Search results for: classification of patterns

Authors: Lily Ingsrisawang, Tasanee Nacharoen

Abstract:

Introduction: The problems of unbalanced data sets generally appear in real world applications. Due to unequal class distribution, many research papers found that the performance of existing classifier tends to be biased towards the majority class. The k -nearest neighbors’ nonparametric discriminant analysis is one method that was proposed for classifying unbalanced classes with good performance. Hence, the methods of discriminant analysis are of interest to us in investigating misclassification error rates for class-imbalanced data of three diabetes risk groups. Objective: The purpose of this study was to compare the classification performance between parametric discriminant analysis and nonparametric discriminant analysis in a three-class classification application of class-imbalanced data of diabetes risk groups. Methods: Data from a healthy project for 599 staffs in a government hospital in Bangkok were obtained for the classification problem. The staffs were diagnosed into one of three diabetes risk groups: non-risk (90%), risk (5%), and diabetic (5%). The original data along with the variables; diabetes risk group, age, gender, cholesterol, and BMI was analyzed and bootstrapped up to 50 and 100 samples, 599 observations per sample, for additional estimation of misclassification error rate. Each data set was explored for the departure of multivariate normality and the equality of covariance matrices of the three risk groups. Both the original data and the bootstrap samples show non-normality and unequal covariance matrices. The parametric linear discriminant function, quadratic discriminant function, and the nonparametric k-nearest neighbors’ discriminant function were performed over 50 and 100 bootstrap samples and applied to the original data. In finding the optimal classification rule, the choices of prior probabilities were set up for both equal proportions (0.33: 0.33: 0.33) and unequal proportions with three choices of (0.90:0.05:0.05), (0.80: 0.10: 0.10) or (0.70, 0.15, 0.15). Results: The results from 50 and 100 bootstrap samples indicated that the k-nearest neighbors approach when k = 3 or k = 4 and the prior probabilities of {non-risk:risk:diabetic} as {0.90:0.05:0.05} or {0.80:0.10:0.10} gave the smallest error rate of misclassification. Conclusion: The k-nearest neighbors approach would be suggested for classifying a three-class-imbalanced data of diabetes risk groups.

Keywords: error rate, bootstrap, diabetes risk groups, k-nearest neighbors

Procedia PDF Downloads 425

Authors: Danilo Habermann, Aleksander Medella, Carla Cremon, Yusef Caceres

Abstract:

This paper aims to analyze the ability of 2d point clouds features to classify different models of helicopters using radars. This method does not need to estimate the blade length, the number of blades of helicopters, and the period of their micro-Doppler signatures. It is also not necessary to generate spectrograms (or any other image based on time and frequency domain). This work transforms a radar return signal into a 2D point cloud and extracts features of it. Three classifiers are used to distinguish 9 different helicopter models in order to analyze the performance of the features used in this work. The high accuracy obtained with each of the classifiers demonstrates that the 2D point clouds features are very useful for classifying helicopters from radar signal.

Keywords: helicopter classification, point clouds features, radar, supervised classifiers

Procedia PDF Downloads 208

Authors: Emmanuel Nkemakolam Okwuduba, Fransica Chinelo Offiah

Abstract:

The technique of teaching chemistry to students is one of the determining factors towards their achievement. Thus, the study investigated the relationship between classroom interaction patterns and students’ achievement in Chemistry. The purpose of this study was to identify patterns of interaction in an observed chemistry classroom, determine the amount of teacher talk, student talk and period of silence and to find out the relationship between them and the mean achievement scores of students. Five research questions and three hypotheses guided the study. The study was a correlational survey. The sample consisted of 450 (212males and 238 females) senior secondary one students and 12 (5males and 7 females) chemistry teachers drawn from 12 selected secondary schools in Awka Education Zone of Anambra state. In each of the 12 selected schools, an intact class was used. Science Interaction Category (SIC) and Chemistry Achievement Test (CAT) were developed, validated and used for data collection. Each teacher was observed three times and the interaction patterns coded using a coding sheet containing the Science Interaction Category. At the end of the observational period, the Chemistry Achievement Test (for collection of data on students’ achievement in chemistry) was administered on the students. Frequencies, percentage, mean, standard deviation and Pearson product moment correlation were used for data analysis. The result showed that the percentages of teacher talk, student talk and silence were 59.6%, 37.6% and 2.8% respectively. The Pearson correlation coefficient(r) for teacher talk, student talk and silence were -0.61, 0.76 and-0.18 respectively. The result showed negative and significant relationship between teacher talk and mean achievement scores of students; positive and significant relationship between student talk and mean achievement scores of students but there is no relationship between period of silence and mean achievement scores of students at 0.05 significant levels. The following recommendations were made based on the findings: teachers should establish high level of student talk through initiation and response as it promotes involvement and enhances achievement.

