Search

We present a method to model interatomic interactions such as energy and forces in a computationally efficient way. The proposed model approximates the energy/forces using a linear combination of random features, thereby enabling fast parameter estimation by solving a linear least-squares problem. We discuss how random features based on stationary and non-stationary kernels can be used for energy approximation and provide results for three classes of materials, namely two-dimensional materials, metals and semiconductors. Force and energy predictions made using the proposed method are in close agreement with density functional theory calculations, with training time that is 96% lower than standard kernel models. Molecular Dynamics calculations using random features based interatomic potentials are shown to agree well with experimental and density functional theory values. Phonon frequencies as computed by random features based interatomic potentials are within 0.1% of the density functional theory results. Furthermore, the proposed random features-based potential addresses scalability issues encountered in this class of machine learning problems. [ABSTRACT FROM AUTHOR]

Background: The Coronavirus disease 2019 (COVID-19) pandemic has affected millions of people across the globe. It is associated with a high mortality rate and has created a global crisis by straining medical resources worldwide. Objectives: To develop and validate machine-learning models for prediction of mechanical ventilation (MV) for patients presenting to emergency room and for prediction of in-hospital mortality once a patient is admitted. Methods: Two cohorts were used for the two different aims. 1980 COVID-19 patients were enrolled for the aim of prediction ofMV. 1036 patients' data, including demographics, past smoking and drinking history, past medical history and vital signs at emergency room (ER), laboratory values, and treatments were collected for training and 674 patients were enrolled for validation using XGBoost algorithm. For the second aim to predict in-hospital mortality, 3491 hospitalized patients via ER were enrolled. CatBoost, a new gradient-boosting algorithm was applied for training and validation of the cohort. Results: Older age, higher temperature, increased respiratory rate (RR) and a lower oxygen saturation (SpO2) from the first set of vital signs were associated with an increased risk of MV amongst the 1980 patients in the ER. The model had a high accuracy of 86.2% and a negative predictive value (NPV) of 87.8%. While, patients who required MV, had a higher RR, Body mass index (BMI) and longer length of stay in the hospital were the major features associated with in-hospital mortality. The second model had a high accuracy of 80% with NPV of 81.6%. Conclusion: Machine learning models using XGBoost and catBoost algorithms can predict need for mechanical ventilation and mortality with a very high accuracy in COVID-19 patients. [ABSTRACT FROM AUTHOR]

Automated metering Infrastructure (AMI) is an integral part of a smart grid. Employing the data collected by the AMI from the consumers to generate accurate electricity consumption forecasts can help the utility in significantly improving the quality of service delivered to the consumer. Design and empirical validation of machine learning based electric energy consumption forecasting systems, is presented in the present study. Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU) and Extreme Learning Machines (ELM) based models are designed and evaluated. One of the major aspects of the work is that the proposed consumption forecasting systems are designed as generalized models, i.e. one single model can be used to generate forecasts for any of the consumers considered, as opposed to the conventional technique of generating a separate model for each consumer. The forecasting systems are designed to generate half-hour-ahead and two-hour-ahead electric energy consumption forecasts. The proposed systems are validated on data for 485 Small and Medium Enterprise (SME) consumers in the CER electric energy consumption dataset. Results indicate that the models proposed in the present study result in good consumption forecast accuracy are hence, well suited for generating electric energy consumption forecast models. [ABSTRACT FROM AUTHOR]

We consider the problem of learning a multivariate function from a set of scattered observations using a sparse low-rank separated representation (SSR) model. The model structure considered here is promising for high-dimensional learning problems; however, existing training algorithms based on alternating least-squares (ALS) are known to have convergence difficulties, particularly when the rank of the model is greater than 1. In the present work, we supplement the model structure with sparsity constraints to ensure the well posedness of the approximation problem. We propose two fast training algorithms to estimate the model parameters: (i) a cyclic coordinate descent algorithm and (ii) a block coordinate descent (BCD) algorithm. While the first algorithm is not provably convergent owing to the non-convexity of the optimization problem, the BCD algorithm guarantees convergence to a Nash equilibrium point. The computational cost of the proposed algorithms is shown to scale linearly with respect to all of the parameters in contrast to methods based on ALS. Numerical studies on synthetic and real-world regression datasets indicate that the proposed SSR model structure holds significant potential for machine learning problems. [ABSTRACT FROM AUTHOR]

Abstract Stock price time series are extremely nonlinear in nature and hence, accurate stock price forecasting has been a challenge. Accurate prediction of stock prices and the direction of stock price movement is also essential for a stock trader/investor in order to trade profitably. A deep learning approach to stock price forecasting is presented in this study. A total of fourteen different deep learning models based on Long-Short Term Memory (LSTM), Gated Recurring Unit (GRU), Convolutional Neural Networks (CNN) and Extreme Learning Machines (ELM) are designed and empirically evaluated on all stocks in the S&P BSE-BANKEX index for their ability to generate one-step ahead and four-step ahead forecasts. Performance of the proposed systems is evaluated in terms of the Root Mean Squared Error (RMSE), Directional Accuracy (DA) and the Median Absolute Percentage Error (MdAPE). Results indicate that deep learning models proposed in this study are capable of generating highly accurate stock price forecasts. [ABSTRACT FROM AUTHOR]

In this paper, we propose a technique based on genetic programming (GP) for meshfree solution of elliptic partial differential equations. We employ the least-squares collocation principle to define an appropriate objective function, which is optimized using GP. Two approaches are presented for the repair of the symbolic expression for the field variables evolved by the GP algorithm to ensure that the governing equations as well as the boundary conditions are satisfied. In the case of problems defined on geometrically simple domains, we augment the solution evolved by GP with additional terms, such that the boundary conditions are satisfied by construction. To satisfy the boundary conditions for geometrically irregular domains, we combine the GP model with a radial basis function network. We improve the computational efficiency and accuracy of both techniques with gradient boosting, a technique originally developed by the machine learning community. Numerical studies are presented for operator problems on regular and irregular boundaries to illustrate the performance of the proposed algorithms. [ABSTRACT FROM AUTHOR]

Due to the prohibitively long experimental and simulation times, dwell fatigue (DF) failure prediction in titanium and its alloys is a challenging task. Since most of these failures have a microstructural level origin, this work focusses on utilizing minimal experiments and machine learning for predicting failure initiation points in a given microstructure. Failure initiation points in commercially pure titanium were identified using interrupted tensile and DF tests. Orientation imaging data was used to train a Random Forest model to calculate the relative importance of various grain orientation-based features to crack nucleation. Subsequently a predictive model for identifying locations that are likely to form a DF crack in a microstructure is developed. [ABSTRACT FROM AUTHOR]

Abstract: Mono-block centrifugal pumps are widely used in a variety of applications. In many applications the role of mono-block centrifugal pump is critical and condition monitoring is essential. Vibration based continuous monitoring and analysis using machine learning approach is gaining momentum. Particularly, artificial neural networks, fuzzy logic have been employed for continuous monitoring and fault diagnosis. This paper presents the use of decision tree and rough sets to generate the rules from statistical features extracted from vibration signals under good and faulty conditions of a mono-block centrifugal pump. A fuzzy classifier is built using decision tree and rough set rules and tested using test data. The results obtained using decision tree rules and those obtained using rough set rules are compared. Finally, the accuracy of a principle component analysis based decision tree-fuzzy system is also evaluated. The study reveals that overall classification accuracy obtained by the decision tree-fuzzy hybrid system is to some extent better than the rough set-fuzzy hybrid system. [Copyright &y& Elsevier]