Search results for: classification of matter

Authors: Carlos Tarmeño Noriega, Igor Aguilar Alonso

Abstract:

Fungal diseases are common in vineyards; they cause a decrease in the quality of the products that can be sold, generating distrust of the customer towards the seller when buying fruit. Currently, technology allows the classification of fruits according to their characteristics thanks to artificial intelligence. This study proposes the implementation of a control system that allows the identification of the main fungal diseases present in the Italia grape, making use of a convolutional neural network (CNN), OpenCV, and TensorFlow. The methodology used was based on a collection of 20 articles referring to the proposed research on quality control, classification, and recognition of fruits through artificial vision techniques.

Keywords: computer vision, convolutional neural networks, quality control, fruit market, OpenCV, TensorFlow

Procedia PDF Downloads 83

Authors: Ruchika Malhotra, Megha Khanna

Abstract:

The development of change prediction models can help the software practitioners in planning testing and inspection resources at early phases of software development. However, a major challenge faced during the training process of any classification model is the imbalanced nature of the software quality data. A data with very few minority outcome categories leads to inefficient learning process and a classification model developed from the imbalanced data generally does not predict these minority categories correctly. Thus, for a given dataset, a minority of classes may be change prone whereas a majority of classes may be non-change prone. This study explores various alternatives for adeptly handling the imbalanced software quality data using different sampling methods and effective MetaCost learners. The study also analyzes and justifies the use of different performance metrics while dealing with the imbalanced data. In order to empirically validate different alternatives, the study uses change data from three application packages of open-source Android data set and evaluates the performance of six different machine learning techniques. The results of the study indicate extensive improvement in the performance of the classification models when using resampling method and robust performance measures.

Keywords: change proneness, empirical validation, imbalanced learning, machine learning techniques, object-oriented metrics

Procedia PDF Downloads 418

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

Abstract:

Cannabis is mostly used for drug production. In some countries, an excessive amount of illegal cannabis is cultivated and sold. Most of the illegal cannabis cultivation occurs on the lands far from settlements. In farmlands, it is cultivated with other crops. In this method, cannabis is surrounded by tall plants like corn and sunflower. It is also cultivated with tall crops as the mixed culture. The common method of the determination of the illegal cultivation areas is to investigate the information obtained from people. This method is not sufficient for the determination of illegal cultivation in remote areas. For this reason, more effective methods are needed for the determination of illegal cultivation. Remote Sensing is one of the most important technologies to monitor the plant growth on the land. The aim of this study is to monitor cannabis cultivation area using satellite imagery. The main purpose of this study was to develop an applicable method for monitoring the cannabis cultivation. For this purpose, cannabis was grown as single or surrounded by the corn and sunflower in plots. The morphological characteristics of cannabis were recorded two times per month during the vegetation period. The spectral signature library was created with the spectroradiometer. The parcels were monitored with high-resolution satellite imagery. With the processing of satellite imagery, the cultivation areas of cannabis were classified. To separate the Cannabis plots from the other plants, the multiresolution segmentation algorithm was found to be the most successful for classification. WorldView Improved Vegetative Index (WV-VI) classification was the most accurate method for monitoring the plant density. As a result, an object-based classification method and vegetation indices were sufficient for monitoring the cannabis cultivation in multi-temporal Earthwiev images.

Keywords: Cannabis, drug, remote sensing, object-based classification

Procedia PDF Downloads 272

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 434

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 227

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 97

Authors: George Zhou, Yunchan Chen, Candace Chien

Abstract:

