Open Access. Powered by Scholars. Published by Universities.®

Engineering Commons

Open Access. Powered by Scholars. Published by Universities.®

2019

Operations Research, Systems Engineering and Industrial Engineering

Adaptive systems

Articles 1 - 15 of 15

Full-Text Articles in Engineering

Using Neural Networks To Forecast Volatility For An Asset Allocation Strategy Based On The Target Volatility, Youngmin Kim, David Lee Enke Mar 2019

Using Neural Networks To Forecast Volatility For An Asset Allocation Strategy Based On The Target Volatility, Youngmin Kim, David Lee Enke

David Lee Enke

The objective of this study is to use artificial neural networks for volatility forecasting to enhance the ability of an asset allocation strategy based on the target volatility. The target volatility level is achieved by dynamically allocating between a risky asset and a risk-free cash position. However, a challenge to data-driven approaches is the limited availability of data since periods of high volatility, such as during financial crises, are relatively rare. To resolve this issue, we apply a stability-oriented approach to compare data for the current period to a past set of data for a period of low volatility, providing ...


Time Series Classification Using Deep Learning For Process Planning: A Case From The Process Industry, Nijat Mehdiyev, Johannes Lahann, Andreas Emrich, David Lee Enke, Peter Fettke, Peter Loos Mar 2019

Time Series Classification Using Deep Learning For Process Planning: A Case From The Process Industry, Nijat Mehdiyev, Johannes Lahann, Andreas Emrich, David Lee Enke, Peter Fettke, Peter Loos

David Lee Enke

Multivariate time series classification has been broadly applied in diverse domains over the past few decades. However, before applying the classification algorithms, the vast majority of current studies extract hand-engineered features that are assumed to detect local patterns in the time series. Therefore, the efficiency and precision of these classification approaches are heavily dependent on the quality of variables defined by domain experts. Recent improvements in the deep learning domain offer opportunities to avoid such an intensive hand-crafted feature engineering which is particularly important for managing the processes based on time-series data obtained from various sensor networks. In our paper ...


Determination Of Rule Patterns In Complex Event Processing Using Machine Learning Techniques, Nijat Mehdiyev, Julian Krumeich, David Lee Enke, Dirk Werth, Peter Loos Mar 2019

Determination Of Rule Patterns In Complex Event Processing Using Machine Learning Techniques, Nijat Mehdiyev, Julian Krumeich, David Lee Enke, Dirk Werth, Peter Loos

David Lee Enke

Complex Event Processing (CEP) is a novel and promising methodology that enables the real-time analysis of stream event data. The main purpose of CEP is detection of the complex event patterns from the atomic and semantically low-level events such as sensor, log, or RFID data. Determination of the rule patterns for matching these simple events based on the temporal, semantic, or spatial correlations is the central task of CEP systems. In the current design of the CEP systems, experts provide event rule patterns. Having reached maturity, the Big Data Systems and Internet of Things (IoT) technology require the implementation of ...


Instance Selection Using Genetic Algorithms For An Intelligent Ensemble Trading System, Youngmin Kim, David Lee Enke Mar 2019

Instance Selection Using Genetic Algorithms For An Intelligent Ensemble Trading System, Youngmin Kim, David Lee Enke

David Lee Enke

Instance selection is a way to remove unnecessary data that can adversely affect the prediction model, thereby selecting representative and relevant data from the original data set that is expected to improve predictive performance. Instance selection plays an important role in improving the scalability of data mining algorithms and has also proven to be successful over a wide range of classification problems. However, instance selection using an evolutionary approach, as proposed in this study, is different from previous methods that have focused on improving accuracy performance in the stock market (i.e., Up or Down forecast). In fact, we propose ...


Optimizing Macd Parameters Via Genetic Algorithms For Soybean Futures, Phoebe S. Wiles, David Lee Enke Mar 2019

Optimizing Macd Parameters Via Genetic Algorithms For Soybean Futures, Phoebe S. Wiles, David Lee Enke

David Lee Enke

To create profits, traders must time the market correctly and enter and exit positions at ideal times. Finding the optimal time to enter the market can be quite daunting. The soybean market can be volatile and complex. Weather, sentiment, supply, and demand can all affect the price of soybeans. Traders typically use either fundamental analysis or technical analysis to predict the market for soybean futures' contracts. Every agricultural future's contract or security contract is different in its nature, volatility, and structure. Therefore, the purpose of this research is to optimize the moving average convergence divergence parameter values from traditionally ...


