Search results for: time series classification

Authors: Sunday Nathaniel Obasi, Chiamak Chinasa Obasi

Abstract:

Soil characterization and classification provide the basic information necessary to create a functional evaluation and soil classification schemes. Fertility capability classification (FCC) on the other hand is a technical system that groups the soils according to kinds of problems they present for management of soil physical and chemical properties. This research was carried out in Ebonyi state, southeastern Nigeria, which is an agrarian state and a leading rice producing part of southeastern Nigeria. In order to maximize the soil and enhance the productivity of rice in Ebonyi soils, soil classification, and fertility classification information need to be supplied. The state was grouped into three locations according to their agricultural zones namely; Ebonyi north, Ebonyi central and Ebonyi south representing Abakaliki, Ikwo and Ivo locations respectively. Major rice growing areas of the soils were located and two profile pits were sunk in each of the studied zones from which soils were characterized, classified and fertility capability classification (FCC) developed. Soil classification was done using United State Department of Agriculture (USDA) Soil Taxonomy and correlated with World Reference Base for soil resources. Results obtained classified Abakaliki 1 and Abakaliki 2 as Typic Fluvaquents (Ochric Fluvisols). Ikwo 1 was classified as Vertic Eutrudepts (Eutric Vertisols) while Ikwo 2 was classified as Typic Eutrudepts (Eutric Cambisols). Ivo 1 and Ivo 2 were both classified as Aquic Eutrudepts (Gleyic Leptosols). Fertility capability classification (FCC) revealed that all studied soils had mostly loamy topsoils and subsoils except Ikwo 1 with clayey topsoil. Limitations encountered in the studied soils include; dryness (d), low ECEC (e), low nutrient capital reserve (k) and water logging/ anaerobic condition (gley). Thus, FCC classifications were Ldek for Abakaliki 1 and 2, Ckv for Ikwo 1, LCk for Ikwo 2 while Ivo 1 and 2 were Legk and Lgk respectively.

Keywords: soil classification, soil fertility, limitations, modifiers, Southeastern Nigeria

Procedia PDF Downloads 108

Authors: Noha Seddik, Sherine Youssef, Mohamed Kholeif

Abstract:

The automated epileptic seizure detection research field has emerged in the recent years; this involves analyzing the Electroencephalogram (EEG) signals instead of the traditional visual inspection performed by expert neurologists. In this study, a Support Vector Machine (SVM) that uses Weighted Permutation Entropy (WPE) as the input feature is proposed for classifying normal and seizure EEG records. WPE is a modified statistical parameter of the permutation entropy (PE) that measures the complexity and irregularity of a time series. It incorporates both the mapped ordinal pattern of the time series and the information contained in the amplitude of its sample points. The proposed system utilizes the fact that entropy based measures for the EEG segments during epileptic seizure are lower than in normal EEG.

Keywords: electroencephalogram (EEG), epileptic seizure detection, weighted permutation entropy (WPE), support vector machine (SVM)

Procedia PDF Downloads 341

Authors: Thanh Noi Phan, Martin Kappas, Jan Degener

Abstract:

The currently launched Sentinel 2 (S2) satellite (June, 2015) bring a great potential and opportunities for land use/cover map applications, due to its fine spatial resolution multispectral as well as high temporal resolutions. So far, there are handful studies using S2 real data for land cover classification. Especially in northern Vietnam, to our best knowledge, there exist no studies using S2 data for land cover map application. The aim of this study is to provide the preliminary result of land cover classification using Sentinel -2 data with a rising state – of – art classifier, Random Forest. A case study with heterogeneous land use/cover in the eastern of Hanoi Capital – Vietnam was chosen for this study. All 10 spectral bands of 10 and 20 m pixel size of S2 images were used, the 10 m bands were resampled to 20 m. Among several classified algorithms, supervised Random Forest classifier (RF) was applied because it was reported as one of the most accuracy methods of satellite image classification. The results showed that the red-edge and shortwave infrared (SWIR) bands play an important role in land cover classified results. A very high overall accuracy above 90% of classification results was achieved.

