Search results for: panel data regression models
Commenced in January 2007
Frequency: Monthly
Edition: International
Paper Count: 29461

Search results for: panel data regression models

29071 An Application for Risk of Crime Prediction Using Machine Learning

Authors: Luis Fonseca, Filipe Cabral Pinto, Susana Sargento

Abstract:

The increase of the world population, especially in large urban centers, has resulted in new challenges particularly with the control and optimization of public safety. Thus, in the present work, a solution is proposed for the prediction of criminal occurrences in a city based on historical data of incidents and demographic information. The entire research and implementation will be presented start with the data collection from its original source, the treatment and transformations applied to them, choice and the evaluation and implementation of the Machine Learning model up to the application layer. Classification models will be implemented to predict criminal risk for a given time interval and location. Machine Learning algorithms such as Random Forest, Neural Networks, K-Nearest Neighbors and Logistic Regression will be used to predict occurrences, and their performance will be compared according to the data processing and transformation used. The results show that the use of Machine Learning techniques helps to anticipate criminal occurrences, which contributed to the reinforcement of public security. Finally, the models were implemented on a platform that will provide an API to enable other entities to make requests for predictions in real-time. An application will also be presented where it is possible to show criminal predictions visually.

Keywords: crime prediction, machine learning, public safety, smart city

Procedia PDF Downloads 85
29070 Performance Comparison of Situation-Aware Models for Activating Robot Vacuum Cleaner in a Smart Home

Authors: Seongcheol Kwon, Jeongmin Kim, Kwang Ryel Ryu

Abstract:

We assume an IoT-based smart-home environment where the on-off status of each of the electrical appliances including the room lights can be recognized in a real time by monitoring and analyzing the smart meter data. At any moment in such an environment, we can recognize what the household or the user is doing by referring to the status data of the appliances. In this paper, we focus on a smart-home service that is to activate a robot vacuum cleaner at right time by recognizing the user situation, which requires a situation-aware model that can distinguish the situations that allow vacuum cleaning (Yes) from those that do not (No). We learn as our candidate models a few classifiers such as naïve Bayes, decision tree, and logistic regression that can map the appliance-status data into Yes and No situations. Our training and test data are obtained from simulations of user behaviors, in which a sequence of user situations such as cooking, eating, dish washing, and so on is generated with the status of the relevant appliances changed in accordance with the situation changes. During the simulation, both the situation transition and the resulting appliance status are determined stochastically. To compare the performances of the aforementioned classifiers we obtain their learning curves for different types of users through simulations. The result of our empirical study reveals that naïve Bayes achieves a slightly better classification accuracy than the other compared classifiers.

Keywords: situation-awareness, smart home, IoT, machine learning, classifier

Procedia PDF Downloads 400
29069 Foreign Direct Investment and Its Impact on the Economic Growth of Emerging Economies: Does Ease of Doing Business Matter?

Authors: Mutaju Marobhe, Pastory Dickson

Abstract:

This study explores the role of Foreign Direct Investment (FDI) in stimulating economic growth of emerging economies. FDIs have been associated with higher economic growth rates in developed countries due to the presence of conducive business conditions e.g. advanced financial markets which may accelerate the rate at which FDI boosts economic growth. So this study sets out to evaluate this macroeconomic phenomenon in emerging economies using the case study of Southern Africa Development Community (SADC) countries. The study uses Ease of Doing Business Index as a variable that moderates the relationship between FDI and economic growth. Panel data ranging from 2010 to 2019 from all SADC members are used and due to the unbalanced nature of the data, fixed effects regression analysis with moderation effect is used to assess this phenomenon. The conclusions and recommendations generated by this study will enable emerging economies to depict how they can be able to significantly improve FDI’s role in accelerating economic growth similarly to developed economies.

Keywords: ease of doing business, economic growth, emerging economies, foreign direct investment

Procedia PDF Downloads 124
29068 Shock Compressibility of Iron Alloys Calculated in the Framework of Quantum-Statistical Models

Authors: Maxim A. Kadatskiy, Konstantin V. Khishchenko

Abstract:

Iron alloys are widespread components in various types of structural materials which are exposed to intensive thermal and mechanical loads. Various quantum-statistical cell models with the approximation of self-consistent field can be used for the prediction of the behavior of these materials under extreme conditions. The application of these models is even more valid, the higher the temperature and the density of matter. Results of Hugoniot calculation for iron alloys in the framework of three quantum-statistical (the Thomas–Fermi, the Thomas–Fermi with quantum and exchange corrections and the Hartree–Fock–Slater) models are presented. Results of quantum-statistical calculations are compared with results from other reliable models and available experimental data. It is revealed a good agreement between results of calculation and experimental data for terra pascal pressures. Advantages and disadvantages of this approach are shown.

