Automatic simulation-based testing of autonomous ships using Gaussian processes and temporal logic

A methodology for automatic simulation-based testing of control systems for autonomous vessels is proposed. The work is motivated by the need for increased test coverage and formalism in the verification efforts. It aims to achieve this by formulating requirements in the formal logic Signal Temporal Logic (STL). This enables automatic evaluation of simulations against requirements using the STL robustness metric, resulting in a robustness score for requirements satisfaction. Furthermore, the proposed method uses a Gaussian Process (GP) model for estimating robustness scores including levels of uncertainty for untested cases. The GP model is updated by running simulations and observing the resulting robustness, and its estimates are used to automatically guide the test case selection toward cases with low robustness or high uncertainty. The main scientific contribution is the development of an automatic testing method which incrementally runs new simulations until the entire parameter space of the case is covered to the desired confidence level, or until a case which falsifies the requirement is identified. The methodology is demonstrated through a case study, where the test object is a Collision Avoidance (CA) system for a small high-speed vessel. STL requirements for safety distance, mission compliance, and COLREG compliance are developed. The proposed method shows promise, by both achieving verification in feasible time and identifying falsifying behaviors which would be difficult to detect manually or using brute-force methods. An additional contribution of this work is a formalization of COLREG using temporal logic, which appears to be an interesting direction for future work.

Financial Time Series Prediction Based on XGBoost and Generative Adversarial Networks

Considering the problems of the model collapse and the low forecast precision in predicting the financial time series of the generative adversarial networks (GAN), we apply the WGAN-GP model to solve the gradient collapse. Extreme gradient boosting (XGBoost) is used for feature extraction to improve prediction accuracy. Alibaba stock is taken as the research object, using XGBoost to optimize its characteristic factors, and training the optimized characteristic variables with WGAN-GP. We compare the prediction results of WGAN-GP model and classical time series prediction models, long short term memory (LSTM) and gate recurrent unit (GRU). In the experimental stage, root mean square error (RMSE) is chosen as the evaluation index. The results of different models show that the RMSE of WGAN-GP model is the smallest, which are 61.94% and 47.42%, lower than that of LSTM model and GRU model respectively. At the same time, the stock price data of Google and Amazon confirm the stability of WGAN-GP model. WGAN-GP model can obtain higher prediction accuracy than the classical time series prediction model.

Non-parametric synergy modeling of chemical compounds with Gaussian processes

Background Understanding the synergetic and antagonistic effects of combinations of drugs and toxins is vital for many applications, including treatment of multifactorial diseases and ecotoxicological monitoring. Synergy is usually assessed by comparing the response of drug combinations to a predicted non-interactive response from reference (null) models. Possible choices of null models are Loewe additivity, Bliss independence and the recently rediscovered Hand model. A different approach is taken by the MuSyC model, which directly fits a generalization of the Hill model to the data. All of these models, however, fit the dose–response relationship with a parametric model. Results We propose the Hand-GP model, a non-parametric model based on the combination of the Hand model with Gaussian processes. We introduce a new logarithmic squared exponential kernel for the Gaussian process which captures the logarithmic dependence of response on dose. From the monotherapeutic response and the Hand principle, we construct a null reference response and synergy is assessed from the difference between this null reference and the Gaussian process fitted response. Statistical significance of the difference is assessed from the confidence intervals of the Gaussian process fits. We evaluate performance of our model on a simulated data set from Greco, two simulated data sets of our own design and two benchmark data sets from Chou and Talalay. We compare the Hand-GP model to standard synergy models and show that our model performs better on these data sets. We also compare our model to the MuSyC model as an example of a recent method on these five data sets and on two-drug combination screens: Mott et al. anti-malarial screen and O’Neil et al. anti-cancer screen. We identify cases in which the HandGP model is preferred and cases in which the MuSyC model is preferred. Conclusion The Hand-GP model is a flexible model to capture synergy. Its non-parametric and probabilistic nature allows it to model a wide variety of response patterns.

Tree pruning in the structural approach to vowel reduction and lenition

The article scrutinises several vowel reduction and lenition phenomena by employing a model of syntax-like structural representations, i.e. Government Phonology 2.0. In contrast to the standard GP model, whereby lenition and vowel reduction can be viewed as shortening, element suppression or status switching, the structural approach employs the procedure of tree pruning with a heavily limited role of melodic annotation. This paper will take a closer look at node removal with special attention to its trajectory. In particular, two basic directionalities are considered: top-down and bottom-up. The former has been proposed to account for vowel reduction whereby the highest positions are deleted retaining the head and potentially its sister. The acquisition of plosives and fricatives points to the latter trajectory, which disposes of nodes closer to the head. However, the choice of positions that are targeted in weak contexts might be also related to the inherently encoded hierarchy of terminal nodes within the constituents in question.

Data Augmentation Based on Generative Adversarial Networks to Improve Stage Classification of Chronic Kidney Disease

The prevalence of chronic kidney disease (CKD) is estimated to be 13.4% worldwide and 15% in the United States. CKD has been recognized as a leading public health problem worldwide. Unfortunately, as many as 90% of CKD patients do not know that they already have CKD. Ultrasonography is usually the first and the most commonly used imaging diagnostic tool for patients at risk of CKD. To provide a consistent assessment of the stage classifications of CKD, this study proposes an auxiliary diagnosis system based on deep learning approaches for renal ultrasound images. The system uses the ACWGAN-GP model and MobileNetV2 pre-training model. The images generated by the ACWGAN-GP generation model and the original images are simultaneously input into the pre-training model MobileNetV2 for training. This classification system achieved an accuracy of 81.9% in the four stages of CKD classification. If the prediction results allowed a higher stage tolerance, the accuracy could be improved by up to 90.1%. The proposed deep learning method solves the problem of imbalance and insufficient data samples during training processes for an automatic classification system and also improves the prediction accuracy of CKD stage diagnosis.

