skip to main content

Title: Predicting human design decisions with deep recurrent neural network combining static and dynamic data
Computational modeling of the human sequential design process and successful prediction of future design decisions are fundamental to design knowledge extraction, transfer, and the development of artificial design agents. However, it is often difficult to obtain designer-related attributes (static data) in design practices, and the research based on combining static and dynamic data (design action sequences) in engineering design is still underexplored. This paper presents an approach that combines both static and dynamic data for human design decision prediction using two different methods. The first method directly combines the sequential design actions with static data in a recurrent neural network (RNN) model, while the second method integrates a feed-forward neural network that handles static data separately, yet in parallel with RNN. This study contributes to the field from three aspects: (a) we developed a method of utilizing designers’ cluster information as a surrogate static feature to combine with a design action sequence in order to tackle the challenge of obtaining designer-related attributes; (b) we devised a method that integrates the function–behavior–structure design process model with the one-hot vectorization in RNN to transform design action data to design process stages where the insights into design thinking can be drawn; (c) to more » the best of our knowledge, it is the first time that two methods of combining static and dynamic data in RNN are compared, which provides new knowledge about the utility of different combination methods in studying sequential design decisions. The approach is demonstrated in two case studies on solar energy system design. The results indicate that with appropriate kernel models, the RNN with both static and dynamic data outperforms traditional models that only rely on design action sequences, thereby better supporting design research where static features, such as human characteristics, often play an important role. « less
Authors:
; ; ;
Award ID(s):
1503196 1842588
Publication Date:
NSF-PAR ID:
10171401
Journal Name:
Design Science
Volume:
6
ISSN:
2053-4701
Sponsoring Org:
National Science Foundation
More Like this
  1. This work proposes an Adaptive Fuzzy Prediction (AFP) method for the attenuation time series in Commercial Microwave links (CMLs). Time-series forecasting models regularly rely on the assumption that the entire data set follows the same Data Generating Process (DGP). However, the signals in wireless microwave links are severely affected by the varying weather conditions in the channel. Consequently, the attenuation time series might change its characteristics significantly at different periods. We suggest an adaptive framework to better employ the training data by grouping sequences with related temporal patterns to consider the non-stationary nature of the signals. The focus in this work is two-folded. The first is to explore the integration of static data of the CMLs as exogenous variables for the attenuation time series models to adopt diverse link characteristics. This extension allows to include various attenuation datasets obtained from additional CMLs in the training process and dramatically increasing available training data. The second is to develop an adaptive framework for short-term attenuation forecasting by employing an unsupervised fuzzy clustering procedure and supervised learning models. We empirically analyzed our framework for model and data-driven approaches with Recurrent Neural Network (RNN) and Autoregressive Integrated Moving Average (ARIMA) variations. We evaluate themore »proposed extensions on real-world measurements collected from 4G backhaul networks, considering dataset availability and the accuracy for 60 seconds prediction. We show that our framework can significantly improve conventional models’ accuracy and that incorporating data from various CMLs is essential to the AFP framework. The proposed methods have been shown to enhance the forecasting model’s performance by 30 − 40%, depending on the specific model and the data availability.« less
  2. This article presents the design process of a supernumerary wearable robotic forearm (WRF), along with methods for stabilizing the robot’s end-effector using human motion prediction. The device acts as a lightweight “third arm” for the user, extending their reach during handovers and manipulation in close-range collaborative activities. It was developed iteratively, following a user-centered design process that included an online survey, contextual inquiry, and an in-person usability study. Simulations show that the WRF significantly enhances a wearer’s reachable workspace volume, while remaining within biomechanical ergonomic load limits during typical usage scenarios. While operating the device in such scenarios, the user introduces disturbances in its pose due to their body movements. We present two methods to overcome these disturbances: autoregressive (AR) time series and a recurrent neural network (RNN). These models were used for forecasting the wearer’s body movements to compensate for disturbances, with prediction horizons determined through linear system identification. The models were trained offline on a subset of the KIT Human Motion Database, and tested in five usage scenarios to keep the 3D pose of the WRF’s end-effector static. The addition of the predictive models reduced the end-effector position errors by up to 26% compared to direct feedback control.
