A Deep Learning Based Approach to Predict Sequential Design Decisions

2019 ◽  
Author(s):  
Molla Hafizur Rahman ◽  
Charles Xie ◽  
Zhenghui Sha
Keyword(s):  
Markov Chain ◽  
System Design ◽  
Design Process ◽  
Design Space ◽  
Markov Chain Model ◽  
Sequential Design ◽  
Chain Model ◽  
Short Term ◽  
Design Decisions ◽  
Term Memory

Abstract During a design process, designers iteratively go back and forth between different design stages to explore the design space and search for the best design solution that satisfies all design constraints. For complex design problems, human has shown surprising capability in effectively reducing the dimensionality of design space and quickly converging it to a reasonable range for algorithms to step in and continue the search process. Therefore, modeling how human designers make decisions in such a sequential design process can help discover beneficial design patterns, strategies, and heuristics, which are important to the development of new algorithms embedded with human intelligence to augment computational design. In this paper, we develop a deep learning based approach to model and predict designers’ sequential decisions in a system design context. The core of this approach is an integration of the function-behavior-structure model for design process characterization and the long short term memory unit model for deep leaning. This approach is demonstrated in a solar energy system design case study, and its prediction accuracy is evaluated benchmarked on several commonly used models for sequential design decisions, such as Markov Chain model, Hidden Markov Chain model, and random sequence generation model. The results indicate that the proposed approach outperforms the other traditional models. This implies that during a system design task, designers are very likely to reply on both short-term and long-term memory of past design decisions in guiding their decision making in future design process. Our approach is general to be applied in many other design contexts as long as the sequential design action data is available.

Predicting Sequential Design Decisions Using the Function-Behavior-Structure Design Process Model and Recurrent Neural Networks

2021 ◽  
pp. 1-46
Author(s):  
Molla Hafizur Rahman ◽  
Charles Xie ◽  
Zhenghui Sha
Keyword(s):  
Markov Chain ◽  
System Design ◽  
Design Process ◽  
Markov Chain Model ◽  
Sequential Design ◽  
Chain Model ◽  
Generation Model ◽  
Short Term ◽  
Design Decisions ◽  
Term Memory

Abstract For complex design problems, human has shown surprising capability in effectively reducing the dimensionality of design space and quickly converging it to a reasonable range for algorithms to step in and continue the search process. Therefore, modeling how human designers make decisions in such a sequential design process can help discover beneficial design patterns, strategies, and heuristics, which are essential to the development of new algorithms embedded with human intelligence to augment the computational design. In this paper, we develop a deep learning-based approach to model and predict designers’ sequential decisions in the systems design context. The core of this approach is an integration of the function-behavior-structure model for design process characterization and the long short-term memory unit model for deep leaning. This approach is demonstrated in two case studies on solar energy system design, and its prediction accuracy is evaluated benchmarking on several commonly used models for sequential design decisions, such as the Markov Chain model, the Hidden Markov Chain model, and the random sequence generation model. The results indicate that the proposed approach outperforms the other traditional models. This implies that during a system design task, designers are very likely to rely on both short-term and long-term memory of past design decisions in guiding their future decision making in the design process. Our approach can support human-computer interactions in design and is general to be applied in other design contexts as long as the sequential data of design actions are available.

Short-term droughts forecast using Markov chain model in Victoria, Australia

2016 ◽  
Vol 129 (1-2) ◽  
pp. 445-457 ◽  
Author(s):  
Siti Nazahiyah Rahmat ◽  
Niranjali Jayasuriya ◽  
Muhammed A. Bhuiyan
Keyword(s):  
Markov Chain ◽  
Markov Chain Model ◽  
Chain Model ◽  
Short Term

Application of Improved GM(1,1)-Markov Chain Model of Business Order Prediction

2011 ◽  
Vol 143-144 ◽  
pp. 468-472
Author(s):  
Yi Liu ◽  
Wei Guo Lin ◽  
Ming Zhong Yang
Keyword(s):  
Markov Chain ◽  
Markov Chain Model ◽  
Business Environment ◽  
Small Sample ◽  
Prediction Methods ◽  
Chain Model ◽  
Order Quantity ◽  
Short Term ◽  
Real World Data ◽  
Strong Ability

Accurate prediction of the order quantity for the next period is very important for the enterprise to enhance the commercial competitive advantage in a highly competitive business environment. GM(1,1) theory is one of the prediction methods that can be built with a small sample and yet has a strong ability to make short-term predictions. The objective of the paper is to propose a order quantity prediction model which is combined the improved GM(1,1) model and Markov chain model .The effectiveness of the proposed approach to the order prediction is demonstrated using real-world data from a famous company in Liuzhou.The results indicate that the method of prediction is satisfying.