Keywords: alloy, Hugoniot, iron, terapascal pressure

Procedia PDF Downloads 320
29067 The Impact of Unconditional and Conditional Conservatism on Cost of Equity Capital: A Quantile Regression Approach for MENA Countries

Authors: Khalifa Maha, Ben Othman Hakim, Khaled Hussainey

Abstract:

Prior empirical studies have investigated the economic consequences of accounting conservatism by examining its impact on the cost of equity capital (COEC). However, findings are not conclusive. We assume that inconsistent results of such association may be attributed to the regression models used in data analysis. To address this issue, we re-examine the effect of different dimension of accounting conservatism: unconditional conservatism (U_CONS) and conditional conservatism (C_CONS) on the COEC for a sample of listed firms from Middle Eastern and North Africa (MENA) countries, applying quantile regression (QR) approach developed by Koenker and Basset (1978). While classical ordinary least square (OLS) method is widely used in empirical accounting research, however it may produce inefficient and bias estimates in the case of departures from normality or long tail error distribution. QR method is more powerful than OLS to handle this kind of problem. It allows the coefficient on the independent variables to shift across the distribution of the dependent variable whereas OLS method only estimates the conditional mean effects of a response variable. We find as predicted that U_CONS has a significant positive effect on the COEC however, C_CONS has a negative impact. Findings suggest also that the effect of the two dimensions of accounting conservatism differs considerably across COEC quantiles. Comparing results from QR method with those of OLS, this study throws more lights on the association between accounting conservatism and COEC.

Keywords: unconditional conservatism, conditional conservatism, cost of equity capital, OLS, quantile regression, emerging markets, MENA countries

Procedia PDF Downloads 342
29066 Fine-Scale Modeling the Influencing Factors of Multi-Time Dimensions of Transit Ridership at Station Level: The Study of Guangzhou City

Authors: Dijiang Lyu, Shaoying Li, Zhangzhi Tan, Zhifeng Wu, Feng Gao

Abstract:

Nowadays, China is experiencing rapidly urban rail transit expansions in the world. The purpose of this study is to finely model factors influencing transit ridership at multi-time dimensions within transit stations’ pedestrian catchment area (PCA) in Guangzhou, China. This study was based on multi-sources spatial data, including smart card data, high spatial resolution images, points of interest (POIs), real-estate online data and building height data. Eight multiple linear regression models using backward stepwise method and Geographic Information System (GIS) were created at station-level. According to Chinese code for classification of urban land use and planning standards of development land, residential land-use were divided into three categories: first-level (e.g. villa), second-level (e.g. community) and third-level (e.g. urban villages). Finally, it concluded that: (1) four factors (CBD dummy, number of feeder bus route, number of entrance or exit and the years of station operation) were proved to be positively correlated with transit ridership, but the area of green land-use and water land-use negative correlated instead. (2) The area of education land-use, the second-level and third-level residential land-use were found to be highly connected to the average value of morning peak boarding and evening peak alighting ridership. But the area of commercial land-use and the average height of buildings, were significantly positive associated with the average value of morning peak alighting and evening peak boarding ridership. (3) The area of the second-level residential land-use was rarely correlated with ridership in other regression models. Because private car ownership is still large in Guangzhou now, and some residents living in the community around the stations go to work by transit at peak time, but others are much more willing to drive their own car at non-peak time. The area of the third-level residential land-use, like urban villages, was highly positive correlated with ridership in all models, indicating that residents who live in the third-level residential land-use are the main passenger source of the Guangzhou Metro. (4) The diversity of land-use was found to have a significant impact on the passenger flow on the weekend, but was non-related to weekday. The findings can be useful for station planning, management and policymaking.

Keywords: fine-scale modeling, Guangzhou city, multi-time dimensions, multi-sources spatial data, transit ridership

Procedia PDF Downloads 124
29065 Prediction of Compressive Strength Using Artificial Neural Network

Authors: Vijay Pal Singh, Yogesh Chandra Kotiyal

Abstract:

Structures are a combination of various load carrying members which transfer the loads to the foundation from the superstructure safely. At the design stage, the loading of the structure is defined and appropriate material choices are made based upon their properties, mainly related to strength. The strength of materials kept on reducing with time because of many factors like environmental exposure and deformation caused by unpredictable external loads. Hence, to predict the strength of materials used in structures, various techniques are used. Among these techniques, Non-Destructive Techniques (NDT) are the one that can be used to predict the strength without damaging the structure. In the present study, the compressive strength of concrete has been predicted using Artificial Neural Network (ANN). The predicted strength was compared with the experimentally obtained actual compressive strength of concrete and equations were developed for different models. A good co-relation has been obtained between the predicted strength by these models and experimental values. Further, the co-relation has been developed using two NDT techniques for prediction of strength by regression analysis. It was found that the percentage error has been reduced between the predicted strength by using combined techniques in place of single techniques.