  3. Time series prediction is an important problem in machine learning. Previous methods for time series prediction did not involve additional information. With a lot of dynamic knowledge graphs available, we can use this additional information to predict the time series better. Recently, there has been a focus on the application of deep representation learning on dynamic graphs. These methods predict the structure of the graph by reasoning over the interactions in the graph at previous time steps. In this paper, we propose a new framework to incorporate the information from dynamic knowledge graphs for time series prediction. We show that if the information contained in the graph and the time series data are closely related, then this inter-dependence can be used to predict the time series with improved accuracy. Our framework, DArtNet, learns a static embedding for every node in the graph as well as a dynamic embedding which is dependent on the dynamic attribute value (time-series). Then it captures the information from the neighborhood by taking a relation specific mean and encodes the history information using RNN. We jointly train the model link prediction and attribute prediction. We evaluate our method on five specially curated datasets for this problemmore »and show a consistent improvement in time series prediction results. We release the data and code of model DArtNet for future research.« less
  4. Citations of scientific papers and patents reveal the knowledge flow and usually serve as the metric for evaluating their novelty and impacts in the field. Citation Forecasting thus has various applications in the real world. Existing works on citation forecasting typically exploit the sequential properties of citation events, without exploring the citation network. In this paper, we propose to explore both the citation network and the related citation event sequences which provide valuable information for future citation forecasting. We propose a novel Citation Network and Event Sequence (CINES) Model to encode signals in the citation network and related citation event sequences into various types of embeddings for decoding to the arrivals of future citations. Moreover, we propose a temporal network attention and three alternative designs of bidirectional feature propagation to aggregate the retrospective and prospective aspects of publications in the citation network, coupled with the citation event sequence embeddings learned by a two-level attention mechanism for the citation forecasting. We evaluate our models and baselines on both a U.S. patent dataset and a DBLP dataset. Experimental results show that our models outperform the state-of-the-art methods, i.e., RMTPP, CYAN-RNN, Intensity-RNN, and PC-RNN, reducing the forecasting error by 37.76% - 75.32%.
  5. The objective of this work is to introduce the application of an artificial neural network (ANN) to assist in the evaporative cooling in data centers. To achieve this task, we employ the neural network algorithms to predict weather conditions outside the data center for direct evaporative cooling (DEC) operations. The predictive analysis helps optimize the cooling control strategy for maximizing the usage of evaporative cooling thereby improving the efficiency of the overall data center cooling system. A typical artificial neural network architecture is dynamic in nature and can perform adaptive learning in minimal computation time. A neural network model of a data center was created using operational historical data collected from a data center cooling control system. The neural network model allows the control of the modular data center (MDC) cooling at optimum configuration in two ways. First way is that the network model minimizes time delay for switching the cooling from one mode to the other. Second way, it improves the reaction behavior of the cooling equipment if an unexpected ambient condition change should come. The data center in consideration is a test bed modular data center that comprises of information Technology (IT) racks, Direct Evaporative cooling (DEC) andmore »Indirect Evaporative Cooling (IEC) modules; the DEC/IEC are used together or in alternative mode to cool the data center room. The facility essentially utilizes outside ambient temperature and humidity conditions that are further conditioned by the DEC and IEC to cool the electronics, a concept know as air-side economization. Various parameters are related to the cooling system operation such as outside air temperature, IT heat load, cold aisle temperature, cold aisle humidity etc. are considered. Some of these parameters are fed into the artificial neural network as inputs and some are set as targets to train the neural network system. After the training the process is completed, certain bucket of data is tested and further used to validate the outputs for various other weather conditions. To make sure the analysis represents real world scenario, the operational data used are from real time data logged on the MDC cooling control unit. Overall, the neural network model is trained and is used to successfully predict the weather conditions and cooling control parameters. The prediction models have been demonstrated for the outputs that are static in nature (Levenberg Marquardt method) as well as the outputs that are dynamic in nature i.e., step-ahead & multistep ahead techniques.« less