Search results for: Countries Classification

Authors: Kamel Belammi, Houria Fatrim

Abstract:

imbalanced data set, a problem often found in real world application, can cause seriously negative effect on classification performance of machine learning algorithms. There have been many attempts at dealing with classification of imbalanced data sets. In medical diagnosis classification, we often face the imbalanced number of data samples between the classes in which there are not enough samples in rare classes. In this paper, we proposed a learning method based on a cost sensitive extension of Least Mean Square (LMS) algorithm that penalizes errors of different samples with different weight and some rules of thumb to determine those weights. After the balancing phase, we applythe different classifiers (support vector machine (SVM), k- nearest neighbor (KNN) and multilayer neuronal networks (MNN)) for balanced data set. We have also compared the obtained results before and after balancing method.

Keywords: multilayer neural networks, k- nearest neighbor, support vector machine, imbalanced medical data, least mean square algorithm, diabetes

Procedia PDF Downloads 531

Authors: Adrián Esteban Ortiz-Valera, Angélica Lozano

Abstract:

In developing countries, informal trade is relevant, but it has been little studied in urban freight transport (UFT) context, although it is a challenge due to the non- contemplated demand it produces and the operational limitations it imposes. Hence, UFT operational improvements (initiatives) and freight attraction models must consider informal trade for developing countries. Afour phasesapproach for characterizing the commercial areas in developing countries (considering both formal and informal establishments) is proposed and applied to ten areas in Mexico City. This characterization is required to calculate real freight trip attraction and then select and/or adapt suitable initiatives. Phase 1 aims the delimitation of the study area. The following information is obtained for each establishment of a potential area: location or geographic coordinates, industrial sector, industrial subsector, and number of employees. Phase 2 characterizes the study area and proposes a set of indicators. This allows a broad view of the operations and constraints of UFT in the study area. Phase 3 classifies the study area according to seven indicators. Each indicator represents a level of conflict in the area due to the presence of formal (registered) and informal establishments on the sidewalks and streets, affecting urban freight transport (and other activities). Phase 4 determines preliminary initiatives which could be implemented in the study area to improve the operation of UFT. The indicators and initiatives relation allows a preliminary initiatives selection. This relation requires to know the following: a) the problems in the area (congested streets, lack of parking space for freight vehicles, etc.); b) the factors which limit initiatives due to informal establishments (reduced streets for freight vehicles; mobility and parking inability during a period, among others), c) the problems in the area due to its physical characteristics; and d) the factors which limit initiatives due to regulations of the area. Several differences in the study areas were observed. As the indicators increases, the areas tend to be less ordered, and the limitations for the initiatives become higher, causing a smaller number of susceptible initiatives. In ordered areas (similar to the commercial areas of developed countries), the current techniquesfor estimating freight trip attraction (FTA) can bedirectly applied, however, in the areas where the level of order is lower due to the presence of informal trade, this is not recommended because the real FTA would not be estimated. Therefore, a technique, which consider the characteristics of the areas in developing countries to obtain data and to estimate FTA, is required. This estimation can be the base for proposing feasible initiatives to such zones. The proposed approach provides a wide view of the needs of the commercial areas of developing countries. The knowledge of these needs would allow UFT´s operation to be improved and its negative impacts to be minimized.

Keywords: freight initiatives, freight trip attraction, informal trade, urban freight transport

Procedia PDF Downloads 139

Authors: Abdesselem Dakhli, Wajdi Bellil, Chokri Ben Amar

Abstract:

DNA Barcode, a short mitochondrial DNA fragment, made up of three subunits; a phosphate group, sugar and nucleic bases (A, T, C, and G). They provide good sources of information needed to classify living species. Such intuition has been confirmed by many experimental results. Species classification with DNA Barcode sequences has been studied by several researchers. The classification problem assigns unknown species to known ones by analyzing their Barcode. This task has to be supported with reliable methods and algorithms. To analyze species regions or entire genomes, it becomes necessary to use similarity sequence methods. A large set of sequences can be simultaneously compared using Multiple Sequence Alignment which is known to be NP-complete. To make this type of analysis feasible, heuristics, like progressive alignment, have been developed. Another tool for similarity search against a database of sequences is BLAST, which outputs shorter regions of high similarity between a query sequence and matched sequences in the database. However, all these methods are still computationally very expensive and require significant computational infrastructure. Our goal is to build predictive models that are highly accurate and interpretable. This method permits to avoid the complex problem of form and structure in different classes of organisms. On empirical data and their classification performances are compared with other methods. Our system consists of three phases. The first is called transformation, which is composed of three steps; Electron-Ion Interaction Pseudopotential (EIIP) for the codification of DNA Barcodes, Fourier Transform and Power Spectrum Signal Processing. The second is called approximation, which is empowered by the use of Multi Llibrary Wavelet Neural Networks (MLWNN).The third is called the classification of DNA Barcodes, which is realized by applying the algorithm of hierarchical classification.