Keywords: rebound, ultra-sonic pulse, penetration, ANN, NDT, regression

Procedia PDF Downloads 401
29064 Low-Cost, Portable Optical Sensor with Regression Algorithm Models for Accurate Monitoring of Nitrites in Environments

Authors: David X. Dong, Qingming Zhang, Meng Lu

Abstract:

Nitrites enter waterways as runoff from croplands and are discharged from many industrial sites. Excessive nitrite inputs to water bodies lead to eutrophication. On-site rapid detection of nitrite is of increasing interest for managing fertilizer application and monitoring water source quality. Existing methods for detecting nitrites use spectrophotometry, ion chromatography, electrochemical sensors, ion-selective electrodes, chemiluminescence, and colorimetric methods. However, these methods either suffer from high cost or provide low measurement accuracy due to their poor selectivity to nitrites. Therefore, it is desired to develop an accurate and economical method to monitor nitrites in environments. We report a low-cost optical sensor, in conjunction with a machine learning (ML) approach to enable high-accuracy detection of nitrites in water sources. The sensor works under the principle of measuring molecular absorptions of nitrites at three narrowband wavelengths (295 nm, 310 nm, and 357 nm) in the ultraviolet (UV) region. These wavelengths are chosen because they have relatively high sensitivity to nitrites; low-cost light-emitting devices (LEDs) and photodetectors are also available at these wavelengths. A regression model is built, trained, and utilized to minimize cross-sensitivities of these wavelengths to the same analyte, thus achieving precise and reliable measurements with various interference ions. The measured absorbance data is input to the trained model that can provide nitrite concentration prediction for the sample. The sensor is built with i) a miniature quartz cuvette as the test cell that contains a liquid sample under test, ii) three low-cost UV LEDs placed on one side of the cell as light sources, with each LED providing a narrowband light, and iii) a photodetector with a built-in amplifier and an analog-to-digital converter placed on the other side of the test cell to measure the power of transmitted light. This simple optical design allows measuring the absorbance data of the sample at the three wavelengths. To train the regression model, absorbances of nitrite ions and their combination with various interference ions are first obtained at the three UV wavelengths using a conventional spectrophotometer. Then, the spectrophotometric data are inputs to different regression algorithm models for training and evaluating high-accuracy nitrite concentration prediction. Our experimental results show that the proposed approach enables instantaneous nitrite detection within several seconds. The sensor hardware costs about one hundred dollars, which is much cheaper than a commercial spectrophotometer. The ML algorithm helps to reduce the average relative errors to below 3.5% over a concentration range from 0.1 ppm to 100 ppm of nitrites. The sensor has been validated to measure nitrites at three sites in Ames, Iowa, USA. This work demonstrates an economical and effective approach to the rapid, reagent-free determination of nitrites with high accuracy. The integration of the low-cost optical sensor and ML data processing can find a wide range of applications in environmental monitoring and management.

Keywords: optical sensor, regression model, nitrites, water quality

Procedia PDF Downloads 49
29063 Analytical Modelling of Surface Roughness during Compacted Graphite Iron Milling Using Ceramic Inserts

Authors: Ş. Karabulut, A. Güllü, A. Güldaş, R. Gürbüz

Abstract:

This study investigates the effects of the lead angle and chip thickness variation on surface roughness during the machining of compacted graphite iron using ceramic cutting tools under dry cutting conditions. Analytical models were developed for predicting the surface roughness values of the specimens after the face milling process. Experimental data was collected and imported to the artificial neural network model. A multilayer perceptron model was used with the back propagation algorithm employing the input parameters of lead angle, cutting speed and feed rate in connection with chip thickness. Furthermore, analysis of variance was employed to determine the effects of the cutting parameters on surface roughness. Artificial neural network and regression analysis were used to predict surface roughness. The values thus predicted were compared with the collected experimental data, and the corresponding percentage error was computed. Analysis results revealed that the lead angle is the dominant factor affecting surface roughness. Experimental results indicated an improvement in the surface roughness value with decreasing lead angle value from 88° to 45°.

Keywords: CGI, milling, surface roughness, ANN, regression, modeling, analysis

Procedia PDF Downloads 429
29062 A Kolmogorov-Smirnov Type Goodness-Of-Fit Test of Multinomial Logistic Regression Model in Case-Control Studies

Authors: Chen Li-Ching

Abstract:

The multinomial logistic regression model is used popularly for inferring the relationship of risk factors and disease with multiple categories. This study based on the discrepancy between the nonparametric maximum likelihood estimator and semiparametric maximum likelihood estimator of the cumulative distribution function to propose a Kolmogorov-Smirnov type test statistic to assess adequacy of the multinomial logistic regression model for case-control data. A bootstrap procedure is presented to calculate the critical value of the proposed test statistic. Empirical type I error rates and powers of the test are performed by simulation studies. Some examples will be illustrated the implementation of the test.

