Search results for: large margin nearest neighbor regression

Authors: Kornelius Ronald Demu, Dewi Retno Sari Saputro, Purnami Widyaningsih

Abstract:

Human Development Index (HDI) is a standard measurement for a country's human development. Several factors may have influenced it, such as life expectancy, gross domestic product (GDP) based on the province's annual expenditure, the number of poor people, and the percentage of an illiterate people. The scatter plot between HDI and the influenced factors show that the plot does not follow a specific pattern or form. Therefore, the HDI's data in Indonesia can be applied with a nonparametric regression model. The estimation of the regression curve in the nonparametric regression model is flexible because it follows the shape of the data pattern. One of the nonparametric regression's method is a truncated spline. Truncated spline regression is one of the nonparametric approach, which is a modification of the segmented polynomial functions. The estimator of a truncated spline regression model was affected by the selection of the optimal knots point. Knot points is a focus point of spline truncated functions. The optimal knots point was determined by the minimum value of generalized cross validation (GCV). In this article were applied the data of Human Development Index with a truncated spline nonparametric regression model. The results of this research were obtained the best-truncated spline regression model to the HDI's data in Indonesia with the combination of optimal knots point 5-5-5-4. Life expectancy and the percentage of an illiterate people were the significant factors depend to the HDI in Indonesia. The coefficient of determination is 94.54%. This means the regression model is good enough to applied on the data of HDI in Indonesia.

Keywords: generalized cross validation (GCV), Human Development Index (HDI), knots point, nonparametric regression, truncated spline

Procedia PDF Downloads 305

Authors: James Purnama, Riri Fitri Sari

Abstract:

We investigate the machine learning algorithm selection problem in the term of a depth image based eye gaze estimation, with respect to its essential difficulty in reducing the number of required training samples and duration time of training. Statistics based prediction accuracy are increasingly used to assess and evaluate prediction or estimation in gaze estimation. This article evaluates Root Mean Squared Error (RMSE) and R-Squared statistical analysis to assess machine learning methods on depth camera data for gaze estimation. There are 4 machines learning methods have been evaluated: Random Forest Regression, Regression Tree, Support Vector Machine (SVM), and Linear Regression. The experiment results show that the Random Forest Regression has the lowest RMSE and the highest R-Squared, which means that it is the best among other methods.

Keywords: gaze estimation, gaze tracking, eye tracking, kinect, regression model, orange python

Procedia PDF Downloads 508

Authors: Alexander David Natanson

Abstract:

This paper focuses on the effect of Sanctuary and Immigration and Customs Enforcement (ICE) policies on local economies. "Sanctuary cities" refers to municipal jurisdictions that limit their cooperation with the federal government's efforts to enforce immigration. Using county-level data from the American Community Survey and ICE data on economic indicators from 2006 to 2018, this study isolates the effects of local immigration policies on U.S. counties. The investigation is accomplished by simultaneously studying the policies' effects in counties where immigrants' families are persecuted via collaboration with Immigration and Customs Enforcement (ICE), in contrast to counties that provide protections. The analysis includes a difference-in-difference & two-way fixed effect model. Results are robust to nearest-neighbor matching, after the random assignment of treatment, after running estimations using different cutoffs for immigration policies, and with a regression discontinuity model comparing bordering counties with opposite policies. Results are also robust after restricting the data to a single-year policy adoption, using the Sun and Abraham estimator, and with event-study estimation to deal with the staggered treatment issue. In addition, the study reverses the estimation to understand what drives the decision to choose policies to detect the presence of reverse causality biases in the estimated policy impact on economic factors. The evidence demonstrates that providing protections to undocumented immigrants increases economic activity. The estimates show gains in per capita income ranging from 3.1 to 7.2, median wages between 1.7 to 2.6, and GDP between 2.4 to 4.1 percent. Regarding labor, sanctuary counties saw increases in total employment between 2.3 to 4 percent, and the unemployment rate declined from 12 to 17 percent. The data further shows that ICE policies have no statistically significant effects on income, median wages, or GDP but adverse effects on total employment, with declines from 1 to 2 percent, mostly in rural counties, and an increase in unemployment of around 7 percent in urban counties. In addition, results show a decline in the foreign-born population in ICE counties but no changes in sanctuary counties. The study also finds similar results for sanctuary counties when separating the data between urban, rural, educational attainment, gender, ethnic groups, economic quintiles, and the number of business establishments. The takeaway from this study is that institutional inclusion creates the dynamic nature of an economy, as inclusion allows for economic expansion due to the extension of fundamental freedoms to newcomers. Inclusive policies show positive effects on economic outcomes with no evident increase in population. To make sense of these results, the hypothesis and theoretical model propose that inclusive immigration policies play an essential role in conditioning the effect of immigration by decreasing uncertainties and constraints for immigrants' interaction in their communities, decreasing the cost from fear of deportation or the constant fear of criminalization and optimize their human capital.