Keywords: DNA barcode, electron-ion interaction pseudopotential, Multi Library Wavelet Neural Networks (MLWNN)

Procedia PDF Downloads 316

Authors: Lilian Bambirra De Assis, Patricia Albuquerque Gomes, Kamila Pagel De Oliveira, Deborah Oliveira Santos, Marcelo Esteves Chaves Campos

Abstract:

This paper aimed to analyze how performance management occurs in the context of the modernization of the federal public sector in Chile and Portugal. To do so, the study was based on a theoretical framework that covers the modernization of public administration to performance management, passing on people management. The work consisted of qualitative-descriptive research in which 16 semi-structured interviews were applied in the countries of study and documents and legislation were used referring to the subject. Performance management, as well as other people management subsystems, is criticized for using private sector management tools, based on a results-driven logic. From this point of view, it is understood that certain practices of the private sector, regarding the measurement of performance, can not be simply inserted in the scenario of the public administration. Beyond this criticism, performance management can contribute to the achievement of the strategic objectives of the countries and its focus is upward, a trend that can be verified through the manuals produced; by the interest of consultants and professional organizations, both public and private; and OECD (Organization for Economic Cooperation and Development) evaluations. In Portugal, public administration reform was implemented during the Constitutional Government (2005-2009) and had as its objective the restructuring of human resources management, with an emphasis on its integration with budget management, which is an inclination of the OECD, while in Chile HRM (Human Resource Management) practices are directed to ministries to a lesser extent than the OECD average. The central human resources management sector, for the most part, coordinates policy but is also responsible for other issues, including payment and classification systems. Chile makes less use of strategic Human Resource Management practices than the average of OECD countries, and its prominence lies in the decentralization of public bodies, which may grant autonomy, but fragments the implementation of policies and practices in that country since they are not adopted by all organs. Through the analysis, it was possible to identify that Chile and Portugal have practices and personnel management policies that make reference to performance management, which is similar to other OECD countries. The study countries also have limitations to implement performance management and the results indicate that there are still processes to be perfected, such as performance appraisal and compensation.

Keywords: management of people in the public sector, modernization of public administration, performance management in the public sector, HRM, OECD

Procedia PDF Downloads 151

Authors: Kazi Rafikoddin

Abstract:

Conditionality refers to a precondition for getting external funds from IMF or WB by giving consent for implementation of the program of economic or political reforms especially relating to open economies. These are put forth under the label of structural adjustment. It is a kind of challenge on the part of borrowing government to exercise balance between the domestic obligations and the expectations of external funding agencies. Countries have to take loans under certain criteria and regulations because better loans are often not readily available. Therefore taking loans and renewing them to pay the same with new interest rates and conditions makes the governments entangled in the circle of debt. They are forced to compete with well-established multinational companies. If their access to industrialized countries' markets is impaired through protectionism, the developed world will be condemning the indebted nations to perpetual financial crisis. On the other hand, the ability to sell their goods free in the world market is reduced through the introduction of Structural Adjustment Programmes. Although there are examples of positive effects on certain economies like India, some Third World, and poor countries have experienced the ire of these remedies. This paper tries to find out the effects of SAPs on some borrowing countries.

Keywords: IMF, world bank, conditionalities, SAPs, Third World Countries

Procedia PDF Downloads 200

Authors: A. Elsehemy, M. Abdeen , T. Nazmy

Abstract:

Since the appearance of the Semantic web, many semantic search techniques and models were proposed to exploit the information in ontology to enhance the traditional keyword-based search. Many advances were made in languages such as English, German, French and Spanish. However, other languages such as Arabic are not fully supported yet. In this paper we present a framework for ontology based information retrieval for Arabic language. Our system consists of four main modules, namely query parser, indexer, search and a ranking module. Our approach includes building a semantic index by linking ontology concepts to documents, including an annotation weight for each link, to be used in ranking the results. We also augmented the framework with an automatic document categorizer, which enhances the overall document ranking. We have built three Arabic domain ontologies: Sports, Economic and Politics as example for the Arabic language. We built a knowledge base that consists of 79 classes and more than 1456 instances. The system is evaluated using the precision and recall metrics. We have done many retrieval operations on a sample of 40,316 documents with a size 320 MB of pure text. The results show that the semantic search enhanced with text classification gives better performance results than the system without classification.