Keywords: case-control studies, goodness-of-fit test, Kolmogorov-Smirnov test, multinomial logistic regression

Procedia PDF Downloads 431
29061 The Sensitivity of Credit Defaults Swaps Premium to Global Risk Factor: Evidence from Emerging Markets

Authors: Oguzhan Cepni, Doruk Kucuksarac, M. Hasan Yilmaz

Abstract:

Changes in the global risk appetite cause co-movement in emerging market risk premiums. However, the sensitivity of the changes in risk premium to the global risk appetite may vary across emerging markets. In this study, how the global risk appetite affects Credit Default Swap (CDS) premiums in emerging markets are analyzed using Principal Component Analysis (PCA) and rolling regressions. The PCA results indicate that the first common component derived by the PCA accounts for almost 76 percent of the common variation in CDS premiums. Additionally, the explanatory power of the first factor seems to be high over the sample period. However, the sensitivity to the global risk factor tends to change over time and across countries. In this regard, fixed effects panel regressions are used to identify the macroeconomic factors driving the heterogeneity across emerging markets. The panel regression results point to the significance of government debt to GDP and international reserves to GDP in explaining sensitivity. Accordingly, countries with lower government debt and higher reserves tend to be less subject to the variations in the global risk appetite.

Keywords: credit default swaps, emerging markets, principal components analysis, sovereign risk

Procedia PDF Downloads 354
29060 Investigating The Nexus Between Energy Deficiency, Environmental Sustainability and Renewable Energy: The Role of Energy Trade in Global Perspectives

Authors: Fahim Ullah, Muhammad Usman

Abstract:

Energy consumption and environmental sustainability are hard challenges of 21st century. Energy richness increases environmental pollution while energy poverty hinders economic growth. Considering these two aspects, present study calculates energy deficiency and examines the role of renewable energy to overcome rising energy deficiency and carbon emission for selected countries from 1990 to 2021. For empirical analysis, this study uses methods of moments panel quantile regression analysis and to check the robustness, study used panel quantile robust analysis. Graphical analysis indicated rising global energy deficiency since last three decades where energy consumption is higher than energy production. Empirical results showed that renewable energy is a significant factor for reducing energy deficiency. Secondly, the energy deficiency increases carbon emission level and again renewable energy decreases emissions level. This study recommends that global energy deficiency and rising carbon emissions can be controlled through structural change in the form of energy transition to replace non-renewable resources with renewable resources.

Keywords: energy deficiency, renewable energy, carbon emission, energy trade, PQL analysis

Procedia PDF Downloads 34
29059 Local Interpretable Model-agnostic Explanations (LIME) Approach to Email Spam Detection

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 22
29058 Hotel and Service Industry in USA: Is It Leveraged? Case Study of Seven Important Hotel Chains

Authors: Azadeh Shahbazi

Abstract:

This study tries to find out the determinants of capital structure in hotel industry in 7 important hotel chains in USA within the period of 12 years of 2000 to 2012. The study is used a panel pooled regression to realize the relation among different variables. Results show that the variables which could make changes in the capital structure of firms are Non-Debt Tax Shield and Tangibility.

Keywords: capital structure, service industry, hospitality, finance

Procedia PDF Downloads 452
29057 Estimation of Coefficients of Ridge and Principal Components Regressions with Multicollinear Data

Authors: Rajeshwar Singh

Abstract:

The presence of multicollinearity is common in handling with several explanatory variables simultaneously due to exhibiting a linear relationship among them. A great problem arises in understanding the impact of explanatory variables on the dependent variable. Thus, the method of least squares estimation gives inexact estimates. In this case, it is advised to detect its presence first before proceeding further. Using the ridge regression degree of its occurrence is reduced but principal components regression gives good estimates in this situation. This paper discusses well-known techniques of the ridge and principal components regressions and applies to get the estimates of coefficients by both techniques. In addition to it, this paper also discusses the conflicting claim on the discovery of the method of ridge regression based on available documents.

Keywords: conflicting claim on credit of discovery of ridge regression, multicollinearity, principal components and ridge regressions, variance inflation factor

Procedia PDF Downloads 387
29056 Sentiment Analysis of Social Media on the Cryptocurrency Price

Authors: Tarek Sadraoui, Ahlem Nasr Othman

Abstract:

Our research deal with studying and testing the effects of social media on the cryptocurrency price during the period 2020-2023. The rise of the phenomena of cryptocurrency in the world raises questions about the importance of sentiment analysis of social media on the price of the cryptocurrency. Using panel data, we show that the positive and negative twits have a positive and statistically significant impact on the price of the cryptocurrency, and neutral twits have exerted a negative and significant effect on the cryptocurrency price. Specifically, we determine the causal relationship, short-term and long-term relationship with ARDL approach between the cryptocurrency price and social media using the Granger causality test.

