Adaptive Personalized Multiple Machine Learning Architecture for Estimating Human Emotional States

2020 ◽  
Vol 24 (5) ◽  
pp. 668-675
Author(s):  
Akihiro Matsufuji ◽  
◽  
Eri Sato-Shimokawara ◽  
Toru Yamaguchi
Keyword(s):  
Machine Learning ◽  
Individual Differences ◽  
Internal State ◽  
Weighted Average ◽  
Learning System ◽  
Emotional States ◽  
Characteristic Model ◽  
Ensemble Machine Learning ◽  
Model Training ◽  
Future Education

Robots have the potential to facilitate the future education of all generations, particularly children. However, existing robots are limited in their ability to automatically perceive and respond to a human emotional states. We hypothesize that these sophisticated models suffer from individual differences in human personality. Therefore, we proposed a multi-characteristic model architecture that combines personalized machine learning models and utilizes the prediction score of each model. This architecture is formed with reference to an ensemble machine learning architecture. In this study, we presented a method for calculating the weighted average in a multi-characteristic architecture by using the similarities between a new sample and the trained characteristics. We estimated the degree of confidence during a communication as a human internal state. Empirical results demonstrate that using the multi-model training of each person’s information to account for individual differences provides improvements over a traditional machine learning system and insight into dealing with various individual differences.

scholarly journals Predicting Emotional States Using Behavioral Markers Derived From Passively Sensed Data: Data-Driven Machine Learning Approach

10.2196/24465 ◽  
2021 ◽  
Vol 9 (3) ◽  
pp. e24465
Author(s):  
Emese Sükei ◽  
Agnes Norbury ◽  
M Mercedes Perez-Rodriguez ◽  
Pablo M Olmos ◽  
Antonio Artés
Keyword(s):  
Mental Health ◽  
Machine Learning ◽  
Time Series ◽  
Individual Differences ◽  
Emotional State ◽  
Series Data ◽  
Emotional States ◽  
Missing Observations ◽  
State Prediction ◽  
Behavioral Markers

Background Mental health disorders affect multiple aspects of patients’ lives, including mood, cognition, and behavior. eHealth and mobile health (mHealth) technologies enable rich sets of information to be collected noninvasively, representing a promising opportunity to construct behavioral markers of mental health. Combining such data with self-reported information about psychological symptoms may provide a more comprehensive and contextualized view of a patient’s mental state than questionnaire data alone. However, mobile sensed data are usually noisy and incomplete, with significant amounts of missing observations. Therefore, recognizing the clinical potential of mHealth tools depends critically on developing methods to cope with such data issues. Objective This study aims to present a machine learning–based approach for emotional state prediction that uses passively collected data from mobile phones and wearable devices and self-reported emotions. The proposed methods must cope with high-dimensional and heterogeneous time-series data with a large percentage of missing observations. Methods Passively sensed behavior and self-reported emotional state data from a cohort of 943 individuals (outpatients recruited from community clinics) were available for analysis. All patients had at least 30 days’ worth of naturally occurring behavior observations, including information about physical activity, geolocation, sleep, and smartphone app use. These regularly sampled but frequently missing and heterogeneous time series were analyzed with the following probabilistic latent variable models for data averaging and feature extraction: mixture model (MM) and hidden Markov model (HMM). The extracted features were then combined with a classifier to predict emotional state. A variety of classical machine learning methods and recurrent neural networks were compared. Finally, a personalized Bayesian model was proposed to improve performance by considering the individual differences in the data and applying a different classifier bias term for each patient. Results Probabilistic generative models proved to be good preprocessing and feature extractor tools for data with large percentages of missing observations. Models that took into account the posterior probabilities of the MM and HMM latent states outperformed those that did not by more than 20%, suggesting that the underlying behavioral patterns identified were meaningful for individuals’ overall emotional state. The best performing generalized models achieved a 0.81 area under the curve of the receiver operating characteristic and 0.71 area under the precision-recall curve when predicting self-reported emotional valence from behavior in held-out test data. Moreover, the proposed personalized models demonstrated that accounting for individual differences through a simple hierarchical model can substantially improve emotional state prediction performance without relying on previous days’ data. Conclusions These findings demonstrate the feasibility of designing machine learning models for predicting emotional states from mobile sensing data capable of dealing with heterogeneous data with large numbers of missing observations. Such models may represent valuable tools for clinicians to monitor patients’ mood states.

scholarly journals Study of power demand forecasting of a hospital by ensemble machine learning

2021 ◽  
Vol 2069 (1) ◽  
pp. 012147
Author(s):  
Mayuka Nakai ◽  
Ryozo Ooka ◽  
Shintaro Ikeda
Keyword(s):  
Machine Learning ◽  
Power Consumption ◽  
Measurement Errors ◽  
Learning Algorithm ◽  
Demand Forecasting ◽  
Weighted Average ◽  
Power Demand ◽  
Efficient Operation ◽  
Ensemble Machine Learning ◽  
Save Energy