Keywords: academic achievement, chemistry, classroom, interactions patterns

Procedia PDF Downloads 294

Authors: Perpetua Modjadji, Sphiwe Madiba

Abstract:

Background: The growth patterns of children are good nutritional indicators of their nutritional status, health, and socioeconomic level. However, the maternal factors and the belief system of the society affect the growth of children promoting undernutrition. This study determined the influence of maternal factors on growth patterns of schoolchildren in a rural site. Methods: A convergent mixed method study was conducted among 508 schoolchildren and their mothers in Dikgale Health and Demographic Surveillance System Site, South Africa. Multistage sampling was used to select schools (purposive) and learners (random), who were paired with their mothers. Anthropometry was measured and socio-demographic, obstetrical, household information, maternal influence on children’s nutrition, and growth were assessed using an interviewer administered questionnaire (quantitative). The influence of the cultural beliefs and practices of mothers on the nutrition and growth of their children was explored using focus group discussions (qualitative). Narratives of mothers were used to best understand growth patterns of schoolchildren (mixed method). Data were analyzed using STATA 14 (quantitative) and Nvivo 11 (qualitative). Quantitative and qualitative data were merged for integrated mixed method analysis using a joint display analysis. Results: Mean age of children was 10 ± 2 years, ranging from 6 to 15 years. Substantial percentages of thinness (25%), underweight (24%), and stunting (22%) were observed among the children. Mothers had a mean age of 37 ± 7 years, and 75% were overweight or obese. A depressed socio-economic status indicated by a higher rate of unemployment with no income (82.3%), and dependency on social grants (86.8%) was observed. Determinants of poor growth patterns were child’s age and gender, maternal age, height and BMI, access to water supply, and refrigerator use. The narratives of mothers suggested that the children in most of their households were exposed to poverty and the inadequate intake of quality food. Conclusion: Poor growth patterns were observed among schoolchildren while their mothers were overweight or obese. Child’s gender, school grade, maternal body mass index, and access to water were the main determinants. Congruence was observed between most qualitative themes and quantitative constructs. A need for a multi sectoral approach considering an evidence based and feasible nutrition programs for schoolchildren, especially those in rural settings and educating mothers, cannot be over-emphasized.

Keywords: growth patterns, maternal factors, rural context, schoolchildren, South Africa

Procedia PDF Downloads 151

Authors: Danielle Shackley, Yetunde Folajimi

Abstract:

As more people turn to the internet seeking health-related information, there is more risk of finding false, inaccurate, or dangerous information. Sentiment analysis is a natural language processing technique that assigns polarity scores to text, ranging from positive, neutral, and negative. In this research, we evaluate the weight of a sentiment analysis feature added to fake health news classification models. The dataset consists of existing reliably labeled health article headlines that were supplemented with health information collected about COVID-19 from social media sources. We started with data preprocessing and tested out various vectorization methods such as Count and TFIDF vectorization. We implemented 3 Naive Bayes classifier models, including Bernoulli, Multinomial, and Complement. To test the weight of the sentiment analysis feature on the dataset, we created benchmark Naive Bayes classification models without sentiment analysis, and those same models were reproduced, and the feature was added. We evaluated using the precision and accuracy scores. The Bernoulli initial model performed with 90% precision and 75.2% accuracy, while the model supplemented with sentiment labels performed with 90.4% precision and stayed constant at 75.2% accuracy. Our results show that the addition of sentiment analysis did not improve model precision by a wide margin; while there was no evidence of improvement in accuracy, we had a 1.9% improvement margin of the precision score with the Complement model. Future expansion of this work could include replicating the experiment process and substituting the Naive Bayes for a deep learning neural network model.

Keywords: sentiment analysis, Naive Bayes model, natural language processing, topic analysis, fake health news classification model

Procedia PDF Downloads 84

Authors: Seung-Hwan Ju, Yo-Han Choi, Hee-Suk Seo, Tae-Kyung Kim

Abstract:

This study investigates the permissions requested by Android applications, and the possibility of identifying suspicious applications based only on information presented to the user before an application is downloaded. The pattern analysis is based on a smaller data set consisting of confirmed malicious applications. The method is evaluated based on its ability to recognize malicious potential in the analyzed applications. In this study, we develop a system to monitor that mobile application permission at application update. This study is a service-based malware analysis. It will be based on the mobile security study.

Keywords: malware patterns, application permission, application analysis, security

Procedia PDF Downloads 510

Authors: Elnaz Lashgari, Emel Demircan

Abstract:

Electromyography (EMG) is one of the most important interfaces between humans and robots for rehabilitation. Decoding this signal helps to recognize muscle activation and converts it into smooth motion for the robots. Detecting each muscle’s pattern during walking and running is vital for improving the quality of a patient’s life. In this study, EMG data from 10 muscles in 10 subjects at 4 different speeds were analyzed. EMG signals are nonlinear with high dimensionality. To deal with this challenge, we extracted some features in time-frequency domain and used manifold learning and Laplacian Eigenmaps algorithm to find the intrinsic features that represent data in low-dimensional space. We then used the Bayesian classifier to identify various patterns of EMG signals for different muscles across a range of running speeds. The best result for vastus medialis muscle corresponds to 97.87±0.69 for sensitivity and 88.37±0.79 for specificity with 97.07±0.29 accuracy using Bayesian classifier. The results of this study provide important insight into human movement and its application for robotics research.