Keywords: social media, Twitter, Google trend, panel, cryptocurrency

Procedia PDF Downloads 84
29055 Ordinal Regression with Fenton-Wilkinson Order Statistics: A Case Study of an Orienteering Race

Authors: Joonas Pääkkönen

Abstract:

In sports, individuals and teams are typically interested in final rankings. Final results, such as times or distances, dictate these rankings, also known as places. Places can be further associated with ordered random variables, commonly referred to as order statistics. In this work, we introduce a simple, yet accurate order statistical ordinal regression function that predicts relay race places with changeover-times. We call this function the Fenton-Wilkinson Order Statistics model. This model is built on the following educated assumption: individual leg-times follow log-normal distributions. Moreover, our key idea is to utilize Fenton-Wilkinson approximations of changeover-times alongside an estimator for the total number of teams as in the notorious German tank problem. This original place regression function is sigmoidal and thus correctly predicts the existence of a small number of elite teams that significantly outperform the rest of the teams. Our model also describes how place increases linearly with changeover-time at the inflection point of the log-normal distribution function. With real-world data from Jukola 2019, a massive orienteering relay race, the model is shown to be highly accurate even when the size of the training set is only 5% of the whole data set. Numerical results also show that our model exhibits smaller place prediction root-mean-square-errors than linear regression, mord regression and Gaussian process regression.

Keywords: Fenton-Wilkinson approximation, German tank problem, log-normal distribution, order statistics, ordinal regression, orienteering, sports analytics, sports modeling

Procedia PDF Downloads 106
29054 Investigation on Performance of Optical Shutter Panels for Transparent Displays

Authors: Jaehong Kim, Sunhee Park, HongSeop Shin, Kyongho Lim, Suhyun Kwon, Don-Gyou Lee, Pureum Kim, Moojong Lim, JongSang Baek

Abstract:

Transparent displays with OLEDs are the most commonly produced forms of see-through displays on the market or in development. In order to block the visual interruption caused by the light coming from the background, the special panel is combined with transparent displays with OLEDs. There is, however, few studies performance of optical shutter panel for transparent displays until now. This paper, therefore, describes the performance of optical shutter panels. The novel evaluation method was developed by measuring the amount of light which can form a transmitted background image. The new proposed method could tell how recognizable transmitted background images cannot be seen, and is consistent with viewer’s perception.

Keywords: optical shutter panel, optical performance, transparent display, visual interruption

Procedia PDF Downloads 508
29053 Corporate Governance and Firm Performance: Empirical Evidence from India

Authors: G. C. Surya Bahadur, Ranjana Kothari

Abstract:

The paper attempts to analyze linkages between corporate governance and firm performance in India. The study employs a panel data of 50 Nifty companies from 2008 to 2012. Using LSDV panel data model and 2SLS model the study reveals that that good corporate governance practices adopted by companies is positively related with financial performance. Board independence, number of board committees and executive compensation are found to have positive relationship while ownership by promoters and financial leverage have negative relationship with performance. There is existence of bi-directional relationship between corporate governance and financial performance. Companies with sound financial performance are more likely to conform to corporate governance norms and standards and implement sound corporate governance system. The findings indicate that companies can enhance business performance and sustainability by embracing sound corporate governance practices.

Keywords: board structure, corporate governance, executive compensation, ownership structure

Procedia PDF Downloads 448
29052 Support Vector Regression for Retrieval of Soil Moisture Using Bistatic Scatterometer Data at X-Band

Authors: Dileep Kumar Gupta, Rajendra Prasad, Pradeep Kumar, Varun Narayan Mishra, Ajeet Kumar Vishwakarma, Prashant K. Srivastava

Abstract:

An approach was evaluated for the retrieval of soil moisture of bare soil surface using bistatic scatterometer data in the angular range of 200 to 700 at VV- and HH- polarization. The microwave data was acquired by specially designed X-band (10 GHz) bistatic scatterometer. The linear regression analysis was done between scattering coefficients and soil moisture content to select the suitable incidence angle for retrieval of soil moisture content. The 250 incidence angle was found more suitable. The support vector regression analysis was used to approximate the function described by the input-output relationship between the scattering coefficient and corresponding measured values of the soil moisture content. The performance of support vector regression algorithm was evaluated by comparing the observed and the estimated soil moisture content by statistical performance indices %Bias, root mean squared error (RMSE) and Nash-Sutcliffe Efficiency (NSE). The values of %Bias, root mean squared error (RMSE) and Nash-Sutcliffe Efficiency (NSE) were found 2.9451, 1.0986, and 0.9214, respectively at HH-polarization. At VV- polarization, the values of %Bias, root mean squared error (RMSE) and Nash-Sutcliffe Efficiency (NSE) were found 3.6186, 0.9373, and 0.9428, respectively.

