Search results for: time series classification

Authors: Haoyu Ma, Bin Hu, Mike Jackson, Jingzhi Yan, Wen Zhao

Abstract:

In this paper we propose a new classification method for automatic sleep scoring using an artificial neural network based decision tree. It attempts to treat sleep scoring progress as a series of two-class problems and solves them with a decision tree made up of a group of neural network classifiers, each of which uses a special feature set and is aimed at only one specific sleep stage in order to maximize the classification effect. A single electroencephalogram (EEG) signal is used for our analysis rather than depending on multiple biological signals, which makes greatly simplifies the data acquisition process. Experimental results demonstrate that the average epoch by epoch agreement between the visual and the proposed method in separating 30s wakefulness+S1, REM, S2 and SWS epochs was 88.83%. This study shows that the proposed method performed well in all the four stages, and can effectively limit error propagation at the same time. It could, therefore, be an efficient method for automatic sleep scoring. Additionally, since it requires only a small volume of data it could be suited to pervasive applications.

Keywords: Sleep, Sleep stage, Automatic sleep scoring, Electroencephalography, Decision tree, Artificial neural network

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2032

Authors: Jun Wan, Zehua Chen, Yingwu Chen, Zhidong Bai

Abstract:

Classification is an interesting problem in functional data analysis (FDA), because many science and application problems end up with classification problems, such as recognition, prediction, control, decision making, management, etc. As the high dimension and high correlation in functional data (FD), it is a key problem to extract features from FD whereas keeping its global characters, which relates to the classification efficiency and precision to heavens. In this paper, a novel automatic method which combined Genetic Algorithm (GA) and classification algorithm to extract classification features is proposed. In this method, the optimal features and classification model are approached via evolutional study step by step. It is proved by theory analysis and experiment test that this method has advantages in improving classification efficiency, precision and robustness whereas using less features and the dimension of extracted classification features can be controlled.

Keywords: Classification, functional data, feature extraction, genetic algorithm, wavelet.

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

Authors: Ramesh K. Sunkaria, Puneeta Marwaha

Abstract:

Non linear methods of heart rate variability (HRV) analysis are becoming more popular. It has been observed that complexity measures quantify the regularity and uncertainty of cardiovascular RR-interval time series. In the present work, SampEn has been evaluated in healthy normal sinus rhythm (NSR) male and female subjects for different data lengths and tolerance level r. It is demonstrated that SampEn is small for higher values of tolerance r. Also SampEn value of healthy female group is higher than that of healthy male group for short data length and with increase in data length both groups overlap each other and it is difficult to distinguish them. The SampEn gives inaccurate results by assigning higher value to female group, because male subject have more complex HRV pattern than that of female subjects. Therefore, this traditional algorithm exhibits higher complexity for healthy female subjects than for healthy male subjects, which is misleading observation. This may be due to the fact that SampEn do not account for multiple time scales inherent in the physiologic time series and the hidden spatial and temporal fluctuations remains unexplored.

Keywords: Heart rate variability, normal sinus rhythm group, RR interval time series, sample entropy.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1720

Authors: Daniel I. Morariu, Lucian N. Vintan, Volker Tresp

Abstract:

Text categorization is the problem of classifying text documents into a set of predefined classes. In this paper, we investigated three approaches to build a meta-classifier in order to increase the classification accuracy. The basic idea is to learn a metaclassifier to optimally select the best component classifier for each data point. The experimental results show that combining classifiers can significantly improve the accuracy of classification and that our meta-classification strategy gives better results than each individual classifier. For 7083 Reuters text documents we obtained a classification accuracies up to 92.04%.

Keywords: Meta-classification, Learning with Kernels, Support Vector Machine, and Performance Evaluation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1569

Authors: Rana Yousef, Khalil el Hindi

Abstract:

The behavior of Radial Basis Function (RBF) Networks greatly depends on how the center points of the basis functions are selected. In this work we investigate the use of instance reduction techniques, originally developed to reduce the storage requirements of instance based learners, for this purpose. Five Instance-Based Reduction Techniques were used to determine the set of center points, and RBF networks were trained using these sets of centers. The performance of the RBF networks is studied in terms of classification accuracy and training time. The results obtained were compared with two Radial Basis Function Networks: RBF networks that use all instances of the training set as center points (RBF-ALL) and Probabilistic Neural Networks (PNN). The former achieves high classification accuracies and the latter requires smaller training time. Results showed that RBF networks trained using sets of centers located by noise-filtering techniques (ALLKNN and ENN) rather than pure reduction techniques produce the best results in terms of classification accuracy. The results show that these networks require smaller training time than that of RBF-ALL and higher classification accuracy than that of PNN. Thus, using ALLKNN and ENN to select center points gives better combination of classification accuracy and training time. Our experiments also show that using the reduced sets to train the networks is beneficial especially in the presence of noise in the original training sets.