Keywords: classify algorithm, classification, land cover, random forest, sentinel 2, Vietnam

Procedia PDF Downloads 350

Authors: Shourav Chowdhury, Subrata Barua, K. M. Naimuddin, Imam Hassan Sajib, Md. Hasan, Shudipta Banik, Muna Das

Abstract:

Traffic accidents stand as a leading cause of fatalities worldwide, significantly impacting global mortality rates. Accurate classification of road accidents through advanced technological solutions presents a crucial opportunity to revolutionize accident prevention and emergency response strategies. This paper presents an advanced deep-learning methodology customized for the classification of road accidents using CCTV surveillance footage. This real-time dataset, comprising approximately 18,000 frames, has been amassed, which is pivotal for enabling comprehensive research in this field. This substantial dataset is the foundation for these investigative efforts, providing a rich and diverse source for conducting an in-depth analysis of the features. It has achieved a remarkable accuracy of 97% on this dataset through the strategic utilization of transfer learning in conjunction with LSTM (Long short-term memory) techniques. This accomplishment underscores the efficacy of our approach, combining the strengths of transfer learning and LSTM models, resulting in a highly accurate classification system for road accident events.

Keywords: accident, CCTV, footage, long short-term memory, surveillance

Procedia PDF Downloads 25

Authors: Ravneil Nand

Abstract:

Cooperative coevolution uses problem decomposition methods to solve a larger problem. The problem decomposition deals with breaking down the larger problem into a number of smaller sub-problems depending on their method. Different problem decomposition methods have their own strengths and limitations depending on the neural network used and application problem. In this paper we are introducing a new problem decomposition method known as Hidden-Neuron Level Decomposition (HNL). The HNL method is competing with established problem decomposition method in time series prediction. The results show that the proposed approach has improved the results in some benchmark data sets when compared to the standalone method and has competitive results when compared to methods from literature.

Keywords: cooperative coevaluation, feed forward network, problem decomposition, neuron, synapse

Procedia PDF Downloads 302

Authors: Saad Al-Baddai, Karema Al-Subari, Elmar Lang, Bernd Ludwig

Abstract:

Empirical mode decomposition (EMD), a new data-driven of time-series decomposition, has the advantage of supposing that a time series is non-linear or non-stationary, as is implicitly achieved in Fourier decomposition. However, the EMD suffers of mode mixing problem in some cases. The aim of this paper is to present a solution for a common type of signals causing of EMD mode mixing problem, in case a signal suffers of an intermittency. By an artificial example, the solution shows superior performance in terms of cope EMD mode mixing problem comparing with the conventional EMD and Ensemble Empirical Mode decomposition (EEMD). Furthermore, the over-sifting problem is also completely avoided; and computation load is reduced roughly six times compared with EEMD, an ensemble number of 50.

Keywords: empirical mode decomposition (EMD), mode mixing, sifting process, over-sifting

Procedia PDF Downloads 363

Authors: Karim Hamidi Machekposhti, Hossein Sedghi, Abdolrasoul Telvari, Hossein Babazadeh

Abstract:

Floods have huge environmental and economic impact. Therefore, flood prediction is given a lot of attention due to its importance. This study analysed the annual maximum streamflow (discharge) (AMS or AMD) of Karkheh River in Karkheh River Basin for flood predicting using ARIMA model. For this purpose, we use the Box-Jenkins approach, which contains four-stage method model identification, parameter estimation, diagnostic checking and forecasting (predicting). The main tool used in ARIMA modelling was the SAS and SPSS software. Model identification was done by visual inspection on the ACF and PACF. SAS software computed the model parameters using the ML, CLS and ULS methods. The diagnostic checking tests, AIC criterion, RACF graph and RPACF graphs, were used for selected model verification. In this study, the best ARIMA models for Annual Maximum Discharge (AMD) time series was (4,1,1) with their AIC value of 88.87. The RACF and RPACF showed residuals’ independence. To forecast AMD for 10 future years, this model showed the ability of the model to predict floods of the river under study in the Karkheh River Basin. Model accuracy was checked by comparing the predicted and observation series by using coefficient of determination (R²).