Keywords: electromyography, manifold learning, ISOMAP, Laplacian Eigenmaps, locally linear embedding

Procedia PDF Downloads 349

Authors: Affordability, Expenditure Patterns towards Sustainable Consumption in Malaysia

Abstract:

Safe drinking water is needed for survival. Households have to pay the water bill monthly. However, lower income households are sometimes unable to afford the cost. This study examines water access and affordability among households in Malaysia and the determinants of water affordability using cross-sectional data and multiple regression. The paper expects that the bill for basic water consumption is inversely related to average income. This means that policy makers need to redesign the water tariff to improve the quality of life of lower income households.

Keywords: affordability, sustainable consumption, income, water tariff

Procedia PDF Downloads 232

Authors: Qingtao Yu, Guojia Ma

Abstract:

Approaches to microwave absorption and low infrared emissivity are often conflicting, as the low-emissivity layer, usually consisting of metals, increases the reflection of microwaves, especially in high frequency. In this study, an infrared-radar compatible stealth surface was fabricated by first depositing a layer of low-emissivity metal film on the surface of a layer of radar-absorbing material. Then, ultrafast laser was used to generate patterns on the metal film, forming a frequency selective surface. With proper pattern design, while the majority of the frequency selective surface is covered by the metal film, it has relatively little influence on the reflection of microwaves between 2 to 18 GHz. At last, structures on the radar-absorbing layer were fabricated by ultra-fast laser to further improve the absorbing bandwidth of the microwave. This study demonstrates that the compatibility between microwave absorption and low infrared emissivity can be achieved by properly designing patterns and structures on the metal film and the radar-absorbing layer accordingly.

Keywords: frequency selective surface, infrared-radar compatible, low infrared emissivity, radar-absorbing material, patterns, structures

Procedia PDF Downloads 118

Authors: Rosa Figueroa, Christopher Flores

Abstract:

Text categorization is the problem of assigning a new document to a set of predetermined categories, on the basis of a training set of free-text data that contains documents whose category membership is known. To train a classification model, it is necessary to extract characteristics in the form of tokens that facilitate the learning and classification process. In text categorization, the feature extraction process involves the use of word sequences also known as N-grams. In general, it is expected that documents belonging to the same category share similar features. The Smith-Waterman (SW) algorithm is a dynamic programming algorithm that performs a local sequence alignment in order to determine similar regions between two strings or protein sequences. This work explores the use of SW algorithm as an alternative to feature extraction in text categorization. The dataset used for this purpose, contains 2,610 annotated documents with the classes Obese/Non-Obese. This dataset was represented in a matrix form using the Bag of Word approach. The score selected to represent the occurrence of the tokens in each document was the term frequency-inverse document frequency (TF-IDF). In order to extract features for classification, four experiments were conducted: the first experiment used SW to extract features, the second one used unigrams (single word), the third one used bigrams (two word sequence) and the last experiment used a combination of unigrams and bigrams to extract features for classification. To test the effectiveness of the extracted feature set for the four experiments, a Support Vector Machine (SVM) classifier was tuned using 20% of the dataset. The remaining 80% of the dataset together with 5-Fold Cross Validation were used to evaluate and compare the performance of the four experiments of feature extraction. Results from the tuning process suggest that SW performs better than the N-gram based feature extraction. These results were confirmed by using the remaining 80% of the dataset, where SW performed the best (accuracy = 97.10%, weighted average F-measure = 97.07%). The second best was obtained by the combination of unigrams-bigrams (accuracy = 96.04, weighted average F-measure = 95.97) closely followed by the bigrams (accuracy = 94.56%, weighted average F-measure = 94.46%) and finally unigrams (accuracy = 92.96%, weighted average F-measure = 92.90%).

Keywords: comorbidities, machine learning, obesity, Smith-Waterman algorithm

Procedia PDF Downloads 285

Authors: Grzegorz Dolzyk, Sungmoon Jung

Abstract:

Thin-walled tubes are commonly used as energy absorption devices for their excellent mechanical properties and high manufacturability. Techniques such as grooving and pre-folded origami shapes were introduced to circular and polygonal tubes to improve its energy absorption efficiency. This paper examines the energy absorption characteristics of circular tubes with pre-embedded curved-crease pattern. Set of numerical analyzes were conducted with different grooving patterns for tubes with various diameter (D) to thickness (t) ratio. It has been found that even very shallow grooving can positively affect thin wall tubes, leading to increased energy absorption and higher crushing load efficiency. The phenomenon is associated with nonsymmetric deformation that is usually observed for tubes with a high D/t ratio ( > 90). Grooving can redirect a natural mode of post-buckling deformation to a one with a higher number of lobes such that its beneficial and more stable. Also, the opposite effect can be achieved, and highly disrupted deformation can be a cause of reduced energy absorption capabilities. Curved-crease engraved patterns can be used to stabilize and change a form of hazardous post-buckling deformation.

