Dataset Information

Modeling Evaluations of Low-Level Sounds in Everyday Situations Using Linear Machine Learning for Variable Selection.

ABSTRACT: Human sound evaluations not only depend on the characteristics of the sound but are also driven by factors related to the listener and the situation. Our research aimed to investigate crucial factors influencing the perception of low-level sounds as they-in addition to the often-researched loud-level sounds-might be decisive to people's quality of life and health. We conducted an online study in which 1,301 participants reported on up to three everyday situations in which they perceived low-level sounds, resulting in a total of 2,800 listening situations. Participants rated the sounds' perceived loudness, timbre, and tonality. Additionally, they described the listening situations employing situational eight dimensions and reported their affective states. All sounds were then assigned to the categories natural, human, and technical. Linear models suggest a significant difference of annoyance ratings across sound categories for binary loudness levels. The ability to mentally fade-out sound was the most crucial situational variable after valence, arousal, and the situation dimensions positivity and negativity. We ultimately selected the most important factors from a large number of independent variables by applying the percentile least absolute shrinkage and selection operator (Lasso) regularization method. The resulting linear regression showed that this novel machine-learning variable-selection technique is applicable in hypothesis testing of noise effects and soundscape research. The typical problems of overfitting and multicollinearity that occur when many situational and personal variables are involved were overcome. This study provides an extensive database of evaluated everyday sounds and listening situations, offering an enormous test power. Our machine learning approach, whose application leads to comprehensive models for the prediction of sound perception, is available for future study designs aiming to model sound perception and evaluation.

SUBMITTER: Versumer S

PROVIDER: S-EPMC7644977 | biostudies-literature | 2020

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Modeling Evaluations of Low-Level Sounds in Everyday Situations Using Linear Machine Learning for Variable Selection.

Versümer Siegbert S Steffens Jochen J Blättermann Patrick P Becker-Schweitzer Jörg J

Frontiers in psychology 20201023

Human sound evaluations not only depend on the characteristics of the sound but are also driven by factors related to the listener and the situation. Our research aimed to investigate crucial factors influencing the perception of low-level sounds as they-in addition to the often-researched loud-level sounds-might be decisive to people's quality of life and health. We conducted an online study in which 1,301 participants reported on up to three everyday situations in which they perceived low-leve ...[more]

PMID: 33192862

Similar Datasets

Project description:Many countries have attempted to mitigate and manage issues related to harmful algal blooms (HABs) by monitoring and predicting their occurrence. The infrequency and duration of HABs occurrence pose the challenge of data imbalance when constructing machine learning models for their prediction. Furthermore, the appropriate selection of input variables is a significant issue because of the complexities between the input and output variables. Therefore, the objective of this study was to improve the predictive performance of HABs using feature selection and data resampling. Data resampling was used to address the imbalance in the minority class data. Two machine learning models were constructed to predict algal alert levels using 10 years of meteorological, hydrodynamic, and water quality data. The improvement in model accuracy due to changes in resampling methods was more noticeable than the improvement in model accuracy due to changes in feature selection methods. Models constructed using combinations of original and synthetic data across all resampling methods demonstrated higher prediction performance for the caution level (L-1) and warning level (L-2) than models constructed using the original data. In particular, the optimal artificial neural network and random forest models constructed using combinations of original and synthetic data showed significantly improved prediction accuracy for L-1 and L-2, representing the transition from normal to bloom formation states in the training and testing steps. The test results of the optimal RF model using the original data indicated prediction accuracies of 98.8% for L0, 50.0% for L1, and 50.0% for L2. In contrast, the optimal random forest model using the Synthetic Minority Oversampling Technique-Edited Nearest Neighbor (ENN) sampling method achieved accuracies of 85.0% for L0, 85.7% for L1, and 100% for L2. Therefore, applying synthetic data can address the imbalance in the observed data and improve the detection performance of machine learning models. Reliable predictions using improved models can support the design of management practices to mitigate HABs in reservoirs and ultimately ensure safe and clean water resources.

Project description:Given the need for knowledge on the restorative potential of urban settings, we sought to estimate the effects of personal and contextual factors on preferences and restoration likelihood assessments for different urban activities-in-environments. We also sought to study the generality of these effects across different countries.We conducted a true experiment with convenience samples of university students in the Netherlands (n = 80), Sweden (n = 100), and the USA (n = 316). In each country, the experiment had a mixed design with activities-in-environments (sitting in a park, sitting in a cafe, walking in a shopping mall, walking along a busy street) manipulated within-subjects and the need for restoration (attentional fatigue, no attentional fatigue) and immediate social context (in company, alone) manipulated between-subjects. The manipulations relied on previously tested scenarios describing everyday situations that participants were instructed to remember and imagine themselves being in. For each imagined situation (activity-in-environment with antecedent fatigue condition and immediate social context), subjects provided two criterion measures: general preference and the likelihood of achieving psychological restoration.The settings received different preference and restoration likelihood ratings as expected, affirming that a busy street, often used in comparisons with natural settings, is not representative of the restorative potential of urban settings. Being with a close friend and attentional fatigue both moderated ratings for specific settings. Findings of additional moderation by country of residence caution against broad generalizations regarding preferences for and the expected restorative effects of different urban settings.Preferences and restoration likelihood ratings for urban activity-environment combinations are subject to multiple personal and contextual determinants, including level of attentional fatigue, being alone versus in company, and broader aspects of the urban context that vary across cities and countries. Claims regarding a lack of restorative quality in urban environments are problematic.

Dataset Information

Modeling Evaluations of Low-Level Sounds in Everyday Situations Using Linear Machine Learning for Variable Selection.

Publications

Modeling Evaluations of Low-Level Sounds in Everyday Situations Using Linear Machine Learning for Variable Selection.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets