y associating active learning methodologies and digital media as a form to improve educational quality, the diversity of experimentations in engineering education has been motivating researches in many areas with poss...
详细信息
Bitcoin is the leading currency in the cryptocurrency market capturing attention worldwide. Forecasting the Bitcoin price as accurate as possible is essential, but due to its high volatility this task is challenging. ...
详细信息
ISBN:
(数字)9781728169262
ISBN:
(纸本)9781728169279
Bitcoin is the leading currency in the cryptocurrency market capturing attention worldwide. Forecasting the Bitcoin price as accurate as possible is essential, but due to its high volatility this task is challenging. Many researchers try, through the years, to develop efficient models for predicting the Bitcoin price using several different data-driven approaches. The objective of this paper is to develop a novel decomposition-ensemble learning model that combines Variational Mode Decomposition (VMD) and Stacking-ensemble learning (STACK) with machine learning algorithms to forecast the Bitcoin price multi-step ahead. The algorithms are k-Nearest Neighbors, Support Vector Regression with Linear kernel, Feed-forward Artificial Neural Network with single-layer perceptron, Generalized Linear Model, and Cubist. Correlation matrix (CORR), principal component analysis (PCA), and Box-Cox transformation (BOXCOX) were used as data preprocessing techniques. Estimating the performance of the proposed models (namely VMD-STACK-CORR, VMD-STACK-PCA, and VMD-STACK-BOXCOX) using relative root mean square error, symmetric mean absolute percentage error, and absolute percentage error measures, defined that for one-day-ahead forecast VMD-STAK-BOXCOX model presented the better performance, and for two and three-days-ahead forecast VMD-STACK-CORR model was chosen, compared to VMD, STACK, and machine learning algorithms models' performance. Diebold-Mariano statistical test was conducted to evaluate a reduction in forecasting errors. Therefore, the proposed models (VMD-STACK-CORR, VMD-STACK-PCA, and VMD-STACK-BOXCOX) indeed forecast accurately Bitcoin price and outperformed the compared models (VMD, STACK, and machine learning models).
The increasing adoption of new automation and information technologies are transforming production systems into cyber-physical systems (CPS). Although consulting companies have developed management frameworks to bette...
详细信息
The increasing adoption of new automation and information technologies are transforming production systems into cyber-physical systems (CPS). Although consulting companies have developed management frameworks to better characterize the implications of these technologies to how operations are managed, mainly focusing on new business models, efficiency, and effectiveness, the real impacts on decision areas (e.g., quality management) and performance objectives (e.g., flexibility) are still unclear. How are management systems being transformed? Are new managerial approaches emerging that address the particularities of new technologies? What are the critical success factors for conducting this transformation? To address these questions, a more systematic approach needs to be undertaken. This paper contributes to this by presenting a protocol to be used in systematic studies of the implications of the adoption of new technologies to the management of operations, and by illustrating its application to the analysis of the adoption of a cognitive vision system in an automotive manufacturer primarily deployed for improving product quality. The analysis protocol is based on Pettigrew’s dimensions of context, content, and process for change initiatives and is further subdivided into information requirements, variables to be analyzed and its potential sources of data. The case shows that the application of the protocol was able to reveal that besides expected effects on quality and productivity, new forms of interaction among workers and between workers and supervisors emerged that need further investigation. From the results of the case, future applications of the protocol are discussed.
Impact of flood depth on traffic volume in two different zones of the Bangkok road network was investigated using traffic data obtained from probe vehicle trajectories.A Macroscopic Fundamental Diagram(MFD)was utilize...
详细信息
Impact of flood depth on traffic volume in two different zones of the Bangkok road network was investigated using traffic data obtained from probe vehicle trajectories.A Macroscopic Fundamental Diagram(MFD)was utilized to compare traffic flow rates across two road network zones in the city for a variety of flood depths,namely 0-5 cm,5-10 cm,10-15 cm,15-30 cm,and more than 30 *** of empirical analysis over an observation period of one year as 2019 showed that flood depths had a strong correlation with the MFD parameters of free-flow speed,maximum flow,and traffic jam *** particular,road floods greatly reduced average maximum flow across the inner city road network in *** floods had a significant impact on traffic characteristics of urban road networks.
Traditionally, for the purpose of classifying the integrity of an engineering structure, one may use the information of the natural frequencies or mode shapes or some other measures derived from the two. In this resea...
详细信息
Traditionally, for the purpose of classifying the integrity of an engineering structure, one may use the information of the natural frequencies or mode shapes or some other measures derived from the two. In this research, we propose a classification method on the basis of the general vibration model. The general vibration model is essentially a set of differential equations describing the dynamics of the structure under consideration. For the purpose of damage detection, a deviation of the general vibration model from the dynamic equilibrium point marks the occurrence of the damage. To demonstrate the effectiveness of the method, we study two simplest dynamical systems consisting of one- and two-concentrated masses subjected to a prescribed dynamic load. The structural damages are introduced artificially by reducing the stiffness of spring in the structures. We find that the general vibration model is more sensitive to damages than the traditional methods.