Keywords: bistatic scatterometer, soil moisture, support vector regression, RMSE, %Bias, NSE

Procedia PDF Downloads 397
29051 Comparison Study of Machine Learning Classifiers for Speech Emotion Recognition

Authors: Aishwarya Ravindra Fursule, Shruti Kshirsagar

Abstract:

In the intersection of artificial intelligence and human-centered computing, this paper delves into speech emotion recognition (SER). It presents a comparative analysis of machine learning models such as K-Nearest Neighbors (KNN),logistic regression, support vector machines (SVM), decision trees, ensemble classifiers, and random forests, applied to SER. The research employs four datasets: Crema D, SAVEE, TESS, and RAVDESS. It focuses on extracting salient audio signal features like Zero Crossing Rate (ZCR), Chroma_stft, Mel Frequency Cepstral Coefficients (MFCC), root mean square (RMS) value, and MelSpectogram. These features are used to train and evaluate the models’ ability to recognize eight types of emotions from speech: happy, sad, neutral, angry, calm, disgust, fear, and surprise. Among the models, the Random Forest algorithm demonstrated superior performance, achieving approximately 79% accuracy. This suggests its suitability for SER within the parameters of this study. The research contributes to SER by showcasing the effectiveness of various machine learning algorithms and feature extraction techniques. The findings hold promise for the development of more precise emotion recognition systems in the future. This abstract provides a succinct overview of the paper’s content, methods, and results.

Keywords: comparison, ML classifiers, KNN, decision tree, SVM, random forest, logistic regression, ensemble classifiers

Procedia PDF Downloads 22
29050 Automatic Adult Age Estimation Using Deep Learning of the ResNeXt Model Based on CT Reconstruction Images of the Costal Cartilage

Authors: Ting Lu, Ya-Ru Diao, Fei Fan, Ye Xue, Lei Shi, Xian-e Tang, Meng-jun Zhan, Zhen-hua Deng

Abstract:

Accurate adult age estimation (AAE) is a significant and challenging task in forensic and archeology fields. Attempts have been made to explore optimal adult age metrics, and the rib is considered a potential age marker. The traditional way is to extract age-related features designed by experts from macroscopic or radiological images followed by classification or regression analysis. Those results still have not met the high-level requirements for practice, and the limitation of using feature design and manual extraction methods is loss of information since the features are likely not designed explicitly for extracting information relevant to age. Deep learning (DL) has recently garnered much interest in imaging learning and computer vision. It enables learning features that are important without a prior bias or hypothesis and could be supportive of AAE. This study aimed to develop DL models for AAE based on CT images and compare their performance to the manual visual scoring method. Chest CT data were reconstructed using volume rendering (VR). Retrospective data of 2500 patients aged 20.00-69.99 years were obtained between December 2019 and September 2021. Five-fold cross-validation was performed, and datasets were randomly split into training and validation sets in a 4:1 ratio for each fold. Before feeding the inputs into networks, all images were augmented with random rotation and vertical flip, normalized, and resized to 224×224 pixels. ResNeXt was chosen as the DL baseline due to its advantages of higher efficiency and accuracy in image classification. Mean absolute error (MAE) was the primary parameter. Independent data from 100 patients acquired between March and April 2022 were used as a test set. The manual method completely followed the prior study, which reported the lowest MAEs (5.31 in males and 6.72 in females) among similar studies. CT data and VR images were used. The radiation density of the first costal cartilage was recorded using CT data on the workstation. The osseous and calcified projections of the 1 to 7 costal cartilages were scored based on VR images using an eight-stage staging technique. According to the results of the prior study, the optimal models were the decision tree regression model in males and the stepwise multiple linear regression equation in females. Predicted ages of the test set were calculated separately using different models by sex. A total of 2600 patients (training and validation sets, mean age=45.19 years±14.20 [SD]; test set, mean age=46.57±9.66) were evaluated in this study. Of ResNeXt model training, MAEs were obtained with 3.95 in males and 3.65 in females. Based on the test set, DL achieved MAEs of 4.05 in males and 4.54 in females, which were far better than the MAEs of 8.90 and 6.42 respectively, for the manual method. Those results showed that the DL of the ResNeXt model outperformed the manual method in AAE based on CT reconstruction of the costal cartilage and the developed system may be a supportive tool for AAE.

Keywords: forensic anthropology, age determination by the skeleton, costal cartilage, CT, deep learning

Procedia PDF Downloads 51
29049 The Relationship between Coping Styles and Internet Addiction among High School Students

Authors: Adil Kaval, Digdem Muge Siyez

Abstract:

With the negative effects of internet use in a person's life, the use of the Internet has become an issue. This subject was mostly considered as internet addiction, and it was investigated. In literature, it is noteworthy that some theoretical models have been proposed to explain the reasons for internet addiction. In addition to these theoretical models, it may be thought that the coping style for stressing events can be a predictor of internet addiction. It was aimed to test with logistic regression the effect of high school students' coping styles on internet addiction levels. Sample of the study consisted of 770 Turkish adolescents (471 girls, 299 boys) selected from high schools in the 2017-2018 academic year in İzmir province. Internet Addiction Test, Coping Scale for Child and Adolescents and a demographic information form were used in this study. The results of the logistic regression analysis indicated that the model of coping styles predicted internet addiction provides a statistically significant prediction of internet addiction. Gender does not predict whether or not to be addicted to the internet. The active coping style is not effective on internet addiction levels, while the avoiding and negative coping style are effective on internet addiction levels. With this model, % 79.1 of internet addiction in high school is estimated. The Negelkerke pseudo R2 indicated that the model accounted for %35 of the total variance. The results of this study on Turkish adolescents are similar to the results of other studies in the literature. It can be argued that avoiding and negative coping styles are important risk factors in the development of internet addiction.