Kidney replacement therapy is the current standard of care for end-stage renal diseases. In-center or home hemodialysis remains an integral component of the therapeutic regimen. Arteriovenous fistulas (AVF) make up the vascular circuit through which blood is filtered and returned. Naturally, AVF patency determines whether adequate clearance and filtration can be achieved and directly influences clinical outcomes. Our aim was to build a deep learning model for automated AVF stenosis screening based on the sound of blood flow through the AVF. A total of 311 patients with AVF were enrolled in this study. Blood flow sounds were collected using a digital stethoscope. For each patient, blood flow sounds were collected at 6 different locations along the patient’s AVF. The 6 locations are artery, anastomosis, distal vein, middle vein, proximal vein, and venous arch. A total of 1866 sounds were collected. The blood flow sounds are labeled as “patent” (normal) or “stenotic” (abnormal). The labels are validated from concurrent ultrasound. Our dataset included 1527 “patent” and 339 “stenotic” sounds. We show that blood flow sounds vary significantly along the AVF. For example, the blood flow sound is loudest at the anastomosis site and softest at the cephalic arch. Contextualizing the sound with location metadata significantly improves classification performance. How to encode and incorporate categorical metadata is an active area of research1. Herein, we study ordinal (i.e., integer) encoding schemes. The numerical representation is concatenated to the flattened feature vector. We train a vision transformer (ViT) on spectrogram image representations of the sound and demonstrate that using scalar multiples of our integer encodings improves classification performance. Models are evaluated using a 10-fold cross-validation procedure. The baseline performance of our ViT without any location metadata achieves an AuROC and AuPRC of 0.68 ± 0.05 and 0.28 ± 0.09, respectively. Using the following encodings of Artery:0; Arch: 1; Proximal: 2; Middle: 3; Distal 4: Anastomosis: 5, the ViT achieves an AuROC and AuPRC of 0.69 ± 0.06 and 0.30 ± 0.10, respectively. Using the following encodings of Artery:0; Arch: 10; Proximal: 20; Middle: 30; Distal 40: Anastomosis: 50, the ViT achieves an AuROC and AuPRC of 0.74 ± 0.06 and 0.38 ± 0.10, respectively. Using the following encodings of Artery:0; Arch: 100; Proximal: 200; Middle: 300; Distal 400: Anastomosis: 500, the ViT achieves an AuROC and AuPRC of 0.78 ± 0.06 and 0.43 ± 0.11. respectively. Interestingly, we see that using increasing scalar multiples of our integer encoding scheme (i.e., encoding “venous arch” as 1,10,100) results in progressively improved performance. In theory, the integer values do not matter since we are optimizing the same loss function; the model can learn to increase or decrease the weights associated with location encodings and converge on the same solution. However, in the setting of limited data and computation resources, increasing the importance at initialization either leads to faster convergence or helps the model escape a local minimum.

Keywords: arteriovenous fistula, blood flow sounds, metadata encoding, deep learning

Procedia PDF Downloads 87

Authors: Wantanee Polviset, N. Prakobsaeng, N. Wetchakama, C. Yuangklang

Abstract:

The aim of this study was to evaluate the effect of soybean oil, palm oil and sunflower oil supplementations in total mixed ration on voluntary feed intake, dry matter (DM) digestibility and blood metabolize in crossbred Thai native x American Brahman Cattle. Three Thai native x American Brahman cattle, one-year-old with liveweight of 116±22.59 kg, were randomly assigned according to a 3 x 3 latin square design. Each period of feeding lasted for 21 days to receive three dietary treatments were soybean oil, palm oil and sunflower oil supplementation at 5%. During the experimental periods, all cattle were fed a diet with total mixed ration containing roughage to concentrate ratio of 40:60 and rice straw was used as a roughage source. Based on the present study, the results revealed that voluntary feed intake (kgDM/head/day) and %BW DM intake were not affected (P>0.05), whereas percentage of dry matter digestibility was greater with the soybean oil supplementation (P<0.01). It was also found that blood glucose, blood urea nitrogen, cholesterol, triglyceride, high density lipoprotein and low density lipoprotein in plasma were similar among treatments. Based on this study, supplementing 5% soybean oil in total mixed ration (TMR) diets was suitable in beef cattle without any effect dry matter digestibility and blood metabolites.

Keywords: plant oils, feed intake, blood metabolize, crossbred Thai native x Brahman cattle

Procedia PDF Downloads 322

Authors: Tsetsegmaa A., Bayarsuren B., Altantsetseg Ts.