Keywords: inclusive and exclusive institutions, post matching, fixed effect, time trend, regression discontinuity, difference-in-difference, randomization inference and sun, Abraham estimator

Procedia PDF Downloads 58

Authors: Retius Chifurira

Abstract:

Logistic regression model is the most used regression model to predict meteorological drought probabilities. When the dependent variable is extreme, the logistic model fails to adequately capture drought probabilities. In order to adequately predict drought probabilities, we use the generalized linear model (GLM) with the quantile function of the generalized extreme value distribution (GEVD) as the link function. The method maximum likelihood estimation is used to estimate the parameters of the generalized extreme value (GEV) regression model. We compare the performance of the logistic and the GEV regression models in predicting drought probabilities for Zimbabwe. The performance of the regression models are assessed using the goodness-of-fit tests, namely; relative root mean square error (RRMSE) and relative mean absolute error (RMAE). Results show that the GEV regression model performs better than the logistic model, thereby providing a good alternative candidate for predicting drought probabilities. This paper provides the first application of GLM derived from extreme value theory to predict drought probabilities for a drought-prone country such as Zimbabwe.

Keywords: generalized extreme value distribution, general linear model, mean annual rainfall, meteorological drought probabilities

Procedia PDF Downloads 160

Authors: Oludamilare Bode Adewuyi, Yanxia Sun, Isaiah Gbadegesin Adebayo

Abstract:

Voltage stability analysis is crucial to the reliable and economic operation of power systems. The power system of developing nations is more susceptible to failures due to the continuously increasing load demand, which is not matched with generation increase and efficient transmission infrastructures. Thus, most power systems are heavily stressed, and the planning of extra generation from distributed generation sources needs to be efficiently done so as to ensure the security of the power system. Some voltage stability index-based approach for DG siting has been reported in the literature. However, most of the existing voltage stability indices, though sufficient, are found to be inaccurate, especially for overloaded power systems. In this paper, the performance of a relatively different approach using a line voltage stability margin indicator, which has proven to have better accuracy, has been presented and compared with a conventional line voltage stability index for DG siting using the Nigerian 28 bus system. Critical boundary index (CBI) for voltage stability margin estimation was deployed to identify suitable locations for DG placement, and the performance was compared with DG placement using the Novel Line Stability Index (NLSI) approach. From the simulation results, both CBI and NLSI agreed greatly on suitable locations for DG on the test system; while CBI identified bus 18 as the most suitable at system overload, NLSI identified bus 8 to be the most suitable. Considering the effect of the DG placement at the selected buses on the voltage magnitude profile, the result shows that the DG placed on bus 18 identified by CBI improved the performance of the power system better.

Keywords: voltage stability analysis, voltage collapse, voltage stability index, distributed generation

Procedia PDF Downloads 60

Authors: James Rigor Camacho, Wansu Lim

Abstract:

Over the last few years, the development of new wearable and processing technologies has accelerated in order to harness physiological data such as electroencephalograms (EEGs) for EEG-based applications. EEG has been demonstrated to be a source of emotion recognition signals with the highest classification accuracy among physiological signals. However, when emotion recognition systems are used for real-time classification, the training unit is frequently left to run offline or in the cloud rather than working locally on the edge. That strategy has hampered research, and the full potential of using an edge AI device has yet to be realized. Edge AI devices are computers with high performance that can process complex algorithms. It is capable of collecting, processing, and storing data on its own. It can also analyze and apply complicated algorithms like localization, detection, and recognition on a real-time application, making it a powerful embedded device. The NVIDIA Jetson series, specifically the Jetson Nano device, was used in the implementation. The cEEGrid, which is integrated to the open-source brain computer-interface platform (OpenBCI), is used to collect EEG signals. An EEG-based real-time emotion recognition system on Edge AI is proposed in this paper. To perform graphical spectrogram categorization of EEG signals and to predict emotional states based on input data properties, machine learning-based classifiers were used. Until the emotional state was identified, the EEG signals were analyzed using the K-Nearest Neighbor (KNN) technique, which is a supervised learning system. In EEG signal processing, after each EEG signal has been received in real-time and translated from time to frequency domain, the Fast Fourier Transform (FFT) technique is utilized to observe the frequency bands in each EEG signal. To appropriately show the variance of each EEG frequency band, power density, standard deviation, and mean are calculated and employed. The next stage is to identify the features that have been chosen to predict emotion in EEG data using the K-Nearest Neighbors (KNN) technique. Arousal and valence datasets are used to train the parameters defined by the KNN technique.Because classification and recognition of specific classes, as well as emotion prediction, are conducted both online and locally on the edge, the KNN technique increased the performance of the emotion recognition system on the NVIDIA Jetson Nano. Finally, this implementation aims to bridge the research gap on cost-effective and efficient real-time emotion recognition using a resource constrained hardware device, like the NVIDIA Jetson Nano. On the cutting edge of AI, EEG-based emotion identification can be employed in applications that can rapidly expand the research and implementation industry's use.