Keywords: Arabic text classification, ontology based retrieval, Arabic semantic web, information retrieval, Arabic ontology

Procedia PDF Downloads 523

Authors: Saurav Kumar Suman, P. Karthigayani

Abstract:

In this paper the height of the tree is estimated and forest types is classified from the multi temporal RISAT-1 Horizontal-Horizontal (HH) and Horizontal-Vertical (HV) Polarised Satellite Aperture Radar (SAR) data. The novelty of the proposed project is combined use of the Back-scattering Coefficients (Sigma Naught) and the Coherence. It uses Water Cloud Model (WCM). The approaches use two main steps. (a) Extraction of the different forest parameter data from the Product.xml, BAND-META file and from Grid-xxx.txt file come with the HH & HV polarized data from the ISRO (Indian Space Research Centre). These file contains the required parameter during height estimation. (b) Calculation of the Vegetation and Ground Backscattering, Coherence and other Forest Parameters. (c) Classification of Forest Types using the ENVI 5.0 Tool and ROI (Region of Interest) calculation.

Keywords: RISAT-1, classification, forest, SAR data

Procedia PDF Downloads 404

Authors: Malraj Bharatha Kiriella

Abstract:

The purpose of this paper is to investigate the determinants of tourism foreign direct investment (TFDI) to selected developing countries during 1978-2017. The study used pooled panel data to estimate an econometric model. The findings show that market size and institutional barriers are determining factors for TFDI in countries, while other variables of positive country conditions, FDI-related government policy, tourism-related infrastructure and labor conditions are insignificant. The result shows that institutional effects are positive, while market size negatively affects TFDI inflows. The research is limited to eight developing countries. The results can be used to support government policy on TFDI. The paper makes the following contributions: First, it provides important insight and understanding into the TFDI decision-making process in developing countries. Second, both TFDI theory and evidence are minimal, and an econometric model developed on the basis of available literature has been empirically tested.

Keywords: determinants, developing countries, FDI in tourism, panel data

Procedia PDF Downloads 106

Authors: Aysun Pınarbaşı, Béla Vizvári

Abstract:

The countries are the units that procure the vaccines during the COVID-19 pandemic. The delivered quantities are huge. The countries must bear the inventory holding cost according to the variation of stock quantities. This cost depends on the speed of the vaccination in the country. This speed is time-dependent. The vaccinated portion of the population can be approximated by the cumulative distribution function of the Cauchy distribution. A model is provided for determining the minimal-cost inventory policy, and its optimality conditions are provided. The model is solved for 20 countries for different numbers of procurements. The results reveal the individual behavior of each country. We provide an inventory policy for the pandemic period for the countries. This paper presents a deterministic model for vaccines with a demand rate variable over time for the countries. It is aimed to provide an analytical model to deal with the minimization of holding cost and develop inventory policies regarding this aim to be used for a variety of perishable products such as vaccines. The saturation process is introduced, and an approximation of the vaccination curve of the countries has been discussed. According to this aspect, a deterministic model for inventory policy has been developed.

Keywords: covid-19, vaccination, inventory policy, bounded total demand, inventory holding cost, cauchy distribution, sigmoid function

Procedia PDF Downloads 73

Authors: Gökhan Karhan, Yavuz Elitok

Abstract:

Nowadays, inequality between developing and underdeveloped countries has a rapid increment. Developed countries impress the underdeveloped countries to become dependent through them. For that reason, Turkey has to increase its capability of making technological innovations. It has tried to be identified by examining the expenses of R&D in public, mercantile establishments and universities in Turkey that which expense is not enough and which expense should be doubled. As a result, developing new resolution strategies will be easier.

Keywords: competitive strength, research and development, technological innovation, Turkey

Procedia PDF Downloads 363

Authors: Sondos M. Hammad, Sherin M. ElGokhy, Mahmoud M. Fahmy, Elsayed A. Sallam

Abstract:

In this paper, an ensemble-based Support Vector Machine (SVM) classification approach is proposed. It is used for miRNA prediction. Three problems, commonly associated with previous approaches, are alleviated. These problems arise due to impose assumptions on the secondary structural of premiRNA, imbalance between the numbers of the laboratory checked miRNAs and the pseudo-hairpins, and finally using a training data set that does not consider all the varieties of samples in different species. We aggregate the predicted outputs of three well-known SVM classifiers; namely, Triplet-SVM, Virgo and Mirident, weighted by their variant features without any structural assumptions. An additional SVM layer is used in aggregating the final output. The proposed approach is trained and then tested with balanced data sets. The results of the proposed approach outperform the three base classifiers. Improved values for the metrics of 88.88% f-score, 92.73% accuracy, 90.64% precision, 96.64% specificity, 87.2% sensitivity, and the area under the ROC curve is 0.91 are achieved.