Abstract:

To make the best decision on reducing harmful emissions from buses, we need to have a clear understanding of the current state of their actual emissions. The emissions from city buses running on high sulfur fuel, particularly particulate matter (PM) and nitrogen oxides (NOx) from the exhaust gases of conventional diesel engines, have been studied and measured with and without diesel particulate filter (DPF) in Ulaanbaatar city. The study was conducted by using the PEMS (Portable Emissions Measurement System) and gravimetric method in real traffic conditions. The obtained data were used to determine the actual emission rates and to evaluate the effectiveness of the selected particulate filters. Actual road and daily PM emissions from city buses were determined during the warm and cold seasons. A bus with an average daily mileage of 242 km was found to emit 166.155 g of PM into the city's atmosphere on average per day, with 141.3 g in summer and 175.8 g in winter. The actual PM of the city bus is 0.6866 g/km. The concentration of NOx in the exhaust gas averages 1410.94 ppm. The use of DPF reduced the exhaust gas opacity of 24 buses by an average of 97% and filtered a total of 340.4 kg of soot from these buses over a period of six months. Retrofitting an old conventional diesel engine with cassette-type silicon carbide (SiC) DPF, despite the laboriousness of cleaning, can significantly reduce particulate matter emissions. Innovation: First comprehensive road PM and NOx emission dataset and actual road emissions from public buses have been identified. PM and NOx mathematical model equations have been estimated as a function of the bus technical speed and engine revolution with and without DPF.

Keywords: conventional diesel, silicon carbide, real-time onboard measurements, particulate matter, diesel retrofit, fuel sulphur

Procedia PDF Downloads 164

Authors: Elias L. Souza, Noeli Sellin, Cintia Marangoni, Ozair Souza

Abstract:

Among the different forms of reuse and recovery of agro-residual waste is the production of biofuels. The production of second-generation ethanol has been evaluated and proposed as one of the technically viable alternatives for this purpose. This research work employed the banana pseudostem as biomass. Two different chemical pre-treatment methods (acid hydrolisis with H2SO4 2% w/w and alkaline hydrolysis with NaOH 3% w/w) of dry and milled biomass (70 g/L of dry matter, ms) were assessed, and the corresponding reducing sugars yield, AR, (YAR), after enzymatic saccharification, were determined. The effect on YAR by increasing the dry matter (ms) from 70 to 100 g/L, in dry and milled biomass and also fresh, were analyzed. Changes in cellulose crystallinity and in biomass surface morphology due to the different chemical pre-treatments were analyzed by X-ray diffraction and scanning electron microscopy. The acid pre-treatment resulted in higher YAR values, whether related to the cellulose content under saccharification (RAR = 79,48) or to the biomass concentration employed (YAR/ms = 32,8%). In a comparison between alkaline and acid pre-treatments, the latter led to an increase in the cellulose content of the reaction mixture from 52,8 to 59,8%; also, to a reduction of the cellulose crystallinity index from 51,19 to 33,34% and increases in RAR (43,1%) and YAR/ms (39,5%). The increase of dry matter (ms) bran from 70 to 100 g/L in the acid pre-treatment, resulted in a decrease of average yields in RAR (43,1%) and YAR/ms (18,2%). Using the pseudostem fresh with broth removed, whether for 70 g/L concentration or 100 g/L in dry matter (ms), similarly to the alkaline pre-treatment, has led to lower average values in RAR (67,2% and 42,2%) and in YAR/ms (28,4% e 17,8%), respectively. The acid pre-treated and saccharificated biomass broth was detoxificated with different activated carbon contents (1,2 and 4% w/v), concentrated up to AR = 100 g/L and fermented by Saccharomyces cerevisiae. The yield values (YP/AR) and productivity (QP) in ethanol were determined and compared to those values obtained from the fermentation of non-concentrated/non-detoxificated broth (AR = 18 g/L) and concentrated/non-detoxificated broth (AR = 100 g/L). The highest average value for YP/AR (0,46 g/g) was obtained from the fermentation of non-concentrated broth. This value did not present a significant difference (p<0,05) when compared to the YP/RS related to the broth concentrated and detoxificated by activated carbon 1% w/v (YP/AR = 0,41 g/g). However, a higher ethanol productivity (QP = 1,44 g/L.h) was achieved through broth detoxification. This value was 75% higher than the average QP determined using concentrated and non-detoxificated broth (QP = 0,82 g/L.h), and 22% higher than the QP found in the non-concentrated broth (QP = 1,18 g/L.h).