Keywords: time series modelling, stochastic processes, ARIMA model, Karkheh river

Procedia PDF Downloads 266

Authors: J. K. Alhassan, S. A. Lawal

Abstract:

This work is on decision tree-based classification for the disbursement of scholarship. Tree-based data mining classification technique is used in other to determine the generic rule to be used to disburse the scholarship. The system based on the defined rules from the tree is able to determine the class (status) to which an applicant shall belong whether Granted or Not Granted. The applicants that fall to the class of granted denote a successful acquirement of scholarship while those in not granted class are unsuccessful in the scheme. An algorithm that can be used to classify the applicants based on the rules from tree-based classification was also developed. The tree-based classification is adopted because of its efficiency, effectiveness, and easy to comprehend features. The system was tested with the data of National Information Technology Development Agency (NITDA) Abuja, a Parastatal of Federal Ministry of Communication Technology that is mandated to develop and regulate information technology in Nigeria. The system was found working according to the specification. It is therefore recommended for all scholarship disbursement organizations.

Keywords: classification, data mining, decision tree, scholarship

Procedia PDF Downloads 344

Authors: Ravinder Bahl, Jamini Sharma

Abstract:

The paper demonstrates analysis of the cervical cancer based on a probabilistic model. It involves technique for classification and prediction by recognizing typical and diagnostically most important test features relating to cervical cancer. The main contributions of the research include predicting the probability of recurrences in no recurrence (first time detection) cases. The combination of the conventional statistical and machine learning tools is applied for the analysis. Experimental study with real data demonstrates the feasibility and potential of the proposed approach for the said cause.

Keywords: cervical cancer, recurrence, no recurrence, probabilistic, classification, prediction, machine learning

Procedia PDF Downloads 327

Authors: Aysegul Sener, Gonca Tuncel Memis, Mirac Kamislioglu

Abstract:

Chaos theory is one of the new paradigms of science since the last century. After determining chaos in the weather systems by Edward Lorenz the popularity of the theory was increased. Chaos is observed in many natural systems and studies continue to defect chaos to other natural systems. Acid rain is one of the environmental problems that have negative effects on environment and acid rains values are monitored continuously. In this study, we aim that analyze the chaotic behavior of acid rains in Turkey with the chaotic defecting approaches. The data of pH degree of rain waters, concentration of sulfate and nitrate data of wet rain water samples in the rain collecting stations which are located in different regions of Turkey are provided by Turkish State Meteorology Service. Lyapunov exponents, reconstruction of the phase space, power spectrums are used in this study to determine and predict the chaotic behaviors of acid rains. As a result of the analysis it is found that acid rain time series have positive Lyapunov exponents and wide power spectrums and chaotic behavior is observed in the acid rain time series.

Keywords: acid rains, chaos, chaotic analysis, Lypapunov exponents

Procedia PDF Downloads 117

Authors: Reza Mohammadi, Mahmod R. Sahebi, Mehrnoosh Omati, Milad Vahidi

Abstract:

Classification of high resolution polarimetric Synthetic Aperture Radar (PolSAR) images plays an important role in land cover and land use management. Recently, classification algorithms based on Bag of Visual Words (BOVW) model have attracted significant interest among scholars and researchers in and out of the field of remote sensing. In this paper, BOVW model with pixel based low-level features has been implemented to classify a subset of San Francisco bay PolSAR image, acquired by RADARSAR 2 in C-band. We have used segment-based decision-making strategy and compared the result with the result of traditional Support Vector Machine (SVM) classifier. 90.95% overall accuracy of the classification with the proposed algorithm has shown that the proposed algorithm is comparable with the state-of-the-art methods. In addition to increase in the classification accuracy, the proposed method has decreased undesirable speckle effect of SAR images.