Keywords: Radial basis function networks, Instance-based reduction, PNN.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1637

Authors: Fabio Fabris, Alex A. Freitas

Abstract:

Hierarchical classification is a special type of classification task where the class labels are organised into a hierarchy, with more generic class labels being ancestors of more specific ones. Meta-learning for classification-algorithm recommendation consists of recommending to the user a classification algorithm, from a pool of candidate algorithms, for a dataset, based on the past performance of the candidate algorithms in other datasets. Meta-learning is normally used in conventional, non-hierarchical classification. By contrast, this paper proposes a meta-learning approach for more challenging task of hierarchical classification, and evaluates it in a large number of bioinformatics datasets. Hierarchical classification is especially relevant for bioinformatics problems, as protein and gene functions tend to be organised into a hierarchy of class labels. This work proposes meta-learning approach for recommending the best hierarchical classification algorithm to a hierarchical classification dataset. This work’s contributions are: 1) proposing an algorithm for splitting hierarchical datasets into new datasets to increase the number of meta-instances, 2) proposing meta-features for hierarchical classification, and 3) interpreting decision-tree meta-models for hierarchical classification algorithm recommendation.

Keywords: Algorithm recommendation, meta-learning, bioinformatics, hierarchical classification.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1295

Authors: Maythapolnun Athimethphat, Boontarika Lerteerawong

Abstract:

There are several approaches for handling multiclass classification. Aside from one-against-one (OAO) and one-against-all (OAA), hierarchical classification technique is also commonly used. A binary classification tree is a hierarchical classification structure that breaks down a k-class problem into binary sub-problems, each solved by a binary classifier. In each node, a set of classes is divided into two subsets. A good class partition should be able to group similar classes together. Many algorithms measure similarity in term of distance between class centroids. Classes are grouped together by a clustering algorithm when distances between their centroids are small. In this paper, we present a binary classification tree with tuned observation-based clustering (BCT-TOB) that finds a class partition by performing clustering on observations instead of class centroids. A merging step is introduced to merge any insignificant class split. The experiment shows that performance of BCT-TOB is comparable to other algorithms.

Keywords: multiclass classification, hierarchical classification, binary classification tree, clustering, observation-based clustering

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1681

Authors: Jorge A. Ruiz-Vanoye, Ocotlán Díaz-Parra, Alejandro Fuentes-Penna, Daniel Vélez-Díaz, Edith Olaco García

Abstract:

In this paper, we present the use of the discriminant analysis to select evolutionary algorithms that better solve instances of the vehicle routing problem with time windows. We use indicators as independent variables to obtain the classification criteria, and the best algorithm from the generic genetic algorithm (GA), random search (RS), steady-state genetic algorithm (SSGA), and sexual genetic algorithm (SXGA) as the dependent variable for the classification. The discriminant classification was trained with classic instances of the vehicle routing problem with time windows obtained from the Solomon benchmark. We obtained a classification of the discriminant analysis of 66.7%.

Keywords: Intelligent transportation systems, data-mining techniques, evolutionary algorithms, discriminant analysis, machine learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1505

Authors: Chokri Slim

Abstract:

The neural network's performance can be measured by efficiency and accuracy. The major disadvantages of neural network approach are that the generalization capability of neural networks is often significantly low, and it may take a very long time to tune the weights in the net to generate an accurate model for a highly complex and nonlinear systems. This paper presents a novel Neuro-fuzzy architecture based on Extended Kalman filter. To test the performance and applicability of the proposed neuro-fuzzy model, simulation study of nonlinear complex dynamic system is carried out. The proposed method can be applied to an on-line incremental adaptive learning for the prediction of financial time series. A benchmark case studie is used to demonstrate that the proposed model is a superior neuro-fuzzy modeling technique.