Keywords: adolescents, coping, internet addiction, regression analysis

Procedia PDF Downloads 150
29048 Investigation on Optical Performance of Operational Shutter Panels for Transparent Displays

Authors: Jaehong Kim, Sunhee Park, HongSeop Shin, Kyongho Lim, Suhyun Kwon, Don-Gyou Lee, Pureum Kim, Moojong Lim, JongSang Baek

Abstract:

Transparent displays with OLEDs are the most commonly produced forms of see-through displays on the market or in development. In order to block the visual interruption caused by the light coming from the background, the special panel is combined with transparent displays with OLEDs. There is, however, few studies optical performance of operational shutter panel for transparent displays until now. This paper, therefore, describes the optical performance of operational shutter panels. The novel evaluation method was developed by measuring the amount of light which can form a transmitted background image. The new proposed method could tell how recognize transmitted background images cannot be seen, and is consistent with viewer’s perception.

Keywords: transparent display, operational shutter panel, optical performance, OLEDs

Procedia PDF Downloads 419
29047 The Intention to Use Telecare in People of Fall Experience: Application of Fuzzy Neural Network

Authors: Jui-Chen Huang, Shou-Hsiung Cheng

Abstract:

This study examined their willingness to use telecare for people who have had experience falling in the last three months in Taiwan. This study adopted convenience sampling and a structural questionnaire to collect data. It was based on the definition and the constructs related to the Health Belief Model (HBM). HBM is comprised of seven constructs: perceived benefits (PBs), perceived disease threat (PDT), perceived barriers of taking action (PBTA), external cues to action (ECUE), internal cues to action (ICUE), attitude toward using (ATT), and behavioral intention to use (BI). This study adopted Fuzzy Neural Network (FNN) to put forward an effective method. It shows the dependence of ATT on PB, PDT, PBTA, ECUE, and ICUE. The training and testing data RMSE (root mean square error) are 0.028 and 0.166 in the FNN, respectively. The training and testing data RMSE are 0.828 and 0.578 in the regression model, respectively. On the other hand, as to the dependence of ATT on BI, as presented in the FNN, the training and testing data RMSE are 0.050 and 0.109, respectively. The training and testing data RMSE are 0.529 and 0.571 in the regression model, respectively. The results show that the FNN method is better than the regression analysis. It is an effective and viable good way.

Keywords: fall, fuzzy neural network, health belief model, telecare, willingness

Procedia PDF Downloads 165
29046 A Monte Carlo Fuzzy Logistic Regression Framework against Imbalance and Separation

Authors: Georgios Charizanos, Haydar Demirhan, Duygu Icen

Abstract:

Two of the most impactful issues in classical logistic regression are class imbalance and complete separation. These can result in model predictions heavily leaning towards the imbalanced class on the binary response variable or over-fitting issues. Fuzzy methodology offers key solutions for handling these problems. However, most studies propose the transformation of the binary responses into a continuous format limited within [0,1]. This is called the possibilistic approach within fuzzy logistic regression. Following this approach is more aligned with straightforward regression since a logit-link function is not utilized, and fuzzy probabilities are not generated. In contrast, we propose a method of fuzzifying binary response variables that allows for the use of the logit-link function; hence, a probabilistic fuzzy logistic regression model with the Monte Carlo method. The fuzzy probabilities are then classified by selecting a fuzzy threshold. Different combinations of fuzzy and crisp input, output, and coefficients are explored, aiming to understand which of these perform better under different conditions of imbalance and separation. We conduct numerical experiments using both synthetic and real datasets to demonstrate the performance of the fuzzy logistic regression framework against seven crisp machine learning methods. The proposed framework shows better performance irrespective of the degree of imbalance and presence of separation in the data, while the considered machine learning methods are significantly impacted.

Keywords: fuzzy logistic regression, fuzzy, logistic, machine learning

Procedia PDF Downloads 44
29045 Bridging the Data Gap for Sexism Detection in Twitter: A Semi-Supervised Approach

Authors: Adeep Hande, Shubham Agarwal

Abstract:

This paper presents a study on identifying sexism in online texts using various state-of-the-art deep learning models based on BERT. We experimented with different feature sets and model architectures and evaluated their performance using precision, recall, F1 score, and accuracy metrics. We also explored the use of pseudolabeling technique to improve model performance. Our experiments show that the best-performing models were based on BERT, and their multilingual model achieved an F1 score of 0.83. Furthermore, the use of pseudolabeling significantly improved the performance of the BERT-based models, with the best results achieved using the pseudolabeling technique. Our findings suggest that BERT-based models with pseudolabeling hold great promise for identifying sexism in online texts with high accuracy.