Keywords: MiRNAs, SVM classification, ensemble algorithm, assumption problem, imbalance data

Procedia PDF Downloads 347

Authors: Elias K. Maragos, Petros E. Maravelakis, Apostolos I. Linardis

Abstract:

Health2020 is a promising framework of policies provided by the World Health Organization (WHO) and aiming to diminish the health and well-being inequalities among the citizens of the European Union (EU) countries. The major demographic, social and environmental changes, in addition to the resent economic crisis prevent the unobstructed and successful implementation of this framework. The unemployment rates and the percentage of people at risk of poverty have increased among the citizens of EU countries. At the same time, the adopted fiscal, economic policies do not help governments to serve their social role and mitigate social and health inequalities. In those circumstances, there is a strong pressure to organize all health system resources efficiently and wisely. In order to provide a unified and value-based framework of valuation, we propose a valuation framework using data envelopment analysis (DEA) and dynamic DEA. We believe that the adopted methodology could provide a robust tool which can capture the degree of success with which policies have been implemented and is capable to determine which of the countries developed the requested policies efficiently and which of the countries have been lagged. Using the proposed methodology, we evaluated the performance of 28 EU member-countries in relation to the Health2020 peripheral targets. We adopted several versions of evaluation, measuring the effectiveness and the efficiency of EU countries from 2011 to 2016. Our results showed stability in technological changes and revealed a group of countries which were benchmarks in most of the years for the inefficient countries.

Keywords: DEA, Health2020, health inequalities, malmquist index, policies evaluation, well-being

Procedia PDF Downloads 142

Authors: Cuneyt Yucelbas, Seral Ozsen, Sule Yucelbas, Gulay Tezel

Abstract:

Due to the fact that there exist only a small number of complex systems in artificial immune system (AIS) that work out nonlinear problems, nonlinear AIS approaches, among the well-known solution techniques, need to be developed. Gaussian function is usually used as similarity estimation in classification problems and pattern recognition. In this study, diagnosis of breast cancer, the second type of the most widespread cancer in women, was performed with different distance calculation functions that euclidean, gaussian and gaussian-euclidean hybrid function in the clonal selection model of classical AIS on Wisconsin Breast Cancer Dataset (WBCD), which was taken from the University of California, Irvine Machine-Learning Repository. We used 3-fold cross validation method to train and test the dataset. According to the results, the maximum test classification accuracy was reported as 97.35% by using of gaussian-euclidean hybrid function for fold-3. Also, mean of test classification accuracies for all of functions were obtained as 94.78%, 94.45% and 95.31% with use of euclidean, gaussian and gaussian-euclidean, respectively. With these results, gaussian-euclidean hybrid function seems to be a potential distance calculation method, and it may be considered as an alternative distance calculation method for hard nonlinear classification problems.

Keywords: artificial immune system, breast cancer diagnosis, Euclidean function, Gaussian function

Procedia PDF Downloads 433

Authors: Rosa L. Figueroa, Christopher A. Flores, Qing Zeng-Treitler

Abstract:

A regular expression consists of sequence characters which allow describing a text path. Usually, in clinical research, regular expressions are manually created by programmers together with domain experts. Lately, there have been several efforts to investigate how to generate them automatically. This article presents a text classification algorithm based on regexes. The algorithm named REX was designed, and then, implemented as a simplified method to create regexes to classify Spanish text automatically. In order to classify ambiguous cases, such as, when multiple labels are assigned to a testing example, REX includes an information gain method Two sets of data were used to evaluate the algorithm’s effectiveness in clinical text classification tasks. The results indicate that the regular expression based classifier proposed in this work performs statically better regarding accuracy and F-measure than Support Vector Machine and Naïve Bayes for both datasets.