Keywords: Neuro-fuzzy, Extended Kalman filter, nonlinear systems, financial time series.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1971

Authors: Meredith Stevenson, John E. Porter

Abstract:

Since the pioneering work of Zadeh, fuzzy set theory has been applied to a myriad of areas. Song and Chissom introduced the concept of fuzzy time series and applied some methods to the enrollments of the University of Alabama. In recent years, a number of techniques have been proposed for forecasting based on fuzzy set theory methods. These methods have either used enrollment numbers or differences of enrollments as the universe of discourse. We propose using the year to year percentage change as the universe of discourse. In this communication, the approach of Jilani, Burney, and Ardil is modified by using the year to year percentage change as the universe of discourse. We use enrollment figures for the University of Alabama to illustrate our proposed method. The proposed method results in better forecasting accuracy than existing models.

Keywords: Fuzzy forecasting, fuzzy time series, fuzzified enrollments, time-invariant model

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2445

Authors: S. Wongkoon, M. Pollar, M. Jaroensutasinee, K. Jaroensutasinee

Abstract:

This study aimed at developing a forecasting model on the number of Dengue Haemorrhagic Fever (DHF) incidence in Northern Thailand using time series analysis. We developed Seasonal Autoregressive Integrated Moving Average (SARIMA) models on the data collected between 2003-2006 and then validated the models using the data collected between January-September 2007. The results showed that the regressive forecast curves were consistent with the pattern of actual values. The most suitable model was the SARIMA(2,0,1)(0,2,0)12 model with a Akaike Information Criterion (AIC) of 12.2931 and a Mean Absolute Percent Error (MAPE) of 8.91713. The SARIMA(2,0,1)(0,2,0)12 model fitting was adequate for the data with the Portmanteau statistic Q20 = 8.98644 ( x20,95= 27.5871, P>0.05). This indicated that there was no significant autocorrelation between residuals at different lag times in the SARIMA(2,0,1)(0,2,0)12 model.

Keywords: Dengue, SARIMA, Time Series Analysis, Northern Thailand.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1953

Authors: Hassan Masoumi, Ahad Salimi, Nazanin Barhemmat, Babak Gholami

Abstract:

Artificial neural networks have gained a lot of interest as empirical models for their powerful representational capacity, multi input and output mapping characteristics. In fact, most feedforward networks with nonlinear nodal functions have been proved to be universal approximates. In this paper, we propose a new supervised method for color image classification based on selforganizing feature maps (SOFM). This algorithm is based on competitive learning. The method partitions the input space using self-organizing feature maps to introduce the concept of local neighborhoods. Our image classification system entered into RGB image. Experiments with simulated data showed that separability of classes increased when increasing training time. In additional, the result shows proposed algorithms are effective for color image classification.

Keywords: Classification, SOFM, neural network, RGB images.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2276

Authors: Mohamed Mounir Tellache, Hiroyuki Kambara, Yasuharu Koike, Makoto Miyakoshi, Natsue Yoshimura

Abstract:

This study explores the practicality of using electroencephalographic (EEG) independent components to predict eight-direction finger movements in pseudo-real-time. Six healthy participants with individual-head MRI images performed finger movements in eight directions with two different arm configurations. The analysis was performed in two stages. The first stage consisted of using independent component analysis (ICA) to separate the signals representing brain activity from non-brain activity signals and to obtain the unmixing matrix. The resulting independent components (ICs) were checked, and those reflecting brain-activity were selected. Finally, the time series of the selected ICs were used to predict eight finger-movement directions using Sparse Logistic Regression (SLR). The second stage consisted of using the previously obtained unmixing matrix, the selected ICs, and the model obtained by applying SLR to classify a different EEG dataset. This method was applied to two different settings, namely the single-participant level and the group-level. For the single-participant level, the EEG dataset used in the first stage and the EEG dataset used in the second stage originated from the same participant. For the group-level, the EEG datasets used in the first stage were constructed by temporally concatenating each combination without repetition of the EEG datasets of five participants out of six, whereas the EEG dataset used in the second stage originated from the remaining participants. The average test classification results across datasets (mean ± S.D.) were 38.62 ± 8.36% for the single-participant, which was significantly higher than the chance level (12.50 ± 0.01%), and 27.26 ± 4.39% for the group-level which was also significantly higher than the chance level (12.49% ± 0.01%). The classification accuracy within [–45°, 45°] of the true direction is 70.03 ± 8.14% for single-participant and 62.63 ± 6.07% for group-level which may be promising for some real-life applications. Clustering and contribution analyses further revealed the brain regions involved in finger movement and the temporal aspect of their contribution to the classification. These results showed the possibility of using the ICA-based method in combination with other methods to build a real-time system to control prostheses.