Keywords: axial crushing, energy absorption, grooving, thin-wall structures

Procedia PDF Downloads 133

Authors: H. Abas Nejad, A. R. Teymoori

Abstract:

Facial expression recognition is one of the open problems in computer vision. Robust neutral face recognition in real time is a major challenge for various supervised learning based facial expression recognition methods. This is due to the fact that supervised methods cannot accommodate all appearance variability across the faces with respect to race, pose, lighting, facial biases, etc. in the limited amount of training data. Moreover, processing each and every frame to classify emotions is not required, as the user stays neutral for the majority of the time in usual applications like video chat or photo album/web browsing. Detecting neutral state at an early stage, thereby bypassing those frames from emotion classification would save the computational power. In this work, we propose a light-weight neutral vs. emotion classification engine, which acts as a preprocessor to the traditional supervised emotion classification approaches. It dynamically learns neutral appearance at Key Emotion (KE) points using a textural statistical model, constructed by a set of reference neutral frames for each user. The proposed method is made robust to various types of user head motions by accounting for affine distortions based on a textural statistical model. Robustness to dynamic shift of KE points is achieved by evaluating the similarities on a subset of neighborhood patches around each KE point using the prior information regarding the directionality of specific facial action units acting on the respective KE point. The proposed method, as a result, improves ER accuracy and simultaneously reduces the computational complexity of ER system, as validated on multiple databases.

Keywords: neutral vs. emotion classification, Constrained Local Model, procrustes analysis, Local Binary Pattern Histogram, statistical model

Procedia PDF Downloads 329

Authors: Ceren Kaya, Okan Erkaymaz, Orhan Ayar, Mahmut Özer

Abstract:

Diabetes Mellitus (Diabetes) is a disease based on insulin hormone disorders and causes high blood glucose. Clinical findings determine that diabetes can be diagnosed by electrophysiological signals obtained from the vital organs. 'Diabetic Retinopathy' is one of the most common eye diseases resulting on diabetes and it is the leading cause of vision loss due to structural alteration of the retinal layer vessels. In this study, features of horizontal and vertical Video-Oculography (VOG) signals have been used to classify non-proliferative and proliferative diabetic retinopathy disease. Twenty-five features are acquired by using discrete wavelet transform with VOG signals which are taken from 21 subjects. Two models, based on multi-layer perceptron and radial basis function, are recommended in the diagnosis of Diabetic Retinopathy. The proposed models also can detect level of the disease. We show comparative classification performance of the proposed models. Our results show that proposed the RBF model (100%) results in better classification performance than the MLP model (94%).

Keywords: diabetic retinopathy, discrete wavelet transform, multi-layer perceptron, radial basis function, video-oculography (VOG)

Procedia PDF Downloads 246

Authors: Rima A. Ajlouni

Abstract:

The discovery of quasi-periodic structures in material science is revealing an exciting new class of symmetries, which has never been explored before. Due to their unique structural and visual properties, these symmetries are drawing interest from many scientific and design disciplines. Especially, in art and architecture, these symmetries can provide a rich source of geometry for exploring new patterns, forms, systems, and structures. However, the structural systems of these complicated symmetries are still posing a perplexing challenge. While much of their local order has been explored, the global governing system is still unresolved. Understanding their unique global long-range order is essential to their generation and application. The recent discovery of dodecagonal quasi-periodic patterns in historical Islamic architecture is generating a renewed interest into understanding the mathematical principles of traditional Islamic geometry. Astonishingly, many centuries before its description in the modern science, ancient artists, by using the most primitive tools (a compass and a straight edge), were able to construct patterns with quasi-periodic formations. These ancient patterns can be found all over the ancient Islamic world, many of which exhibit formations with 5, 8, 10 and 12 quasi-periodic symmetries. Based on the examination of these historical patterns and derived from the generating principles of Islamic geometry, a global multi-level structural model is presented that is able to describe the global long-range order of dodecagonal quasi-periodic formations in Islamic Architecture. Furthermore, this method is used to construct new quasi-periodic tiling systems as well as generating their deflation and inflation rules. This method can be used as a general guiding principle for constructing infinite patches of dodecagon-based quasi-periodic formations, without the need for local strategies (tiling, matching, grid, substitution, etc.) or complicated mathematics; providing an easy tool for scientists, mathematicians, teachers, designers and artists, to generate and study a wide range of dodecagonal quasi-periodic formations.

Keywords: dodecagonal, Islamic architecture, long-range order, quasi-periodi

Procedia PDF Downloads 393

Authors: Yoshimoto Kurihara, Tad Gonsalves

Abstract:

Currently, in the field of object posture estimation, there is research on estimating the position and angle of an object by storing a 3D model of the object to be estimated in advance in a computer and matching it with the model. However, in this research, we have succeeded in creating a module that is much simpler, smaller in scale, and faster in operation. Our 6D pose estimation model consists of two different networks – a classification network and a regression network. From a single RGB image, the trained model estimates the class of the object in the image, the coordinates of the object, and its rotation angle in 3D space. In addition, we compared the estimation accuracy of each camera position, i.e., the angle from which the object was captured. The highest accuracy was recorded when the camera position was 75°, the accuracy of the classification was about 87.3%, and that of regression was about 98.9%.