Global warming due to excessive emission greenhouse gases is a significant issue faced by humanity, and collectively, cars and trucks contribute about 20% to the entire global-warming gases. For a reason, recently, ma...
详细信息
Global warming due to excessive emission greenhouse gases is a significant issue faced by humanity, and collectively, cars and trucks contribute about 20% to the entire global-warming gases. For a reason, recently, many attempts have been endured to reduce the emission and to increase fuel efficiency, including vehicle platooning, better driving strategy, and increasing engine efficiency. This study intends to provide a more detail assessment regarding the effects of the driving strategy to fuel consumption. For the purpose, the vehicle dynamics are quantified by employing the car-following model based on the optimal velocity model. The fuel consumption is estimated from the regression model of Ahn 18 . The result suggests that the braking distance strongly affects fuel consumption.
The classification of vehicles is a matter of great importance for traffic control and management, helping with traffic surveillance as well as in statistical data collection. Among the several vehicular classificatio...
详细信息
The classification of vehicles is a matter of great importance for traffic control and management, helping with traffic surveillance as well as in statistical data collection. Among the several vehicular classification techniques, the most popular uses inductive loop sensors, because they achieve high accuracy rate at low cost. This paper proposes 5 different vehicle classification models by inductive waveform analysis: KNN, SVC, Decision Tree, Random Forest, and Voting Classifier. A brief introduction to the mathematical basis of these models and the main forms of vehicle detection are also presented. The obtained results reached an accuracy of 94% and showed how inductive waveform analysis is still a valid option for vehicle classification.
Illegal tapping of fuel pipelines has recently become one of the most relevant safety problems faced by the industry. Hundreds of illegal interventions have been reported around the world, causing a significant number...
详细信息
ISBN:
(数字)9781728169262
ISBN:
(纸本)9781728169279
Illegal tapping of fuel pipelines has recently become one of the most relevant safety problems faced by the industry. Hundreds of illegal interventions have been reported around the world, causing a significant number of deaths, relevant impacts on the environment, and capital loss. Therefore, it is important to develop systems that are able to detect such scenarios at an early stage, enabling a fast counteract. To this end, machine learning algorithms can train models on available data for detecting future issues. Most recently, ensemble learning and dynamic classifier selection (DCS) techniques have been achieving promising results in supervised learning tasks. Such models are usually trained based on a single criterion. However, it is desirable to take into account both the number of false positives (FP) and false negatives (FN) for the illegal tapping detection task, since they are conflicting and both lead to financial losses and/or accidents. Therefore, this work proposes a novel DCS technique based on multiple criteria, namely overall local class-specific accuracy (OLCA), which employs multi-criteria decision making for dynamically selecting the best classifier for a new sample given the local true positive and negative ratios. A numerical experiment is conducted for assessing the generalization performance of the proposed method in an oil pipeline, with the goal of detecting illegal taping using pressure transient signals. Results show that OLCA is able to reduce the number of both FP and FN when dynamically selecting the classifiers of a baseline Random Forest ensemble.
This paper addresses the problem of maintenance facilities (depot) location in electric power distribution systems with a focus on strategic planning. Power interruptions can be harmful for both society and distributi...
详细信息
The development of accurate models to forecast electricity energy prices is a challenge due to the number of factors which can affect this commodity. In this paper, a hybrid multi-stage approach is proposed to forecas...
详细信息
ISBN:
(数字)9781728169262
ISBN:
(纸本)9781728169279
The development of accurate models to forecast electricity energy prices is a challenge due to the number of factors which can affect this commodity. In this paper, a hybrid multi-stage approach is proposed to forecast multi-stepahead (one, two and three-month-ahead) Brazilian commercial and residential electricity energy prices. The proposed data analysis combines the pre-processing named complementary ensemble empirical mode decomposition (CEEMD) in the first stage coupled with the coyote optimization algorithm (COA) to define the CEEMD's hyperparameters, aiming to deal with time series non-linearities and enhance the model's performance. On the next stage, four machine learning models named extreme learning machine, Gaussian process, gradient boosting machine, and relevance vector machine are employed to train and predict the CEEMD's components. Finally, in the final stage, the results of the previous step are directly integrated to compose a heterogeneous ensemble learning of components to obtain the final forecasts. In this case, a grid of models is obtained. The best model is one that has better generalization out-of-sample. Through developed comparisons, results showed that combining COA-CEEMD with a heterogeneous ensemble learning can develop accurate forecasts. The modeling developed in this paper is promising and can support decision making in electricity energy price forecasting.
暂无评论