Keywords: information gain, regular expressions, smith-waterman algorithm, text classification

Procedia PDF Downloads 319

Authors: Alcino Panguana

Abstract:

All Portuguese-speaking African countries are in Sub-Saharan Africa, a region that has high infant mortality rates, being responsible for 49.6% of deaths in Portuguese-speaking African countries, Angola has levels of infant mortality among children, where 2017, 156 children who died before reaching 1 year of life in 1000 live births. Although there is an increase in studies that document trends and specific causes of infant mortality in each country, historical-comparative studies of infant mortality among these countries remain rare. Understanding the trend of this indicator is important for policymakers and planners in order to improve access to successful child survival operations. Lusophone Africa continues with high infant mortality rates in the order of 64 deaths per thousand births. Assuming heterogeneities that can characterize these countries, raise an analysis investigated indicator at the country level to understand the pattern and historical trend of infant mortality within Lusophone Africa from the year 2021. The result is to understand the levels and evolution of infant mortality in Portuguese-speaking African countries.

Keywords: child mortality, levels, trends, lusophone African countries

Procedia PDF Downloads 140

Authors: Abdullah Bal

Abstract:

This paper presents a one-class classification (OCC) technique based on Fukunaga-Koontz Transform (FKT) for binary classification problems. The FKT is originally a powerful tool to feature selection and ordering for two-class problems. To utilize the standard FKT for data domain description problem (i.e., one-class classification), in this paper, a set of non-class samples which exist outside of positive class (target class) describing boundary formed with limited training data has been constructed synthetically. The tunnel-like decision boundary around upper and lower border of target class samples has been designed using statistical properties of feature vectors belonging to the training data. To capture higher order of statistics of data and increase discrimination ability, the proposed method, termed one-class FKT (OC-FKT), has been extended to its nonlinear version via kernel machines and referred as OC-KFKT for short. Multiple kernel learning (MKL) is a favorable family of machine learning such that tries to find an optimal combination of a set of sub-kernels to achieve a better result. However, the discriminative ability of some of the base kernels may be low and the OC-KFKT designed by this type of kernels leads to unsatisfactory classification performance. To address this problem, the quality of sub-kernels should be evaluated, and the weak kernels must be discarded before the final decision making process. MKL/OC-FKT and selective MKL/OC-FKT frameworks have been designed stimulated by ensemble learning (EL) to weight and then select the sub-classifiers using the discriminability and diversities measured by eigenvalue ratios. The eigenvalue ratios have been assessed based on their regions on the FKT subspaces. The comparative experiments, performed on various low and high dimensional data, against state-of-the-art algorithms confirm the effectiveness of our techniques, especially in case of small sample size (SSS) conditions.

Keywords: ensemble methods, fukunaga-koontz transform, kernel-based methods, multiple kernel learning, one-class classification

Procedia PDF Downloads 19

Authors: Steffy Maria Joseph, Abdu Rahiman V, Abdul Hameed K. M.

Abstract:

Online handwritten character recognition is a challenging field in Artificial Intelligence. The classification success rate of current techniques decreases when the dataset involves similarity and complexity in stroke styles, number of strokes and stroke characteristics variations. Malayalam is a complex south indian language spoken by about 35 million people especially in Kerala and Lakshadweep islands. In this paper, we consider the significant feature extraction for the similar stroke styles of Malayalam. This extracted feature set are suitable for the recognition of other handwritten south indian languages like Tamil, Telugu and Kannada. A classification scheme based on support vector machines (SVM) is proposed to improve the accuracy in classification and recognition of online malayalam handwritten characters. SVM Classifiers are the best for real world applications. The contribution of various features towards the accuracy in recognition is analysed. Performance for different kernels of SVM are also studied. A graphical user interface has developed for reading and displaying the character. Different writing styles are taken for each of the 44 alphabets. Various features are extracted and used for classification after the preprocessing of input data samples. Highest recognition accuracy of 97% is obtained experimentally at the best feature combination with polynomial kernel in SVM.

Keywords: SVM, matlab, malayalam, South Indian scripts, onlinehandwritten character recognition

Procedia PDF Downloads 574

Authors: Shelby Simpson, William Stanley, Namir Naba, Xiaodi Wang

Abstract:

Both t-SNE and UMAP are brand new state of art tools to predominantly preserve the local structure that is to group neighboring data points together, which indeed provides a very informative visualization of heterogeneity in our data. In this research, we develop a t-SNE and UMAP base neural network image classification algorithm to embed the original dataset to a corresponding low dimensional dataset as a preprocessing step, then use this embedded database as input to our specially designed neural network classifier for image classification. We use the fashion MNIST data set, which is a labeled data set of images of clothing objects in our experiments. t-SNE and UMAP are used for dimensionality reduction of the data set and thus produce low dimensional embeddings. Furthermore, we use the embeddings from t-SNE and UMAP to feed into two neural networks. The accuracy of the models from the two neural networks is then compared to a dense neural network that does not use embedding as an input to show which model can classify the images of clothing objects more accurately.

