Search results for: satellite imagery classification

Authors: Urvee B. Trivedi, U. D. Dalal

Abstract:

As wireless communication services grow quickly; the seriousness of spectrum utilization has been on the rise gradually. An emerging technology, cognitive radio has come out to solve today’s spectrum scarcity problem. To support the spectrum reuse functionality, secondary users are required to sense the radio frequency environment, and once the primary users are found to be active, the secondary users are required to vacate the channel within a certain amount of time. Therefore, spectrum sensing is of significant importance. Once sensing is done, different prediction rules apply to classify the traffic pattern of primary user. Primary user follows two types of traffic patterns: periodic and stochastic ON-OFF patterns. A cognitive radio can learn the patterns in different channels over time. Two types of classification methods are discussed in this paper, by considering edge detection and by using autocorrelation function. Edge detection method has a high accuracy but it cannot tolerate sensing errors. Autocorrelation-based classification is applicable in the real environment as it can tolerate some amount of sensing errors.

Keywords: cognitive radio (CR), probability of detection (PD), probability of false alarm (PF), primary user (PU), secondary user (SU), fast Fourier transform (FFT), signal to noise ratio (SNR)

Procedia PDF Downloads 333

Authors: Mahtab Davari, Charles Edward Okon, Somayeh Aghanavesi

Abstract:

Every institute of learning is usually interested in the performance of enrolled students. The level of these performances determines the approach an institute of study may adopt in rendering academic services. The focus of this paper is to evaluate students' academic performance in given courses of study using machine learning methods. This study evaluated various supervised machine learning classification algorithms such as Logistic Regression (LR), Support Vector Machine, Random Forest, Decision Tree, K-Nearest Neighbors, Linear Discriminant Analysis, and Quadratic Discriminant Analysis, using selected features to predict study performance. The accuracy, precision, recall, and F1 score obtained from a 5-Fold Cross-Validation were used to determine the best classification algorithm to predict students’ performances. SVM (using a linear kernel), LDA, and LR were identified as the best-performing machine learning methods. Also, using the LR model, this study identified students' educational habits such as reading and paying attention in class as strong determinants for a student to have an above-average performance. Other important features include the academic history of the student and work. Demographic factors such as age, gender, high school graduation, etc., had no significant effect on a student's performance.

Keywords: student performance, supervised machine learning, classification, cross-validation, prediction

Procedia PDF Downloads 98

Authors: Girish J. Showkatramani, Arthi M. Krishna, Sashi Nareddi, Naresh Nula, Aaron Pepe, Glen Brown, Greg Gabel, Chris Doninger

Abstract:

Trademark examination and approval is a complex process that involves analysis and review of the design components of the marks such as the visual representation as well as the textual data associated with marks such as marks' description. Currently, the process of identifying marks with similar visual representation is done manually in United States Patent and Trademark Office (USPTO) and takes a considerable amount of time. Moreover, the accuracy of these searches depends heavily on the experts determining the trademark design codes used to catalog the visual design codes in the mark. In this study, we explore several methods to automate trademark design code classification. Based on recent successes of convolutional neural networks in image classification, we have used several different convolutional neural networks such as Google’s Inception v3, Inception-ResNet-v2, and Xception net. The study also looks into other techniques to augment the results from CNNs such as using Open Source Computer Vision Library (OpenCV) to pre-process the images. This paper reports the results of the various models trained on year of annotated trademark images.