Keywords: biofuels, biomass, saccharification, bioethanol

Procedia PDF Downloads 343

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 297

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 338

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 259

Authors: Mustafa Alhamdi

Abstract:

Industrial application to classify gamma rays and neutron events is investigated in this study using deep machine learning. The identification using a convolutional neural network and recursive neural network showed a significant improvement in predication accuracy in a variety of applications. The ability to identify the isotope type and activity from spectral information depends on feature extraction methods, followed by classification. The features extracted from the spectrum profiles try to find patterns and relationships to present the actual spectrum energy in low dimensional space. Increasing the level of separation between classes in feature space improves the possibility to enhance classification accuracy. The nonlinear nature to extract features by neural network contains a variety of transformation and mathematical optimization, while principal component analysis depends on linear transformations to extract features and subsequently improve the classification accuracy. In this paper, the isotope spectrum information has been preprocessed by finding the frequencies components relative to time and using them as a training dataset. Fourier transform implementation to extract frequencies component has been optimized by a suitable windowing function. Training and validation samples of different isotope profiles interacted with CdTe crystal have been simulated using Geant4. The readout electronic noise has been simulated by optimizing the mean and variance of normal distribution. Ensemble learning by combing voting of many models managed to improve the classification accuracy of neural networks. The ability to discriminate gamma and neutron events in a single predication approach using deep machine learning has shown high accuracy using deep learning. The paper findings show the ability to improve the classification accuracy by applying the spectrogram preprocessing stage to the gamma and neutron spectrums of different isotopes. Tuning deep machine learning models by hyperparameter optimization of neural network models enhanced the separation in the latent space and provided the ability to extend the number of detected isotopes in the training database. Ensemble learning contributed significantly to improve the final prediction.

Keywords: machine learning, nuclear physics, Monte Carlo simulation, noise estimation, feature extraction, classification

Procedia PDF Downloads 150

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 155

Authors: Amrit Ladhani

Abstract:

The cyclic universe theory is a model of cosmic evolution according to which the universe undergoes endless cycles of expansion and cooling, each beginning with a “big bang” and ending in a “big crunch”. In this paper, we propose a unique property of Space-time. This particular and marvelous nature of space shows us that space can stretch, expand, and shrink. This property of space is caused by the size of the universe change over time: growing or shrinking. The observed accelerated expansion, which relates to the stretching of Shrunk space for the new theory, is derived. This theory is based on three underlying notions: First, the Big Bang is not the beginning of Space-time, but rather, at the very beginning fraction of a second, there was an infinite force of infinite Shrunk space in the cosmic singularity that force gave rise to the big bang and caused the rapidly growing of space, and all other forms of energy are transformed into new matter and radiation and a new period of expansion and cooling begins. Second, there was a previous phase leading up to it, with multiple cycles of contraction and expansion that repeat indefinitely. Third, the two principal long-range forces are the gravitational force and the repulsive force generated by shrink space. They are the two most fundamental quantities in the universe that govern cosmic evolution. They may provide the clockwork mechanism that operates our eternal cyclic universe. The universe will not continue to expand forever; no need, however, for dark energy and dark matter. This new model of Space-time and its unique properties enables us to describe a sequence of events from the Big Bang to the Big Crunch.