Keywords: 6D posture estimation, image recognition, deep learning, AlexNet

Procedia PDF Downloads 141

Authors: Amin Nakhostin-Ansari, Samaneh Akbarour, Khosro Sadeghniiat Haghighi, Zahra Banafsheh Alemohammad, Farnaz Etesam, Arezu Najafi, Mahnaz Khalafehnilsaz

Abstract:

Introduction: The outbreak of coronavirus disease has considerably burdened the healthcare system in Iran. This study aimed to evaluate the characteristics of insomnia experienced by the general Iranian population during the COVID-19 pandemic. Method: A scale(FCV-19) was used for Fear of COVID-19, Insomnia Severity Index (ISI), Patient Health Questionnaire-2 (PHQ-2), and Generalized Anxiety Disorder Scale-2 (GAD-2) for detailed characterization of insomnia and its patterns Results: In total, 675 people with insomnia with the mean age of 40.28 years (SD=11.15) participated in this study. Prevalence of difficulty initiating sleep (DIS), difficulty maintaining sleep (DMS), and early morning awakening (EMA) were 91.4%, 86.7%, and 77%, respectively. DIS, DMS, and EMA were more common in people with depression and anxiety. FCV-19 score was higher in those with more severe types of DIS, DMS, and EMA (P<0.001). FCV-19 was a risk factor for all patterns of insomnia (OR=1.19, 1.12, 1.02 for DIS, DMS, and EMA, respectively). Conclusion: fear of COVID-19 is a major factor to insomnia patterns. Investigation of COVID-19 fear in people with insomnia and the addition of attributed relieving or management strategies to conventional management of insomnia are reasonable approaches to improve the sleep condition of people in the pandemic.

Keywords: insomnia, difficulty maintaining sleep, COVID-19, Coronavirus

Procedia PDF Downloads 155

Authors: Khries Sawsan

Abstract:

the phenomenon of urbanization is considered as one of the most important tourism resources that differ from one country to another and from one region to another in the same country. Our concern in tourism accommodation is explained by the fact that their location is directly related to the movement to tourist sites .Besides, these constructions comport security considered as the most important motivation for tourists in their choice of any destination. Hotels are the most representative expression of tourism. This is due to their physical prominence in the landscape and being the sole urban component totally unique to tourism. This study sheds light on the impact of tourism development on the spatial pattern in Jordan. It describes the linkages between existing tourism development policies and the spatial development patterns that have occurred as a result throughout Jordan, particularly looking at the impact that tourism has had on the physical environment of major tourism destinations. It puts an illustrative plan of the impact of the augmentation of tourism accommodations in Jordan in the past 40 years ago. The findings of this study help us to understand better the operation of Jordan’ dynamic changes in the location An intensive analysis is then applied on a representative case study in three regions: Amman, Petra and Aqaba. The study proceeds from an historical perspective to, show the evolution of the current development patterns an increase of tourism’s impact on spatial, in the presence of factors as political and economic stability, is expected.

Keywords: spatial patterns, urbanisation, spatial transformations, tourism planning, Jordan

Procedia PDF Downloads 534

Authors: Xiaoqi Jia, Qing Zhu, Hao Zhang, Su Yang

Abstract:

A gender recognition system is able to tell the gender of the given person through a few of frontal facial images. An effective gender recognition approach enables to improve the performance of many other applications, including security monitoring, human-computer interaction, image or video retrieval and so on. In this paper, we present an effective method for gender classification task in frontal facial images based on deep belief networks (DBNs), which can pre-train model and improve accuracy a little bit. Our experiments have shown that the pre-training method with DBNs for gender classification task is feasible and achieves a little improvement of accuracy on FERET and CAS-PEAL-R1 facial datasets.

Keywords: gender recognition, beep belief net-works, semi-supervised learning, greedy-layer wise RBMs

Procedia PDF Downloads 434

Authors: Oumaima Khlifati, Khadija Baba

Abstract:

Pavement distress is the main factor responsible for the deterioration of road structure durability, damage vehicles, and driver comfort. Transportation agencies spend a high proportion of their funds on pavement monitoring and maintenance. The auscultation of pavement distress was based on the manual survey, which was extremely time consuming, labor intensive, and required domain expertise. Therefore, the automatic distress detection is needed to reduce the cost of manual inspection and avoid more serious damage by implementing the appropriate remediation actions at the right time. Inspired by recent deep learning applications, this paper proposes an algorithm for automatic road distress detection and classification using on the Deep Convolutional Neural Network (DCNN). In this study, the types of pavement distress are classified as transverse or longitudinal cracking, alligator, pothole, and intact pavement. The dataset used in this work is composed of public asphalt pavement images. In order to learn the structure of the different type of distress, the DCNN models are trained and tested as a multi-label classification task. In addition, to get the highest accuracy for our model, we adjust the structural optimization hyper parameters such as the number of convolutions and max pooling, filers, size of filters, loss functions, activation functions, and optimizer and fine-tuning hyper parameters that conclude batch size and learning rate. The optimization of the model is executed by checking all feasible combinations and selecting the best performing one. The model, after being optimized, performance metrics is calculated, which describe the training and validation accuracies, precision, recall, and F1 score.