Keywords: Bag of Visual Words (BOVW), classification, feature extraction, land cover management, Polarimetric Synthetic Aperture Radar (PolSAR)

Procedia PDF Downloads 177

Authors: Wanhyun Cho, Soonja Kang, Sangkyoon Kim, Soonyoung Park

Abstract:

In this paper, we propose a novel inference algorithm for the multi-class Gaussian process classification model that can be used in the field of human behavior recognition. This algorithm can drive simultaneously both a posterior distribution of a latent function and estimators of hyper-parameters in a Gaussian process classification model with multi-class. Our algorithm is based on the Laplace approximation (LA) technique and variational EM framework. This is performed in two steps: called expectation and maximization steps. First, in the expectation step, using the Bayesian formula and LA technique, we derive approximately the posterior distribution of the latent function indicating the possibility that each observation belongs to a certain class in the Gaussian process classification model. Second, in the maximization step, using a derived posterior distribution of latent function, we compute the maximum likelihood estimator for hyper-parameters of a covariance matrix necessary to define prior distribution for latent function. These two steps iteratively repeat until a convergence condition satisfies. Moreover, we apply the proposed algorithm with human action classification problem using a public database, namely, the KTH human action data set. Experimental results reveal that the proposed algorithm shows good performance on this data set.

Keywords: bayesian rule, gaussian process classification model with multiclass, gaussian process prior, human action classification, laplace approximation, variational EM algorithm

Procedia PDF Downloads 304

Authors: Daniel Fulus Fom, Gau Patrick Damulak

Abstract:

In this study, the Autoregressive Fractional Integrated Moving Average (ARFIMA) and Jordan Recurrent Neural Network (JRNN) models were employed to model the forecasting performance of the daily turbidity flow of White Clay Creek (WCC). The two methods were applied to the log difference series of the daily turbidity flow series of WCC. The measurements of error employed to investigate the forecasting performance of the ARFIMA and JRNN models are the Root Mean Square Error (RMSE) and the Mean Absolute Error (MAE). The outcome of the investigation revealed that the forecasting performance of the JRNN technique is better than the forecasting performance of the ARFIMA technique in the mean square error sense. The results of the ARFIMA and JRNN models were obtained by the simulation of the models using MATLAB version 8.03. The significance of using the log difference series rather than the difference series is that the log difference series stabilizes the turbidity flow series than the difference series on the ARFIMA and JRNN.

Keywords: auto regressive, mean absolute error, neural network, root square mean error

Procedia PDF Downloads 243

Authors: Harish Krishnamurthy, Anna Lafontant, Ren Yi

Abstract:

Unidentified Flying Objects (UFOs) have been an interesting topic for most enthusiasts and hence people all over the United States report such findings online at the National UFO Report Center (NUFORC). Some of these reports are a hoax and among those that seem legitimate, our task is not to establish that these events confirm that they indeed are events related to flying objects from aliens in outer space. Rather, we intend to identify if the report was a hoax as was identified by the UFO database team with their existing curation criterion. However, the database provides a wealth of information that can be exploited to provide various analyses and insights such as social reporting, identifying real-time spatial events and much more. We perform analysis to localize these time-series geospatial events and correlate with known real-time events. This paper does not confirm any legitimacy of alien activity, but rather attempts to gather information from likely legitimate reports of UFOs by studying the online reports. These events happen in geospatial clusters and also are time-based. We look at cluster density and data visualization to search the space of various cluster realizations to decide best probable clusters that provide us information about the proximity of such activity. A random forest classifier is also presented that is used to identify true events and hoax events, using the best possible features available such as region, week, time-period and duration. Lastly, we show the performance of the scheme on various days and correlate with real-time events where one of the UFO reports strongly correlates to a missile test conducted in the United States.

Keywords: time-series clustering, feature extraction, hoax prediction, geospatial events

Procedia PDF Downloads 346

Authors: Kejal Khatri, Vishnu Narayan Mishra

Abstract:

We compute the degree of approximation of functions\tilde{f}\in H_w, a new Banach space using (T.E^1) summability means of conjugate Fourier series. In this paper, we extend the results of Singh and Mahajan which in turn generalizes the result of Lal and Yadav. Some corollaries have also been deduced from our main theorem and particular cases.