Keywords: dark matter, dark energy, cosmology, big bang and big crunch

Procedia PDF Downloads 78

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 452

Authors: Lee Artz

Abstract:

Based on content analyses of major US media, immediately following the George Floyd killing in May 2020, some mayors and local, state, and national officials offered favorable representations of protests against police violence. As the protest movement grew to historic proportions with 26 million joining actions in large cities and small towns, dominant representations of racism by elected officials and leading media shifted—replacing both the voices and demands of protestors with representations by elected officials. Major media quoted Black mayors and Congressional representatives who emphasized concerns about looting and the disruption of public safety. Media coverage privileged elected officials who criticized movement demands for defunding police and deplored isolated instances of property damaged by protestors. Subsequently, public opinion polls saw an increase in concern for law and order tropes and a decrease in support for protests against police violence. Black Lives Matter and local organizations had no coordinated response and no effective means of communication to counter dominant representations voiced by politicians and globally disseminated by major media. Politician and media-instigated public opinion shifts indicate that social movements need their own means of communication and collective decision-making--both of which were largely missing from Black Lives Matter leaders, leading to disaffection and a political split by more than 20 local affiliates. By itself, social media by myriad individuals and groups had limited purchase as a means for social movement communication and organization. Lacking a collaborative, coordinated strategy, organization, and independent media, the loose network of Black Lives Matter groups was unable to offer more accurate, democratic, and favorable representations of protests and their demands for more justice and equality. The fight for equality was diverted by the fight for representation.

Keywords: black lives matter, public opinion, racism, representations, social movements

Procedia PDF Downloads 179

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 93

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 133

Authors: Khalifa Alatresh, Mirac Aydin

Abstract:

This research explores the impacts of irrigation by treated wastewater (TWW) on the mineralogical and chemical attributes of sandy calcareous soils in the Southern region of Misurata. Soil samples obtained from three horizons (A, B, and C) of six TWW-irrigated pedons (29years) and six other pedons from nearby non-irrigated areas (dry-control). The results demonstrated that the TWW-irrigated pedons had significantly higher salinity (EC), sodium adsorption ratio (SAR), exchangeable sodium percentage (ESP), cation exchange capacity (CEC), available phosphor (AP), total nitrogen (TN), and organic matter (OM) relative to the control pedons. Nonetheless, all the values of interest (EC < 4000 µs/cm < SAR < 13, pH < 8.5 and ESP < 15) remained lower than the thresholds, showing no issues with sodicity or salinity. Irrigated pedons contained significantly higher amounts of total clay and showed an altered distribution of particle sizes and minerals identified (quartz, calcite, microcline, albite, anorthite, and dolomite) within the profile. The observed results included the occurrence of Margarite, Anorthite, Chabazite, and Tridymite minerals after the application of TWW in small quantities that are not enough to influence soil genesis and classification.0,51 cm.

Keywords: treated wastewater, sandy calcareous soils, soil mineralogy, and chemistry

Procedia PDF Downloads 114

Authors: Alireza Nejadmohammad Namaghi

Abstract:

Investigators have reported that mulches increase production potential in arid and semi arid lands. Mulches are covering materials that are used on soil surface for efficiency irrigation, erosion control, weed control, evaporation decrease and improvement of water perpetration. Our aim and local situation determine the kind of material that we can use. In this research we used different mulches including chemical mulch (M1), Aquasorb polymer, manure mulch (M2), Residue mulch (M3) and polyethylene mulch (M4), with control treatment (M0), without usage of mulch, on germination, biomass dry matter and cottonseed yield (Varamin variety) in Kashan area. Randomized complete block (RCB) design have measured the cotton yield with 3 replications for measuring the biomass dry matter and 4 replication in tow irrigation periods as 7 and 14 days. Germination percentage for M0, M1, M2, M3 and M4 treatment were receptivity 64, 65, 76, 57 and 72% Biomass dry matter average for M0, M1, M2, M3 and M4 treatment were receptivity 276, 306, 426, 403 and 476 gram per plot. M4 treatment (polyethylene Mulch) had the most effect, M2 and M3 had no significant as well as M0 and M1. Total yield average with respect to 7 days irrigation for M0, M1, M2, M3 and M4 treatment were receptivity 700, 725, 857, 1057 and 1273 gram per plot. Dunken ne multiple showed no significant different among M0, M1, M2, and M3, but M4 ahs the most effect on yield. Total yield average with respect to 14 days irrigation for M0, M1, M2, M3 and M4 treatment were receptivity 535, 507, 690, 957 and 1047 gram per plot. These were significant difference between all treatments and control treatment. Results showed that used different mulches with water decrease in dry situation can increase the yield significantly.