Keywords: Brain-computer interface, BCI, electroencephalography, EEG, finger motion decoding, independent component analysis, pseudo-real-time motion decoding.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 544

Authors: Siriporn Meenanan

Abstract:

The objective of this study is to investigate the attitude of Thai students towards the Thai series "Hormones the Series Season 2". This study was conducted in the quantitative research, and the questionnaires were used to collect data from 400 people of the sample group. Descriptive statistics were used in data analysis. The findings reveal that most participants have positive comments regarding the series. They strongly agreed that the series reflects on the way of life and problems of teenagers in Thailand. Hence, the participants believe that if adults have a chance to watch the series, they will have the better understanding of the teenagers. In addition, the participants also agreed that the contents of the play are appropriate and satisfiable as the contents of “Hormones the Series Season 2” will raise awareness among the teens and use it as a guide to prevent problems that might happen during their teenage life.

Keywords: Content analysis, attitude, Thai series, Hormones the series.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 910

Authors: Bhaskar Thakker, Anoop Lal Vyas

Abstract:

Wrist pulse analysis for identification of health status is found in Ancient Indian as well as Chinese literature. The preprocessing of wrist pulse is necessary to remove outlier pulses and fluctuations prior to the analysis of pulse pressure signal. This paper discusses the identification of irregular pulses present in the pulse series and intricacies associated with the extraction of time domain pulse features. An approach of Dynamic Time Warping (DTW) has been utilized for the identification of outlier pulses in the wrist pulse series. The ambiguity present in the identification of pulse features is resolved with the help of first derivative of Ensemble Average of wrist pulse series. An algorithm for detecting tidal and dicrotic notch in individual wrist pulse segment is proposed.

Keywords: Wrist Pulse Segment, Ensemble Average, Dynamic Time Warping (DTW), Pulse Similarity Vector.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2039

Authors: Insung Jung, lockjo Koo, Gi-Nam Wang

Abstract:

The objective of this paper is to design a model of human vital sign prediction for decreasing prediction error by using two states mapping based time series neural network BP (back-propagation) model. Normally, lot of industries has been applying the neural network model by training them in a supervised manner with the error back-propagation algorithm for time series prediction systems. However, it still has a residual error between real value and prediction output. Therefore, we designed two states of neural network model for compensation of residual error which is possible to use in the prevention of sudden death and metabolic syndrome disease such as hypertension disease and obesity. We found that most of simulations cases were satisfied by the two states mapping based time series prediction model compared to normal BP. In particular, small sample size of times series were more accurate than the standard MLP model. We expect that this algorithm can be available to sudden death prevention and monitoring AGENT system in a ubiquitous homecare environment.

Keywords: Neural network, U-healthcare, prediction, timeseries, computer aided prediction.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1939

Authors: Celso A. G. Santos, Paula K. M. M. Freire

Abstract:

The urban centers within northeastern Brazil are mainly influenced by the intense rainfalls, which can occur after long periods of drought, when flood events can be observed during such events. Thus, this paper aims to study the rainfall frequencies in such region through the wavelet transform. An application of wavelet analysis is done with long time series of the total monthly rainfall amount at the capital cities of northeastern Brazil. The main frequency components in the time series are studied by the global wavelet spectrum and the modulation in separated periodicity bands were done in order to extract additional information, e.g., the 8 and 16 months band was examined by an average of all scales, giving a measure of the average annual variance versus time, where the periods with low or high variance could be identified. The important increases were identified in the average variance for some periods, e.g. 1947 to 1952 at Teresina city, which can be considered as high wet periods. Although, the precipitation in those sites showed similar global wavelet spectra, the wavelet spectra revealed particular features. This study can be considered an important tool for time series analysis, which can help the studies concerning flood control, mainly when they are applied together with rainfall-runoff simulations.

