Search results for: Gaussian process classification model with multiclass

Authors: Hina Gull, Farooque Azam, Wasi Haider Butt, Sardar Zafar Iqbal

Abstract:

The software system goes through a number of stages during its life and a software process model gives a standard format for planning, organizing and running a project. The article presents a new software development process model named as “Divide and Conquer Process Model", based on the idea first it divides the things to make them simple and then gathered them to get the whole work done. The article begins with the backgrounds of different software process models and problems in these models. This is followed by a new divide and conquer process model, explanation of its different stages and at the end edge over other models is shown.

Keywords: Process Model, Waterfall, divide and conquer, Requirements.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1921

Authors: Jouhra Dad, Mohammed Ouali, Yahia Lebbah

Abstract:

Urban road network traffic has become one of the most studied research topics in the last decades. This is mainly due to the enlargement of the cities and the growing number of motor vehicles traveling in this road network. One of the most sensitive problems is to verify if the network is congestion-free. Another related problem is the automatic reconfiguration of the network without building new roads to alleviate congestions. These problems require an accurate model of the traffic to determine the steady state of the system. An alternative is to simulate the traffic to see if there are congestions and when and where they occur. One key issue is to find an adequate model for road intersections. Once the model established, either a large scale model is built or the intersection is represented by its performance measures and simulation for analysis. In both cases, it is important to seek the queueing model to represent the road intersection. In this paper, we propose to model the road intersection as a BCMP queueing network and we compare this analytical model against a simulation model for validation.

Keywords: Queueing theory, transportation systems, BCMPqueueing network, performance measures, modeling, simulation

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2432

Authors: Nebi Gedik

Abstract:

One of the important parts of the brain-computer interface (BCI) studies is the classification of motor imagery (MI) obtained by electroencephalography (EEG). The major goal is to provide non-muscular communication and control via assistive technologies to people with severe motor disorders so that they can communicate with the outside world. In this study, an EEG signal classification approach based on multiscale and multi-resolution transform method is presented. The proposed approach is used to decompose the EEG signal containing motor image information (right- and left-hand movement imagery). The decomposition process is performed using curvelet transform which is a multiscale and multiresolution analysis method, and the transform output was evaluated as feature data. The obtained feature set is subjected to feature selection process to obtain the most effective ones using t-test methods. SVM and k-NN algorithms are assigned for classification.

Keywords: motor imagery, EEG, curvelet transform, SVM, k-NN

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 601

Authors: Jia Xin Low, Keng Wah Choo

Abstract:

This paper presents an automatic normal and abnormal heart sound classification model developed based on deep learning algorithm. MITHSDB heart sounds datasets obtained from the 2016 PhysioNet/Computing in Cardiology Challenge database were used in this research with the assumption that the electrocardiograms (ECG) were recorded simultaneously with the heart sounds (phonocardiogram, PCG). The PCG time series are segmented per heart beat, and each sub-segment is converted to form a square intensity matrix, and classified using convolutional neural network (CNN) models. This approach removes the need to provide classification features for the supervised machine learning algorithm. Instead, the features are determined automatically through training, from the time series provided. The result proves that the prediction model is able to provide reasonable and comparable classification accuracy despite simple implementation. This approach can be used for real-time classification of heart sounds in Internet of Medical Things (IoMT), e.g. remote monitoring applications of PCG signal.

Keywords: Convolutional neural network, discrete wavelet transform, deep learning, heart sound classification.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1136

Authors: Shih-Ching Lo

Abstract:

Understanding driving behavior is a complicated researching topic. To describe accurate speed, flow and density of a multiclass users traffic flow, an adequate model is needed. In this study, we propose the concept of standard passenger car equivalent (SPCE) instead of passenger car equivalent (PCE) to estimate the influence of heavy vehicles and slow cars. Traffic cellular automata model is employed to calibrate and validate the results. According to the simulated results, the SPCE transformations present good accuracy.

Keywords: traffic flow, passenger car equivalent, cellular automata

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1701

Authors: M. Ben Othmen, M. Sayadi, F. Fnaiech

Abstract:

Wavelet transform provides several important characteristics which can be used in a texture analysis and classification. In this work, an efficient texture classification method, which combines concepts from wavelet and co-occurrence matrices, is presented. An Euclidian distance classifier is used to evaluate the various methods of classification. A comparative study is essential to determine the ideal method. Using this conjecture, we developed a novel feature set for texture classification and demonstrate its effectiveness

Keywords: Classification, Wavelet, Co-occurrence, Euclidian Distance, Classifier, Texture.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1475

Authors: B. Leela Devi, A. Sankar

Abstract:

The web’s increased popularity has included a huge amount of information, due to which automated web page classification systems are essential to improve search engines’ performance. Web pages have many features like HTML or XML tags, hyperlinks, URLs and text contents which can be considered during an automated classification process. It is known that Webpage classification is enhanced by hyperlinks as it reflects Web page linkages. The aim of this study is to reduce the number of features to be used to improve the accuracy of the classification of web pages. In this paper, a novel feature selection method using an improved Particle Swarm Optimization (PSO) using principle of evolution is proposed. The extracted features were tested on the WebKB dataset using a parallel Neural Network to reduce the computational cost.