Keywords: edge AI device, EEG, emotion recognition system, supervised learning algorithm, sensors

Procedia PDF Downloads 78

Authors: Sofia Stoica

Abstract:

In this paper, we use historical data to predict the stock price of a tech company. To this end, we use a dataset consisting of the stock prices in the past five years of ten major tech companies – Adobe, Amazon, Apple, Facebook, Google, Microsoft, Netflix, Oracle, Salesforce, and Tesla. We experimented with a variety of models– a linear regressor model, K nearest Neighbors (KNN), a sequential neural network – and algorithms - Multiplicative Weight Update, and AdaBoost. We found that the sequential neural network performed the best, with a testing error of 0.18%. Interestingly, the linear model performed the second best with a testing error of 0.73%. These results show that using historical data is enough to obtain high accuracies, and a simple algorithm like linear regression has a performance similar to more sophisticated models while taking less time and resources to implement.

Keywords: finance, machine learning, opening price, stock market

Procedia PDF Downloads 120

Authors: Sihem Oujdi, Hafida Belbachir

Abstract:

Existing methods of data mining cannot be applied on spatial data because they require spatial specificity consideration, as spatial relationships. This paper focuses on the classification with decision trees, which are one of the data mining techniques. We propose an extension of the C4.5 algorithm for spatial data, based on two different approaches Join materialization and Querying on the fly the different tables. Similar works have been done on these two main approaches, the first - Join materialization - favors the processing time in spite of memory space, whereas the second - Querying on the fly different tables- promotes memory space despite of the processing time. The modified C4.5 algorithm requires three entries tables: a target table, a neighbor table, and a spatial index join that contains the possible spatial relationship among the objects in the target table and those in the neighbor table. Thus, the proposed algorithms are applied to a spatial data pattern in the accidentology domain. A comparative study of our approach with other works of classification by spatial decision trees will be detailed.

Keywords: C4.5 algorithm, decision trees, S-CART, spatial data mining

Procedia PDF Downloads 591

Authors: Jameela Ali, Hamid A. Jalab, Loay E. George, Abdul Rahim Ahmad, Azizah Suliman, Karim Al-Jashamy

Abstract:

Red blood cells (RBC) are the most common types of blood cells and are the most intensively studied in cell biology. The lack of RBCs is a condition in which the amount of hemoglobin level is lower than normal and is referred to as “anemia”. Abnormalities in RBCs will affect the exchange of oxygen. This paper presents a comparative study for various techniques for classifying the RBCs as normal, or abnormal (anemic) using WEKA. WEKA is an open source consists of different machine learning algorithms for data mining applications. The algorithm tested are Radial Basis Function neural network, Support vector machine, and K-Nearest Neighbors algorithm. Two sets of combined features were utilized for classification of blood cells images. The first set, exclusively consist of geometrical features, was used to identify whether the tested blood cell has a spherical shape or non-spherical cells. While the second set, consist mainly of textural features was used to recognize the types of the spherical cells. We have provided an evaluation based on applying these classification methods to our RBCs image dataset which were obtained from Serdang Hospital-alaysia, and measuring the accuracy of test results. The best achieved classification rates are 97%, 98%, and 79% for Support vector machines, Radial Basis Function neural network, and K-Nearest Neighbors algorithm respectively.

Keywords: K-nearest neighbors algorithm, radial basis function neural network, red blood cells, support vector machine

Procedia PDF Downloads 374

Authors: Yasser M. Saad, Amr A. El Hanafy, Saleh A. Alkarim, Hussein A. Almehdar, Elrashdy M. Redwan

Abstract:

Camels are substantial providers of transport, milk, sport, meat, shelter, security and capital in many countries, particularly in Saudi Arabia. Inter simple sequence repeat technique was used to detect the genetic variations among some camel breeds (Majaheim, Safra, Wadah, and Hamara). Actual number of alleles, effective number of alleles, gene diversity, Shannon’s information index and polymorphic bands were calculated for each evaluated camel breed. Neighbor-joining tree that re-constructed for evaluated these camel breeds showed that, Hamara breed is distantly related from the other evaluated camels. In addition, the polymorphic sites, haplotypes and nucleotide diversity were identified for some camelidae cox1 gene sequences (obtained from NCBI). The distance value between C. bactrianus and C. dromedarius (0.072) was relatively low. Analysis of genetic diversity is an important way for conserving Camelus dromedarius genetic resources.

