scholarly journals A quantitative uncertainty metric controls error in neural network-driven chemical discovery

2019 ◽  
Vol 10 (34) ◽  
pp. 7913-7922 ◽  
Author(s):  
Jon Paul Janet ◽  
Chenru Duan ◽  
Tzuhsiung Yang ◽  
Aditya Nandy ◽  
Heather J. Kulik
Keyword(s):  
Organic Chemistry ◽  
Neural Network ◽  
Machine Learning ◽  
Learning Model ◽  
Model Errors ◽  
Machine Learning Model ◽  
Predictive Approach ◽  
Inorganic And Organic

A predictive approach for driving down machine learning model errors is introduced and demonstrated across discovery for inorganic and organic chemistry.

scholarly journals Neural Network–Based Algorithm for Adjusting Activity Targets to Sustain Exercise Engagement Among People Using Activity Trackers: Retrospective Observation and Algorithm Development Study

10.2196/18142 ◽  
2020 ◽  
Vol 8 (9) ◽  
pp. e18142
Author(s):  
Ramin Mohammadi ◽  
Mursal Atif ◽  
Amanda Jayne Centi ◽  
Stephen Agboola ◽  
Kamal Jethwani ◽  
...  
Keyword(s):  
Neural Network ◽  
Physical Activity ◽  
Machine Learning ◽  
Learning Model ◽  
Step Count ◽  
Daily Step ◽  
Activity Tracker ◽  
Activity Trackers ◽  
Machine Learning Model ◽  
Daily Step Count

Background It is well established that lack of physical activity is detrimental to the overall health of an individual. Modern-day activity trackers enable individuals to monitor their daily activities to meet and maintain targets. This is expected to promote activity encouraging behavior, but the benefits of activity trackers attenuate over time due to waning adherence. One of the key approaches to improving adherence to goals is to motivate individuals to improve on their historic performance metrics. Objective The aim of this work was to build a machine learning model to predict an achievable weekly activity target by considering (1) patterns in the user’s activity tracker data in the previous week and (2) behavior and environment characteristics. By setting realistic goals, ones that are neither too easy nor too difficult to achieve, activity tracker users can be encouraged to continue to meet these goals, and at the same time, to find utility in their activity tracker. Methods We built a neural network model that prescribes a weekly activity target for an individual that can be realistically achieved. The inputs to the model were user-specific personal, social, and environmental factors, daily step count from the previous 7 days, and an entropy measure that characterized the pattern of daily step count. Data for training and evaluating the machine learning model were collected over a duration of 9 weeks. Results Of 30 individuals who were enrolled, data from 20 participants were used. The model predicted target daily count with a mean absolute error of 1545 (95% CI 1383-1706) steps for an 8-week period. Conclusions Artificial intelligence applied to physical activity data combined with behavioral data can be used to set personalized goals in accordance with the individual’s level of activity and thereby improve adherence to a fitness tracker; this could be used to increase engagement with activity trackers. A follow-up prospective study is ongoing to determine the performance of the engagement algorithm.

scholarly journals BonDNet: A Graph Neural Network for the Prediction of Bond Dissociation Energies for Charged Molecules

2020 ◽  
Author(s):  
Mingjian Wen ◽  
Samuel Blau ◽  
Evan Spotte-Smith ◽  
Shyam Dwaraknath ◽  
Kristin Persson
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Chemical Reactivity ◽  
Absolute Error ◽  
Learning Model ◽  
Chemical Processes ◽  
Accurate Prediction ◽  
Global Features ◽  
Bond Dissociation ◽  
Machine Learning Model

<div><div><div><p>A broad collection of technologies, including e.g. drug metabolism, biofuel combustion, photochemical decontamination of water, and interfacial passivation in energy production/storage systems rely on chemical processes that involve bond-breaking molecular reactions. In this context, a fundamental thermodynamic property of interest is the bond dissociation energy (BDE) which measures the strength of a chemical bond. Fast and accurate prediction of BDEs for arbitrary molecules would lay the groundwork for data-driven projections of complex reaction cascades and hence a deeper understanding of these critical chemical processes and, ultimately, how to reverse design them. In this paper, we propose a chemically inspired graph neural network machine learning model, BonDNet, for the rapid and accurate prediction of BDEs. BonDNet maps the difference between the molecular representations of the reactants and products to the reaction BDE. Because of the use of this difference representation and the introduction of global features, including molecular charge, it is the first machine learning model capable of predicting both homolytic and heterolytic BDEs for molecules of any charge. To test the model, we have constructed a dataset of both homolytic and heterolytic BDEs for neutral and charged (1 and +1) molecules. BonDNet achieves a mean absolute error (MAE) of 0.022 eV for unseen test data, significantly below chemical accuracy (0.043 eV). Besides the ability to handle complex bond dissociation reactions that no previous model could con- sider, BonDNet distinguishes itself even in only predicting homolytic BDEs for neutral molecules; it achieves an MAE of 0.020 eV on the PubChem BDE dataset, a 20% improvement over the previous best performing model. We gain additional insight into the model’s predictions by analyzing the patterns in the features representing the molecules and the bond dissociation reactions, which are qualitatively consistent with chemical rules and intuition. BonDNet is just one application of our general approach to representing and learning chemical reactivity, and it could be easily extended to the prediction of other reaction properties in the future.</p></div></div></div>

scholarly journals Development of a Machine Learning Model for Knowledge Acquisition, Relationship Extraction and Discovery in Domain Ontology Engineering using Jaccord Relationship Extraction and Neural Network