Keywords: rainfall data, urban center, wavelet transform.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2406

Authors: R. Mechgoug, A. Titaouine

Abstract:

Fuzzy systems have been successfully used for exchange rate forecasting. However, fuzzy system is very confusing and complex to be designed by an expert, as there is a large set of parameters (fuzzy knowledge base) that must be selected, it is not a simple task to select the appropriate fuzzy knowledge base for an exchange rate forecasting. The researchers often look the effect of fuzzy knowledge base on the performances of fuzzy system forecasting. This paper proposes a genetic fuzzy predictor to forecast the future value of daily US Dollar/Euro exchange rate time’s series. A range of methodologies based on a set of fuzzy predictor’s which allow the forecasting of the same time series, but with a different fuzzy partition. Each fuzzy predictor is built from two stages, where each stage is performed by a real genetic algorithm.

Keywords: Foreign exchange rate, time series forecasting, Fuzzy System, and Genetic Algorithm.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1955

Authors: Khalid M. Aamir, Mohammad A. Maud

Abstract:

Power Spectral Density (PSD) of quasi-stationary processes can be efficiently estimated using the short time Fourier series (STFT). In this paper, an algorithm has been proposed that computes the PSD of quasi-stationary process efficiently using offline autoregressive model order estimation algorithm, recursive parameter estimation technique and modified sliding window discrete Fourier Transform algorithm. The main difference in this algorithm and STFT is that the sliding window (SW) and window for spectral estimation (WSA) are separately defined. WSA is updated and its PSD is computed only when change in statistics is detected in the SW. The computational complexity of the proposed algorithm is found to be lesser than that for standard STFT technique.

Keywords: Power Spectral Density (PSD), quasi-stationarytime series, short time Fourier Transform, Sliding window DFT.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1922

Authors: Vesile Evrim, Aliyu Awwal

Abstract:

Today, there is a large number of political transcripts available on the Web to be mined and used for statistical analysis, and product recommendations. As the online political resources are used for various purposes, automatically determining the political orientation on these transcripts becomes crucial. The methodologies used by machine learning algorithms to do an automatic classification are based on different features that are classified under categories such as Linguistic, Personality etc. Considering the ideological differences between Liberals and Conservatives, in this paper, the effect of Personality traits on political orientation classification is studied. The experiments in this study were based on the correlation between LIWC features and the BIG Five Personality traits. Several experiments were conducted using Convote U.S. Congressional- Speech dataset with seven benchmark classification algorithms. The different methodologies were applied on several LIWC feature sets that constituted by 8 to 64 varying number of features that are correlated to five personality traits. As results of experiments, Neuroticism trait was obtained to be the most differentiating personality trait for classification of political orientation. At the same time, it was observed that the personality trait based classification methodology gives better and comparable results with the related work.

Keywords: Politics, personality traits, LIWC, machine learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2120

Authors: Hema C. R., Paulraj M. P., S. Yaacob, A. H. Adom, R. Nagarajan

Abstract:

Motor imagery classification provides an important basis for designing Brain Machine Interfaces [BMI]. A BMI captures and decodes brain EEG signals and transforms human thought into actions. The ability of an individual to control his EEG through imaginary mental tasks enables him to control devices through the BMI. This paper presents a method to design a four state BMI using EEG signals recorded from the C3 and C4 locations. Principle features extracted through principle component analysis of the segmented EEG are analyzed using two novel classification algorithms using Elman recurrent neural network and functional link neural network. Performance of both classifiers is evaluated using a particle swarm optimization training algorithm; results are also compared with the conventional back propagation training algorithm. EEG motor imagery recorded from two subjects is used in the offline analysis. From overall classification performance it is observed that the BP algorithm has higher average classification of 93.5%, while the PSO algorithm has better training time and maximum classification. The proposed methods promises to provide a useful alternative general procedure for motor imagery classification

Keywords: Motor Imagery, Brain Machine Interfaces, Neural Networks, Particle Swarm Optimization, EEG signal processing.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2402

Authors: Ramin Vafadary, Maryam Khanbaghi

Abstract:

Forecasting electricity load is important for various purposes like planning, operation and control. Forecasts can save operating and maintenance costs, increase the reliability of power supply and delivery systems, and correct decisions for future development. This paper compares various time series methods to forecast 24 hours ahead of electricity load. The methods considered are the Holt-Winters smoothing, SARIMA Modeling, LSTM Network, Fbprophet and Tensorflow probability. The performance of each method is evaluated by using the forecasting accuracy criteria namely, the Mean Absolute Error and Root Mean Square Error. The National Renewable Energy Laboratory (NREL) residential energy consumption data are used to train the models. The results of this study show that SARIMA model is superior to the others for 24 hours ahead forecasts. Furthermore, a Bagging technique is used to make the predictions more robust. The obtained results show that by Bagging multiple time-series forecasts we can improve the robustness of the models for 24 hour ahead electricity load forecasting.