Keywords: trademark design code, convolutional neural networks, trademark image classification, trademark image search, Inception-ResNet-v2

Procedia PDF Downloads 212

Authors: Arturo Maldonado

Abstract:

In the iron ore mining industry, the intact strength of rock units is defined using the uniaxial compressive strength (UCS). This parameter is very important for the classification of shale materials, allowing the split between rock and cohesive soils based on the magnitude of UCS. For this research, it is assumed that UCS less than or equal to 1 MPa is representative of soils. Several researchers have anticipated that the magnitude of UCS reduces with weathering progression, also since UCS is a directional property, its magnitude depends upon the rock fabric orientation. Thus, the paper presents how the UCS of shales is affected by both weathering grade and bedding orientation. The mineralogy of shales has been defined using Hyper-spectral and chemical assays to define the mineral constituents of shale and other non-shale materials. Geological classification tools have been used to define distinct lithological types, and in this manner, the author uses mineralogical datasets to recognize and isolate shales from other rock types and develop tertiary plots for fresh and weathered shales. The mineralogical classification of shales has reduced the contamination of lithology types and facilitated the study of the physical factors affecting the intact strength of shales, like anisotropic strength due to bedding orientation. The analysis of mineralogical characteristics of shales is perhaps the most important contribution of this paper to other researchers who may wish to explore similar methods.

Keywords: rock mechanics, mineralogy, shales, weathering, anisotropy

Procedia PDF Downloads 26

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 57

Authors: Ankur P. Sati, Manju Mohan

Abstract:

The hazardous combination of smoke and pollutant gases, smog, is harmful for health. There are strong evidences that the Agricultural waste burning (AWB) in the Northern India leads to adverse air quality in Delhi and its surrounding regions. A severe smog episode was observed over Delhi, India during November 2012 which resulted in very low visibility and various respiratory problems. Very high values of pollutants (PM10 as high as 989 µg m-3, PM2.5 as high as 585 µg m-3 an NO2 as high as 540 µg m-3) were measured all over Delhi during the smog episode. Ultra Violet Aerosol Index (UVAI) from Aura satellite and Aerosol Optical Depth (AOD) are used in the present study along with the output trajectories from HYSPLIT model and the in-situ data. Satellite data also reveal that AOD, UVAI are always at its highest during the farmfires duration in Punjab region of India and the extent of these farmfires may be increasing. It is observed that during the smog episode all the AOD, UVAI, PM2.5 and PM10 values surpassed those of the Diwali period (one of the most polluted events in the city) by a considerable amount at all stations across Delhi. The parameters used from the remote sensing data and the ground based observations at various stations across Delhi are very well in agreement about the intensity of Smog episode. The analysis clearly shows that regional pollution can have greater contributions in deteriorating the air quality than the local under adverse meteorological conditions.

Keywords: smog, farmfires, AOD, remote sensing

Procedia PDF Downloads 224

Authors: Tamar Trop, Boris Portnov

Abstract:

Public Space Lighting (PSL) of outdoor urban areas promotes comfort, defines spaces and neighborhood identities, enhances perceived safety and security, and contributes to residential satisfaction and wellbeing. However, if excessive or misdirected, PSL leads to unnecessary energy waste and increased greenhouse gas emissions, poses a non-negligible threat to the nocturnal environment, and may become a potential health hazard. At present, PSL is designed according to international, regional, and national standards, which consolidate best practice. Yet, knowledge regarding the optimal light characteristics needed for creating a perception of personal comfort and safety in densely populated residential areas, and the factors associated with this perception, is still scarce. The presented study suggests a paradigm shift in designing PSL towards a user-centered approach, which incorporates pedestrians' perspectives into the process. The study is an ongoing joint research project between China and Israel Ministries of Science and Technology. Its main objectives are to reveal inhabitants' perceptions of and preferences for PSL in different densely populated neighborhoods in China and Israel, and to develop a model that links instrumentally measured parameters of PSL (e.g., intensity, spectra and glare) with its perceived comfort and quality, while controlling for three groups of attributes: locational, temporal, and individual. To investigate measured and perceived PSL, the study employed various research methods and data collection tools, developed a location-based mobile application, and used multiple data sources, such as satellite multi-spectral night-time light imagery, census statistics, and detailed planning schemes. One of the study’s preliminary findings is that higher sense of safety in the investigated neighborhoods is not associated with higher levels of light intensity. This implies potential for energy saving in brightly illuminated residential areas. Study findings might contribute to the design of a smart and adaptive PSL strategy that enhances pedestrians’ perceived safety and comfort while reducing light pollution and energy consumption.