2019 ◽  
Vol 8 (3) ◽  
pp. 7809-7817
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Knowledge Acquisition ◽  
Language Processing ◽  
Learning Model ◽  
Heterogeneous Data ◽  
Relationship Extraction ◽  
Machine Learning Model ◽  
Proposed Model ◽  
Domain Independent

Creating a fast domain independent ontology through knowledge acquisition is a key problem to be addressed in the domain of knowledge engineering. Updating and validation is impossible without the intervention of domain experts, which is an expensive and tedious process. Thereby, an automatic system to model the ontology has become essential. This manuscript presents a machine learning model based on heterogeneous data from multiple domains including agriculture, health care, food and banking, etc. The proposed model creates a complete domain independent process that helps in populating the ontology automatically by extracting the text from multiple sources by applying natural language processing and various techniques of data extraction. The ontology instances are classified based on the domain. A Jaccord Relationship extraction process and the Neural Network Approval for Automated Theory is used for retrieval of data, automated indexing, mapping and knowledge discovery and rule generation. The results and solutions show the proposed model can automatically and efficiently construct automated Ontology

scholarly journals Predicting Sentiment Polarity of Microblogs using an LSTM – CNN Deep Learning Model

2019 ◽  
Vol 8 (6) ◽  
pp. 4368-4373
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Prediction Accuracy ◽  
Short Term Memory ◽  
Learning Model ◽  
Supervised Machine Learning ◽  
Machine Learning Model ◽  
Proposed Model ◽  
Network Approaches

In this paper we propose a novel supervised machine learning model to predict the polarity of sentiments expressed in microblogs. The proposed model has a stacked neural network structure consisting of Long Short Term Memory (LSTM) and Convolutional Neural Network (CNN) layers. In order to capture the long-term dependencies of sentiments in the text ordering of a microblog, the proposed model employs an LSTM layer. The encodings produced by the LSTM layer are then fed to a CNN layer, which generates localized patterns of higher accuracy. These patterns are capable of capturing both local and global long-term dependences in the text of the microblogs. It was observed that the proposed model performs better and gives improved prediction accuracy when compared to semantic, machine learning and deep neural network approaches such as SVM, CNN, LSTM, CNN-LSTM, etc. This paper utilizes the benchmark Stanford Large Movie Review dataset to show the significance of the new approach. The prediction accuracy of the proposed approach is comparable to other state-of-art approaches.

scholarly journals Material removal predictions in the robot glass polishing process using machine learning

2021 ◽  
Vol 4 (1) ◽  
Author(s):  
Max Schneckenburger ◽  
Sven Höfler ◽  
Luis Garcia ◽  
Rui Almeida ◽  
Rainer Börret
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Material Removal ◽  
Optical Glass ◽  
Learning Model ◽  
Machine Learning Algorithms ◽  
List Type ◽  
Polishing Process ◽  
Machine Learning Model ◽  
Glass Polishing

Abstract Robot polishing is increasingly being used in the production of high-end glass workpieces such as astronomy mirrors, lithography lenses, laser gyroscopes or high-precision coordinate measuring machines. The quality of optical components such as lenses or mirrors can be described by shape errors and surface roughness. Whilst the trend towards sub nanometre level surfaces finishes and features progresses, matching both form and finish coherently in complex parts remains a major challenge. With increasing optic sizes, the stability of the polishing process becomes more and more important. If not empirically known, the optical surface must be measured after each polishing step. One approach is to mount sensors on the polishing head in order to measure process-relevant quantities. On the basis of these data, machine learning algorithms can be applied for surface value prediction. Due to the modification of the polishing head by the installation of sensors and the resulting process influences, the first machine learning model could only make removal predictions with insufficient accuracy. The aim of this work is to show a polishing head optimised for the sensors, which is coupled with a machine learning model in order to predict the material removal and failure of the polishing head during robot polishing. The artificial neural network is developed in the Python programming language using the Keras deep learning library. It starts with a simple network architecture and common training parameters. The model will then be optimised step-by-step using different methods and optimised in different steps. The data collected by a design of experiments with the sensor-integrated glass polishing head are used to train the machine learning model and to validate the results. The neural network achieves a prediction accuracy of the material removal of 99.22%. Article highlights First machine learning model application for robot polishing of optical glass ceramics The polishing process is influenced by a large number of different process parameters. Machine learning can be used to adjust any process parameter and predict the change in material removal with a certain probability. For a trained model,empirical experiments are no longer necessary Equipping a polishing head with sensors, which provides the possibility for 100% control