Keywords: distress pavement, hyperparameters, automatic classification, deep learning

Procedia PDF Downloads 71

Authors: Qing Wu, Fei-Yan Li, Heng-Chang Zhang

Abstract:

Multitask learning support vector machines (SVMs) have recently attracted increasing research attention. Given several related tasks, the single-task learning methods trains each task separately and ignore the inner cross-relationship among tasks. However, multitask learning can capture the correlation information among tasks and achieve better performance by training all tasks simultaneously. In addition, the asymmetric squared loss function can better improve the generalization ability of the models on the most asymmetric distributed data. In this paper, we first make two assumptions on the relatedness among tasks and propose two multitask learning proximal support vector machine algorithms, named MTL-a-PSVM and EMTL-a-PSVM, respectively. MTL-a-PSVM seeks a trade-off between the maximum expectile distance for each task model and the closeness of each task model to the general model. As an extension of the MTL-a-PSVM, EMTL-a-PSVM can select appropriate kernel functions for shared information and private information. Besides, two corresponding special cases named MTL-PSVM and EMTLPSVM are proposed by analyzing the asymmetric squared loss function, which can be easily implemented by solving linear systems. Experimental analysis of three classification datasets demonstrates the effectiveness and superiority of our proposed multitask learning algorithms.

Keywords: multitask learning, asymmetric squared loss, EMTL-a-PSVM, classification

Procedia PDF Downloads 99

Authors: Thrivikraman Aswathi, S. Advaith

Abstract:

As there can be cases where the use of real data is somehow limited, such as when it is hard to get access to a large volume of real data, we need to go for synthetic data generation. This produces high-quality synthetic data while maintaining the statistical properties of a specific dataset. In the present work, a generative adversarial network (GAN) is trained to produce multivariate time series (MTS) data since the MTS is now being gathered more often in various real-world systems. Furthermore, the GAN-generated MTS data is fed into a transformer-based deep learning architecture that carries out the data categorization into predefined classes. Further, the model is evaluated across various distinct domains by generating corresponding MTS data.

Keywords: GAN, transformer, classification, multivariate time series

Procedia PDF Downloads 113

Authors: Subhadeep Mandal, Sujoy Bhattacharya, Pabitra Mitra, Diya Guha Roy, Seema Bhattacharya

Abstract:

E-commerce firms allow customers to evaluate and review the things they buy as a positive or bad experience. The e-commerce transaction processes are made up of a variety of diverse organizations and activities that operate independently but are connected together to complete the transaction (from placing an order to the goods reaching the client). After a negative shopping experience, clients frequently disregard the critical assessment of these businesses and submit their feedback on an all-over basis, which benefits certain enterprises but is tedious for others. In this article, we solely dealt with negative reviews and attempted to distinguish between negative reviews where the e-commerce firm is explicitly blamed by customers for a bad purchasing experience and other negative reviews.

Keywords: e-commerce, online shopping, customer reviews, customer behaviour, text analytics, n-grams classification

Procedia PDF Downloads 245

Authors: Eugene Y. J. Aw, J. W. Koh, S. H. Chew, K. E. Chua, P. L. Goh, Grace H. B. Foo, M. L. Leong

Abstract:

This paper presents the evaluation of various soil testing methods such as the four-probe soil electrical resistivity method and cone penetration test (CPT) that can complement a newly developed novel rapid soil classification scheme using computer vision, to improve the accuracy and productivity of on-site classification of excavated soil. In Singapore, excavated soils from the local construction industry are transported to Staging Grounds (SGs) to be reused as fill material for land reclamation. Excavated soils are mainly categorized into two groups (“Good Earth” and “Soft Clay”) based on particle size distribution (PSD) and water content (w) from soil investigation reports and on-site visual survey, such that proper treatment and usage can be exercised. However, this process is time-consuming and labor-intensive. Thus, a rapid classification method is needed at the SGs. Four-probe soil electrical resistivity and CPT were evaluated for their feasibility as suitable additions to the computer vision system to further develop this innovative non-destructive and instantaneous classification method. The computer vision technique comprises soil image acquisition using an industrial-grade camera; image processing and analysis via calculation of Grey Level Co-occurrence Matrix (GLCM) textural parameters; and decision-making using an Artificial Neural Network (ANN). It was found from the previous study that the ANN model coupled with ρ can classify soils into “Good Earth” and “Soft Clay” in less than a minute, with an accuracy of 85% based on selected representative soil images. To further improve the technique, the following three items were targeted to be added onto the computer vision scheme: the apparent electrical resistivity of soil (ρ) measured using a set of four probes arranged in Wenner’s array, the soil strength measured using a modified mini cone penetrometer, and w measured using a set of time-domain reflectometry (TDR) probes. Laboratory proof-of-concept was conducted through a series of seven tests with three types of soils – “Good Earth”, “Soft Clay,” and a mix of the two. Validation was performed against the PSD and w of each soil type obtained from conventional laboratory tests. The results show that ρ, w and CPT measurements can be collectively analyzed to classify soils into “Good Earth” or “Soft Clay” and are feasible as complementing methods to the computer vision system.