Keywords: mulch, cotton, arid land management, irrigation systems

Procedia PDF Downloads 84

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 130

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 257

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 239

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 54

Authors: Mengsha Yin

Abstract:

Extractable organic matter (EOM) from thirty-six biogenic gas source rocks from the Sanhu Depression in Qaidam Basin in northwestern China were obtained via Soxhlet extraction. Twenty-nine of them were conducted SARA (Saturates, Aromatics, Resins and Asphaltenes) separation for bulk composition analysis. Saturated and aromatic fractions of all the extractions were analyzed by Gas Chromatography-Mass Spectrometry (GC-MS) to investigate the compound compositions. More abundant n-alkanes, naphthalene, phenanthrene, dibenzothiophene and their alkylated products occur in samples in shallower depths. From 2000m downward, concentrations of these compounds increase sharply, and concentration ratios of more-over-less biodegradation susceptible compounds coincidently decrease dramatically. ∑iC15-16, 18-20/∑nC15-16, 18-20 and hopanoids/∑n-alkanes concentration ratios and mono- and tri-aromatic sterane concentrations and concentration ratios frequently fluctuate with depth rather than trend with it, reflecting effects from organic input and paleoenvironments other than biodegradation. Saturated and aromatic compound distributions on the saturates and aromatics total ion chromatogram (TIC) traces of samples display different degrees of biodegradation. Dramatic and simultaneous variations in compound concentrations and their ratios at 2000m and their changes with depth underneath cooperatively justified the crucial control of burial depth on organic matter biodegradation scales in source rocks and prompted the proposition that 2000m is the bottom depth boundary for active microbial activities in this study. The study helps to better curb the conditions where effective source rocks occur in terms of depth in the Sanhu biogenic gas fields and calls for additional attention to source rock pore size estimation during biogenic gas source rock appraisals.

Keywords: pore space, Sanhu depression, saturated and aromatic hydrocarbon compound concentration, source rock organic matter biodegradation, total ion chromatogram

Procedia PDF Downloads 156

Authors: Ma Cecilia Siva

Abstract:

This study introduces a Bidirectional Encoder Representations from Transformers (BERT)-based machine learning model aimed at improving educational counseling by automating the process of recommending academic strands for students. The framework is designed to streamline and enhance the strand selection process by analyzing students' profiles and suggesting suitable academic paths based on their interests, strengths, and goals. Data was gathered from a sample of 200 grade 10 students, which included personal essays and survey responses relevant to strand alignment. After thorough preprocessing, the text data was tokenized, label-encoded, and input into a fine-tuned BERT model set up for multi-label classification. The model was optimized for balanced accuracy and computational efficiency, featuring a multi-category classification layer with sigmoid activation for independent strand predictions. Performance metrics showed an F1 score of 88%, indicating a well-balanced model with precision at 80% and recall at 100%, demonstrating its effectiveness in providing reliable recommendations while reducing irrelevant strand suggestions. To facilitate practical use, the final deployment phase created a recommendation framework that processes new student data through the trained model and generates personalized academic strand suggestions. This automated recommendation system presents a scalable solution for academic guidance, potentially enhancing student satisfaction and alignment with educational objectives. The study's findings indicate that expanding the data set, integrating additional features, and refining the model iteratively could improve the framework's accuracy and broaden its applicability in various educational contexts.

Keywords: tokenized, sigmoid activation, transformer, multi category classification

Procedia PDF Downloads 8

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 137

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 395