Keywords: Web page classification, WebKB Dataset, Term Frequency-Inverse Document Frequency (TF-IDF), Particle Swarm Optimization (PSO).

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3253

Authors: Hassan Ezzaidi, Jean Rouat

Abstract:

Recently many research has been conducted to retrieve pertinent parameters and adequate models for automatic music genre classification. In this paper, two measures based upon information theory concepts are investigated for mapping the features space to decision space. A Gaussian Mixture Model (GMM) is used as a baseline and reference system. Various strategies are proposed for training and testing sessions with matched or mismatched conditions, long training and long testing, long training and short testing. For all experiments, the file sections used for testing are never been used during training. With matched conditions all examined measures yield the best and similar scores (almost 100%). With mismatched conditions, the proposed measures yield better scores than the GMM baseline system, especially for the short testing case. It is also observed that the average discrimination information measure is most appropriate for music category classifications and on the other hand the divergence measure is more suitable for music subcategory classifications.

Keywords: Audio feature, information measures, music genre.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1570

Authors: Yan Su, L. C. Chan

Abstract:

A novel typical day prediction model have been built and validated by the measured data of a grid-connected solar photovoltaic (PV) system in Macau. Unlike conventional statistical method used by previous study on PV systems which get results by averaging nearby continuous points, the present typical day statistical method obtain the value at every minute in a typical day by averaging discontinuous points at the same minute in different days. This typical day statistical method based on discontinuous point averaging makes it possible for us to obtain the Gaussian shape dynamical distributions for solar irradiance and output power in a yearly or monthly typical day. Based on the yearly typical day statistical analysis results, the maximum possible accumulated output energy in a year with on site climate conditions and the corresponding optimal PV system running time are obtained. Periodic Gaussian shape prediction models for solar irradiance, output energy and system energy efficiency have been built and their coefficients have been determined based on the yearly, maximum and minimum monthly typical day Gaussian distribution parameters, which are obtained from iterations for minimum Root Mean Squared Deviation (RMSD). With the present model, the dynamical effects due to time difference in a day are kept and the day to day uncertainty due to weather changing are smoothed but still included. The periodic Gaussian shape correlations for solar irradiance, output power and system energy efficiency have been compared favorably with data of the PV system in Macau and proved to be an improvement than previous models.

Keywords: Grid Connected, RMSD, Solar PV System, Typical Day.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1672

Authors: Sallama Athab, Hala Bahjat, Zhang Yinghui

Abstract:

Background detection is essential in video analyses; optimization is often needed in order to achieve real time calculation. Information gathered by dual cameras placed in the front and rear part of an Autonomous Vehicle (AV) is integrated for background detection. In this paper, real time calculation is achieved on the proposed technique by using Priority Regions (PR) and Parallel Processing together where each frame is divided into regions then and each region process is processed in parallel. PR division depends upon driver view limitations. A background detection system is built on the Temporal Difference (TD) and Gaussian Filtering (GF). Temporal Difference and Gaussian Filtering with multi threshold and sigma (weight) value are be based on PR characteristics. The experiment result is prepared on real scene. Comparison of the speed and accuracy with traditional background detection techniques, the effectiveness of PR and parallel processing are also discussed in this paper.

Keywords: Autonomous Vehicle, Background Detection, Dual Camera, Gaussian Filtering, Parallel Processing.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1687

Authors: Risanuri Hidayat

Abstract:

BER analysis of Impulse Radio Ultra Wideband (IRUWB) pulse modulations over S-V channel model is proposed in this paper. The UWB pulse is Gaussian monocycle pulse modulated using Pulse Amplitude Modulation (PAM) and Pulse Position Modulation (PPM). The channel model is generated from a modified S-V model. Bit-error rate (BER) is measured over several of bit rates. The result shows that all modulation are appropriate for both LOS and NLOS channel, but PAM gives better performance in bit rates and SNR. Moreover, as standard of speed has been given for UWB, the communication is appropriate with high bit rates in LOS channel.

