Data based predictive models for odor perception

Abstract Machine learning and data analytics are being increasingly used for quantitative structure property relation (QSPR) applications in the chemical domain where the traditional Edisonian approach towards knowledge-discovery have not been fruitful. The perception of odorant stimuli is one such application as olfaction is the least understood among all the other senses. In this study, we employ machine learning based algorithms and data analytics to address the efficacy of using a data-driven approach to predict the perceptual attributes of an odorant namely the odorant characters (OC) of “sweet” and “musky”. We first analyze a psychophysical dataset containing perceptual ratings of 55 subjects to reveal patterns in the ratings given by subjects. We then use the data to train several machine learning algorithms such as random forest, gradient boosting and support vector machine for prediction of the odor characters and report the structural features correlating well with the odor characters based on the optimal model. Furthermore, we analyze the impact of the data quality on the performance of the models by comparing the semantic descriptors generally associated with a given odorant to its perception by majority of the subjects. The study presents a methodology for developing models for odor perception and provides insights on the perception of odorants by untrained human subjects and the effect of the inherent bias in the perception data on the model performance. The models and methodology developed here could be used for predicting odor characters of new odorants.

Download Full-text

Performance of three machine learning algorithms for predicting soil organic carbon in German agricultural soil

10.5194/soil-2021-107 ◽

2021 ◽

Author(s):

Ali Sakhaee ◽

Anika Gebauer ◽

Mareike Ließ ◽

Axel Don

Keyword(s):

Machine Learning ◽

Organic Carbon ◽

Soil Organic Carbon ◽

Agricultural Soil ◽

Learning Algorithms ◽

Model Performance ◽

Machine Learning Algorithms ◽

Support Vector ◽

Organic Soils ◽

The Impact

Abstract. Soil organic carbon (SOC), as the largest terrestrial carbon pool, has the potential to influence climate change and mitigation, and consequently SOC monitoring is important in the frameworks of different international treaties. There is therefore a need for high resolution SOC maps. Machine learning (ML) offers new opportunities to do this due to its capability for data mining of large datasets. The aim of this study, therefore, was to test three commonly used algorithms in digital soil mapping – random forest (RF), boosted regression trees (BRT) and support vector machine for regression (SVR) – on the first German Agricultural Soil Inventory to model agricultural topsoil SOC content. Nested cross-validation was implemented for model evaluation and parameter tuning. Moreover, grid search and differential evolution algorithm were applied to ensure that each algorithm was tuned and optimised suitably. The SOC content of the German Agricultural Soil Inventory was highly variable, ranging from 4 g kg−1 to 480 g kg−1. However, only 4 % of all soils contained more than 87 g kg−1 SOC and were considered organic or degraded organic soils. The results show that SVR provided the best performance with RMSE of 32 g kg−1 when the algorithms were trained on the full dataset. However, the average RMSE of all algorithms decreased by 34 % when mineral and organic soils were modeled separately, with the best result from SVR with RMSE of 21 g kg−1. Model performance is often limited by the size and quality of the available soil dataset for calibration and validation. Therefore, the impact of enlarging the training data was tested by including 1223 data points from the European Land Use/Land Cover Area Frame Survey for agricultural sites in Germany. The model performance was enhanced for maximum 1 % for mineral soils and 2 % for organic soils. Despite the capability of machine learning algorithms in general, and particularly SVR, in modelling SOC on a national scale, the study showed that the most important to improve the model performance was separate modelling of mineral and organic soils.

Download Full-text

Using Machine Learning to Predict Mortality for COVID-19 Patients on Day 0 in the ICU

Frontiers in Digital Health ◽

10.3389/fdgth.2021.681608 ◽

2022 ◽

Vol 3 ◽

Author(s):

Elham Jamshidi ◽

Amirhossein Asgary ◽

Nader Tavakoli ◽

Alireza Zali ◽

Soroush Setareh ◽

...

