This paper proposes a sequence-to-sequence model for data-to-text generation, called DM-NLG, to generate a natural language text from structured nonlinguistic input. Specifically, by adding a dynamic memory module to the attention-based sequence-to-sequence model, it can store the information that leads to generate previous output words and use it to generate the next word. In this way, the decoder part of the model is aware of all previous decisions, and as a result, the generation of duplicate words or incomplete semantic concepts is prevented. To improve the generated sentences quality by the DM-NLG decoder, a postprocessing step is performed using the pretrained language models. To prove the effectiveness of the DM-NLG model, we performed experiments on five different datasets and observed that our proposed model is able to reduce the slot error rate rate by 50% and improve the BLEU by 10%, compared to the state-of-the-art models.

The aerodynamic modelling is one of the challenging tasks that is generally established using the results of the computational fluid dynamic software and wind tunnel analysis performed either on the scaled model or the prototype. In order to improve the confidence of the estimates, the conventional parameter estimation methods such as equation error method (EEM) and output error method (OEM) are more often applied to extract the aircraft’s stability and control derivatives from its respective flight test data. The quality of the estimates gets influenced due to the presence of the measurement and process noises in the flight test data. With the advancement in the machine learning algorithms, the data driven methods have got more attention in the modelling of a system based on the input-output measurements and also, in the identification of the system/model parameters. The research article investigates the longitudinal stability and control derivatives of the aerodynamic models by using an integrated optimisation algorithm based on a recurrent neural network. The flight test data of Hansa-3 and HFB 320 aircraft were used as case studies to see the efficacy of the parameter estimation algorithm and further, the confidence of the estimates were demonstrated in terms of the standard deviations. Finally, the simulated variables obtained using the estimates demonstrate a qualitative estimation in the presence of the noise.

Accurate prediction of laminar-turbulent transition is a critical element of computational fluid dynamics simulations for aerodynamic design across multiple flow regimes. Traditional methods of transition prediction cannot be easily extended to flow configurations where the transition process depends on a large set of parameters. In comparison, neural network methods allow higher dimensional input features to be considered without compromising the efficiency and accuracy of the traditional data-driven models. Neural network methods proposed earlier follow a cumbersome methodology of predicting instability growth rates over a broad range of frequencies, which are then processed to obtain the N-factor envelope, and then, the transition location based on the correlating N-factor. This paper presents an end-to-end transition model based on a recurrent neural network, which sequentially processes the mean boundary-layer profiles along the surface of the aerodynamic body to directly predict the N-factor envelope and the transition locations over a two-dimensional airfoil. The proposed transition model has been developed and assessed using a large database of 53 airfoils over a wide range of chord Reynolds numbers and angles of attack. The large universe of airfoils encountered in various applications causes additional difficulties. As such, we provide further insights on selecting training datasets from large amounts of available data. Although the proposed model has been analyzed for two-dimensional boundary layers in this paper, it can be easily generalized to other flows due to embedded feature extraction capability of convolutional neural network in the model.

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 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.

Maritime anomaly detection can improve the situational awareness of vessel traffic supervisors and reduce maritime accidents. In order to better detect anomalous behaviour of a vessel in real time, a method that consists of a Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm and a recurrent neural network is presented. In the method presented, the parameters of the DBSCAN algorithm were determined through statistical analysis, and the results of clustering were taken as the traffic patterns to train a recurrent neural network composed of Long Short-Term Memory (LSTM) units. The neural network was applied as a vessel trajectory predictor to conduct real-time maritime anomaly detection. Based on data from the Chinese Zhoushan Islands, experiments verified the applicability of the proposed method. The results show that the proposed method can detect anomalous behaviours of a vessel regarding speed, course and route quickly.

Our aim is to develop a smartphone-based life-logging system. Human activity recognition (HAR) is one of the core techniques to realize it. Recent studies reported the effectiveness of feed-forward neural network (FF-NN) and recurrent neural network (RNN) as a classifier for HAR task. However, there are still unresolved problems in those studies: (1) a life-logging system using only a smartphone for recording device has not been developed, (2) only indoor activities have been utilized for evaluation, (3) insufficient investigations/evaluations of RNN. In this study, we address these unresolved problems as follows: (1) we build a prototype system for life-logging and conduct data recording experiment on this system to include both indoor and outdoor activities. The experimental results of HAR on this new dataset showed that RNN-based classifier was still effective. (2) From the results of a HAR experiment, it was demonstrated that a multi-layered Simple Recurrent Unit with a non-linear transform at the bottom layer and a highway-connection was the most effective. (3) We could grasp the reason for the improvement of RNN from FF-NN by observing the posterior probabilities over test data.

The Global Positioning System (GPS) can be employed as a free attitude determination interferometer when carrier phase measurements are utilized. Conventional approaches for the baseline vectors are essentially based on the least-squares or Kalman filtering methods. The raw attitude solutions are inherently noisy if the solutions of baseline vectors are obtained based on the least-squares method. The Kalman filter attempts to minimize the error variance of the estimation errors and will provide the optimal result while it is required that the complete a priori knowledge of both the process noise and measurement noise covariance matrices are available. In this article, a neural network state estimator, which replaces the Kalman filter, will be incorporated into the attitude determination mechanism for estimating the attitude angles from the noisy raw attitude solutions. Employing the neural network estimator improves robustness compared to the Kalman filtering method when uncertainty in noise statistical knowledge exists. Simulation is conducted and a comparative evaluation based on the neural network estimator and Kalman filter is provided.

This paper describes the design of an Internal Model Control (IMC) system for a planar two-degree-of-freedom robot. IMC was investigated as an alternative to the basic inverse control scheme which is difficult to implement. The proposed IMC system consisted of a forward internal neural model of the robot, a neural controller and a conventional feedback controller, all of which were realised easily. Both the neural model and the neural controller were based on recurrent networks which were trained using the backpropagation (BP) algorithm. The paper presents the results obtained with two types of recurrent networks as well as a conventional PID system.