Keywords: t-SNE, UMAP, fashion MNIST, neural networks

Procedia PDF Downloads 197

Authors: Yvette Reisinger

Abstract:

Relatively little is known about the Arab travel market, especially the outbound travel market from Arab countries in the Middle East. The Kuwaiti travel market is the smallest yet fastest growing in the Gulf Cooperation Council (GCC) region. The Kuwaiti travel market represents a great potential for the international tourism industry. Kuwaiti nationals have a very high spending power due to the Kuwaiti dinar being the highest-valued currency unit in the world. Although Europe, North America, and Asia/Pacific try to attract the Arab tourist market the number of Kuwaiti travellers attracted to these destinations is very low. The success in attracting the Kuwaiti travel market to Western countries must be guided by an analysis of the factors that affect its travel decisions. The objective of the study is to identify major factors that influence Kuwaiti nationals’ intentions to travel to Western countries. A model is developed and empirically tested on a sample of 343 Kuwaiti nationals. A series of regression analyses are run to determine the effects of different factors on Kuwaiti’s travel decisions. A Herman’s single factor test and Durbin-Watson test are used to assess the validity of the regression model. Analysis is controlled for socio-demographics. The results show that the Muslim friendly amenities and destination cognitive image exert significant effects on Kuwaiti nationals’ intentions to travel to Western countries. The study provides a better understanding of the factors that attract Kuwaiti tourists to Western countries. By knowing what encourages Kuwaitis to travel to Western countries marketers can plan and promote these countries accordingly. The study provides a foundation of future empirical research into the Kuwaiti/Arab travel market.

Keywords: Kuwaiti travel market, travel decisions, Western countries

Procedia PDF Downloads 190

Authors: Ali J. Ghandour, Houssam A. Krayem, Abedelkarim A. Jezzini

Abstract:

High-resolution satellite images and remote sensing can provide global information in a fast way compared to traditional methods of data collection. Under such high resolution, a road is not a thin line anymore. Objects such as cars and trees are easily identifiable. Automatic vehicles enumeration can be considered one of the most important applications in traffic management. In this paper, autonomous vehicle detection and classification approach in highway environment is proposed. This approach consists mainly of three stages: (i) first, a set of preprocessing operations are applied including soil, vegetation, water suppression. (ii) Then, road networks detection and delineation is implemented using built-up area index, followed by several morphological operations. This step plays an important role in increasing the overall detection accuracy since vehicles candidates are objects contained within the road networks only. (iii) Multi-level Otsu segmentation is implemented in the last stage, resulting in vehicle detection and classification, where detected vehicles are classified into cars and trucks. Accuracy assessment analysis is conducted over different study areas to show the great efficiency of the proposed method, especially in highway environment.

Keywords: remote sensing, object identification, vehicle and road extraction, vehicle and road features-based classification

Procedia PDF Downloads 230

Authors: Majid Habib Khan, Jinwei Zhao, Xinhong Hei, Liu Jiedong, Rana Shahzad Noor, Muhammad Imran

Abstract:

Deep learning is increasingly employed in image classification, yet the scarcity and high cost of labeled data for training remain a challenge. Limited samples often lead to overfitting due to biased sample distribution. This paper introduces a dynamic distribution calibration method for few-shot learning. Initially, base and new class samples undergo normalization to mitigate disparate feature magnitudes. A pre-trained model then extracts feature vectors from both classes. The method dynamically selects distribution characteristics from base classes (both adjacent and remote) in the embedding space, using a threshold value approach for new class samples. Given the propensity of similar classes to share feature distributions like mean and variance, this research assumes a Gaussian distribution for feature vectors. Subsequently, distributional features of new class samples are calibrated using a corrected hyperparameter, derived from the distribution features of both adjacent and distant base classes. This calibration augments the new class sample set. The technique demonstrates significant improvements, with up to 4% accuracy gains in few-shot classification challenges, as evidenced by tests on miniImagenet and CUB datasets.

Keywords: deep learning, computer vision, image classification, few-shot learning, threshold

Procedia PDF Downloads 64

Authors: Mekamı Hayet, Bounoua Nacer, Benabderrahmane Sidahmed, Taleb Ahmed

Abstract:

Pose estimation is an important task in computer vision. Though the majority of the existing solutions provide good accuracy results, they are often overly complex and computationally expensive. In this perspective, we propose the use of dimensionality reduction techniques to address the problem of facial pose estimation. Firstly, a face image is converted into one-dimensional time series using Hilbert space filling curve, then the approach converts these time series data to a symbolic representation. Furthermore, a distance matrix is calculated between symbolic series of an input learning dataset of images, to generate classifiers of frontal vs. profile face pose. The proposed method is evaluated with three public datasets. Experimental results have shown that our approach is able to achieve a correct classification rate exceeding 97% with K-NN algorithm.