Keywords: energy efficiency, light pollution, public space lighting, PSL, safety perceptions

Procedia PDF Downloads 111

Authors: R. Vidhya, M. Navamuniyammal M. Sivakumar, S. Reeta

Abstract:

The unplanned urbanization affects the environment due to pollution, conditions of the atmosphere, decreased vegetation and the pervious and impervious soil surface. Considered to be a cumulative effect of all these impacts is the Urban Heat Island. In this paper, the urban heat island effect is studied for the Chennai city, TamilNadu, South India using satellite remote sensing data. LANDSAT 8 OLI and TIRS DATA acquired on 9th September 2014 were used to Land Surface Temperature (LST) map, vegetation fraction map, Impervious surface fraction, Normalized Difference Water Index (NDWI), Normalized Difference Building Index (NDBI) and Normalized Difference Vegetation Index (NDVI) map. The relationship among LST, Vegetation fraction, NDBI, NDWI, and NDVI was calculated. The Chennai city’s Urban Heat Island effect is significant, and the results indicate LST has strong negative correlation with the vegetation present and positive correlation with NDBI. The vegetation is the main factor to control urban heat island effect issues in urban area like Chennai City. This study will help in developing measures to land use planning to reduce the heat effects in urban area based on remote sensing derivatives.

Keywords: land surface temperature, brightness temperature, emissivity, vegetation index

Procedia PDF Downloads 258

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 399

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 415

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 198

Authors: Lela Gadrani, Mariam Tsitsagi

Abstract:

Human is a part of the urban landscape and responsible for it. Urbanization of cities includes the longest phase; thus none of the environment ever undergoes such anthropogenic impact as the area of large cities. The post-Soviet period is very interesting in terms of scientific research. The changes that have occurred in the cities since the collapse of the Soviet Union have not yet been analyzed best to our knowledge. In this context, the aim of this paper is to analyze the changes in the land use of the three large cities of Georgia (Tbilisi, Kutaisi, Batumi). Tbilisi as a capital city, Batumi as a port city, and Kutaisi as a former industrial center. Data used during the research process are conventionally divided into satellite and supporting materials. For this purpose, the largest topographic maps (1:10 000) of all three cities were analyzed, Tbilisi General Plans (1896, 1924), Tbilisi and Kutaisi historical maps. The main emphasis was placed on the classification of Landsat images. In this case, we have classified the images LULC (LandUse / LandCover) of all three cities taken in 1987 and 2016 using the supervised and unsupervised methods. All the procedures were performed in the programs: Arc GIS 10.3.1 and ENVI 5.0. In each classification we have singled out the following classes: built-up area, water bodies, agricultural lands, green cover and bare soil, and calculated the areas occupied by them. In order to check the validity of the obtained results, additionally we used the higher resolution images of CORONA and Sentinel. Ultimately we identified the changes that took place in the land use in the post-Soviet period in the above cities. According to the results, a large wave of changes touched Tbilisi and Batumi, though in different periods. It turned out that in the case of Tbilisi, the area of developed territory has increased by 13.9% compared to the 1987 data, which is certainly happening at the expense of agricultural land and green cover, in particular, the area of agricultural lands has decreased by 4.97%; and the green cover by 5.67%. It should be noted that Batumi has obviously overtaken the country's capital in terms of development. With the unaided eye it is clear that in comparison with other regions of Georgia, everything is different in Batumi. In fact, Batumi is an unofficial summer capital of Georgia. Undoubtedly, Batumi’s development is very important both in economic and social terms. However, there is a danger that in the uneven conditions of urban development, we will eventually get a developed center - Batumi, and multiple underdeveloped peripheries around it. Analysis of the changes in the land use is of utmost importance not only for quantitative evaluation of the changes already implemented, but for future modeling and prognosis of urban development. Raster data containing the classes of land use is an integral part of the city's prognostic models.