Keywords: IR-UWB, S-V Channel Model, LOS NLOS, PAM, PPM

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2336

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 of 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, 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 APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 457

Authors: Karim Abouelmehdi, Loubna Dali, Elmoutaoukkil Abdelmajid, Hoda Elsayed Eladnani Fatiha, Benihssane Abderahim

Abstract:

The security of cloud services is the concern of cloud service providers. In this paper, we will mention different classifications of cloud attacks referred by specialized organizations. Each agency has its classification of well-defined properties. The purpose is to present a high-level classification of current research in cloud computing security. This classification is organized around attack strategies and corresponding defenses.

Keywords: Cloud computing, security, classification, risk.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2072

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 APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1512

Authors: Refaat M Mohamed, Ayman El-Baz, Aly A. Farag

Abstract:

This paper introduces a novel approach to estimate the clique potentials of Gibbs Markov random field (GMRF) models using the Support Vector Machines (SVM) algorithm and the Mean Field (MF) theory. The proposed approach is based on modeling the potential function associated with each clique shape of the GMRF model as a Gaussian-shaped kernel. In turn, the energy function of the GMRF will be in the form of a weighted sum of Gaussian kernels. This formulation of the GMRF model urges the use of the SVM with the Mean Field theory applied for its learning for estimating the energy function. The approach has been tested on synthetic texture images and is shown to provide satisfactory results in retrieving the synthesizing parameters.

Keywords: Image Modeling, MRF, Parameters Estimation, SVM Learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1627

Authors: Mitko Veta, Tomislav Kartalov, Zoran Ivanovski

Abstract:

Organization of video databases is becoming difficult task as the amount of video content increases. Video classification based on the content of videos can significantly increase the speed of tasks such as browsing and searching for a particular video in a database. In this paper, a content-based videos classification system for the classes indoor and outdoor is presented. The system is intended to be used on a mobile platform with modest resources. The algorithm makes use of the temporal redundancy in videos, which allows using an uncomplicated classification model while still achieving reasonable accuracy. The training and evaluation was done on a video database of 443 videos downloaded from a video sharing service. A total accuracy of 87.36% was achieved.

Keywords: Indoor/outdoor, video classification, imageclassification

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1512

Authors: B. Elshafei, X. Mao

Abstract:

The demand for renewable energy is significantly increasing, major investments are being supplied to the wind power generation industry as a leading source of clean energy. The wind energy sector is entirely dependable and driven by the prediction of wind speed, which by the nature of wind is very stochastic and widely random. This s0tudy employs deep multi-fidelity Gaussian process regression, used to predict wind speeds for medium term time horizons. Data of the RUNE experiment in the west coast of Denmark were provided by the Technical University of Denmark, which represent the wind speed across the study area from the period between December 2015 and March 2016. The study aims to investigate the effect of pre-processing the data by denoising the signal using empirical wavelet transform (EWT) and engaging the vector components of wind speed to increase the number of input data layers for data fusion using deep multi-fidelity Gaussian process regression (GPR). The outcomes were compared using root mean square error (RMSE) and the results demonstrated a significant increase in the accuracy of predictions which demonstrated that using vector components of the wind speed as additional predictors exhibits more accurate predictions than strategies that ignore them, reflecting the importance of the inclusion of all sub data and pre-processing signals for wind speed forecasting models.

Keywords: Data fusion, Gaussian process regression, signal denoise, temporal extrapolation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 490

Authors: Kavita Burse, R.N. Yadav, S.C. Shrivastava, Vishnu Pratap Singh Kirar

Abstract:

During signal transmission, the combined effect of the transmitter filter, the transmission medium, and additive white Gaussian noise (AWGN) are included in the channel which distort and add noise to the signal. This causes the well defined signal constellation to spread causing errors in bit detection. A compact pi neural network with minimum number of nodes is proposed. The replacement of summation at each node by multiplication results in more powerful mapping. The resultant pi network is tested on six different channels.

Keywords: Additive white Gaussian noise, digitalcommunication system, multiplicative neuron, Pi neural network.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1657

Authors: Mohammad Rakibul Islam

Abstract:

In this paper, a Gaussian multiple input multiple output multiple eavesdropper (MIMOME) channel is considered where a transmitter communicates to a receiver in the presence of an eavesdropper. We present a technique for determining the secrecy capacity of the multiple input multiple output (MIMO) channel under Gaussian noise. We transform the degraded MIMOME channel into multiple single input multiple output (SIMO) Gaussian wire-tap channels and then use scalar approach to convert it into two equivalent multiple input single output (MISO) channels. The secrecy capacity model is then developed for the condition where the channel state information (CSI) for main channel only is known to the transmitter. The results show that the secret communication is possible when the eavesdropper channel noise is greater than a cutoff noise level. The outage probability is also analyzed of secrecy capacity is also analyzed. The effect of fading and outage probability is also analyzed.