Keywords: machine learning, pattern recognition, facial pose classification, time series

Procedia PDF Downloads 349

Authors: Bernur Acikgoz

Abstract:

The purpose of this paper is to investigate the effects of public spending on economic growth and examine the sources of economic growth in developed countries since the 1990s. This paper analyses whether public spending effect on economic growth based on Cobb-Douglas Production Function with the two econometric models with Autoregressive Distributed Lag (ARDL) and Dynamic Fixed Effect (DFE) for 21 developed countries (high-income OECD countries), over the period 1990-2013. Our models results are parallel to each other and the models support that public spending has an important role for economic growth. This result is accurate with theories and previous empirical studies.

Keywords: public spending, economic growth, panel data, ARDL models

Procedia PDF Downloads 368

Authors: Kenan Morani, Esra Kaya Ayana

Abstract:

This study aimed to develop a novel pipeline for COVID-19 detection using a large and rigorously annotated database of computed tomography (CT) images. The pipeline consists of UNet-based segmentation, lung extraction, and a classification part, with the addition of optional slice removal techniques following the segmentation part. In this work, a batch normalization was added to the original UNet model to produce lighter and better localization, which is then utilized to build a full pipeline for COVID-19 diagnosis. To evaluate the effectiveness of the proposed pipeline, various segmentation methods were compared in terms of their performance and complexity. The proposed segmentation method with batch normalization outperformed traditional methods and other alternatives, resulting in a higher dice score on a publicly available dataset. Moreover, at the slice level, the proposed pipeline demonstrated high validation accuracy, indicating the efficiency of predicting 2D slices. At the patient level, the full approach exhibited higher validation accuracy and macro F1 score compared to other alternatives, surpassing the baseline. The classification component of the proposed pipeline utilizes a convolutional neural network (CNN) to make final diagnosis decisions. The COV19-CT-DB dataset, which contains a large number of CT scans with various types of slices and rigorously annotated for COVID-19 detection, was utilized for classification. The proposed pipeline outperformed many other alternatives on the dataset.

Keywords: classification, computed tomography, lung extraction, macro F1 score, UNet segmentation

Procedia PDF Downloads 129

Authors: Guoliang Lu, Changhou Lu, Xueyong Li

Abstract:

In action recognition, previous studies have demonstrated the effectiveness of using multiple features to improve the recognition performance. We focus on two practical issues: i) most studies use a direct way of concatenating/accumulating multi features to evaluate the similarity between two actions. This way could be too strong since each kind of feature can include different dimensions, quantities, etc; ii) in many studies, the employed classification methods lack of a flexible and effective mechanism to add new feature(s) into classification. In this paper, we explore an unified scheme based on recently-proposed multi-dimensional dynamic time warping (MD-DTW). Experiments demonstrated the scheme's effectiveness of combining multi-feature and the flexibility of adding new feature(s) to increase the recognition performance. In addition, the explored scheme also provides us an open architecture for using new advanced classification methods in the future to enhance action recognition.

Keywords: action recognition, multi features, dynamic time warping, feature combination

Procedia PDF Downloads 436

Authors: I. Erins, J. Erina

Abstract:

The aim of the present article is to determine the impact of the external and internal factors of bank performance on the profitability indicators of the CEE countries banks in the period from 2006 to 2012. On the basis of research conducted abroad on bank and macroeconomic profitability indicators, in order to obtain research results, the authors evaluated return on average assets (ROAA) and return on average equity (ROAE) indicators of the CEE countries banks. The authors analyzed profitability indicators of banks using descriptive methods, SPSS data analysis methods as well as data correlation and linear regression analysis. The authors concluded that most internal and external indicators of bank performance have no direct effect on the profitability of the banks in the CEE countries. The only exceptions are credit risk and bank size which affect one of the measures of bank profitability–return on average equity.