scholarly journals Spatio-temporal Markov chain model for very-short-term wind power forecasting

2019 ◽  
Vol 2019 (18) ◽  
pp. 5018-5022 ◽  
Author(s):  
Yongning Zhao ◽  
Lin Ye ◽  
Zheng Wang ◽  
Linlin Wu ◽  
Bingxu Zhai ◽  
...  
Keyword(s):  
Markov Chain ◽  
Wind Power ◽  
Markov Chain Model ◽  
Chain Model ◽  
Short Term ◽  
Wind Power Forecasting ◽  
Spatio Temporal ◽  
Power Forecasting

scholarly journals Predicting the Albanian economic development using multivariate Markov chain model

2020 ◽  
Author(s):  
Eralda Gjika (Dhamo) ◽  
Lule Basha ◽  
Xhensilda Allka ◽  
Aurora Ferrja
Keyword(s):  
Economic Development ◽  
Markov Chain ◽  
Markov Chain Model ◽  
Consumer Price Index ◽  
Forecast Model ◽  
Chain Model ◽  
Short Term ◽  
Probability Forecast ◽  
Fifth Order ◽  
Yearly Data

In this work, the economic development and relation to social and demography indices in Albania were studied. Four time series (yearly data for the period 1995–2018) were considered: consumer price index (CPI), unemployment rate, inflation and life expectancy. In our approach, a first and fifth order multivariate Markov chain model was proposed to predict the economic situation in Albania in the proceedings years. Tests and accuracy analysis of the model were performed. The prediction probabilities fall in the interval of 0.47 to 0.52 and the accuracy of both models is 75%. Our approach is a short term probability forecast model that can be used by the policymakers to evaluate and undertake initiatives to improve the situation in the country.

scholarly journals Integrating Sequence Learning and Game Theory to Predict Design Decisions Under Competition

2020 ◽  
Vol 143 (5) ◽  
Author(s):  
Alparslan Emrah Bayrak ◽  
Zhenghui Sha
Keyword(s):  
Game Theory ◽  
Sequence Learning ◽  
Short Term Memory ◽  
Function Optimization ◽  
Sequential Design ◽  
Sampling Point ◽  
Short Term ◽  
Design Decisions ◽  
Term Memory ◽  
Long Short Term Memory

Abstract Design can be viewed as a sequential and iterative search process. Fundamental understanding and computational modeling of human sequential design decisions are essential for developing new methods in design automation and human–AI collaboration. This paper presents an approach for predicting designers’ future search behaviors in a sequential design process under an unknown objective function by combining sequence learning with game theory. While the majority of existing studies focus on analyzing sequential design decisions from the descriptive and prescriptive point of view, this study is motivated to develop a predictive framework. We use data containing designers’ actual sequential search decisions under competition collected from a black-box function optimization game developed previously. We integrate the long short-term memory networks with the Delta method to predict the next sampling point with a distribution, and combine this model with a non-cooperative game to predict whether a designer will stop searching the design space or not based on their belief of the opponent’s best design. In the function optimization game, the proposed model accurately predicts 82% of the next design variable values and 92% of the next function values in the test data with an upper and lower bound, suggesting that a long short-term memory network can effectively predict the next design decisions based on their past decisions. Further, the game-theoretic model predicts that 60.8% of the participants stop searching for designs sooner than they actually do while accurately predicting when the remaining 39.2% of the participants stop. These results suggest that a majority of the designers show a strong tendency to overestimate their opponents’ performance, leading them to spend more on searching for better designs than they would have, had they known their opponents’ actual performance.

Short-Term Prediction of Wind Power Output Based on Markov Chain

2013 ◽  
Vol 448-453 ◽  
pp. 1789-1795
Author(s):  
De Xin Li ◽  
Xiang Yu Lv ◽  
Zhi Hui Song
Keyword(s):  
Markov Chain ◽  
Wind Power ◽  
Power Output ◽  
Wind Farm ◽  
Markov Chain Model ◽  
Forecast Accuracy ◽  
Chain Model ◽  
Short Term ◽  
Term Prediction ◽  
Short Term Prediction

Wind power short-term predicting technology has a great significance in process of wind power decision-making. Recent years, the technology had been studied extensively in industry. Markov chain model has strong adaptability, forecast accuracy higher and other else advantages, which is suitable for wind power short-term prediction. This paper have set up one step Markov prediction model and based on which predicting short-term wind power output, and taken the historical power data of an actual wind farm in Jilin Province as an example to simulate and analyze. The paper also have proposed and used RMSE, MXPE, MAPE error analysis indicators to analyze simulation results of different status spaces. The results showed that when the status space is 60 the prediction accuracy of the method is best.

Sign in / Sign up

Export Citation Format

Share Document