Keywords: computer vision technique, cone penetration test, electrical resistivity, rapid and non-destructive, soil classification

Procedia PDF Downloads 223

Authors: Jamshid Qodirov, Sirojiddin Komolov, Ravilov Mirahmad, Olimjon Mirzayev

Abstract:

Nowadays, natural language processing tools play a crucial role in our daily lives, including various techniques with text processing. There are very advanced models in modern languages, such as English, Russian etc. But, in some languages, such as Uzbek, the NLP models have been developed recently. Thus, there are only a few NLP models in Uzbek language. Moreover, there is no such work that could show which Uzbek NLP model behaves in different situations and when to use them. This work tries to close this gap and compares the Uzbek NLP models existing as of the time this article was written. The authors try to compare the NLP models in two different scenarios: sentiment analysis and sentence similarity, which are the implementations of the two most common problems in the industry: classification and similarity. Another outcome from this work is two datasets for classification and sentence similarity in Uzbek language that we generated ourselves and can be useful in both industry and academia as well.

Keywords: NLP, benchmak, bert, vectorization

Procedia PDF Downloads 40

Authors: A. Terfous, Y. Liu, A. Ghenaim, P. A. Garambois

Abstract:

With increasing urbanization worldwide, it is crucial to sustainably manage sediment flows in urban networks and especially in stormwater detention basins. One key aspect is to propose optimized designs for detention tanks in order to best reduce flood peak flows and in the meantime settle particles. It is, therefore, necessary to understand complex flows patterns and sediment deposition conditions in stormwater detention basins. The aim of this paper is to study flow structure and particle deposition pattern for a given tank geometry in view to control and maximize sediment deposition. Both numerical simulation and experimental works were done to investigate the flow and sediment distribution in a storm tank with a cavity. As it can be indicated, the settle distribution of the particle in a rectangular tank is mainly determined by the flow patterns and the bed shear stress. The flow patterns in a rectangular tank differ with different geometry, entrance flow rate and the water depth. With the changing of flow patterns, the bed shear stress will change respectively, which also play an influence on the particle settling. The accumulation of the particle in the bed changes the conditions at the bottom, which is ignored in the investigations, however it worth much more attention, the influence of the accumulation of the particle on the sedimentation should be important. The approach presented here is based on the resolution of the Reynolds averaged Navier-Stokes equations to account for turbulent effects and also a passive particle transport model. An analysis of particle deposition conditions is presented in this paper in terms of flow velocities and turbulence patterns. Then sediment deposition zones are presented thanks to the modeling with particle tracking method. It is shown that two recirculation zones seem to significantly influence sediment deposition. Due to the possible overestimation of particle trap efficiency with standard wall functions and stick conditions, further investigations seem required for basal boundary conditions based on turbulent kinetic energy and shear stress. These observations are confirmed by experimental investigations processed in the laboratory.

Keywords: storm sewers, sediment deposition, numerical simulation, experimental investigation

Procedia PDF Downloads 310

Authors: Natthawut Arin

Abstract:

In forensic contexts, competency to stand trial assessments are the most common referrals. The defendants may attempt to endorse psychopathology symptoms and feign incompetent. Coaching, which can be teaching them test-taking strategies to avoid detection of psychopathological symptoms feigning. Recently, the Symptom Validity Testings (SVTs) were created to detect feigning. Moreover, the works of the literature showed that the effects of coaching on SVTs may be more robust to the effects of coaching. Thai Symptom Validity Test (SVT-Th) was designed as SVTs which demonstrated adequate psychometric properties and ability to classify between feigners and honest responders. Thus, the current study to examine the utility as the robustness of SVT-Th in the detection of feigned psychopathology. Participants consisted of 120 were recruited from undergraduate courses in psychology, randomly assigned to one of three groups. The SVT-Th was administered to those three scenario-experimental groups: (a) Uncoached group were asked to respond honestly (n=40), (b) Symptom-coached without warning group were asked to feign psychiatric symptoms to gain incompetency to stand trial (n=40), while (c) Test-coached with warning group were asked to feign psychiatric symptoms to avoid test detection but being incompetency to stand trial (n=40). Group differences were analyzed using one-way ANOVAs. The result revealed an uncoached group (M = 4.23, SD.= 5.20) had significantly lower SVT-Th mean scores than those both coached groups (M =185.00, SD.= 72.88 and M = 132.10, SD.= 54.06, respectively). Classification rates were calculated to determine the classification accuracy. Result indicated that SVT-Th had overall classification accuracy rates of 96.67% with acceptable of 95% sensitivity and 100% specificity rates. Overall, the results of the present study indicate that the SVT-Th yielded high adequate indices of accuracy and these findings suggest that the SVT-Th is robustness against coaching.

Keywords: incompetency to stand trial, coaching, robustness, classification accuracy

Procedia PDF Downloads 123

Authors: Songul Cinaroglu

Abstract:

Background: Random Forest is an efficient, multi-class machine learning method using for classification, regression and other tasks. This method is operating by constructing each tree using different bootstrap sample of the data. Determining the number of trees in random forests is an open question in the literature for studies about improving classification performance of random forests. Aim: The aim of this study is to analyze whether there is an optimal number of trees in Random Forests and how performance of Random Forests differ according to increase in number of trees using sample health data sets in R programme. Method: In this study we analyzed the performance of Random Forests as the number of trees grows and doubling the number of trees at every iteration using “random forest” package in R programme. For determining minimum and optimal number of trees we performed Mc Nemar test and Area Under ROC Curve respectively. Results: At the end of the analysis it was found that as the number of trees grows, it does not always means that the performance of the forest is better than forests which have fever trees. In other words larger number of trees only increases computational costs but not increases performance results. Conclusion: Despite general practice in using random forests is to generate large number of trees for having high performance results, this study shows that increasing number of trees doesn’t always improves performance. Future studies can compare different kinds of data sets and different performance measures to test whether Random Forest performance results change as number of trees increase or not.