Keyword(s):

Machine Learning ◽

Treatment Strategies ◽

Machine Learning Algorithms ◽

Gradient Boosting ◽

Support Vector ◽

Early Prediction ◽

Distribution Width ◽

Predictive Values ◽

Prediction Of Mortality ◽

The Impact

Rationale: Given the expanding number of COVID-19 cases and the potential for new waves of infection, there is an urgent need for early prediction of the severity of the disease in intensive care unit (ICU) patients to optimize treatment strategies.Objectives: Early prediction of mortality using machine learning based on typical laboratory results and clinical data registered on the day of ICU admission.Methods: We retrospectively studied 797 patients diagnosed with COVID-19 in Iran and the United Kingdom (U.K.). To find parameters with the highest predictive values, Kolmogorov-Smirnov and Pearson chi-squared tests were used. Several machine learning algorithms, including Random Forest (RF), logistic regression, gradient boosting classifier, support vector machine classifier, and artificial neural network algorithms were utilized to build classification models. The impact of each marker on the RF model predictions was studied by implementing the local interpretable model-agnostic explanation technique (LIME-SP).Results: Among 66 documented parameters, 15 factors with the highest predictive values were identified as follows: gender, age, blood urea nitrogen (BUN), creatinine, international normalized ratio (INR), albumin, mean corpuscular volume (MCV), white blood cell count, segmented neutrophil count, lymphocyte count, red cell distribution width (RDW), and mean cell hemoglobin (MCH) along with a history of neurological, cardiovascular, and respiratory disorders. Our RF model can predict patient outcomes with a sensitivity of 70% and a specificity of 75%. The performance of the models was confirmed by blindly testing the models in an external dataset.Conclusions: Using two independent patient datasets, we designed a machine-learning-based model that could predict the risk of mortality from severe COVID-19 with high accuracy. The most decisive variables in our model were increased levels of BUN, lowered albumin levels, increased creatinine, INR, and RDW, along with gender and age. Considering the importance of early triage decisions, this model can be a useful tool in COVID-19 ICU decision-making.

Download Full-text

Comparative Analysis of Two Machine Learning Algorithms in Predicting Site-Level Net Ecosystem Exchange in Major Biomes

Remote Sensing ◽

10.3390/rs13122242 ◽

2021 ◽

Vol 13 (12) ◽

pp. 2242

Author(s):

Jianzhao Liu ◽

Yunjiang Zuo ◽

Nannan Wang ◽

Fenghui Yuan ◽

Xinhao Zhu ◽

...

Keyword(s):

Machine Learning ◽

Learning Algorithms ◽

Substantial Reduction ◽

Model Performance ◽

Extreme Heat ◽

Machine Learning Algorithms ◽

Gradient Boosting ◽

Ecological Data ◽

Extreme Gradient Boosting ◽

The Impact

The net ecosystem CO2 exchange (NEE) is a critical parameter for quantifying terrestrial ecosystems and their contributions to the ongoing climate change. The accumulation of ecological data is calling for more advanced quantitative approaches for assisting NEE prediction. In this study, we applied two widely used machine learning algorithms, Random Forest (RF) and Extreme Gradient Boosting (XGBoost), to build models for simulating NEE in major biomes based on the FLUXNET dataset. Both models accurately predicted NEE in all biomes, while XGBoost had higher computational efficiency (6~62 times faster than RF). Among environmental variables, net solar radiation, soil water content, and soil temperature are the most important variables, while precipitation and wind speed are less important variables in simulating temporal variations of site-level NEE as shown by both models. Both models perform consistently well for extreme climate conditions. Extreme heat and dryness led to much worse model performance in grassland (extreme heat: R2 = 0.66~0.71, normal: R2 = 0.78~0.81; extreme dryness: R2 = 0.14~0.30, normal: R2 = 0.54~0.55), but the impact on forest is less (extreme heat: R2 = 0.50~0.78, normal: R2 = 0.59~0.87; extreme dryness: R2 = 0.86~0.90, normal: R2 = 0.81~0.85). Extreme wet condition did not change model performance in forest ecosystems (with R2 changing −0.03~0.03 compared with normal) but led to substantial reduction in model performance in cropland (with R2 decreasing 0.20~0.27 compared with normal). Extreme cold condition did not lead to much changes in model performance in forest and woody savannas (with R2 decreasing 0.01~0.08 and 0.09 compared with normal, respectively). Our study showed that both models need training samples at daily timesteps of >2.5 years to reach a good model performance and >5.4 years of daily samples to reach an optimal model performance. In summary, both RF and XGBoost are applicable machine learning algorithms for predicting ecosystem NEE, and XGBoost algorithm is more feasible than RF in terms of accuracy and efficiency.

