Search results for: time series classification

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 237

Authors: K. E. Ch. Vidyasagar, M. Moghavvemi, T. S. S. T. Prabhat

Abstract:

Epilepsy is a global problem, and with seizures eluding even the smartest of diagnoses a requirement for automatic detection of the same using electroencephalogram (EEG) would have a huge impact in diagnosis of the disorder. Among a multitude of methods for automatic epilepsy detection, one should find the best method out, based on accuracy, for classification. This paper reasons out, and rationalizes, the best methods for classification. Accuracy is based on the classifier, and thus this paper discusses classifiers like quadratic discriminant analysis (QDA), classification and regression tree (CART), support vector machine (SVM), naive Bayes classifier (NBC), linear discriminant analysis (LDA), K-nearest neighbor (KNN) and artificial neural networks (ANN). Results show that ANN is the most accurate of all the above stated classifiers with 97.7% accuracy, 97.25% specificity and 98.28% sensitivity in its merit. This is followed closely by SVM with 1% variation in result. These results would certainly help researchers choose the best classifier for detection of epilepsy.

Keywords: classification, seizure, KNN, SVM, LDA, ANN, epilepsy

Procedia PDF Downloads 502

Authors: Xiaoli Zhang, Xiongfei Li, Yuncong Feng

Abstract:

ROC curves, as a widely used evaluating tool in machine learning field, are the tradeoff of true positive rate and negative rate. However, they are blamed for ignoring some vital information in the evaluation process, such as the amount of information about the target that each instance carries, predicted score given by each classification model to each instance. Hence, in this paper, a new classification performance method is proposed by extending the Receiver Operator Characteristic (ROC) curves to 3D space, which is denoted as 3D ROC Histogram. In the histogram, the

Keywords: classification, performance evaluation, receiver operating characteristic histogram, hardness prediction

Procedia PDF Downloads 304

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 264

Authors: Boukari Nassim

Abstract:

This paper describes the use of odd pair autoregressive coefficients (Yule _Walker and Burg) for the feature extraction of electroencephalogram (EEG) signals. In the classification: the radial basis function neural network neural network (RBFNN) is employed. The RBFNN is described by his architecture and his characteristics: as the RBF is defined by the spread which is modified for improving the results of the classification. Five types of EEG signals are defined for this work: Set A, Set B for normal signals, Set C, Set D for interictal signals, set E for ictal signal (we can found that in Bonn university). In outputs, two classes are given (AC, AD, AE, BC, BD, BE, CE, DE), the best accuracy is calculated at 99% for the combined odd pair autoregressive coefficients. Our method is very effective for the diagnosis of epileptic EEG signals.

Keywords: epilepsy, EEG signals classification, combined odd pair autoregressive coefficients, radial basis function neural network

Procedia PDF Downloads 337

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 269

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 368

Authors: Ebtehal Aljedaani, Maha Aljohani

Abstract:

Privacy and security patterns are both important for developing software that protects users' data and privacy. Privacy patterns are designed to address common privacy problems, such as unauthorized data collection and disclosure. Security patterns are designed to protect software from attack and ensure reliability and trustworthiness. Using privacy and security patterns, software engineers can implement security and privacy by design principles, which means that security and privacy are considered throughout the software development process. These patterns are available to translate "security & privacy-by-design" into practical advice for software engineering. Previous research on privacy and security patterns has typically focused on one category of patterns at a time. This paper aims to bridge this gap by merging the two categories and identifying their similarities and differences. To do this, the authors conducted a systematic literature review of 25 research papers on privacy and security patterns. The papers were analysed based on the category of the pattern, the classification of the pattern, and the security requirements that the pattern addresses. This paper presents the results of a comprehensive review of privacy and security design patterns. The review is intended to help future IT designers understand the relationship between the two types of patterns and how to use them to design secure and privacy-preserving software. The paper provides a clear classification of privacy and security design patterns, along with examples of each type. The authors found that there is only one widely accepted classification of privacy design patterns, while there are several competing classifications of security design patterns. Three types of security design patterns were found to be the most commonly used.