Keywords: Secrecy capacity, MIMO, wiretap channel, covariance matrix, fading.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1565

Authors: Iliycho P. Iliev, Desislava S. Voynikova, Snezhana G. Gocheva-Ilieva

Abstract:

This paper examines the available experiment data for a copper bromide vapor laser (CuBr laser), emitting at two wavelengths - 510.6 and 578.2nm. Laser output power is estimated based on 10 independent input physical parameters. A classification and regression tree (CART) model is obtained which describes 97% of data. The resulting binary CART tree specifies which input parameters influence considerably each of the classification groups. This allows for a technical assessment that indicates which of these are the most significant for the manufacture and operation of the type of laser under consideration. The predicted values of the laser output power are also obtained depending on classification. This aids the design and development processes considerably.

Keywords: Classification and regression trees (CART), Copper Bromide laser (CuBr laser), laser generation, nonparametric statistical model.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1814

Authors: Mana Tarjoman, Shaghayegh Zarei

Abstract:

Using efficient classification methods is necessary for automatic fingerprint recognition system. This paper introduces a new structural approach to fingerprint classification by using the directional image of fingerprints to increase the number of subclasses. In this method, the directional image of fingerprints is segmented into regions consisting of pixels with the same direction. Afterwards the relational graph to the segmented image is constructed and according to it, the super graph including prominent information of this graph is formed. Ultimately we apply a matching technique to compare obtained graph with the model graphs in order to classify fingerprints by using cost function. Increasing the number of subclasses with acceptable accuracy in classification and faster processing in fingerprints recognition, makes this system superior.

Keywords: Classification, Directional image, Fingerprint, Graph, Super graph.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3618

Authors: Saleh Mesbah Elkaffas, Ahmed A. Toony

Abstract:

This paper details the application of a genetic programming framework for induction of useful classification rules from a database of income statements, balance sheets, and cash flow statements for North American public companies. Potentially interesting classification rules are discovered. Anomalies in the discovery process merit further investigation of the application of genetic programming to the dataset for the problem domain.

Keywords: Genetic programming, data mining classification rule.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1536

Authors: S. Pattanapairoj, D. Chetchotsak

Abstract:

This paper proposed classification models that would be used as a proxy for hard disk drive (HDD) functional test equitant which required approximately more than two weeks to perform the HDD status classification in either “Pass" or “Fail". These models were constructed by using committee network which consisted of a number of single neural networks. This paper also included the method to solve the problem of sparseness data in failed part, which was called “enforce learning method". Our results reveal that the constructed classification models with the proposed method could perform well in the sparse data conditions and thus the models, which used a few seconds for HDD classification, could be used to substitute the HDD functional tests.

Keywords: Sparse data, Classifications, Committee network

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1728

Authors: A. S. Adesuyi, Z. Munch

Abstract:

This study investigates the use of a time-series of MODIS NDVI data to identify agricultural land cover change on an annual time step (2007 - 2012) and characterize the trend. Following an ISODATA classification of the MODIS imagery to selectively mask areas not agriculture or semi-natural, NDVI signatures were created to identify areas cereals and vineyards with the aid of ancillary, pictometry and field sample data for 2010. The NDVI signature curve and training samples were used to create a decision tree model in WEKA 3.6.9 using decision tree classifier (J48) algorithm; Model 1 including ISODATA classification and Model 2 not. These two models were then used to classify all data for the study area for 2010, producing land cover maps with classification accuracies of 77% and 80% for Model 1 and 2 respectively. Model 2 was subsequently used to create land cover classification and change detection maps for all other years. Subtle changes and areas of consistency (unchanged) were observed in the agricultural classes and crop practices. Over the years as predicted by the land cover classification. Forty one percent of the catchment comprised of cereals with 35% possibly following a crop rotation system. Vineyards largely remained constant with only one percent conversion to vineyard from other land cover classes.

Keywords: Change detection, Land cover, NDVI, time-series.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2279

Authors: Tossaporn Kachanubal, Somkait Udomhunsakul

Abstract:

In this paper, we proposed a method to classify each type of natural rock texture. Our goal is to classify 26 classes of rock textures. First, we extract five features of each class by using principle component analysis combining with the use of applied spatial frequency measurement. Next, the effective node number of neural network was tested. We used the most effective neural network in classification process. The results from this system yield quite high in recognition rate. It is shown that high recognition rate can be achieved in separation of 26 stone classes.