Keywords: Bagging, Fbprophet, Holt-Winters, LSTM, Load Forecast, SARIMA, tensorflow probability, time series.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 403

Authors: Jimeng Shi, Mahek Jain, Giri Narasimhan

Abstract:

Time Series Forecasting (TSF) is used to predict the target variables at a future time point based on the learning from previous time points. To keep the problem tractable, learning methods use data from a fixed length window in the past as an explicit input. In this paper, we study how the performance of predictive models change as a function of different look-back window sizes and different amounts of time to predict into the future. We also consider the performance of the recent attention-based transformer models, which had good success in the image processing and natural language processing domains. In all, we compare four different deep learning methods (Recurrent Neural Network (RNN), Long Short-term Memory (LSTM), Gated Recurrent Units (GRU), and Transformer) along with a baseline method. The dataset (hourly) we used is the Beijing Air Quality Dataset from the website of University of California, Irvine (UCI), which includes a multivariate time series of many factors measured on an hourly basis for a period of 5 years (2010-14). For each model, we also report on the relationship between the performance and the look-back window sizes and the number of predicted time points into the future. Our experiments suggest that Transformer models have the best performance with the lowest Mean   Absolute Errors (MAE = 14.599, 23.273) and Root Mean Square Errors (RSME = 23.573, 38.131) for most of our single-step and multi-steps predictions. The best size for the look-back window to predict 1 hour into the future appears to be one day, while 2 or 4 days perform the best to predict 3 hours into the future.

Keywords: Air quality prediction, deep learning algorithms, time series forecasting, look-back window.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1033

Authors: Rao Fu, Jie Chen, Shutian Zeng, Yiping Zhuang, Agus Sudjianto

Abstract:

Generative Adversarial Net (GAN) has proved to be a powerful machine learning tool in image data analysis and generation. In this paper, we propose to use Conditional Generative Adversarial Net (CGAN) to learn and simulate time series data. The conditions include both categorical and continuous variables with different auxiliary information. Our simulation studies show that CGAN has the capability to learn different types of normal and heavy-tailed distributions, as well as dependent structures of different time series. It also has the capability to generate conditional predictive distributions consistent with training data distributions. We also provide an in-depth discussion on the rationale behind GAN and the neural networks as hierarchical splines to establish a clear connection with existing statistical methods of distribution generation. In practice, CGAN has a wide range of applications in market risk and counterparty risk analysis: it can be applied to learn historical data and generate scenarios for the calculation of Value-at-Risk (VaR) and Expected Shortfall (ES), and it can also predict the movement of the market risk factors. We present a real data analysis including a backtesting to demonstrate that CGAN can outperform Historical Simulation (HS), a popular method in market risk analysis to calculate VaR. CGAN can also be applied in economic time series modeling and forecasting. In this regard, we have included an example of hypothetical shock analysis for economic models and the generation of potential CCAR scenarios by CGAN at the end of the paper.

Keywords: Conditional Generative Adversarial Net, market and credit risk management, neural network, time series.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1128

Authors: Bingquan Shen

Abstract:

Convolutional Neural Networks (CNN) have demonstrated their effectiveness in synthesizing 3D views of object instances at various viewpoints. Given the problem where one have limited viewpoints of a particular object for classification, we present a pose normalization architecture to transform the object to existing viewpoints in the training dataset before classification to yield better classification performance. We have demonstrated that this Pose Normalization Network (PNN) can capture the style of the target object and is able to re-render it to a desired viewpoint. Moreover, we have shown that the PNN improves the classification result for the 3D chairs dataset and ShapeNet airplanes dataset when given only images at limited viewpoint, as compared to a CNN baseline.

