodology permits to meet the hazard-levelled target extreme event in the probabilistic and deterministic forms. A MATLAB code is developed involving OpenSees to calculate the collapse capacities of the 8 archetype RC structures having 2 to 20 stories for regression process. The incremental dynamic analysis (IDA) method is used to calculate the structure’s collapse values accounting for the element stiffness and strength deterioration. The general near field set presented by FEMA is used in a series of performing nonlinear analyses. 8 linear relationships are developed for the 8structutres leading to the correlation coefficient up to 0.93. A collapse capacity near field prediction equation is developed taking into account the results of regression processes obtained from the 8 structures. The proposed prediction equation is validated against a set of actual near field records leading to a good agreement. Implementation of the proposed equation to the four archetype RC structures demonstrated different collapse capacities at near field site compared to those of FEMA. The reasons of differences are believed to be due to accounting for the spectral shape effects.Keywords: collapse capacity, fragility analysis, spectral shape effects, IDA method
Procedia PDF Downloads 2292886 The Effect of Students’ Social and Scholastic Background and Environmental Impact on Shaping Their Pattern of Digital Learning in Academia: A Pre- and Post-COVID Comparative View
Authors: Nitza Davidovitch, Yael Yossel-Eisenbach
Abstract:
The purpose of the study was to inquire whether there was a change in the shaping of undergraduate students’ digitally-oriented study pattern in the pre-Covid (2016-2017) versus post-Covid period (2022-2023), as affected by three factors: social background characteristics, high school, and academic background characteristics. These two-time points were cauterized by dramatic changes in teaching and learning at institutions of higher education. The data were collected via cross-sectional surveys at two-time points, in the 2016-2017 academic school year (N=443) and in the 2022-2023 school year (N=326). The questionnaire was distributed on social media and it includes questions on demographic background characteristics, previous studies in high school and present academic studies, and questions on learning and reading habits. Method of analysis: A. Statistical descriptive analysis, B. Mean comparison tests were conducted to analyze the variations in the mean score for the digitally-oriented learning pattern variable at two-time points (pre- and post-Covid) in relation to each of the independent variables. C. Analysis of variance was performed to test the main effects and the interactions. D. Applying linear regression, the research aimed to examine the combined effect of the independent variables on shaping students' digitally-oriented learning habits. The analysis includes four models. In all four models, the dependent variable is students’ perception of digitally oriented learning. The first model included social background variables; the second model included scholastic background as well. In the third model, the academic background variables were added, and the fourth model includes all the independent variables together with the variable of period (pre- and post-COVID). E. Factor analysis confirms using the principal component method with varimax rotation; the variables were constructed by a weighted mean of all the relevant statements merged to form a single variable denoting a shared content world. The research findings indicate a significant rise in students’ perceptions of digitally-oriented learning in the post-COVID period. From a gender perspective, the impact of COVID on shaping a digital learning pattern was much more significant for female students. The socioeconomic status perspective is eliminated when controlling for the period, and the student’s job is affected - more than all other variables. It may be assumed that the student’s work pattern mediates effects related to the convenience offered by digital learning regarding distance and time. The significant effect of scholastic background on shaping students’ digital learning patterns remained stable, even when controlling for all explanatory variables. The advantage that universities had over colleges in shaping a digital learning pattern in the pre-COVID period dissipated. Therefore, it can be said that after COVID, there was a change in how colleges shape students’ digital learning patterns in such a way that no institutional differences are evident with regard to shaping the digital learning pattern. The study shows that period has a significant independent effect on shaping students’ digital learning patterns when controlling for the explanatory variables.Keywords: learning pattern, COVID, socioeconomic status, digital learning
Procedia PDF Downloads 502885 Studying in Private Muslim Schools in Australia: Implications for Identity, Religiosity, and Adjustment
Authors: Hisham Motkal Abu-Rayya, Maram Hussein Abu-Rayya
Abstract:
Education in religious private schools raises questions regarding identity, belonging and adaptation in multicultural Australia. This research project aimed at examined cultural identification styles among Australian adolescent Muslims studying in Muslim schools, adolescents’ religiosity and the interconnections between cultural identification styles, religiosity, and adaptation. Two Muslim high school samples were recruited for the purposes of this study, one from Muslim schools in metropolitan Sydney and one from Muslim schools in metropolitan Melbourne. Participants filled in a survey measuring themes of the current study. Findings revealed that the majority of Australian adolescent Muslims showed a preference for the integration identification style (55.2%); separation was less prevailing (26.9%), followed by assimilation (9.7%) and marginalisation (8.3%). Supporting evidence suggests that the styles of identification were valid representation of the participants’ identification. A series of hierarchical regression analyses revealed that while adolescents’ preference for integration of their cultural and Australian identities was advantageous for a range of their psychological and socio-cultural adaptation measures, marginalisation was consistently the worst. Further hierarchical regression analyses showed that adolescent Muslims’ religiosity was better for a range of their adaptation measures compared to their preference for an integration acculturation style. Theoretical and practical implications of these findings are discussed.Keywords: adaptation, identity, multiculturalism, religious school education
Procedia PDF Downloads 2952884 Evaluation of the Beach Erosion Process in Varadero, Matanzas, Cuba: Effects of Different Hurricane Trajectories
Authors: Ana Gabriela Diaz, Luis Fermín Córdova, Jr., Roberto Lamazares
Abstract:
The island of Cuba, the largest of the Greater Antilles, is located in the tropical North Atlantic. It is annually affected by numerous weather events, which have caused severe damage to our coastal areas. In the same way that many other coastlines around the world, the beautiful beaches of the Hicacos Peninsula also suffer from erosion. This leads to a structural regression of the coastline. If measures are not taken, the hotels will be exposed to the advance of the sea, and it will be a serious problem for the economy. With the aim of studying the intensity of this type of activity, specialists of group of coastal and marine engineering from CIH, in the framework of the research conducted within the project MEGACOSTAS 2, provide their research to simulate extreme events and assess their impact in coastal areas, mainly regarding the definition of flood volumes and morphodynamic changes in sandy beaches. The main objective of this work is the evaluation of the process of Varadero beach erosion (the coastal sector has an important impact in the country's economy) on the Hicacos Peninsula for different paths of hurricanes. The mathematical model XBeach, which was integrated into the Coastal engineering system introduced by the project of MEGACOSTA 2 to determine the area and the more critical profiles for the path of hurricanes under study, was applied. The results of this project have shown that Center area is the greatest dynamic area in the simulation of the three paths of hurricanes under study, showing high erosion volumes and the greatest average length of regression of the coastline, from 15- 22 m.Keywords: beach, erosion, mathematical model, coastal areas
Procedia PDF Downloads 2222883 An Indoor Positioning System in Wireless Sensor Networks with Measurement Delay
Authors: Pyung Soo Kim, Eung Hyuk Lee, Mun Suck Jang
Abstract:
In the current paper, an indoor positioning system is proposed with consideration of measurement delay. Firstly, an estimation filter with a measurement delay is designed for the indoor positioning mechanism under a weighted least square criterion, which utilizes only finite measurements on the most recent window. The proposed estimation filtering based scheme gives the filtered estimates for position, velocity and acceleration of moving target in real-time, while removing undesired noisy effects and preserving desired moving positions. Secondly, the proposed scheme is shown to have good inherent properties such as unbiasedness, efficiency, time-invariance, deadbeat, and robustness due to the finite memory structure. Finally, computer simulations shows that the performance of the proposed estimation filtering based scheme can outperform to the existing infinite memory filtering based mechanism.Keywords: indoor positioning system, wireless sensor networks, measurement delay
Procedia PDF Downloads 478