Keywords: camel, genetics, ISSR, neighbor-joining

Procedia PDF Downloads 441

Authors: Fadlan Atmaja Nursiwan, Ugi Kurnia Gusti

Abstract:

Garba Hill, located in Tekana Village, South Sumatera Province is comprised to South Sumatra Basin and classified as back arc basin. This area is entered as an active margin of Sundaland which experiences subduction several times since Mesozoic to recent time. The traces of Mesozoic subduction in the southern part of Sumatra island are exposed in Garba Hill area. The aim of this investigation is to study the tectonic changes in the first phase in Mesozoic era at the active margin of Sundaland which causes the rocks assemblage in Garba hill consist of continental and oceanic plate rocks which the correlation between those rocks show indistinct relation. This investigation is conducted by field observation in Tekana village and Lubar Village, Muara Dua, South Sumatra along with laboratory analysis included fossil and geochemistry analysis of radiolarian chert, petrography analysis of granite and basalt, and structural modelling. Fossil and geochemistry analysis of radiolarian chert and geochemistry of granite rocks shown the relation between the two rocks and Mesozoic subduction of Woyla terrane on western margin of Sundaland. Petrography analysis from granite and basalt depict the tectonic affinity of rocks. Moreover, structural analysis showed the changes of lineation direction from N-S to WNW-ESE.

Keywords: granite, mesozoic, radiolarian, subduction traces

Procedia PDF Downloads 307

Authors: Kehinde Peter Oyeduntan, Kayode Oshinubi

Abstract:

Nigeria is referred as the ‘Giant of Africa’ due to high population, land mass and large economy. However, it still trails far behind many smaller economies in the continent in terms of maritime operations. As we have seen that the maritime industry is the spark plug for national growth, because it houses the most crucial infrastructure that generates wealth for a nation, it is worrisome that a nation with six seaports lag in maritime activities. In this research, we have studied how the Gross Domestic Product (GDP) of the maritime transport influences the Nigerian economy. To do this, we applied Simple Linear Regression (SLR), Support Vector Machine (SVM), Polynomial Regression Model (PRM), Generalized Additive Model (GAM) and Generalized Linear Mixed Model (GLMM) to model the relationship between the nation’s Total GDP (TGDP) and the Maritime Transport GDP (MGDP) using a time series data of 20 years. The result showed that the MGDP is statistically significant to the Nigerian economy. Amongst the statistical tool applied, the PRM of order 4 describes the relationship better when compared to other methods. The recommendations presented in this study will guide policy makers and help improve the economy of Nigeria in terms of its GDP.

Keywords: maritime transport, economy, GDP, regression, port

Procedia PDF Downloads 119

Authors: Imen Aouini, Lamia Ben Azzouz

Abstract:

The energy need is growing rapidly due to the population growth and the large new usage of power. Several works put considerable efforts to make the electricity grid more intelligent to reduce essentially energy consumption and provide efficiency and reliability of power systems. The Smart Grid is a complex architecture that covers critical devices and systems vulnerable to significant attacks. Hence, security is a crucial factor for the success and the wide deployment of Smart Grids. In this paper, we present security issues of the Smart Grid architecture and we highlight open issues that will make the Smart Grid security a challenging research area in the future.

Keywords: smart grids, smart meters, home area network, neighbor area network

Procedia PDF Downloads 394

Authors: M. T. Alodat

Abstract:

In this paper, we propose a generalization to the Gaussian process regression(GPR) model called the extended skew Gaussian process for regression(ESGPr) model. The ESGPR model works better than the GPR model when the errors are skewed. We derive the predictive distribution for the ESGPR model at a new input. Also we apply the ESGPR model to FOREX data and we find that it fits the Forex data better than the GPR model.

Keywords: extended skew normal distribution, Gaussian process for regression, predictive distribution, ESGPr model

Procedia PDF Downloads 522

Authors: Kajingulu Malandala, Ranganai Edmore

Abstract:

The asymmetric Laplace distribution (ADL) is commonly used as the likelihood function of the Bayesian quantile regression, and it offers different families of likelihood method for quantile regression. Notwithstanding their popularity and practicality, ADL is not smooth and thus making it difficult to maximize its likelihood. Furthermore, Bayesian inference is time consuming and the selection of likelihood may mislead the inference, as the Bayes theorem does not automatically establish the posterior inference. Furthermore, ADL does not account for greater skewness and Kurtosis. This paper develops a new aspect of quantile regression approach for count data based on inverse of the cumulative density function of the Poisson, binomial and Delaporte distributions using the integrated nested Laplace Approximations. Our result validates the benefit of using the integrated nested Laplace Approximations and support the approach for count data.