Keywords: Convolutional neural networks, object classification, pose normalization, viewpoint invariant.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1076

Authors: Ritu Vijay, Rekha Govil

Abstract:

The design of a complete expansion that allows for compact representation of certain relevant classes of signals is a central problem in signal processing applications. Achieving such a representation means knowing the signal features for the purpose of denoising, classification, interpolation and forecasting. Multilayer Neural Networks are relatively a new class of techniques that are mathematically proven to approximate any continuous function arbitrarily well. Radial Basis Function Networks, which make use of Gaussian activation function, are also shown to be a universal approximator. In this age of ever-increasing digitization in the storage, processing, analysis and communication of information, there are numerous examples of applications where one needs to construct a continuously defined function or numerical algorithm to approximate, represent and reconstruct the given discrete data of a signal. Many a times one wishes to manipulate the data in a way that requires information not included explicitly in the data, which is done through interpolation and/or extrapolation. Tidal data are a very perfect example of time series and many statistical techniques have been applied for tidal data analysis and representation. ANN is recent addition to such techniques. In the present paper we describe the time series representation capabilities of a special type of ANN- Radial Basis Function networks and present the results of tidal data representation using RBF. Tidal data analysis & representation is one of the important requirements in marine science for forecasting.

Keywords: ANN, RBF, Tidal Data.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1608

Authors: B. S. Saini, Dilbag Singh, Moin Uddin, Vinod Kumar

Abstract:

The RR interval series is non-stationary and unevenly spaced in time. For estimating its power spectral density (PSD) using traditional techniques like FFT, require resampling at uniform intervals. The researchers have used different interpolation techniques as resampling methods. All these resampling methods introduce the low pass filtering effect in the power spectrum. The lomb transform is a means of obtaining PSD estimates directly from irregularly sampled RR interval series, thus avoiding resampling. In this work, the superiority of Lomb transform method has been established over FFT based approach, after applying linear and cubicspline interpolation as resampling methods, in terms of reproduction of exact frequency locations as well as the relative magnitudes of each spectral component.

Keywords: HRV, Lomb Transform, Resampling, RR-intervals.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3183

Authors: Samy Sadek, Ayoub Al-Hamadi, Bernd Michaelis, Usama Sayed

Abstract:

In this paper, we propose a supervised method for color image classification based on a multilevel sigmoidal neural network (MSNN) model. In this method, images are classified into five categories, i.e., “Car", “Building", “Mountain", “Farm" and “Coast". This classification is performed without any segmentation processes. To verify the learning capabilities of the proposed method, we compare our MSNN model with the traditional Sigmoidal Neural Network (SNN) model. Results of comparison have shown that the MSNN model performs better than the traditional SNN model in the context of training run time and classification rate. Both color moments and multi-level wavelets decomposition technique are used to extract features from images. The proposed method has been tested on a variety of real and synthetic images.

Keywords: Image classification, multi-level neural networks, feature extraction, wavelets decomposition.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1605

Authors: Qi Xiu, Hiromu Hota, Yohsuke Ishii, Takuya Oda

Abstract:

Recently, collectable manufacturing data are rapidly increasing. On the other hand, mega recall is getting serious as a social problem. Under such circumstances, there are increasing needs for preventing mega recalls by defect analysis such as root cause analysis and abnormal detection utilizing manufacturing data. However, the time to classify strings in manufacturing data by traditional method is too long to meet requirement of quick defect analysis. Therefore, we present String Length Distribution Classification method (SLDC) to correctly classify strings in a short time. This method learns character features, especially string length distribution from Product ID, Machine ID in BOM and asset list. By applying the proposal to strings in actual manufacturing data, we verified that the classification time of strings can be reduced by 80%. As a result, it can be estimated that the requirement of quick defect analysis can be fulfilled.

Keywords: Data quality, feature selection, probability distribution, string classification, string length.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1284

Authors: Y. Tiamaz, N. Souissi

Abstract:

The purpose of this paper is to present a classification of Lean models which aims to capture all the concepts related to this approach and thus facilitate its implementation. This classification allows the identification of the most relevant models according to several dimensions. From this perspective, we present a review and an analysis of Lean models literature and we propose dimensions for the classification of the current proposals while respecting among others the axes of the Lean approach, the maturity of the models as well as their application domains. This classification allowed us to conclude that researchers essentially consider the Lean approach as a toolbox also they design their models to solve problems related to a specific environment. Since Lean approach is no longer intended only for the automotive sector where it was invented, but to all fields (IT, Hospital, ...), we consider that this approach requires a generic model that is capable of being implemented in all areas.

Keywords: Lean approach, lean models, classification, dimensions, holistic view.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1204