Keywords: design patterns, security, privacy, classification of patterns, security patterns, privacy patterns

Procedia PDF Downloads 110

Authors: Eiman Kattan

Abstract:

This study aims to evaluate the impact of classifying labelled remote sensing images conventional neural network (CNN) architecture, i.e., AlexNet on different land cover scenarios based on two remotely sensed datasets from different point of views such as the computational time and performance. Thus, a set of experiments were conducted to specify the effectiveness of the selected convolutional neural network using two implementing approaches, named fully trained and fine-tuned. For validation purposes, two remote sensing datasets, AID, and RSSCN7 which are publicly available and have different land covers features were used in the experiments. These datasets have a wide diversity of input data, number of classes, amount of labelled data, and texture patterns. A specifically designed interactive deep learning GPU training platform for image classification (Nvidia Digit) was employed in the experiments. It has shown efficiency in training, validation, and testing. As a result, the fully trained approach has achieved a trivial result for both of the two data sets, AID and RSSCN7 by 73.346% and 71.857% within 24 min, 1 sec and 8 min, 3 sec respectively. However, dramatic improvement of the classification performance using the fine-tuning approach has been recorded by 92.5% and 91% respectively within 24min, 44 secs and 8 min 41 sec respectively. The represented conclusion opens the opportunities for a better classification performance in various applications such as agriculture and crops remote sensing.

Keywords: conventional neural network, remote sensing, land cover, land use

Procedia PDF Downloads 352

Authors: Anupam Das

Abstract:

Although financial liberalization has been one of the most important policy prescriptions of international organizations like the World Bank and the IMF, the effect of financial liberalization on economic growth in developing countries is far from unanimous. Since the '80s, South Asian countries made a significant development in liberalization the financial sector. However, due to unavailability of a sufficient number of time series observations, the relationship between economic growth and financial development has not been investigated adequately. We aim to fill this gap by examining time series data of five developing countries from the South Asian region: Bangladesh, India, Pakistan, Sri Lanka, and Nepal. Applying the cointegration tests and Granger causality within the vector error correction model (VECM), we do not find unanimous evidence of financial development on positive economic growth. These results are helpful for developing countries which have been trying to liberalize the financial sector in recent decades.

Keywords: economic growth, financial development, Granger causality, South Asia

Procedia PDF Downloads 363

Authors: V. Yu. Volgutov, A. I. Orlova, S. A. Khainakov

Abstract:

NaZr2(PO4)3 (NZP) and their structural analogues are characterized by a peculiar behaviors on heating – they have different expansion and contraction along different crystallographic directions due to specific arrangements of crystal structure in these compounds. An important feature of such structures is the ability to incorporate into their structural analogues wide variety of metal cations having different size and oxidation states, with different combinations and concentrations. These cations are located in different crystallographic non-equivalent positions of octahedral tetrahedral crystal framework as well as in inter-framework cavities. Through, due to iso- and hetero-valent isomorphism of the cations (and the anions) in NZP, it becomes possible to tuning the compositions and to obtain the compounds with ‘on a plan’ properties. For the design of compounds with low and ultra-low thermal expansion including those with tailored thermal expansion properties, the following crystallochemical principles it seems are promising: 1) Insertion into crystal M1 position the cations having different sizes and, 2) the variation in the composition of compounds, providing different occupation of crystal M1 position. Following these principles we have designed and synthesized the next NZP-type phosphates series: a) where radii of the cations in the M1 crystal position was varied: Zr1/4Zr2(PO4)3 - Th1/4Zr2(PO4)3 (series I); R1/3Zr2(PO4)3 where R= Nd, Eu, Er (series II), b) where the occupation of M1 crystal position was varied: Zr1/4Zr2(PO4)3-Er1/3Zr2(PO4)3 (series III) and Zr1/4Zr2(PO4)3-Sr1/2Zr2(PO4)3 (series IV). The thermal expansion parameters were determined over the range of 25-800ºC. For each series the minimum axial coefficient of thermal expansion αa = αb, αc and their anisotropy Δα = Iαa - αcI, 10-6 K-1 was found as next: -1.51, 1.07, 2.58 for Th1/4Zr2(PO4)3 (series I); -0.72, 0.10, 0.81 for Nd1/3Zr2(PO4)3 (series II); -2.78, 1.35, 4.12 for Er1/6Zr1/8Zr2(PO4)3 (series III); 2.23, 1.32, 0.91 for Sr1/2Zr2(PO4)3 (series IV). The measured tendencies of the thermal expansion of crystals were in good agreement with predicted ones. For one of the members from the studied phosphates namely Th1/16Zr3/16Zr2(PO4)3 structural refinement have been carried out at 25, 200, 600, and 800°C. The dependencies of the structural parameters with the temperature have been determined.