Keywords: quantile regression, Delaporte distribution, count data, integrated nested Laplace approximation

Procedia PDF Downloads 134

Authors: Forrest Kaatz, Adhemar Bultheel

Abstract:

We use an informational statistical mechanics approach to study the catalytic thermodynamics of platinum and palladium cuboctahedral nanoclusters. Nanoclusters and their adatoms are viewed as chemical graphs with a nearest neighbor adjacency matrix. We use the Morse potential to determine bond energies between cluster atoms in a coordination type calculation. We use adsorbate energies calculated from density functional theory (DFT) to study the adatom effects on the thermodynamic quantities, which are derived from a Hamiltonian. Oxygen radical and molecular adsorbates are studied on platinum clusters and hydrogen on palladium clusters. We calculate the entropy, free energy, and total energy as the coverage of adsorbates increases from bridge and hollow sites on the surface. Thermodynamic behavior versus adatom coverage is related to the structural distribution of adatoms on the nanocluster surfaces. The thermodynamic functions are characterized using a simple adsorption model, with linear trends as the coverage of adatoms increases. The data exhibits size effects for the measured thermodynamic properties with cluster diameters between 2 and 5 nm. Entropy and enthalpy calculations of Pt-O2 compare well with previous theoretical data for Pt(111)-O2, and our Pd-H results show similar trends as experimental measurements for Pd-H2 nanoclusters. Our methods are general and may be applied to wide variety of nanocluster adsorbate systems.

Keywords: catalytic thermodynamics, palladium nanocluster absorbates, platinum nanocluster absorbates, statistical mechanics

Procedia PDF Downloads 125

Authors: Ana Paula Camelo, Keila Sanches

Abstract:

The Geographically Weighted Regression (GWR) was proposed in geography literature to allow relationship in a regression model to vary over space. In Brazil, the agricultural exploitation of the Cerrado Biome is the main cause of deforestation. In this study, we propose a methodology using geostatistical methods to characterize the spatial dependence of deforestation in the Cerrado based on agricultural production indicators. Therefore, it was used the set of exploratory spatial data analysis tools (ESDA) and confirmatory analysis using GWR. It was made the calibration a non-spatial model, evaluation the nature of the regression curve, election of the variables by stepwise process and multicollinearity analysis. After the evaluation of the non-spatial model was processed the spatial-regression model, statistic evaluation of the intercept and verification of its effect on calibration. In an analysis of Spearman’s correlation the results between deforestation and livestock was +0.783 and with soybeans +0.405. The model presented R²=0.936 and showed a strong spatial dependence of agricultural activity of soybeans associated to maize and cotton crops. The GWR is a very effective tool presenting results closer to the reality of deforestation in the Cerrado when compared with other analysis.

Keywords: deforestation, geographically weighted regression, land use, spatial analysis

Procedia PDF Downloads 330

Authors: Jameela Ali, Hamid A. Jalab, Loay E. George, Abdul Rahim Ahmad, Azizah Suliman, Karim Al-Jashamy

Abstract:

Red blood cells (RBC) are the most common types of blood cells and are the most intensively studied in cell biology. The lack of RBCs is a condition in which the amount of hemoglobin level is lower than normal and is referred to as “anemia”. Abnormalities in RBCs will affect the exchange of oxygen. This paper presents a comparative study for various techniques for classifyig the red blood cells as normal, or abnormal (anemic) using WEKA. WEKA is an open source consists of different machine learning algorithms for data mining applications. The algorithm tested are Radial Basis Function neural network, Support vector machine, and K-Nearest Neighbors algorithm. Two sets of combined features were utilized for classification of blood cells images. The first set, exclusively consist of geometrical features, was used to identify whether the tested blood cell has a spherical shape or non-spherical cells. While the second set, consist mainly of textural features was used to recognize the types of the spherical cells. We have provided an evaluation based on applying these classification methods to our RBCs image dataset which were obtained from Serdang Hospital-Malaysia, and measuring the accuracy of test results. The best achieved classification rates are 97%, 98%, and 79% for Support vector machines, Radial Basis Function neural network, and K-Nearest Neighbors algorithm respectively

Keywords: red blood cells, classification, radial basis function neural networks, suport vector machine, k-nearest neighbors algorithm

Procedia PDF Downloads 439

Authors: Ahmed BenSaïda

Abstract:

This paper investigates the association between financial technology (FinTech) growth and bank performance in the Gulf Cooperation Council (GCC) region. Application is conducted on a panel dataset containing the annual observations of banks covering the period from 2012 to 2021. FinTech growth is set as an explanatory variable on three proxies of bank performance. These proxies are the return on assets (ROA), return on equity (ROE), and net interest margin (NIM). Moreover, several control variables are added to the model, including bank-specific and macroeconomic variables. The results are significant as all the proxies of the bank performance are negatively affected by the growth of FinTech startups. Consequently, banks are urged to proactively invest in FinTech startups and engage in partnerships to avoid the risk of disruption.