Download Full-text

Redis-Based Messaging Queue and Cache-Enabled Parallel Processing Social Media Analytics Framework

The Computer Journal ◽

10.1093/comjnl/bxaa114 ◽

2020 ◽

Author(s):

Ravindra Kumar Singh ◽

Harsh Kumar Verma

Keyword(s):

Machine Learning ◽

Social Media ◽

Real Time ◽

Data Analytics ◽

Machine Learning Algorithms ◽

Gradient Boosting ◽

Support Vector ◽

Social Media Analytics ◽

Data Engineering ◽

Extreme Gradient Boosting

Abstract The extensive usage of social media polarity analysis claims the need for real-time analytics and runtime outcomes on dashboards. In data analytics, only 30% of the time is consumed in modeling and evaluation stages and 70% is consumed in data engineering tasks. There are lots of machine learning algorithms to achieve a desirable outcome in prediction points of view, but they lack in handling data and their transformation so-called data engineering tasks, and reducing its time remained still challenging. The contribution of this research paper is to encounter the mentioned challenges by presenting a parallelly, scalable, effective, responsive and fault-tolerant framework to perform end-to-end data analytics tasks in real-time and batch-processing manner. An experimental analysis on Twitter posts supported the claims and signifies the benefits of parallelism of data processing units. This research has highlighted the importance of processing mentioned URLs and embedded images along with post content to boost the prediction efficiency. Furthermore, this research additionally provided a comparison of naive Bayes, support vector machines, extreme gradient boosting and long short-term memory (LSTM) machine learning techniques for sentiment analysis on Twitter posts and concluded LSTM as the most effective technique in this regard.

Download Full-text

Machine-Learning-Based Prediction of Corrosion Behavior in Additively Manufactured Inconel 718

Data ◽

10.3390/data6080080 ◽

2021 ◽

Vol 6 (8) ◽

pp. 80

Author(s):

O. V. Mythreyi ◽

M. Rohith Srinivaas ◽

Tigga Amit Kumar ◽

R. Jayaganthan

Keyword(s):

Machine Learning ◽

Corrosion Behavior ◽

Inconel 718 ◽

Polynomial Regression ◽

Research Work ◽

Model Performance ◽

Machine Learning Algorithms ◽

Gradient Boosting ◽

Support Vector ◽

Extreme Gradient Boosting

This research work focuses on machine-learning-assisted prediction of the corrosion behavior of laser-powder-bed-fused (LPBF) and postprocessed Inconel 718. Corrosion testing data of these specimens were collected and fit into the following machine learning algorithms: polynomial regression, support vector regression, decision tree, and extreme gradient boosting. The model performance, after hyperparameter optimization, was evaluated using a set of established metrics: R2, mean absolute error, and root mean square error. Among the algorithms, the extreme gradient boosting algorithm performed best in predicting the corrosion behavior, closely followed by other algorithms. Feature importance analysis was executed in order to determine the postprocessing parameters that influenced the most the corrosion behavior in Inconel 718 manufactured by LPBF.

Download Full-text

An Interpretable Aid Decision-Making Model for Flag State Control Ship Detention Based on SMOTE and XGBoost

Journal of Marine Science and Engineering ◽

10.3390/jmse9020156 ◽

2021 ◽

Vol 9 (2) ◽

pp. 156

Author(s):

Jian He ◽

Yong Hao ◽

Xiaoqiong Wang

Keyword(s):

Machine Learning ◽

Decision Making ◽

Model Performance ◽

Machine Learning Algorithms ◽

Gradient Boosting ◽

Support Vector ◽

State Control ◽

Extreme Gradient Boosting ◽

Decision Making Model ◽

Flag State

The reasonable decision of ship detention plays a vital role in flag state control (FSC). Machine learning algorithms can be applied as aid tools for identifying ship detention. In this study, we propose a novel interpretable ship detention decision-making model based on machine learning, termed SMOTE-XGBoost-Ship detention model (SMO-XGB-SD), using the extreme gradient boosting (XGBoost) algorithm and the synthetic minority oversampling technique (SMOTE) algorithm to identify whether a ship should be detained. Our verification results show that the SMO-XGB-SD algorithm outperforms random forest (RF), support vector machine (SVM), and logistic regression (LR) algorithm. In addition, the new algorithm also provides a reasonable interpretation of model performance and highlights the most important features for identifying ship detention using the Shapley additive explanations (SHAP) algorithm. The SMO-XGB-SD model provides an effective basis for aiding decisions on ship detention by inland flag state control officers (FSCOs) and the ship safety management of ship operating companies, as well as training services for new FSCOs in maritime organizations.