Keywords: classification methods, decision trees, number of trees, random forest

Procedia PDF Downloads 386

Authors: Turgut Coskun

Abstract:

'Concreteness effect' refers to faster processing of concrete words and 'compound facilitation' refers to faster response to compounds. In this study, our main goal was to investigate the interaction between compound facilitation and concreteness effect. The latter might modulate compound processing basing on constituents’ transparency patterns. To evaluate these, we created lists for compound and monomorphemic words, sub-categorized them into concrete and abstract words, and further sub-categorized them basing on their transparency. The transparency conditions were opaque-opaque (OO), transparent-opaque (TO), and transparent-transparent (TT). We used RT data from English Lexicon Project (ELP) for our comparisons. The results showed the importance of concreteness factor (facilitation) in both compound and monomorphemic processing. Important for our present concern, separate concrete and abstract compound analyses revealed different patterns for OO, TO, and TT compounds. Concrete TT and TO conditions were processed faster than Concrete OO, Abstract OO and Abstract TT compounds, however, they weren’t processed faster than Abstract TO compounds. These results may reflect on different representation patterns of concrete and abstract compounds.

Keywords: abstract word, compound representation, concrete word, constituent transparency, processing speed

Procedia PDF Downloads 183

Authors: Levent Basayigit, Sinan Demir, Yusuf Ucar, Burhan Kara

Abstract:

Many research projects require accurate delineation of the different land cover type of the agricultural area. Especially it is critically important for the definition of specific plants like cannabis. However, the complexity of vegetation stands structure, abundant vegetation species, and the smooth transition between different seconder section stages make vegetation classification difficult when using traditional approaches such as the maximum likelihood classifier. Most of the time, classification distinguishes only between trees/annual or grain. It has been difficult to accurately determine the cannabis mixed with other plants. In this paper, a mixed distribution models approach is applied to classify pure and mix cannabis parcels using Worldview-2 imagery in the Lakes region of Turkey. Five different land use types (i.e. sunflower, maize, bare soil, and cannabis) were identified in the image. A constrained Gaussian mixture discriminant analysis (GMDA) was used to unmix the image. In the study, 255 reflectance ratios derived from spectral signatures of seven bands (Blue-Green-Yellow-Red-Rededge-NIR1-NIR2) were randomly arranged as 80% for training and 20% for test data. Gaussian mixed distribution model approach is proved to be an effective and convenient way to combine very high spatial resolution imagery for distinguishing cannabis vegetation. Based on the overall accuracies of the classification, the Gaussian mixed distribution model was found to be very successful to achieve image classification tasks. This approach is sensitive to capture the illegal cannabis planting areas in the large plain. This approach can also be used for monitoring and determination with spectral reflections in illegal cannabis planting areas.

Keywords: Gaussian mixture discriminant analysis, spectral mixture model, Worldview-2, land parcels

Procedia PDF Downloads 185

Authors: Carmen M. Gonzalez-Henriquez, Mauricio A. Sarabia-Vallejos, Juan Rodriguez-Hernandez

Abstract:

DMAEMA, as a monomer, has been widely studied and used in several application fields due to their pH-sensitive capacity (tertiary amine protonation), being relevant in the biomedical area as a potential carrier for drugs focused on the treatment of genetic or acquired diseases (efficient gene transfection), among others. Additionally, the inhibition of bacterial growth and, therefore, their antimicrobial activity, can be used as dual-functional antifogging/antimicrobial polymer coatings. According to their interesting physicochemical characteristics and biocompatible properties, DMAEMA was used as a monomer to synthesize a smart pH-sensitive hydrogel, namely poly(HEMA-co-PEGDA575-co-DMAEMA). Thus, different mole ratios (ranging from 5:1:0 to 0:1:5, according to the mole ratio between HEMA, PEGDA, and DEAEMA, respectively) were used in this research. The surface patterns formed via a two-step polymerization (redox- and photo-polymerization) were first chemically studied via 1H-NMR and elemental analysis. Secondly, the samples were morphologically analyzed by using Field-Emission Scanning Electron Microscopy (FE-SEM) and Atomic Force Microscopy (AFM) techniques. Then, a particular relation between HEMA, PEGDA, and DEAEMA (0:1:5) was also characterized at three different pH (5.4, 7.4 and 8.3). The hydrodynamic radius and zeta potential of the micro-hydrogel particles (emulsion) were carried out as a possible control for morphology, exploring the effect that produces hydrogel micelle dimensions in the wavelength, height, and roughness of the wrinkled patterns. Finally, contact angle and cross-hatch adhesion test was carried out for the hydrogels supported on glass using TSM-silanized surfaces in order to measure their mechanical properties.

Keywords: wrinkled patterns, smart pH-sensitive hydrogels, hydrogel micelle diameter, adhesion tests

Procedia PDF Downloads 196