Keywords: financial technology, bank performance, GCC countries, panel regression

Procedia PDF Downloads 48

Authors: Chao Yang, Jinchuan Zhang, Yongqiang Xiong

Abstract:

The Lower Cambrian Niutitang Formation shale (NFS) deposited in the marine deep-shelf environment in Southeast Upper Yangtze (SUY), possess excellent source rock basis for shale gas generation, however, it is currently challenged by being over-mature with strong tectonic deformations, leading to much uncertainty of gas-bearing potential. With emphasis on the shale gas enrichment of the NFS, analyses were made based on the regional gas-bearing differences obtained from field gas-desorption testing of 18 geological survey wells across the study area. Results show that the NFS bears low gas content of 0.2-2.5 m³/t, and the eastern region of SUY is higher than the western region in gas content. Moreover, the methane fraction also presents the similar regional differentiation with the western region less than 10 vol.% while the eastern region generally more than 70 vol.%. Through the analysis of geological theory, the following conclusions are drawn: Depositional environment determines the gas-enriching zones. In the western region, the Dengying Formation underlying the NFS in unconformity contact was mainly plateau facies dolomite with caves and thereby bears poor gas-sealing ability. Whereas the Laobao Formation underling the NFS in eastern region was a set of siliceous rocks of shelf-slope facies, which can effectively prevent the shale gas from escaping away from the NFS. The tectonic conditions control the gas-enriching bands in the SUY, which is located in the fold zones formed by the thrust of the Southern China plate towards to the Sichuan Basin. Compared with the western region located in the trough-like folds, the eastern region at the fold-thrust belts was uplifted early and deformed weakly, resulting in the relatively less mature level and relatively slight tectonic deformation of the NFS. Faults determine whether shale gas can be accumulated in large scale. Four deep and large normal faults in the study area cut through the Niutitang Formation to the Sinian strata, directly causing a large spillover of natural gas in the adjacent areas. For the secondary faults developed within the shale formation, the reverse faults generally have a positive influence on the shale accumulation while the normal faults perform the opposite influence. Overall, shale gas enrichment targets of the NFS, are the areas with certain thickness of siliceous rocks at the basement of the Niutitang Formation, and near the margin of the paleouplift with less developed faults. These findings provide direction for shale gas exploration in South China, and also provide references for the areas with similar geological conditions all over the world.

Keywords: over-mature marine shale, shale gas accumulation, structure-complicated area, Southeast Upper Yangtze

Procedia PDF Downloads 121

Authors: Rohini Hariharan, Yazhini R., Blessy Maria Mathew

Abstract:

The task of detecting email spam is a very important one in the era of digital technology that needs effective ways of curbing unwanted messages. This paper presents an approach aimed at making email spam categorization algorithms transparent, reliable and more trustworthy by incorporating Local Interpretable Model-agnostic Explanations (LIME). Our technique assists in providing interpretable explanations for specific classifications of emails to help users understand the decision-making process by the model. In this study, we developed a complete pipeline that incorporates LIME into the spam classification framework and allows creating simplified, interpretable models tailored to individual emails. LIME identifies influential terms, pointing out key elements that drive classification results, thus reducing opacity inherent in conventional machine learning models. Additionally, we suggest a visualization scheme for displaying keywords that will improve understanding of categorization decisions by users. We test our method on a diverse email dataset and compare its performance with various baseline models, such as Gaussian Naive Bayes, Multinomial Naive Bayes, Bernoulli Naive Bayes, Support Vector Classifier, K-Nearest Neighbors, Decision Tree, and Logistic Regression. Our testing results show that our model surpasses all other models, achieving an accuracy of 96.59% and a precision of 99.12%.

Keywords: text classification, LIME (local interpretable model-agnostic explanations), stemming, tokenization, logistic regression.

Procedia PDF Downloads 18

Authors: Kang-Mo Jung

Abstract:

The use of regularization for statistical methods has become popular. The least absolute shrinkage and selection operator (LASSO) framework has become the standard tool for sparse regression. However, it is well known that the LASSO is sensitive to outliers or leverage points. We consider a new robust estimation which is composed of the weighted loss function of the pairwise difference of residuals and the adaptive penalty function regulating the tuning parameter for each variable. Rank regression is resistant to regression outliers, but not to leverage points. By adopting a weighted loss function, the proposed method is robust to leverage points of the predictor variable. Furthermore, the adaptive penalty function gives us good statistical properties in variable selection such as oracle property and consistency. We develop an efficient algorithm to compute the proposed estimator using basic functions in program R. We used an optimal tuning parameter based on the Bayesian information criterion (BIC). Numerical simulation shows that the proposed estimator is effective for analyzing real data set and contaminated data.