Keywords: analysis, geo information system, remote sensing, LULC

Procedia PDF Downloads 438

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 78

Authors: Maria A. Castillo H., Andres R. Leandro, Jose F. Bienvenido B.

Abstract:

During the last 20 years, the globalization of economies, population growth, and the increase in the consumption of fresh agricultural products have generated greater demand for ornamentals, flowers, fresh fruits, and vegetables, mainly from tropical areas. This market situation has demanded greater competitiveness and control over production, with more efficient protected agriculture technologies, which provide greater productivity and allow us to guarantee the quality and quantity that is required in a constant and sustainable way. Guatemala, located in the north of Central America, is one of the largest exporters of agricultural products in the region and exports fresh vegetables, flowers, fruits, ornamental plants, and foliage, most of which were grown in greenhouses. Although there are no official agricultural statistics on greenhouse production, several thesis works, and congress reports have presented consistent estimates. A wide range of protection structures and roofing materials are used, from the most basic and simple ones for rain control to highly technical and automated structures connected with remote sensors for monitoring and control of crops. With this breadth of technological models, it is necessary to analyze georeferenced data related to the cultivated area, to the different existing models, and to the covering materials, integrated with altitude, climate, and soil data. The georeferenced registration of the production units, the data collection with digital tools, the use of satellite images, and geographic information systems (GIS) provide reliable tools to elaborate more complete, agile, and dynamic information maps. This study details a methodology proposed for gathering georeferenced data of high protection structures (greenhouses) in Guatemala, structured in four phases: diagnosis of available information, the definition of the geographic frame, selection of satellite images, and integration with an information system geographic (GIS). It especially takes account of the actual lack of complete data in order to obtain a reliable decision-making system; this gap is solved through the proposed methodology. A summary of the results is presented in each phase, and finally, an evaluation with some improvements and tentative recommendations for further research is added. The main contribution of this study is to propose a methodology that allows to reduce the gap of georeferenced data in protected agriculture in this specific area where data is not generally available and to provide data of better quality, traceability, accuracy, and certainty for the strategic agricultural decision öaking, applicable to other crops, production models and similar/neighboring geographic areas.

Keywords: greenhouses, protected agriculture, GIS, Guatemala, satellite image, digital tools, precision agriculture

Procedia PDF Downloads 179

Authors: Lai-Fen Yang

Abstract:

In this increasingly visual world, how can we best decipher and understand the many ways that our everyday lives are organized around looking practices and the many images we encounter each day? Indeed, how we interact with and interpret visual images is a basic component of human life. Today, however, we are living in one of the most artificial visual and image-saturated cultures in human history, which makes understanding the complex construction and multiple social functions of visual imagery more important than ever before. Themes regarding our experience of a visually pervasive mediated culture, here, termed visual spectacle.

Keywords: visual culture, contemporary, images, literacy

Procedia PDF Downloads 493

Authors: Omer Burak Iskender, Keck Voon Ling, Vincent Dubanchet, Luca Simonini

Abstract:

This paper presents Guidance and Control (G&C) strategy to approach and synchronize with potentially rotating targets. The proposed strategy generates and tracks a safe trajectory for space servicing missions, including tasks like approaching, inspecting, and capturing. The main objective of this paper is to validate the G&C laws using a Hardware-In-the-Loop (HIL) setup with realistic rendezvous and docking equipment. Throughout this work, the assumption of full relative state feedback is relaxed by onboard sensors that bring realistic errors and delays and, while the proposed closed loop approach demonstrates the robustness to the above mentioned challenge. Moreover, G&C blocks are unified via the Model Predictive Control (MPC) paradigm, and the coupling between translational motion and rotational motion is addressed via dual quaternion based kinematic description. In this work, G&C is formulated as a convex optimization problem where constraints such as thruster limits and the output constraints are explicitly handled. Furthermore, the Monte-Carlo method is used to evaluate the robustness of the proposed method to the initial condition errors, the uncertainty of the target's motion and attitude, and actuator errors. A capture scenario is tested with the robotic test bench that has onboard sensors which estimate the position and orientation of a drifting satellite through camera imagery. Finally, the approach is compared with currently used robust H-infinity controllers and guidance profile provided by the industrial partner. The HIL experiments demonstrate that the proposed strategy is a potential candidate for future space servicing missions because 1) the algorithm is real-time implementable as convex programming offers deterministic convergence properties and guarantee finite time solution, 2) critical physical and output constraints are respected, 3) robustness to sensor errors and uncertainties in the system is proven, 4) couples translational motion with rotational motion.