Abstract To save energy in existing buildings, power demand can be predicted so a more efficient operation of equipment can be realized, like utilizing heat storage to lower the peak. Many attempts to predict building power consumption by machine learning have used simulation values in virtual buildings with no measurement errors or defects in the data. These models tend to have higher accuracy scores but have the risk of overfitting and possibly malfunction for missing data or outliers. To avoid the problems, this study proposes an ensemble machine learning algorithm to forecast power demand for a hospital building in Japan. Using the power consumption data, predictions were made by using algorithms such as Deep Neural Network (DNN) and Random Forest (RF). Each algorithm was combined to create ensemble models that take the weighted average of the predicted values. Consequently, we overcame the issues of each individual method, and achieved higher prediction accuracies. We selected the appropriate method for forecasting the power demand of real buildings based on accuracy. In future studies, we will apply the same methodology to predict cooling load.

scholarly journals Ensemble Machine Learning Assisted Reservoir Characterization Using Field Production Data–An Offshore Field Case Study

Energies ◽  
2021 ◽  
Vol 14 (4) ◽  
pp. 1052
Author(s):  
Baozhong Wang ◽  
Jyotsna Sharma ◽  
Jianhua Chen ◽  
Patricia Persaud
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Reservoir Characterization ◽  
Time Lapse ◽  
Production Data ◽  
Oil Saturation ◽  
Ensemble Machine Learning ◽  
Input Parameters ◽  
Saturation Profiles ◽  
Field Production

Estimation of fluid saturation is an important step in dynamic reservoir characterization. Machine learning techniques have been increasingly used in recent years for reservoir saturation prediction workflows. However, most of these studies require input parameters derived from cores, petrophysical logs, or seismic data, which may not always be readily available. Additionally, very few studies incorporate the production data, which is an important reflection of the dynamic reservoir properties and also typically the most frequently and reliably measured quantity throughout the life of a field. In this research, the random forest ensemble machine learning algorithm is implemented that uses the field-wide production and injection data (both measured at the surface) as the only input parameters to predict the time-lapse oil saturation profiles at well locations. The algorithm is optimized using feature selection based on feature importance score and Pearson correlation coefficient, in combination with geophysical domain-knowledge. The workflow is demonstrated using the actual field data from a structurally complex, heterogeneous, and heavily faulted offshore reservoir. The random forest model captures the trends from three and a half years of historical field production, injection, and simulated saturation data to predict future time-lapse oil saturation profiles at four deviated well locations with over 90% R-square, less than 6% Root Mean Square Error, and less than 7% Mean Absolute Percentage Error, in each case.

Machine-learning algorithm as a prognostic tool in non-obstructive acute-on-chronic kidney disease in the cat

2021 ◽  
pp. 1098612X2110012
Author(s):  
Jade Renard ◽  
Mathieu R Faucher ◽  
Anaïs Combes ◽  
Didier Concordet ◽  
Brice S Reynolds
Keyword(s):  
Machine Learning ◽  
Chronic Kidney Disease ◽  
Kidney Disease ◽  
Decision Tree ◽  
Diagnostic Performance ◽  
Clinical Signs ◽  
Learning System ◽  
Clinical Severity ◽  
Medium Term ◽  
Term Survival

Objectives The aim of this study was to develop an algorithm capable of predicting short- and medium-term survival in cases of intrinsic acute-on-chronic kidney disease (ACKD) in cats. Methods The medical record database was searched to identify cats hospitalised for acute clinical signs and azotaemia of at least 48 h duration and diagnosed to have underlying chronic kidney disease based on ultrasonographic renal abnormalities or previously documented azotaemia. Cases with postrenal azotaemia, exposure to nephrotoxicants, feline infectious peritonitis or neoplasia were excluded. Clinical variables were combined in a clinical severity score (CSS). Clinicopathological and ultrasonographic variables were also collected. The following variables were tested as inputs in a machine learning system: age, body weight (BW), CSS, identification of small kidneys or nephroliths by ultrasonography, serum creatinine at 48 h (Crea48), spontaneous feeding at 48 h (SpF48) and aetiology. Outputs were outcomes at 7, 30, 90 and 180 days. The machine-learning system was trained to develop decision tree algorithms capable of predicting outputs from inputs. Finally, the diagnostic performance of the algorithms was calculated. Results Crea48 was the best predictor of survival at 7 days (threshold 1043 µmol/l, sensitivity 0.96, specificity 0.53), 30 days (threshold 566 µmol/l, sensitivity 0.70, specificity 0.89) and 90 days (threshold 566 µmol/l, sensitivity 0.76, specificity 0.80), with fewer cats still alive when their Crea48 was above these thresholds. A short decision tree, including age and Crea48, predicted the 180-day outcome best. When Crea48 was excluded from the analysis, the generated decision trees included CSS, age, BW, SpF48 and identification of small kidneys with an overall diagnostic performance similar to that using Crea48. Conclusions and relevance Crea48 helps predict short- and medium-term survival in cats with ACKD. Secondary variables that helped predict outcomes were age, CSS, BW, SpF48 and identification of small kidneys.

Sign in / Sign up

Export Citation Format

Share Document