Keywords: adaptive penalty function, robust penalized regression, variable selection, weighted rank regression

Procedia PDF Downloads 432

Authors: Xiaobo Liu, Rakesh Mishra, Yun Zhang

Abstract:

Continuous monitoring of forest canopy height with large coverage is essential for obtaining forest carbon stocks and emissions, quantifying biomass estimation, analyzing vegetation coverage, and determining biodiversity. LiDAR can be used to collect accurate woody vegetation structure such as canopy height. However, LiDAR’s coverage is usually limited because of its high cost and limited maneuverability, which constrains its use for dynamic and large area forest canopy monitoring. On the other hand, optical satellite images, like Sentinel-2, have the ability to cover large forest areas with a high repeat rate, but they do not have height information. Hence, exploring the solution of integrating LiDAR data and Sentinel-2 images to enlarge the coverage of forest canopy height prediction and increase the prediction repeat rate has been an active research topic in the environmental remote sensing community. In this study, we explore the potential of training a Random Forest Regression (RFR) model and a Convolutional Neural Network (CNN) model, respectively, to develop two predictive models for predicting and validating the forest canopy height of the Acadia Forest in New Brunswick, Canada, with a 10m ground sampling distance (GSD), for the year 2018 and 2021. Two 10m airborne LiDAR-derived canopy height models, one for 2018 and one for 2021, are used as ground truth to train and validate the RFR and CNN predictive models. To evaluate the prediction performance of the trained RFR and CNN models, two new predicted canopy height maps (CHMs), one for 2018 and one for 2021, are generated using the trained RFR and CNN models and 10m Sentinel-2 images of 2018 and 2021, respectively. The two 10m predicted CHMs from Sentinel-2 images are then compared with the two 10m airborne LiDAR-derived canopy height models for accuracy assessment. The validation results show that the mean absolute error (MAE) for year 2018 of the RFR model is 2.93m, CNN model is 1.71m; while the MAE for year 2021 of the RFR model is 3.35m, and the CNN model is 3.78m. These demonstrate the feasibility of using the RFR and CNN models developed in this research for predicting large-coverage forest canopy height at 10m spatial resolution and a high revisit rate.

Keywords: remote sensing, forest canopy height, LiDAR, Sentinel-2, artificial intelligence, random forest regression, convolutional neural network

Procedia PDF Downloads 55

Authors: Karina Zaccari, Ernesto Cordeiro Marujo

Abstract:

This paper presents a Machine Learning (ML) approach to support Meningitis diagnosis in patients at a children’s hospital in Sao Paulo, Brazil. The aim is to use ML techniques to reduce the use of invasive procedures, such as cerebrospinal fluid (CSF) collection, as much as possible. In this study, we focus on predicting the probability of Meningitis given the results of a blood and urine laboratory tests, together with the analysis of pain or other complaints from the patient. We tested a number of different ML algorithms, including: Adaptative Boosting (AdaBoost), Decision Tree, Gradient Boosting, K-Nearest Neighbors (KNN), Logistic Regression, Random Forest and Support Vector Machines (SVM). Decision Tree algorithm performed best, with 94.56% and 96.18% accuracy for training and testing data, respectively. These results represent a significant aid to doctors in diagnosing Meningitis as early as possible and in preventing expensive and painful procedures on some children.

Keywords: machine learning, medical diagnosis, meningitis detection, pediatric research

Procedia PDF Downloads 122

Authors: Arfan Ali Nagra, Tariq Shahzad, Meshal Alharbi, Khalid Masood Khan, Muhammad Mugees Asif, Taher M. Ghazal, Khmaies Ouahada

Abstract:

Gene selection is an essential step for the classification of microarray cancer data. Gene expression cancer data (DNA microarray) facilitates computing the robust and concurrent expression of various genes. Particle swarm optimization (PSO) requires simple operators and less number of parameters for tuning the model in gene selection. The selection of a prognostic gene with small redundancy is a great challenge for the researcher as there are a few complications in PSO based selection method. In this research, a new variant of PSO (Self-inertia weight adaptive PSO) has been proposed. In the proposed algorithm, SIW-APSO-ELM is explored to achieve gene selection prediction accuracies. This new algorithm balances the exploration capabilities of the improved inertia weight adaptive particle swarm optimization and the exploitation. The self-inertia weight adaptive particle swarm optimization (SIW-APSO) is used to search the solution. The SIW-APSO is updated with an evolutionary process in such a way that each particle iteratively improves its velocities and positions. The extreme learning machine (ELM) has been designed for the selection procedure. The proposed method has been to identify a number of genes in the cancer dataset. The classification algorithm contains ELM, K- centroid nearest neighbor (KCNN), and support vector machine (SVM) to attain high forecast accuracy as compared to the start-of-the-art methods on microarray cancer datasets that show the effectiveness of the proposed method.