Keywords: large language models, semi-supervised learning, sexism detection, data sparsity

Procedia PDF Downloads 48
29044 On Panel Data Analysis of Factors on Economic Advances in Some African Countries

Authors: Ayoola Femi J., Kayode Balogun

Abstract:

In some African Countries, increase in Gross Domestic Products (GDP) has not translated to real development as expected by common-man in his household. For decades, a lot of contests on economic growth and development has been a nagging issues. The focus of this study is to analysing the effects of economic determinants/factors on economic advances in some African Countries by employing panel data analysis. The yearly (1990-2013) data were obtained from the world economic outlook database of the International Monetary Fund (IMF), for probing the effects of these variables on growth rate in some selected African countries which include: Nigeria, Algeria, Angola, Benin, Botswana, Burundi, Cape-Verde, Cameroun, Central African Republic, Chad, Republic Of Congo, Cote di’ Voire, Egypt, Equatorial-Guinea, Ethiopia, Gabon, Ghana, Guinea Bissau, Kenya, Lesotho, Madagascar, Mali, Mauritius, Morocco, Mozambique, Niger, Rwanda, Senegal, Seychelles, Sierra Leone, South Africa, Sudan, Swaziland, Tanzania, Togo, Tunisia, and Uganda. The effects of 6 macroeconomic variables on GDP were critically examined. We used 37 Countries GDP as our dependent variable and 6 independent variables used in this study include: Total Investment (totinv), Inflation (inf), Population (popl), current account balance (cab), volume of imports of goods and services (vimgs), and volume of exports of goods and services (vexgs). The results of our analysis shows that total investment, population and volume of exports of goods and services strongly affect the economic growth. We noticed that population of these selected countries positively affect the GDP while total investment and volume of exports negatively affect GDP. On the contrary, inflation, current account balance and volume of imports of goods and services’ contribution to the GDP are insignificant. The results of our analysis shows that total investment, population and volume of exports of goods and services strongly affect the economic growth. We noticed that population of these selected countries positively affect the GDP while total investment and volume of exports negatively affect GDP. On the contrary, inflation, current account balance and volume of imports of goods and services’ contribution to the GDP are insignificant. The results of this study would be useful for individual African governments for developing a suitable and appropriate economic policies and strategies. It will also help investors to understand the economic nature and viability of Africa as a continent as well as its individual countries.

Keywords: African countries, economic growth and development, gross domestic products, static panel data models

Procedia PDF Downloads 452
29043 Determinants of Profitability in Indian Pharmaceutical Firms in the New Intellectual Property Rights Regime

Authors: Shilpi Tyagi, D. K. Nauriyal

Abstract:

This study investigates the firm level determinants of profitability of Indian drug and pharmaceutical industry. The study uses inflation adjusted panel data for a period 2000-2013 and applies OLS regression model with Driscoll-Kraay standard errors. It has been found that export intensity, A&M intensity, firm’s market power and stronger patent regime dummy have exercised positive influence on profitability. The negative and statistically significant influence of R&D intensity and raw material import intensity points to the need for firms to adopt suitable investment strategies. The study suggests that firms are required to pay far more attention to optimize their operating expenditures, advertisement and marketing expenditures and improve their export orientation, as part of the long term strategy.

Keywords: Indian pharmaceutical industry, profits, TRIPS, performance

Procedia PDF Downloads 416
29042 Forecasting the Sea Level Change in Strait of Hormuz

Authors: Hamid Goharnejad, Amir Hossein Eghbali

Abstract:

Recent investigations have demonstrated the global sea level rise due to climate change impacts. In this study climate changes study the effects of increasing water level in the strait of Hormuz. The probable changes of sea level rise should be investigated to employ the adaption strategies. The climatic output data of a GCM (General Circulation Model) named CGCM3 under climate change scenario of A1b and A2 were used. Among different variables simulated by this model, those of maximum correlation with sea level changes in the study region and least redundancy among themselves were selected for sea level rise prediction by using stepwise regression. One models of Discrete Wavelet artificial Neural Network (DWNN) was developed to explore the relationship between climatic variables and sea level changes. In these models, wavelet was used to disaggregate the time series of input and output data into different components and then ANN was used to relate the disaggregated components of predictors and predictands to each other. The results showed in the Shahid Rajae Station for scenario A1B sea level rise is among 64 to 75 cm and for the A2 Scenario sea level rise is among 90 to 105 cm. Furthermore the result showed a significant increase of sea level at the study region under climate change impacts, which should be incorporated in coastal areas management.

Keywords: climate change scenarios, sea-level rise, strait of Hormuz, forecasting

Procedia PDF Downloads 244