Evaluating Forecasting Methods By Considering Different Accuracy Measures, Nijat Mehdiyev, David Lee Enke, Peter Fettke, Peter Loos Mar 2019

Evaluating Forecasting Methods By Considering Different Accuracy Measures, Nijat Mehdiyev, David Lee Enke, Peter Fettke, Peter Loos

David Lee Enke

Choosing the appropriate forecasting technique to employ is a challenging issue and requires a comprehensive analysis of empirical results. Recent research findings reveal that the performance evaluation of forecasting models depends on the accuracy measures adopted. Some methods indicate superior performance when error based metrics are used, while others perform better when precision values are adopted as accuracy measures. As scholars tend to use a smaller subset of accuracy metrics to assess the performance of forecasting models, there is a need for a concept of multiple accuracy dimensions to assure the robustness of evaluation. Therefore, the main purpose of this ...


Noise Canceling In Volatility Forecasting Using An Adaptive Neural Network Filter, Soheil Almasi Monfared, David Lee Enke Mar 2019

Noise Canceling In Volatility Forecasting Using An Adaptive Neural Network Filter, Soheil Almasi Monfared, David Lee Enke

David Lee Enke

Volatility forecasting models are becoming more accurate, but noise looks to be an inseparable part of these forecasts. Nonetheless, using adaptive filters to cancel the noise should help improve the performance of the forecasting models. Adaptive filters have the advantage of changing based on the environment. This feature is vital when they are used along with a model for volatility forecasting and error cancellation in the financial markets. Nonlinear Autoregressive (NAR) neural networks have simple structures, but they are efficient tools in error cancelation systems when working with non-stationary and random walk noise processes. For this research, an adaptive threshold ...


Entity Resolution Using Convolutional Neural Network, Ram Deepak Gottapu, Cihan H. Dagli, Bharami Ali Mar 2019

Entity Resolution Using Convolutional Neural Network, Ram Deepak Gottapu, Cihan H. Dagli, Bharami Ali

Cihan H. Dagli

Entity resolution is an important application in field of data cleaning. Standard approaches like deterministic methods and probabilistic methods are generally used for this purpose. Many new approaches using single layer perceptron, crowdsourcing etc. are developed to improve the efficiency and also to reduce the time of entity resolution. The approaches used for this purpose also depend on the type of dataset, labeled or unlabeled. This paper presents a new method for labeled data which uses single layered convolutional neural network to perform entity resolution. It also describes how crowdsourcing can be used with the output of the convolutional neural ...


Genetic Algorithm Optimization Of Sos Meta-Architecture Attributes For Fuzzy Rule Based Assessments, Andrew Renault, Cihan H. Dagli Mar 2019

Genetic Algorithm Optimization Of Sos Meta-Architecture Attributes For Fuzzy Rule Based Assessments, Andrew Renault, Cihan H. Dagli

Cihan H. Dagli

The analysis of an acknowledged systems of systems (SoS) meta-architecture requires a preliminary method for potential trade space exploration to ensure compliance to evolving capability requirements. It is important to assess the SoS meta-architecture concept to ensure that it satisfies all stakeholder needs and requirements in the early stages of development. There are numerous linguistic terms called key performance attributes (KPAs) that could be used to assess the different aspects of the architectures capabilities, however, too many KPAs could complicate the assessment. The initial population of suitable KPAs is reduced through non-derivative based optimization employed by a genetic algorithm (GA ...


Establishing Rules For Self-Organizing Systems-Of-Systems, David M. Curry, Cihan H. Dagli Mar 2019

Establishing Rules For Self-Organizing Systems-Of-Systems, David M. Curry, Cihan H. Dagli

Cihan H. Dagli

Self-organizing systems-of-systems offer the possibility of autonomously adapting to new circumstances and tasking. This could significantly benefit large endeavors such as smart cities and national defense by increasing the probability that new situations are expediently handled. Complex self-organizing behaviors can be produced by a large set of individual agents all following the same simple set of rules. While biological rule sets have application in achieving human goals, other rules sets may be necessary as these goals are not necessarily mirrored in nature. To this end, a set of system, rather than biologically, inspired rules is introduced and an agent-based model ...