Keywords: high-temperature crystallography, NaZr2(PO4)3, (NZP) analogs, structural-chemical principles, tuning thermal expansion

Procedia PDF Downloads 225

Authors: Hao-Hsiang Ku, Ching-Ho Chi

Abstract:

Big data applications have become an imperative for many fields. Many researchers have been devoted into increasing correct rates and reducing time complexities. Hence, the study designs and proposes an Ontology-based backpropagation neural network classification and reasoning strategy for NoSQL big data applications, which is called ON4NoSQL. ON4NoSQL is responsible for enhancing the performances of classifications in NoSQL and SQL databases to build up mass behavior models. Mass behavior models are made by MapReduce techniques and Hadoop distributed file system based on Hadoop service platform. The reference engine of ON4NoSQL is the ontology-based backpropagation neural network classification and reasoning strategy. Simulation results indicate that ON4NoSQL can efficiently achieve to construct a high performance environment for data storing, searching, and retrieving.

Keywords: Hadoop, NoSQL, ontology, back propagation neural network, high distributed file system

Procedia PDF Downloads 251

Authors: Abdelkhalek Bakkari

Abstract:

Image segmentation is a critical step in image processing and pattern recognition. In this paper, we proposed a new robust automatic image classification based on a dynamic fuzzy c-means algorithm and mathematical morphology. The proposed segmentation algorithm (DFCM_MM) has been applied to MR perfusion images. The obtained results show the validity and robustness of the proposed approach.

Keywords: segmentation, classification, dynamic, fuzzy c-means, MR image

Procedia PDF Downloads 459

Authors: P. S. Jagadeesh Kumar, Yang Yung, Wenli Hu

Abstract:

Speech emotion classification is a dominant research field in finding a sturdy and profligate classifier appropriate for different real-life applications. This effort accentuates on classifying different emotions from speech signal quarried from the features related to pitch, formants, energy contours, jitter, shimmer, spectral, perceptual and temporal features. Tensor deep stacking neural networks were supported to examine the factors that influence the classification success rate. Facial electromyography signals were composed of several forms of focuses in a controlled atmosphere by means of audio-visual stimuli. Proficient facial electromyography signals were pre-processed using moving average filter, and a set of arithmetical features were excavated. Extracted features were mapped into consistent emotions using bilinear mapping. With facial electromyography signals, a database comprising diverse emotions will be exposed with a suitable fine-tuning of features and training data. A success rate of 92% can be attained deprived of increasing the system connivance and the computation time for sorting diverse emotional states.

Keywords: speech emotion classification, tensor deep stacking neural networks, facial electromyography, bilinear mapping, audio-visual stimuli

Procedia PDF Downloads 238

Authors: Lule Basha, Eralda Gjika

Abstract:

The exchange rate is one of the most important economic variables, especially for a small, open economy such as Albania. Its effect is noticeable in one country's competitiveness, trade and current account, inflation, wages, domestic economic activity, and bank stability. This study investigates the fluctuation of Albania’s exchange rates using monthly average foreign currency, Euro (Eur) to Albanian Lek (ALL) exchange rate with a time span from January 2008 to June 2021, and the macroeconomic factors that have a significant effect on the exchange rate. Initially, the Random Forest Regression algorithm is constructed to understand the impact of economic variables on the behavior of monthly average foreign currencies exchange rates. Then the forecast of macro-economic indicators for 12 months was performed using time series models. The predicted values received are placed in the random forest model in order to obtain the average monthly forecast of the Euro to Albanian Lek (ALL) exchange rate for the period July 2021 to June 2022.