Application of Machine Learning to Interpret Steady State Drainage Relative Permeability Experiments

2021 ◽  
Author(s):  
Eric Sonny Mathew ◽  
Moussa Tembely ◽  
Waleed AlAmeri ◽  
Emad W. Al-Shalabi ◽  
Abdul Ravoof Shaik
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Experimental Data ◽  
Steady State ◽  
Relative Permeability ◽  
Learning Model ◽  
Gradient Boosting ◽  
Data Set ◽  
Machine Learning Model ◽  
Extreme Gradient Boosting

Abstract A meticulous interpretation of steady-state or unsteady-state relative permeability (Kr) experimental data is required to determine a complete set of Kr curves. In this work, three different machine learning models was developed to assist in a faster estimation of these curves from steady-state drainage coreflooding experimental runs. The three different models that were tested and compared were extreme gradient boosting (XGB), deep neural network (DNN) and recurrent neural network (RNN) algorithms. Based on existing mathematical models, a leading edge framework was developed where a large database of Kr and Pc curves were generated. This database was used to perform thousands of coreflood simulation runs representing oil-water drainage steady-state experiments. The results obtained from these simulation runs, mainly pressure drop along with other conventional core analysis data, were utilized to estimate Kr curves based on Darcy's law. These analytically estimated Kr curves along with the previously generated Pc curves were fed as features into the machine learning model. The entire data set was split into 80% for training and 20% for testing. K-fold cross validation technique was applied to increase the model accuracy by splitting the 80% of the training data into 10 folds. In this manner, for each of the 10 experiments, 9 folds were used for training and the remaining one was used for model validation. Once the model is trained and validated, it was subjected to blind testing on the remaining 20% of the data set. The machine learning model learns to capture fluid flow behavior inside the core from the training dataset. The trained/tested model was thereby employed to estimate Kr curves based on available experimental results. The performance of the developed model was assessed using the values of the coefficient of determination (R2) along with the loss calculated during training/validation of the model. The respective cross plots along with comparisons of ground-truth versus AI predicted curves indicate that the model is capable of making accurate predictions with error percentage between 0.2 and 0.6% on history matching experimental data for all the three tested ML techniques (XGB, DNN, and RNN). This implies that the AI-based model exhibits better efficiency and reliability in determining Kr curves when compared to conventional methods. The results also include a comparison between classical machine learning approaches, shallow and deep neural networks in terms of accuracy in predicting the final Kr curves. The various models discussed in this research work currently focusses on the prediction of Kr curves for drainage steady-state experiments; however, the work can be extended to capture the imbibition cycle as well.

scholarly journals A Deep Neural Network for Accurate and Robust Prediction of the Glass Transition Temperature of Polyhydroxyalkanoate Homo- and Copolymers

Materials ◽  
2020 ◽  
Vol 13 (24) ◽  
pp. 5701
Author(s):  
Zhuoying Jiang ◽  
Jiajie Hu ◽  
Babetta L. Marrone ◽  
Ghanshyam Pilania ◽  
Xiong (Bill) Yu
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Glass Transition ◽  
Transition Temperature ◽  
Glass Transition Temperature ◽  
Deep Neural Network ◽  
Learning Model ◽  
Support Vector ◽  
Model Framework ◽  
Machine Learning Model

The purpose of this study was to develop a data-driven machine learning model to predict the performance properties of polyhydroxyalkanoates (PHAs), a group of biosourced polyesters featuring excellent performance, to guide future design and synthesis experiments. A deep neural network (DNN) machine learning model was built for predicting the glass transition temperature, Tg, of PHA homo- and copolymers. Molecular fingerprints were used to capture the structural and atomic information of PHA monomers. The other input variables included the molecular weight, the polydispersity index, and the percentage of each monomer in the homo- and copolymers. The results indicate that the DNN model achieves high accuracy in estimation of the glass transition temperature of PHAs. In addition, the symmetry of the DNN model is ensured by incorporating symmetry data in the training process. The DNN model achieved better performance than the support vector machine (SVD), a nonlinear ML model and least absolute shrinkage and selection operator (LASSO), a sparse linear regression model. The relative importance of factors affecting the DNN model prediction were analyzed. Sensitivity of the DNN model, including strategies to deal with missing data, were also investigated. Compared with commonly used machine learning models incorporating quantitative structure–property (QSPR) relationships, it does not require an explicit descriptor selection step but shows a comparable performance. The machine learning model framework can be readily extended to predict other properties.

Sign in / Sign up

Export Citation Format

Share Document