Keywords: conjugate Fourier series, degree of approximation, Hölder metric, matrix summability, product summability

Procedia PDF Downloads 379

Authors: Jonas Pedro Fabris, Alberth Almeida Amorim Souza, Maria Emilia Camargo, Suzana Leitão Russo

Abstract:

With the law Nº. 9279, of May 14, 1996, the Brazilian government regulates rights and obligations relating to industrial property considering the economic development of the country as granting patents, trademark registration, registration of industrial designs and other forms of protection copyright. In this study, we show the application of the methodology of Box and Jenkins in the series of deposits of industrial design at the National Institute of Industrial Property for the period from May 1996 to April 2013. First, a graphical analysis of the data was done by observing the behavior of the data and the autocorrelation function. The best model found, based on the analysis of charts and statistical tests suggested by Box and Jenkins methodology, it was possible to determine the model number for the deposit of industrial design, SARIMA (2,1,0)(2,0,0), with an equal to 9.88% MAPE.

Keywords: ARIMA models, autocorrelation, Box and Jenkins Models, industrial design, MAPE, time series

Procedia PDF Downloads 515

Authors: Yuzuru Mitsui, Takashi Ikegami

Abstract:

The exponents of Taylor’s law in deterministic chaotic systems are computed, and their meanings are intensively discussed. Taylor’s law is the scaling relationship between the mean and variance (in both space and time) of population abundance, and this law is known to hold in a variety of ecological time series. The exponents found in the temporal Taylor’s law are different from those of the spatial Taylor’s law. The temporal Taylor’s law is calculated on the time series from the same locations (or the same initial states) of different temporal phases. However, with the spatial Taylor’s law, the mean and variance are calculated from the same temporal phase sampled from different places. Most previous studies were done with stochastic models, but we computed the temporal and spatial Taylor’s law in deterministic systems. The temporal Taylor’s law evaluated using the same initial state, and the spatial Taylor’s law was evaluated using the ensemble average and variance. There were two main discoveries from this work. First, it is often stated that deterministic systems tend to have the value two for Taylor’s exponent. However, most of the calculated exponents here were not two. Second, we investigated the relationships between chaotic features measured by the Lyapunov exponent, the correlation dimension, and other indexes with Taylor’s exponents. No strong correlations were found; however, there is some relationship in the same model, but with different parameter values, and we will discuss the meaning of those results at the end of this paper.

Keywords: chaos, density effect, population dynamics, Taylor’s law

Procedia PDF Downloads 149

Authors: Najoua El Hajjaji El Idrissi, Necip Gokhan Kasapoglu

Abstract:

Polarimetric Synthetic Aperture Radar-based imaging is a powerful technique used for earth observation and classification of surfaces. Forest evolution has been one of the vital areas of attention for the remote sensing experts. The information about forest areas can be achieved by remote sensing, whether by using active radars or optical instruments. However, due to several weather constraints, such as cloud cover, limited information can be recovered using optical data and for that reason, Polarimetric Synthetic Aperture Radar (PolSAR) is used as a powerful tool for forestry inventory. In this [14paper, we applied support vector machine (SVM) and Mahalanobis distance to the fully polarimetric AIRSAR P, L, C-bands data from the Nezer forest areas, the classification is based in the separation of different tree ages. The classification results were evaluated and the results show that the SVM performs better than the Mahalanobis distance and SVM achieves approximately 75% accuracy. This result proves that SVM classification can be used as a useful method to evaluate fully polarimetric SAR data with sufficient value of accuracy.

Keywords: classification, synthetic aperture radar, SAR polarimetry, support vector machine, mahalanobis distance

Procedia PDF Downloads 102

Authors: Subham Kharel, Sudha Ravindranath, A. Vidya, B. Chandrasekaran, K. Ganesha Raj, T. Shesadri

Abstract:

Digitization of urban features is a tedious and time-consuming process when done manually. In addition to this problem, Indian cities have complex habitat patterns and convoluted clustering patterns, which make it even more difficult to map features. This paper makes an attempt to classify urban objects in the satellite image using object-oriented classification techniques in which various classes such as vegetation, water bodies, buildings, and shadows adjacent to the buildings were mapped semi-automatically. Building layer obtained as a result of object-oriented classification along with already available building layers was used. The main focus, however, lay in the extraction of high-rise buildings using spatial technology, digital image processing, and modeling, which would otherwise be a very difficult task to carry out manually. Results indicated a considerable rise in the total number of buildings in the city. High-rise buildings were successfully mapped using satellite imagery, spatial technology along with logical reasoning and mathematical considerations. The results clearly depict the ability of Remote Sensing and GIS to solve complex problems in urban scenarios like studying urban sprawl and identification of more complex features in an urban area like high-rise buildings and multi-dwelling units. Object-Oriented Technique has been proven to be effective and has yielded an overall efficiency of 80 percent in the classification of high-rise buildings.