Keywords: exchange rate, random forest, time series, machine learning, prediction

Procedia PDF Downloads 92

Authors: M. Safa, A. Sabet, S. MacGillivray, M. Davidson, K. Kaczmarczyk, C. T. Haas, G. E. Gibson, D. Rayside

Abstract:

To address construction project requirements and specifications, scholars and practitioners need to establish a taxonomy according to a scheme that best fits their need. While existing characterization methods are continuously being improved, new ones are devised to cover project properties which have not been previously addressed. One such method, the Project Definition Rating Index (PDRI), has received limited consideration strictly as a classification scheme. Developed by the Construction Industry Institute (CII) in 1996, the PDRI has been refined over the last two decades as a method for evaluating a project's scope definition completeness during front-end planning (FEP). The main contribution of this study is a review of practical project classification methods, and a discussion of how PDRI can be used to classify projects based on their readiness in the FEP phase. The proposed model has been applied to 59 construction projects in Ontario, and the results are discussed.

Keywords: project classification, project definition rating index (PDRI), risk, project goals alignment

Procedia PDF Downloads 664

Authors: Almahd Alshereef, Ahmed Alkilany, Hammad Said, Azuraliza Abu Bakar

Abstract:

From time to time, electrical power grid is directed by the National Electricity Operator to conduct load shedding, which involves hours' power outages on the area of this study, Southern Electrical Grid of Libya (SEGL). Load shedding is conducted in order to alleviate pressure on the National Electricity Grid at times of peak demand. This approach has chosen a set of categories to study load-shedding problem considering the effect of the demand priorities on the operation of the power system during emergencies. Classification of category region for load shedding problem is solved by a new algorithm (the harmony algorithm) based on the "random generation list of category region", which is a possible solution with a proximity degree to the optimum. The obtained results prove additional enhancements compared to other heuristic approaches. The case studies are carried out on SEGL.

Keywords: optimization, harmony algorithm, load shedding, classification

Procedia PDF Downloads 378

Authors: Regina Chua

Abstract:

To reduce the costs of re-fielding a large survey, a Random Forest classifier was applied to measure the accuracy of classifying individuals into their assigned segments with the fewest possible questions. Given a long survey, one needed to determine the most predictive ten or fewer questions that would accurately assign new individuals to custom segments. Furthermore, the solution needed to be quick in its classification and usable in non-Python environments. In this paper, a supervised Random Forest classifier was modeled on a dataset with 7,000 individuals, 60 questions, and 254 features. The Random Forest consisted of an iterative collection of individual decision trees that result in a predicted segment with robust precision and recall scores compared to a single tree. A random 70-30 stratified sampling for training the algorithm was used, and accuracy trade-offs at different depths for each segment were identified. Ultimately, the Random Forest classifier performed at 87% accuracy at a depth of 10 with 20 instead of 254 features and 10 instead of 60 questions. With an acceptable accuracy in prioritizing feature selection, new tools were developed for non-Python environments: a worksheet with a formulaic version of the algorithm and an embedded function to predict the segment of an individual in real-time. Random Forest was determined to be an optimal classification model by its feature selection, performance, processing speed, and flexible application in other environments.

Keywords: machine learning, supervised learning, data science, random forest, classification, prediction, predictive modeling

Procedia PDF Downloads 83

Authors: Ouafae Baida, Najma Hamzaoui, Maha Akbib, Abdelfettah Sedqui, Abdelouahid Lyhyaoui

Abstract:

Numerous scientific works present various methods to analyze the data for several domains, specially the comparison of classifications. In our recent work, we presented a new approach to help the user choose the best classification method from the results obtained by every method, by basing itself on the distances between the trees of classification. The result of our approach was in the form of a dendrogram contains methods as a succession of connections. This approach is much needed in phylogeny analysis. This discipline is intended to analyze the sequences of biological macro molecules for information on the evolutionary history of living beings, including their relationship. The product of phylogeny analysis is a phylogenetic tree. In this paper, we recommend the use of a new method of construction the phylogenetic tree based on comparison of different classifications obtained by different molecular genes.

Keywords: hierarchical classification, classification methods, structure of tree, genes, phylogenetic analysis

Procedia PDF Downloads 492

Authors: N. Fuad, M. N. Taib, R. Jailani, M. E. Marwan

Abstract:

In this paper, the comparison between k-Nearest Neighbor (kNN) algorithms for classifying the 3D EEG model in brain balancing is presented. The EEG signal recording was conducted on 51 healthy subjects. Development of 3D EEG models involves pre-processing of raw EEG signals and construction of spectrogram images. Then, maximum PSD values were extracted as features from the model. There are three indexes for the balanced brain; index 3, index 4 and index 5. There are significant different of the EEG signals due to the brain balancing index (BBI). Alpha-α (8–13 Hz) and beta-β (13–30 Hz) were used as input signals for the classification model. The k-NN classification result is 88.46% accuracy. These results proved that k-NN can be used in order to predict the brain balancing application.