Keywords: dual quaternion, model predictive control, real-time experimental test, rendezvous and docking, spacecraft autonomy, space servicing

Procedia PDF Downloads 126

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 277

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 325

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 240

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 133

Authors: Doaa Hamdi, Ahmed Hashem

Abstract:

The present study aims at integrating the ASTER data and Landsat 8 data to discriminate and map alteration and/or mineralization zones in addition to delineating different lithological units of Humr Akarim Granites area. The study area is located at 24º9' to 24º13' N and 34º1' to 34º2'45"E., covering a total exposed surface area of about 17 km². The area is characterized by rugged topography with low to moderate relief. Geologic fieldwork and petrographic investigations revealed that the basement complex of the study area is composed of metasediments, mafic dikes, older granitoids, and alkali-feldspar granites. Petrographic investigations revealed that the secondary minerals in the study area are mainly represented by chlorite, epidote, clay minerals and iron oxides. These minerals have specific spectral signatures in the region of visible near-infrared and short-wave infrared (0.4 to 2.5 µm). So that the ASTER imagery processing was concentrated on VNIR-SWIR spectrometric data in order to achieve the purposes of this study (geologic mapping of hydrothermal alteration zones and delineate possible radioactive potentialities). Mapping of hydrothermal alterations zones in addition to discriminating the lithological units in the study area are achieved through the utilization of some different image processing, including color band composites (CBC) and data transformation techniques such as band ratios (BR), band ratio codes (BRCs), principal component analysis(PCA), Crosta Technique and minimum noise fraction (MNF). The field verification and petrographic investigation confirm the results of ASTER imagery and Landsat 8 data, proposing a geological map (scale 1:50000).

Keywords: remote sensing, petrography, mineralization, alteration detection

Procedia PDF Downloads 141

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 127

Authors: Gannouni Sonia, Hammami Asma, Saidi Salwa, Rebai Noamen

Abstract:

Water resources in Tunisia have experienced quantitative and qualitative degradation, especially when talking about wetlands and Sbekhas. Indeed, the objective of this work is to study the spatio-temporal evolution of salinity for 29 years (from 1987 to 2016). A study of the connection between surface water and groundwater is necessary to know the degree of influence of the Sebkha brines on the water table. The evolution of surface salinity is determined by remote sensing based on Landsat TM and OLI/TIRS satellite images of the years 1987, 2007, 2010, and 2016. The processing of these images allowed us to determine the NDVI(Normalized Difference Vegetation Index), the salinity index, and the surface temperature around Sebkha. In addition, through a geographic information system(GIS), we could establish a map of the distribution of salinity in the subsurface of the water table of Chott Mariem and Hergla/SidiBouAli/Kondar. The results of image processing and the calculation of the index and surface temperature show an increase in salinity downstream of in addition to the sebkha and the development of vegetation cover upstream and the western part of the sebkha. This richness may be due both to contamination by seawater infiltration from the barrier beach of Hergla as well as the passage of groundwater to the sebkha.

Keywords: spatio-temporal monitoring, salinity, satellite images, NDVI, sebkha

Procedia PDF Downloads 111

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 427

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 63

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 92

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 105

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 237

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 217

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 34