Keywords: object oriented classification, shadow extraction, high-rise buildings, satellite imagery, spatial technology

Procedia PDF Downloads 118

Authors: Ali Asheibi

Abstract:

The rapid increase in the size of databases required to store power quality monitoring data has demanded new techniques for analysing and understanding the data. One suggested technique to assist in analysis is data mining. Preparing raw data to be ready for data mining exploration take up most of the effort and time spent in the whole data mining process. Clustering is an important technique in data mining and machine learning in which underlying and meaningful groups of data are discovered. Large amounts of harmonic data have been collected from an actual harmonic monitoring system in a distribution system in Australia for three years. This amount of acquired data makes it difficult to identify operational events that significantly impact the harmonics generated on the system. In this paper, harmonic data preparation processes to better understanding of the data have been presented. Underlying classes in this data has then been identified using clustering technique based on the Minimum Message Length (MML) method. The underlying operational information contained within the clusters can be rapidly visualised by the engineers. The C5.0 algorithm was used for classification and interpretation of the generated clusters.

Keywords: data mining, harmonic data, clustering, classification

Procedia PDF Downloads 219

Authors: Yung-Chung Chuang

Abstract:

The cultural layers of archaeological sites are mainly affected by surface land use, land cover, and root system of surface vegetation. For this reason, continuous monitoring of land use and land cover change is important for archaeological sites protection and management. However, in actual operation, on-site investigation and orthogonal photograph interpretation require a lot of time and manpower. For this reason, it is necessary to perform a good alternative for surface vegetation survey in an automated or semi-automated manner. In this study, we applied semi-automatic digital aerial survey technology and canopy characters classification with very high-resolution aerial photographs for surface vegetation interpretation of archaeological sites. The main idea is based on different landscape or forest type can easily be distinguished with canopy characters (e.g., specific texture distribution, shadow effects and gap characters) extracted by semi-automatic image classification. A novel methodology to classify the shape of canopy characters using landscape indices and multivariate statistics was also proposed. Non-hierarchical cluster analysis was used to assess the optimal number of canopy character clusters and canonical discriminant analysis was used to generate the discriminant functions for canopy character classification (seven categories). Therefore, people could easily predict the forest type and vegetation land cover by corresponding to the specific canopy character category. The results showed that the semi-automatic classification could effectively extract the canopy characters of forest and vegetation land cover. As for forest type and vegetation type prediction, the average prediction accuracy reached 80.3%~91.7% with different sizes of test frame. It represented this technology is useful for archaeological site survey, and can improve the classification efficiency and data update rate.

Keywords: digital aerial survey, canopy characters classification, archaeological sites, multivariate statistics

Procedia PDF Downloads 113

Authors: Zuhier Altawallbeh

Abstract:

This paper investigates the approximate analytical solutions of general form of Volterra integro-differential equations system by using the residual power series method (for short RPSM). The proposed method produces the solutions in terms of convergent series requires no linearization or small perturbation and reproduces the exact solution when the solution is polynomial. Some examples are given to demonstrate the simplicity and efficiency of the proposed method. Comparisons with the Laplace decomposition algorithm verify that the new method is very effective and convenient for solving system of pantograph equations.