Keywords: power spectral density, 3D EEG model, brain balancing, kNN

Procedia PDF Downloads 472

Authors: H. Abas Nejad, A. R. Teymoori

Abstract:

Facial expression recognition is one of the open problems in computer vision. Robust neutral face recognition in real time is a major challenge for various supervised learning based facial expression recognition methods. This is due to the fact that supervised methods cannot accommodate all appearance variability across the faces with respect to race, pose, lighting, facial biases, etc. in the limited amount of training data. Moreover, processing each and every frame to classify emotions is not required, as the user stays neutral for the majority of the time in usual applications like video chat or photo album/web browsing. Detecting neutral state at an early stage, thereby bypassing those frames from emotion classification would save the computational power. In this work, we propose a light-weight neutral vs. emotion classification engine, which acts as a preprocessor to the traditional supervised emotion classification approaches. It dynamically learns neutral appearance at Key Emotion (KE) points using a textural statistical model, constructed by a set of reference neutral frames for each user. The proposed method is made robust to various types of user head motions by accounting for affine distortions based on a textural statistical model. Robustness to dynamic shift of KE points is achieved by evaluating the similarities on a subset of neighborhood patches around each KE point using the prior information regarding the directionality of specific facial action units acting on the respective KE point. The proposed method, as a result, improves ER accuracy and simultaneously reduces the computational complexity of ER system, as validated on multiple databases.

Keywords: neutral vs. emotion classification, Constrained Local Model, procrustes analysis, Local Binary Pattern Histogram, statistical model

Procedia PDF Downloads 329

Authors: F. Messaoudi, O. Haddad, R. Bouras, S. Kaci

Abstract:

The development of self-compacting concrete (SCC) marks a huge step towards improved efficiency and working conditions on construction sites and in the precast industry. SCC flows easily into more complex shapes and through reinforcement bars, reduces the manpower required for the placement; no vibration is required to ensure correct compaction of concrete. This concrete contains a high volume of binder which is controlled by their rheological behavior. The paste consists of binders (Portland cement with or without supplementary cementitious materials), water, chemical admixtures and fillers. In this study, two series of tests were performed on self-compacting cement pastes made with marble waste additions as the mineral addition. The first series of this investigation was to determine the flow time of paste using Marsh cone, the second series was to determine the rheological parameters of the same paste namely yield stress and plastic viscosity using the rheometer Haake RheoStress 1. The results of this investigation allowed us to study the evolution of the yield stress, viscosity and the flow time Marsh cone paste as a function of the composition of the paste. A correlation between the results obtained on the flow test Marsh cone and those of the plastic viscosity on the mottled different cement pastes is proposed.

Keywords: adjuvant, rheological parameter, self-compacting cement pastes, waste marble

Procedia PDF Downloads 266

Authors: Jairson Barbosa Rodrigues, Paulo Romero Martins Maciel, Germano Crispim Vasconcelos

Abstract:

This paper presents an investigation of the performance impacts regarding the variation of five factors (input data size, node number, cores, memory, and disks) when applying a distributed implementation of Naïve Bayes for text classification of a large Corpus on the Spark big data processing framework. Problem: The algorithm's performance depends on multiple factors, and knowing before-hand the effects of each factor becomes especially critical as hardware is priced by time slice in cloud environments. Objectives: To explain the functional relationship between factors and performance and to develop linear predictor models for time and cost. Methods: the solid statistical principles of Design of Experiments (DoE), particularly the randomized two-level fractional factorial design with replications. This research involved 48 real clusters with different hardware arrangements. The metrics were analyzed using linear models for screening, ranking, and measurement of each factor's impact. Results: Our findings include prediction models and show some non-intuitive results about the small influence of cores and the neutrality of memory and disks on total execution time, and the non-significant impact of data input scale on costs, although notably impacts the execution time.