Keywords: microarray cancer, improved PSO, ELM, SVM, evolutionary algorithms

Procedia PDF Downloads 52

Authors: Benjamin Leiby, Darryl Ahner

Abstract:

This study demonstrates an alternative stochastic imputation approach for large datasets when preferred commercial packages struggle to iterate due to numerical problems. A large country conflict dataset motivates the search to impute missing values well over a common threshold of 20% missingness. The methodology capitalizes on correlation while using model residuals to provide the uncertainty in estimating unknown values. Examination of the methodology provides insight toward choosing linear or nonlinear modeling terms. Static tolerances common in most packages are replaced with tailorable tolerances that exploit residuals to fit each data element. The methodology evaluation includes observing computation time, model fit, and the comparison of known values to replaced values created through imputation. Overall, the country conflict dataset illustrates promise with modeling first-order interactions while presenting a need for further refinement that mimics predictive mean matching.

Keywords: correlation, country conflict, imputation, stochastic regression

Procedia PDF Downloads 91

Authors: Filippo Portera

Abstract:

Usually standard algorithms employ a loss where each error is the mere absolute difference between the true value and the prediction, in case of a regression task. In the present, we present several error weighting schemes that are a generalization of the consolidated routine. We study both a binary classification model for Support Vextor Classification and a regression net for Multylayer Perceptron. Results proves that the error is never worse than the standard procedure and several times it is better.

Keywords: loss, binary-classification, MLP, weights, regression

Procedia PDF Downloads 64

Authors: P. Vanichkobchinda

Abstract:

The Logistics Transportation techniques, Open Vehicle Routing (OVR) is an approach toward transportation cost reduction, especially for long distance pickup and delivery nodes. The outstanding characteristic of OVR is that the route starting node and ending node are not necessary the same as in typical vehicle routing problems. This advantage enables the routing to flow continuously and the vehicle does not always return to its home base. This research aims to develop a heuristic for the open vehicle routing problem with pickup and delivery under time window and loading capacity constraints to minimize the total distance. The proposed heuristic is developed based on the Insertion method, which is a simple method and suitable for the rapid calculation that allows insertion of the new additional transportation requirements along the original paths. According to the heuristic analysis, cost comparisons between the proposed heuristic and companies are using method, nearest neighbor method show that the insertion heuristic. Moreover, the proposed heuristic gave superior solutions in all types of test problems. In conclusion, the proposed heuristic can effectively and efficiently solve the open vehicle routing. The research indicates that the improvement of new transport's calculation and the open vehicle routing with "Insertion Heuristic" represent a better outcome with 34.3 percent in average. in cost savings. Moreover, the proposed heuristic gave superior solutions in all types of test problems. In conclusion, the proposed heuristic can effectively and efficiently solve the open vehicle routing.

Keywords: business competitiveness, cost reduction, SMEs, logistics transportation, VRP

Procedia PDF Downloads 660

Authors: Partha Protim Majumder, Sajeeb Das, Sharun Akter Khushbu

Abstract:

Bengali is widely spoken in the world, but Bengali speech recognition has not received much attention. Here, we are conducting the toughest task because it must be performed in a noisy place in our study. Another challenge we overcome is dealing with speeches and collecting data on third genders, and our approach is to recognize the gender in speeches. All of the Bangla speech samples used in this study were short and were taken from real-life situations. We employed the male, female, and third-gender categories of speech. In this study, we derive the feature from the spoken word. We used MFCC(1-20), ZCR,rolloff,spec_cen, RMSE, and chroma_stft. Here, we used the algorithms Gboost, Random Forest, K-Nearest Neighbors (KNN), Decision Tree, Naive Bayes, and Logistic Regression (LR) to assess the performance of recognition metrics, and we got the highest performance from random forest in recognizing the gender of the speeches.

Keywords: MFCC, ZCR, Bengali, LR, RMSE, roll-off, Gboost

Procedia PDF Downloads 34

Authors: Ghada Abo-Zaid

Abstract:

Introduction: Oil is one of the most income source in Bahrain. Low oil price influence on the economy growth and the investment rate in Bahrain. For example, the economic growth was 3.7% in 2012, and it reduced to 2.9% in 2015. Investment rate was 9.8% in 2012, and it is reduced to be 5.9% and -12.1% in 2014 and 2015, respectively. The inflation rate is increased to the peak point in 2013 with 3.3 %. Objectives: The objectives here are to build statistical models to examine the effect of the interest rate inflation rate on the growth economy in Bahrain from 2000 to 2018. Methods: This study based on 18 years, and the multiple regression model is used for the analysis. All of the missing data are omitted from the analysis. Results: Regression model is used to examine the association between the Growth national product (GNP), the inflation rate, and real interest rate. We found that (i) Increase the real interest rate decrease the GNP. (ii) Increase the inflation rate does not effect on the growth economy in Bahrain since the average of the inflation rate was almost 2%, and this is considered as a low percentage. Conclusion: There is a positive impact of the real interest rate on the GNP in Bahrain. While the inflation rate does not show any negative influence on the GNP as the inflation rate was not large enough to effect negatively on the economy growth rate in Bahrain.

Keywords: growth national product, egypt, regression model, interest rate

Procedia PDF Downloads 126