Keywords: integro-differential equation, pantograph equations, system of initial value problems, residual power series method

Procedia PDF Downloads 396

Authors: Ibrahim Can, Fatih Tosunoğlu

Abstract:

The flow duration curve (FDC) is an informative method that represents the flow regime’s properties for a river basin. Therefore, the FDC is widely used for water resource projects such as hydropower, water supply, irrigation and water quality management. The primary purpose of this study is to obtain synthetic daily flow duration curves for Çoruh Basin, Turkey. For this aim, we firstly developed univariate auto-regressive moving average (ARMA) models for daily flows of 9 stations located in Çoruh basin and then these models were used to generate 100 synthetic flow series each having same size as historical series. Secondly, flow duration curves of each synthetic series were drawn and the flow values exceeded 10, 50 and 95 % of the time and 95% confidence limit of these flows were calculated. As a result, flood, mean and low flows potential of Çoruh basin will comprehensively be represented.

Keywords: ARMA models, Çoruh basin, flow duration curve, Turkey

Procedia PDF Downloads 364

Authors: Vishal Das, Tianyi Mao, Zhicheng Geng, Carmen Flores, Diego Pelloso, Fang Wang

Abstract:

Accurate sell-in and sell-out forecasting is a ubiquitous problem in the retail industry. It is an important element of any demand planning activity. As a global food and beverage company, Nestlé has hundreds of products in each geographical location that they operate in. Each product has its sell-in and sell-out time series data, which are forecasted on a weekly and monthly scale for demand and financial planning. To address this challenge, Nestlé Chilein collaboration with Amazon Machine Learning Solutions Labhas developed their in-house solution of using machine learning models for forecasting. Similar products are combined together such that there is one model for each product category. In this way, the models learn from a larger set of data, and there are fewer models to maintain. The solution is scalable to all product categories and is developed to be flexible enough to include any new product or eliminate any existing product in a product category based on requirements. We show how we can use the machine learning development environment on Amazon Web Services (AWS) to explore a set of forecasting models and create business intelligence dashboards that can be used with the existing demand planning tools in Nestlé. We explored recent deep learning networks (DNN), which show promising results for a variety of time series forecasting problems. Specifically, we used a DeepAR autoregressive model that can group similar time series together and provide robust predictions. To further enhance the accuracy of the predictions and include domain-specific knowledge, we designed an ensemble approach using DeepAR and XGBoost regression model. As part of the ensemble approach, we interlinked the sell-out and sell-in information to ensure that a future sell-out influences the current sell-in predictions. Our approach outperforms the benchmark statistical models by more than 50%. The machine learning (ML) pipeline implemented in the cloud is currently being extended for other product categories and is getting adopted by other geomarkets.

Keywords: sell-in and sell-out forecasting, demand planning, DeepAR, retail, ensemble machine learning, time-series

Procedia PDF Downloads 214

Authors: Bandhan Dey, Muhsina Bintoon Yiasha, Gulam Sulaman Choudhury

Abstract:

Chest disease is one of the most problematic ailments in our regular life. There are many known chest diseases out there. Diagnosing them correctly plays a vital role in the process of treatment. There are many methods available explicitly developed for different chest diseases. But the most common approach for diagnosing these diseases is through X-ray. In this paper, we proposed a multi-classification deep learning model for diagnosing COVID-19, lung cancer, pneumonia, tuberculosis, and atelectasis from chest X-rays. In the present work, we used the transfer learning method for better accuracy and fast training phase. The performance of three architectures is considered: InceptionV3, VGG-16, and VGG-19. We evaluated these deep learning architectures using public digital chest x-ray datasets with six classes (i.e., COVID-19, lung cancer, pneumonia, tuberculosis, atelectasis, and normal). The experiments are conducted on six-classification, and we found that VGG16 outperforms other proposed models with an accuracy of 95%.

Keywords: deep learning, image classification, X-ray images, Tensorflow, Keras, chest diseases, convolutional neural networks, multi-classification

Procedia PDF Downloads 59

Authors: Zahra Abdolkarimi, Naser Zourikalatehsamad,

Abstract:

Up to 40 years ago, after recognition of epilepsy, it was generally believed that these attacks occurred randomly and suddenly. However, thanks to the advance of mathematics and engineering, such attacks can be predicted within a few minutes or hours. In this way, various algorithms for long-term prediction of the time and frequency of the first attack are presented. In this paper, by considering the nonlinear nature of brain signals and dynamic recorded brain signals, ANFIS model is presented to predict the brain signals, since according to physiologic structure of the onset of attacks, more complex neural structures can better model the signal during attacks. Contribution of this work is the co-evolution algorithm for optimization of ANFIS network parameters. Our objective is to predict brain signals based on time series obtained from brain signals of the people suffering from epilepsy using ANFIS. Results reveal that compared to other methods, this method has less sensitivity to uncertainties such as presence of noise and interruption in recorded signals of the brain as well as more accuracy. Long-term prediction capacity of the model illustrates the usage of planted systems for warning medication and preventing brain signals.