Keywords: big data, design of experiments, distributed machine learning, natural language processing, spark

Procedia PDF Downloads 102

Authors: Oumaima Khlifati, Khadija Baba

Abstract:

Pavement distress is the main factor responsible for the deterioration of road structure durability, damage vehicles, and driver comfort. Transportation agencies spend a high proportion of their funds on pavement monitoring and maintenance. The auscultation of pavement distress was based on the manual survey, which was extremely time consuming, labor intensive, and required domain expertise. Therefore, the automatic distress detection is needed to reduce the cost of manual inspection and avoid more serious damage by implementing the appropriate remediation actions at the right time. Inspired by recent deep learning applications, this paper proposes an algorithm for automatic road distress detection and classification using on the Deep Convolutional Neural Network (DCNN). In this study, the types of pavement distress are classified as transverse or longitudinal cracking, alligator, pothole, and intact pavement. The dataset used in this work is composed of public asphalt pavement images. In order to learn the structure of the different type of distress, the DCNN models are trained and tested as a multi-label classification task. In addition, to get the highest accuracy for our model, we adjust the structural optimization hyper parameters such as the number of convolutions and max pooling, filers, size of filters, loss functions, activation functions, and optimizer and fine-tuning hyper parameters that conclude batch size and learning rate. The optimization of the model is executed by checking all feasible combinations and selecting the best performing one. The model, after being optimized, performance metrics is calculated, which describe the training and validation accuracies, precision, recall, and F1 score.

Keywords: distress pavement, hyperparameters, automatic classification, deep learning

Procedia PDF Downloads 71

Authors: Gu Pang, Bartosz Gebka

Abstract:

We forecast the demand of total container throughput at the Indonesia’s largest seaport, Tanjung Priok Port. We propose four univariate forecasting models, including SARIMA, the additive Seasonal Holt-Winters, the multiplicative Seasonal Holt-Winters and the Vector Error Correction Model. Our aim is to provide insights into whether forecasting the total container throughput obtained by historical aggregated port throughput time series is superior to the forecasts of the total throughput obtained by summing up the best individual terminal forecasts. We test the monthly port/individual terminal container throughput time series between 2003 and 2013. The performance of forecasting models is evaluated based on Mean Absolute Error and Root Mean Squared Error. Our results show that the multiplicative Seasonal Holt-Winters model produces the most accurate forecasts of total container throughput, whereas SARIMA generates the worst in-sample model fit. The Vector Error Correction Model provides the best model fits and forecasts for individual terminals. Our results report that the total container throughput forecasts based on modelling the total throughput time series are consistently better than those obtained by combining those forecasts generated by terminal-specific models. The forecasts of total throughput until the end of 2018 provide an essential insight into the strategic decision-making on the expansion of port's capacity and construction of new container terminals at Tanjung Priok Port.

Keywords: SARIMA, Seasonal Holt-Winters, Vector Error Correction Model, container throughput

Procedia PDF Downloads 492

Authors: Jinhoa Lee

Abstract:

The relationships between environmental quality, energy use and economic output have created growing attention over the past decades among researchers and policy makers. Focusing on the empirical aspects of the role of CO2 emissions and energy use in affecting the economic output, this paper is an effort to fulfil the gap in a comprehensive case study at a country level using modern econometric techniques. To achieve the goal, this country-specific study examines the short-run and long-run relationships among energy consumption, carbon dioxide (CO2) emissions and gross domestic product (GDP) for Oman using time series analysis from the year 1980-2010. To investigate the relationships between the variables, this paper employs the Augmented Dickey Fuller (ADF) test for stationary, Johansen maximum likelihood method for co-integration and a Vector Error Correction Model (VECM) for both short- and long-run causality among the research variables for the sample. All the variables in this study show very strong significant effects on GDP in the country for the long term. The long-run equilibrium in the VECM suggests positive long-run causalities from CO2 emissions to GDP. Conversely, negative impacts of energy consumption on GDP are found to be significant in Oman during the period. In the short run, there exist negative unidirectional causalities among GDP, CO2 emissions and energy consumption running from GDP to CO2 emissions and from energy consumption to CO2 emissions. Overall, the results support arguments that there are relationships among environmental quality, energy use and economic output in Oman over of period 1980-2010.