Download Full-text

Forecasting US movies box office performances in Turkey using machine learning algorithms

Journal of Intelligent & Fuzzy Systems ◽

10.3233/jifs-189120 ◽

2020 ◽

Vol 39 (5) ◽

pp. 6579-6590

Author(s):

Sandy Çağlıyor ◽

Başar Öztayşi ◽

Selime Sezgin

Keyword(s):

Machine Learning ◽

Global Economy ◽

Learning Algorithms ◽

Forecast Model ◽

Machine Learning Algorithms ◽

Gradient Boosting ◽

High Stakes ◽

Box Office ◽

Industry Forecast ◽

The Impact

The motion picture industry is one of the largest industries worldwide and has significant importance in the global economy. Considering the high stakes and high risks in the industry, forecast models and decision support systems are gaining importance. Several attempts have been made to estimate the theatrical performance of a movie before or at the early stages of its release. Nevertheless, these models are mostly used for predicting domestic performances and the industry still struggles to predict box office performances in overseas markets. In this study, the aim is to design a forecast model using different machine learning algorithms to estimate the theatrical success of US movies in Turkey. From various sources, a dataset of 1559 movies is constructed. Firstly, independent variables are grouped as pre-release, distributor type, and international distribution based on their characteristic. The number of attendances is discretized into three classes. Four popular machine learning algorithms, artificial neural networks, decision tree regression and gradient boosting tree and random forest are employed, and the impact of each group is observed by compared by the performance models. Then the number of target classes is increased into five and eight and results are compared with the previously developed models in the literature.

Download Full-text

Predicting Future Occurrence of Acute Hypotensive Episodes Using Noninvasive and Invasive Features

Military Medicine ◽

10.1093/milmed/usaa418 ◽

2021 ◽

Vol 186 (Supplement_1) ◽

pp. 445-451

Author(s):

Yifei Sun ◽

Navid Rashedi ◽

Vikrant Vaze ◽

Parikshit Shah ◽

Ryan Halter ◽

...

Keyword(s):

Machine Learning ◽

Support Vector Machine ◽

Real World ◽

Short Term Memory ◽

Model Performance ◽

Learning Technologies ◽

Machine Learning Algorithms ◽

Support Vector ◽

K Nearest Neighbor ◽

Continuous Map

ABSTRACT Introduction Early prediction of the acute hypotensive episode (AHE) in critically ill patients has the potential to improve outcomes. In this study, we apply different machine learning algorithms to the MIMIC III Physionet dataset, containing more than 60,000 real-world intensive care unit records, to test commonly used machine learning technologies and compare their performances. Materials and Methods Five classification methods including K-nearest neighbor, logistic regression, support vector machine, random forest, and a deep learning method called long short-term memory are applied to predict an AHE 30 minutes in advance. An analysis comparing model performance when including versus excluding invasive features was conducted. To further study the pattern of the underlying mean arterial pressure (MAP), we apply a regression method to predict the continuous MAP values using linear regression over the next 60 minutes. Results Support vector machine yields the best performance in terms of recall (84%). Including the invasive features in the classification improves the performance significantly with both recall and precision increasing by more than 20 percentage points. We were able to predict the MAP with a root mean square error (a frequently used measure of the differences between the predicted values and the observed values) of 10 mmHg 60 minutes in the future. After converting continuous MAP predictions into AHE binary predictions, we achieve a 91% recall and 68% precision. In addition to predicting AHE, the MAP predictions provide clinically useful information regarding the timing and severity of the AHE occurrence. Conclusion We were able to predict AHE with precision and recall above 80% 30 minutes in advance with the large real-world dataset. The prediction of regression model can provide a more fine-grained, interpretable signal to practitioners. Model performance is improved by the inclusion of invasive features in predicting AHE, when compared to predicting the AHE based on only the available, restricted set of noninvasive technologies. This demonstrates the importance of exploring more noninvasive technologies for AHE prediction.