Keywords: Texture classification, SFM, neural network, rock texture classification.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2000

Authors: Qian-Ping Guo, Hou-Biao Li

Abstract:

The generalized Higham matrix is a complex symmetric matrix A = B + iC, where both B ∈ Cn×n and C ∈ Cn×n are Hermitian positive definite, and i = √−1 is the imaginary unit. The growth factor in Gaussian elimination is less than 3√2 for this kind of matrices. In this paper, we give a new brief proof on this result by different techniques, which can be understood very easily, and obtain some new findings.

Keywords: CSPD matrix, positive definite, Schur complement, Higham matrix, Gaussian elimination, Growth factor.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1738

Authors: Yilun Shang

Abstract:

We consider a heterogeneously mixing SIR stochastic epidemic process in populations described by a general graph. Likelihood theory is developed to facilitate statistic inference for the parameters of the model under complete observation. We show that these estimators are asymptotically Gaussian unbiased estimates by using a martingale central limit theorem.

Keywords: statistic inference, maximum likelihood, epidemicmodel, heterogeneous mixing.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1399

Authors: Helyane B. Borges, Julio Cesar Nievola

Abstract:

Hierarchical classification is a problem with applications in many areas as protein function prediction where the dates are hierarchically structured. Therefore, it is necessary the development of algorithms able to induce hierarchical classification models. This paper presents experimenters using the algorithm for hierarchical classification called Multi-label Hierarchical Classification using a Competitive Neural Network (MHC-CNN). It was tested in ten datasets the Gene Ontology (GO) Cellular Component Domain. The results are compared with the Clus-HMC and Clus-HSC using the hF-Measure.

Keywords: Hierarchical Classification, Competitive Neural Network, Global Classifier.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2374

Authors: Cheng Zeng, George Michailidis, Hitoshi Iyatomi, Leo L Duan

Abstract:

The conditional density characterizes the distribution of a response variable y given other predictor x, and plays a key role in many statistical tasks, including classification and outlier detection. Although there has been abundant work on the problem of Conditional Density Estimation (CDE) for a low-dimensional response in the presence of a high-dimensional predictor, little work has been done for a high-dimensional response such as images. The promising performance of normalizing flow (NF) neural networks in unconditional density estimation acts a motivating starting point. In this work, we extend NF neural networks when external x is present. Specifically, they use the NF to parameterize a one-to-one transform between a high-dimensional y and a latent z that comprises two components [zP , zN]. The zP component is a low-dimensional subvector obtained from the posterior distribution of an elementary predictive model for x, such as logistic/linear regression. The zN component is a high-dimensional independent Gaussian vector, which explains the variations in y not or less related to x. Unlike existing CDE methods, the proposed approach, coined Augmented Posterior CDE (AP-CDE), only requires a simple modification on the common normalizing flow framework, while significantly improving the interpretation of the latent component, since zP represents a supervised dimension reduction. In image analytics applications, AP-CDE shows good separation of x-related variations due to factors such as lighting condition and subject id, from the other random variations. Further, the experiments show that an unconditional NF neural network, based on an unsupervised model of z, such as Gaussian mixture, fails to generate interpretable results.

Keywords: Conditional density estimation, image generation, normalizing flow, supervised dimension reduction.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 142

Authors: G. Türkmen, Ö. Tekin, K. Kurtuluş, Y. Y. Yurtseven, M. Baran

Abstract:

A scanning electron microscope (SEM) is a type of electron microscope mainly used in nanoscience and nanotechnology areas. Automatic image recognition and classification are among the general areas of application concerning SEM. In line with these usages, the present paper proposes a deep learning algorithm that classifies SEM images into nine categories by means of an online application to simplify the process. The NFFA-EUROPE - 100% SEM data set, containing approximately 21,000 images, was used to train and test the algorithm at 80% and 20%, respectively. Validation was carried out using a separate data set obtained from the Middle East Technical University (METU) in Turkey. To increase the accuracy in the results, the Inception ResNet-V2 model was used in view of the Fine-Tuning approach. By using a confusion matrix, it was observed that the coated-surface category has a negative effect on the accuracy of the results since it contains other categories in the data set, thereby confusing the model when detecting category-specific patterns. For this reason, the coated-surface category was removed from the train data set, hence increasing accuracy by up to 96.5%.

Keywords: Convolutional Neural Networks, deep learning, image classification, scanning electron microscope.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 183