Development of a Gaussian Process Model as a Surrogate to Study Load Bridging Performance in Racked Pallets

Current pallet design methodology frequently underestimates the load capacity of the pallet by assuming the payload is uniformly distributed and flexible. By considering the effect of payload characteristics and their interactions during pallet design, the structure of pallets can be optimized and raw material consumption reduced. The objective of this study was to develop a full description of how such payload characteristics affect load bridging on unit loads of stacked corrugated boxes on warehouse racking support. To achieve this goal, the authors expanded on a previously developed finite element model of a simplified unit load segment and conducted a study to screen for the significant factors and interactions. Subsequently, a Gaussian process (GP) regression model was developed to efficiently and accurately replicate the simulation model. Using this GP model, a quantification of the effects and interactions of all the identified significant factors was provided. With this information, packaging designers and researchers can engineer unit loads that consider the effect of the relevant design variables and their impact on pallet performance. Such a model has not been previously developed and can potentially reduce packaging materials’ costs.

Determination of the Concentration of Propionic Acid in an Aqueous Solution by POD-GP Model and Spectroscopy

Biorefining and biorefineries are the future of industry and energy. It is still a long way to complete its implementation, but small biorefineries focused mainly on the production of fuels and energy are more and more frequent in rural areas and large areas located near big cities in which, in addition to fuels and energy, various organic substances of high market value are also produced. In order to optimize biogas production and to control methane fermentation processes, fast and accurate identification of carboxylic acid concentrations, including propionic acid as a precursor to acetic acid, is needed. In this study, a process quality control method was developed to evaluate the propionic acid content of an aqueous solution from the fermentation mass. The proposed methodology is based on near infrared spectroscopy with multivariate analysis and stochastic metamodeling with a denoising procedure based on proper orthogonal decomposition (POD). The proposed methodology uses the Bayesian theory, which provides additional information on the magnitude of the correlation between state and control variables. The calibration model was, therefore, constructed by using Gaussian Processes (GP) to predict propionic acid content in the aqueous solution using an NIR-Vis spectrophotometer. The design of the calibration model was based on absorbance spectra and calculation data from selected wavelength ranges from 305 nm to 2210 nm. Measurement data were first denoised and truncated to build a fast and reliable metamodel for precise identification of the acid content of an aqueous solution at a concentration from 0 to 5.66%. The mean estimation error generated by the metamodel does not exceed 0.7%.

Predicting H2S emission from gravity sewer using an adaptive neuro-fuzzy inference system

A predictive model to estimate hydrogen sulfide (H2S) emission from sewers would offer engineers and asset managers the ability to evaluate the possible odor/corrosion problems during the design and operation of sewers to avoid in-sewer complications. This study aimed to model and forecast H2S emission from a gravity sewer, as a function of temperature and hydraulic conditions, without requiring prior knowledge of H2S emission mechanism. Two different adaptive neuro-fuzzy inference system (ANFIS) models using grid partitioning (GP) and subtractive clustering (SC) approaches were developed, validated, and tested. The ANFIS-GP model was constructed with two Gaussian membership functions for each input. For the development of the ANFIS-SC model, the MATLAB default values for clustering parameters were selected. Results clearly indicated that both the best ANFIS-GP and ANFIS-SC models produced smaller error compared with the multiple regression models and demonstrated a superior predictive performance on forecasting H2S emission with an excellent R2 value of >0.99. However, the ANFIS-GP model possessed fewer rules and parameters than the ANFIS-SC model. These findings validate the ANFIS-GP model as a potent tool for predicting H2S emission from gravity sewers.

A Comparison of Gaussian Process and M5P for Prediction of Soil Permeability Coefficient

The permeability coefficient (k) of soil is one of the most important parameters affecting soil characteristics such as shear strength or settlement. Thus, determining soil permeability coefficient is very crucial; however, a field test for determining this parameter is difficult, time-consuming, and expensive. In this study, soft computing methods, namely, M5P and Gaussian process (GP), for estimating the permeability coefficient were constructed and compared. The results of this paper indicate that the two soft computing algorithms functioned well in predicting k. These two methods gave high accuracy of prediction capability. The determination coefficient of M5P (R2 = 0.766) was higher than that (R2 = 0.700) of GP. This implies that the M5P model is more reliable estimation than the GP model in predicting soils’ permeability coefficient (k). This proves that applying these machine learning techniques can provide an alternative for predicting basic soil parameters, including the permeability coefficient of soil.

Forecasting Current Velocity and Profile in a Strait Water using Warped Gaussian Process

Ocean current forecast is vital for developing tidal energy and construction of offshore structures in the strait waters. This paper developed a short-term ocean current forecasting approach using the warped Gaussian process (WGP), which consists of the measured data preprocessing, kernel function selection, and data forecasting using WGP. A preprocessing using the wavelet thresholding method was proposed to enhance the quality of the measured raw data. The theory of WGP and the commonly used kernel functions were briefly introduced. The sliding time window and one-step ahead strategies were employed to increase the accuracy of predictions. Observations collected during an ocean current measurement campaign executed in a strait water on the coast of the East China Sea were used as an example dataset. The current velocity and profile were forecasted and validated using the example dataset as an illustration of the framework of the developed approach. The effects of window length, kernel function, and time interval on the WGP forecasting efficiency and precision were investigated. The forecasting performance of the developed WGP model was discussed by comparing it with the standard GP model. The current profile with a 95% confidence interval was also predicted by the developed WGP model at a certain point. The validation shows that the developed model is efficient in the short-term ocean current forecast.