Multiobjective System Of Systems Architecting With Performance Improvement Funds, Hadi Farhangi, Dincer Konur, Cihan H. Dagli Mar 2019

Multiobjective System Of Systems Architecting With Performance Improvement Funds, Hadi Farhangi, Dincer Konur, Cihan H. Dagli

Cihan H. Dagli

A System of Systems architecting problem aims to determine a selection of systems, which are capable of providing a set of desired capabilities. A SoS architect usually has multiple objectives in generating efficient architectures such as minimization of the total cost and maximization the overall performance of the SoS. This study formulates a biobjective SoS architecting problem with these two objectives. Here, we consider that, by allocating funds to the systems, the SoS architect can improve the performance of the capabilities the systems can provide. The resulting architecting problem is a biobjective mixed-integer linear programming model. Specifically, the system selection ...


Selecting Attributes, Rules, And Membership Functions For Fuzzy Sos Architecture Evaluation, Louis Pape, Siddhartha Agarwal, Cihan H. Dagli Mar 2019

Selecting Attributes, Rules, And Membership Functions For Fuzzy Sos Architecture Evaluation, Louis Pape, Siddhartha Agarwal, Cihan H. Dagli

Cihan H. Dagli

The development of the FILA-SoS meta-architecture approach to acknowledged systems of systems (SoS) analysis allows a relatively unbiased method for exploring a potential SoS architecture space. This paper delves more deeply into the process of building the lists of desirable fuzzy attributes of a SoS, developing rules for combining attribute values to an overall assessment, and discovering membership function shapes that work well. A wide range of options exist for all the individual elements of SoS assessment. Some recommendations for finding an appropriate combination for the adjustable parameters of fuzzy assessment models through random architecture chromosome testing and iteration are ...


Combining Max-Min And Max-Max Approaches For Robust Sos Architecting, Hadi Farhangi, Dincer Konur, Cihan H. Dagli Mar 2019

Combining Max-Min And Max-Max Approaches For Robust Sos Architecting, Hadi Farhangi, Dincer Konur, Cihan H. Dagli

Cihan H. Dagli

A System of Systems (SoS) architecting problem requires creating a selection of systems in order to provide a set of capabilities. SoS architecting finds many applications in military/defense projects. In this paper, we study a multi-objective SoS architecting problem, where the cost of the architecture is minimized while its performance is maximized. The cost of the architecture is the summation of the costs of the systems to be included in the SoS. Similarly, the performance of the architecture is defined as the sum of the performance of the capabilities, where the performance of a capability is the sum of ...


Application Of An Artificial Neural Network To Predict Graduation Success At The United States Military Academy, Gene Lesinski, Steven Corns, Cihan H. Dagli Mar 2019

Application Of An Artificial Neural Network To Predict Graduation Success At The United States Military Academy, Gene Lesinski, Steven Corns, Cihan H. Dagli

Cihan H. Dagli

This paper presents a neural network approach to classify student graduation status based upon selected academic, demographic, and other indicators. A multi-layer feedforward network with backpropagation learning is used as the model framework. The model is trained, tested, and validated using 5100 student samples with data compiled from admissions records and institutional research databases. Nine input variables consist of categorical and numeric data elements including: high school rank, high school quality, standardized test scores, high school faculty assessments, extra-curricular activity score, parent's education status, and time since high school graduation. These inputs and the multi-layer neural network model are ...


Application Of An Artificial Neural Network To Predict Graduation Success At The United States Military Academy, Gene Lesinski, Steven Corns, Cihan H. Dagli Mar 2019

Application Of An Artificial Neural Network To Predict Graduation Success At The United States Military Academy, Gene Lesinski, Steven Corns, Cihan H. Dagli

Steven Corns

This paper presents a neural network approach to classify student graduation status based upon selected academic, demographic, and other indicators. A multi-layer feedforward network with backpropagation learning is used as the model framework. The model is trained, tested, and validated using 5100 student samples with data compiled from admissions records and institutional research databases. Nine input variables consist of categorical and numeric data elements including: high school rank, high school quality, standardized test scores, high school faculty assessments, extra-curricular activity score, parent's education status, and time since high school graduation. These inputs and the multi-layer neural network model are ...