Download Full-text

Prediction of Healing Performance of Autogenous Healing Concrete Using Machine Learning

Materials ◽

10.3390/ma14154068 ◽

2021 ◽

Vol 14 (15) ◽

pp. 4068

Author(s):

Xu Huang ◽

Mirna Wasouf ◽

Jessada Sresakoolchai ◽

Sakdirat Kaewunruen

Keyword(s):

Machine Learning ◽

Search Algorithm ◽

Weather Conditions ◽

Prediction Performance ◽

Machine Learning Algorithms ◽

Coefficient Of Determination ◽

Gradient Boosting ◽

Support Vector ◽

Self Healing ◽

Artificial Neural Network Ann

Cracks typically develop in concrete due to shrinkage, loading actions, and weather conditions; and may occur anytime in its life span. Autogenous healing concrete is a type of self-healing concrete that can automatically heal cracks based on physical or chemical reactions in concrete matrix. It is imperative to investigate the healing performance that autogenous healing concrete possesses, to assess the extent of the cracking and to predict the extent of healing. In the research of self-healing concrete, testing the healing performance of concrete in a laboratory is costly, and a mass of instances may be needed to explore reliable concrete design. This study is thus the world’s first to establish six types of machine learning algorithms, which are capable of predicting the healing performance (HP) of self-healing concrete. These algorithms involve an artificial neural network (ANN), a k-nearest neighbours (kNN), a gradient boosting regression (GBR), a decision tree regression (DTR), a support vector regression (SVR) and a random forest (RF). Parameters of these algorithms are tuned utilising grid search algorithm (GSA) and genetic algorithm (GA). The prediction performance indicated by coefficient of determination (R2) and root mean square error (RMSE) measures of these algorithms are evaluated on the basis of 1417 data sets from the open literature. The results show that GSA-GBR performs higher prediction performance (R2GSA-GBR = 0.958) and stronger robustness (RMSEGSA-GBR = 0.202) than the other five types of algorithms employed to predict the healing performance of autogenous healing concrete. Therefore, reliable prediction accuracy of the healing performance and efficient assistance on the design of autogenous healing concrete can be achieved.

Download Full-text

Comparison of Ensemble Machine Learning Methods for Soil Erosion Pin Measurements

ISPRS International Journal of Geo-Information ◽

10.3390/ijgi10010042 ◽

2021 ◽

Vol 10 (1) ◽

pp. 42

Author(s):

Kieu Anh Nguyen ◽

Walter Chen ◽

Bor-Shiun Lin ◽

Uma Seeboonruang

Keyword(s):

Machine Learning ◽

Soil Erosion ◽

Ensemble Methods ◽

Machine Learning Algorithms ◽

Multivariate Adaptive Regression Splines ◽

Gradient Boosting ◽

Support Vector ◽

Ensemble Machine Learning ◽

Boosting Method ◽

Bagging Method

Although machine learning has been extensively used in various fields, it has only recently been applied to soil erosion pin modeling. To improve upon previous methods of quantifying soil erosion based on erosion pin measurements, this study explored the possible application of ensemble machine learning algorithms to the Shihmen Reservoir watershed in northern Taiwan. Three categories of ensemble methods were considered in this study: (a) Bagging, (b) boosting, and (c) stacking. The bagging method in this study refers to bagged multivariate adaptive regression splines (bagged MARS) and random forest (RF), and the boosting method includes Cubist and gradient boosting machine (GBM). Finally, the stacking method is an ensemble method that uses a meta-model to combine the predictions of base models. This study used RF and GBM as the meta-models, decision tree, linear regression, artificial neural network, and support vector machine as the base models. The dataset used in this study was sampled using stratified random sampling to achieve a 70/30 split for the training and test data, and the process was repeated three times. The performance of six ensemble methods in three categories was analyzed based on the average of three attempts. It was found that GBM performed the best among the ensemble models with the lowest root-mean-square error (RMSE = 1.72 mm/year), the highest Nash-Sutcliffe efficiency (NSE = 0.54), and the highest index of agreement (d = 0.81). This result was confirmed by the spatial comparison of the absolute differences (errors) between model predictions and observations using GBM and RF in the study area. In summary, the results show that as a group, the bagging method and the boosting method performed equally well, and the stacking method was third for the erosion pin dataset considered in this study.

Download Full-text