Keywords: co-evolution algorithms, brain signals, time series, neural networks, ANFIS model, physiologic structure, time prediction, epilepsy suffering, illustrates model

Procedia PDF Downloads 248

Authors: Ronak Khosravi, Mahmood Abbasi Layegh, Siamak Haghipour, Avin Esmaili

Abstract:

In this paper, a study on classification of musical woodwind instruments using a small set of features selected from a broad range of extracted ones by the sequential forward selection method was carried out. Firstly, we extract 42 features for each record in the music database of 402 sound files belonging to five different groups of Flutes (end blown and internal duct), Single –reed, Double –reed (exposed and capped), Triple reed and Quadruple reed. Then, the sequential forward selection method is adopted to choose the best feature set in order to achieve very high classification accuracy. Two different classification techniques of support vector machines and relevance vector machines have been tested out and an accuracy of up to 96% can be achieved by using 21 time, frequency and coefficient features and relevance vector machine with the Gaussian kernel function.

Keywords: coefficient features, relevance vector machines, spectral features, support vector machines, temporal features

Procedia PDF Downloads 286

Authors: Syed Aziz Rasool, Ayesha Zaman

Abstract:

Poverty is one of the most important problems for any developing nation. Workers’ remittances and investment plays a crucial role in development of any country by reducing the poverty level in Pakistan. This research studies the relationship between workers’ remittances and poverty alleviation. It also focused the significant effect on poverty reduction. This study uses time series data for the period of 1972-2013. Autoregressive Distributed Lag (ARDL)Model and Error Correction (ECM)Model has been used in order to find out the long run and short run relationship between the worker’s remittances and poverty level respectively. Thus, inflow of remittances showed the significant and negative impact on poverty level. Moreover, coefficient of error correction model explains the adjustment towards convergence and it has highly significant and negative value. According to this research, Policy makers should strongly focus on positive and effective policies to attract more remittances. JELCODE: JEL: J61

Keywords: ECM, ARDL, AIC, SC

Procedia PDF Downloads 255

Authors: Bharatendra Rai

Abstract:

The sequence of words in text data has long-term dependencies and is known to suffer from vanishing gradient problems when developing deep learning models. Although recurrent networks such as long short-term memory networks help to overcome this problem, achieving high text classification performance is a challenging problem. Convolutional recurrent networks that combine the advantages of long short-term memory networks and convolutional neural networks can be useful for text classification performance improvements. However, arriving at suitable hyperparameter values for convolutional recurrent networks is still a challenging task where fitting a model requires significant computing resources. This paper illustrates the advantages of using convolutional recurrent networks for text classification with the help of statistically planned computer experiments for hyperparameter tuning.

Keywords: long short-term memory networks, convolutional recurrent networks, text classification, hyperparameter tuning, Tukey honest significant differences

Procedia PDF Downloads 86

Authors: S. Channgam, A. Sae-Tang, T. Termsaithong

Abstract:

In this research, the occurrences of large size events in various system sizes of the Bak-Tang-Wiesenfeld sandpile model are considered. The system sizes (square lattice) of model considered here are 25×25, 50×50, 75×75 and 100×100. The cross-correlation between the ratio of sites containing 3 grain time series and the large size event time series for these 4 system sizes are also analyzed. Moreover, a prediction method of the large-size event for the 50×50 system size is also introduced. Lastly, it can be shown that this prediction method provides a slightly higher efficiency than random predictions.

Keywords: Bak-Tang-Wiesenfeld sandpile model, cross-correlation, avalanches, prediction method

Procedia PDF Downloads 352