Keywords: banks, CEE countries, profitability ROAA, ROAE

Procedia PDF Downloads 365

Authors: Belhouchet Selma, Ben Amar Anis

Abstract:

We examine the impact of COVID-19 transmission, containment measures, and vaccination growth on daily stock market returns for the G7 countries (Canada, France, Germany, Italy, Japan, the United Kingdom, and the United States) from January 22, 2020, to August 31, 2021, more than a year and a half after COVID-19. For this objective, we use panel pooled ordinary least squares regressions. Our findings indicate that the spread of the pandemic has a negative impact on the daily performance of the world's seven main stock markets. Government measures to improve stock market returns are no longer successful. Furthermore, our findings demonstrate that immunization efforts in G7 nations do not increase stock market performance in these countries. A variety of robustness tests back up our conclusions. Our findings have far-reaching implications for investors, governments, and regulators not only in the G7 countries but also in all developed countries and all countries globally.

Keywords: COVID-19, G7 stock market, containment measures, vaccination

Procedia PDF Downloads 98

Authors: Zohreh Bang Tavakoli, Shuktika Chatterjee

Abstract:

This study investigates the fiscal policy impact on countries’ economic growth in developing countries with a different external debt level. The fiscal policy effectiveness has been re-emphasized in the global financial crisis of 2008 with the external debt as its new contemporary driver (Ruščáková and Semančíková, 2016). According to Bouakez, (2014 ) different theories have proposed the economic consequence of fiscal policy, specifically for developing countries. However, fiscal policy literature is lacking research regarding the fiscal policy’s effectiveness with the external debt’s contributions through comprehensive study (Canh, 2018). Also, according to scholars, high levels of external debt will influence economic growth. First, through foreign resources and channel of investment in which high level of debt decreases the amount of foreign investment in the developing countries. Second, through the deterioration of foreign investors and fiscal policies related to a high level of debt (Cordella, et.al., 2010). Therefore, this study proposed that only countries with a low external debt level and appropriate fiscal policies and good quality institutions can gain the proper quantity and quality of foreign investors, which will help the economic growth. For this, this research is examining the impact of fiscal policy on developing countries' economic growth in the situation of different external debt levels.

Keywords: fiscal policy, external debt, gross domestic product, developing countries

Procedia PDF Downloads 156

Authors: Anukriti Kumar, Tanmay Singh, Dinesh Kumar Vishwakarma

Abstract:

Traffic control has been one of the most common and irritating problems since the time automobiles have hit the roads. Problems like traffic congestion have led to a significant time burden around the world and one significant solution to these problems can be the proper implementation of the Intelligent Transport System (ITS). It involves the integration of various tools like smart sensors, artificial intelligence, position technologies and mobile data services to manage traffic flow, reduce congestion and enhance driver's ability to avoid accidents during adverse weather. Road and traffic signs’ recognition is an emerging field of research in ITS. Classification problem of traffic signs needs to be solved as it is a major step in our journey towards building semi-autonomous/autonomous driving systems. The purpose of this work focuses on implementing an approach to solve the problem of traffic sign classification by developing a Convolutional Neural Network (CNN) classifier using the GTSRB (German Traffic Sign Recognition Benchmark) dataset. Rather than using hand-crafted features, our model addresses the concern of exploding huge parameters and data method augmentations. Our model achieved an accuracy of around 97.6% which is comparable to various state-of-the-art architectures.

Keywords: multiclass classification, convolution neural network, OpenCV

Procedia PDF Downloads 174

Authors: Ebtehal Aljedaani, Maha Aljohani

Abstract:

Privacy and security patterns are both important for developing software that protects users' data and privacy. Privacy patterns are designed to address common privacy problems, such as unauthorized data collection and disclosure. Security patterns are designed to protect software from attack and ensure reliability and trustworthiness. Using privacy and security patterns, software engineers can implement security and privacy by design principles, which means that security and privacy are considered throughout the software development process. These patterns are available to translate "security & privacy-by-design" into practical advice for software engineering. Previous research on privacy and security patterns has typically focused on one category of patterns at a time. This paper aims to bridge this gap by merging the two categories and identifying their similarities and differences. To do this, the authors conducted a systematic literature review of 25 research papers on privacy and security patterns. The papers were analysed based on the category of the pattern, the classification of the pattern, and the security requirements that the pattern addresses. This paper presents the results of a comprehensive review of privacy and security design patterns. The review is intended to help future IT designers understand the relationship between the two types of patterns and how to use them to design secure and privacy-preserving software. The paper provides a clear classification of privacy and security design patterns, along with examples of each type. The authors found that there is only one widely accepted classification of privacy design patterns, while there are several competing classifications of security design patterns. Three types of security design patterns were found to be the most commonly used.

Keywords: design patterns, security, privacy, classification of patterns, security patterns, privacy patterns

Procedia PDF Downloads 129