Keywords: CO2 emissions, energy consumption, GDP, Oman, time series analysis

Procedia PDF Downloads 449

Authors: Haonan Hu, Shuge Lei, Dasheng Sun, Huabin Zhang, Kehong Yuan, Jian Dai, Jijun Tang

Abstract:

This paper focuses on the classification task of breast ultrasound images and conducts research on the reliability measurement of classification results. A dual-channel evaluation framework was developed based on the proposed inference reliability and predictive reliability scores. For the inference reliability evaluation, human-aligned and doctor-agreed inference rationals based on the improved feature attribution algorithm SP-RISA are gracefully applied. Uncertainty quantification is used to evaluate the predictive reliability via the test time enhancement. The effectiveness of this reliability evaluation framework has been verified on the breast ultrasound clinical dataset YBUS, and its robustness is verified on the public dataset BUSI. The expected calibration errors on both datasets are significantly lower than traditional evaluation methods, which proves the effectiveness of the proposed reliability measurement.

Keywords: medical imaging, ultrasound imaging, XAI, uncertainty measurement, trustworthy AI

Procedia PDF Downloads 77

Authors: Yoonjung An, Yongtae Park

Abstract:

Knowledge flows are a critical source of faster technological progress and stouter economic growth. Knowledge flows have been accelerated dramatically with the establishment of a patent system in which each patent is required by law to disclose sufficient technical information for the invention to be recreated. Patent analysis, thus, has been widely used to help investigate technological knowledge flows. However, the existing research is limited in terms of both subject and approach. Particularly, in most of the previous studies, business method (BM) patents were not covered although they are important drivers of knowledge flows as other patents. In addition, these studies usually focus on the static analysis of knowledge flows. Some use approaches that incorporate the time dimension, yet they still fail to trace a true dynamic process of knowledge flows. Therefore, we investigate dynamic patterns of knowledge flows driven by BM patents using a Hidden Markov Model (HMM). An HMM is a popular statistical tool for modeling a wide range of time series data, with no general theoretical limit in regard to statistical pattern classification. Accordingly, it enables characterizing knowledge patterns that may differ by patent, sector, country and so on. We run the model in sets of backward citations and forward citations to compare the patterns of knowledge utilization and knowledge dissemination.

Keywords: business method patents, dynamic pattern, Hidden-Markov Model, knowledge flow

Procedia PDF Downloads 319

Authors: Darren Zou

Abstract:

Forecasting the stock market is a very challenging task. Various economic indicators such as GDP, exchange rates, interest rates, and unemployment have a substantial impact on the stock market. Time series models are the traditional methods used to predict stock market changes. In this paper, a machine learning method, Bayesian Additive Regression Tree (BART) is used in predicting stock market indexes based on multiple economic indicators. BART can be used to model heterogeneous treatment effects, and thereby works well when models are misspecified. It also has the capability to handle non-linear main effects and multi-way interactions without much input from financial analysts. In this research, BART is proposed to provide a reliable prediction on day-to-day stock market activities. By comparing the analysis results from BART and with time series method, BART can perform well and has better prediction capability than the traditional methods.

Keywords: BART, Bayesian, predict, stock

Procedia PDF Downloads 112

Authors: Rufus Temidayo Akinnubi, M. O. Adeniyi

Abstract:

Existing diurnal air temperature models simulate night time air temperature over Nigeria with high biases. An improved parameterization is presented for modeling the diurnal pattern of air temperature (Ta) which is applicable in the calculation of turbulent heat fluxes in Global climate models, based on Nigeria Micrometeorological Experimental site (NIMEX) surface layer observations. Five diurnal Ta models for estimating hourly Ta from daily maximum, daily minimum, and daily mean air temperature were validated using root-mean-square error (RMSE), Mean Error Bias (MBE) and scatter graphs. The original Fourier series model showed better performance for unstable air temperature parameterizations while the stable Ta was strongly overestimated with a large error. The model was improved with the inclusion of the atmospheric cooling rate that accounts for the temperature inversion that occurs during the nocturnal boundary layer condition. The MBE and RMSE estimated by the modified Fourier series model reduced by 4.45 oC and 3.12 oC during the transitional period from dry to wet stable atmospheric conditions. The modified Fourier series model gave good estimation of the diurnal weather patterns of Ta when compared with other existing models for a tropical environment.

Keywords: air temperature, mean bias error, Fourier series analysis, surface energy balance,

Procedia PDF Downloads 221