Machine learning method predicting thermal performance of conformal cooling systems
Ontology highlight
ABSTRACT:
SUBMITTER: Zhao Z
PROVIDER: S-EPMC11343755 | biostudies-literature | 2024 Jan
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:The escalating global climate crisis and energy challenges have made the development of efficient radiative cooling materials increasingly urgent. This study presents a machine-learning-based model for predicting the performance of radiative cooling aerogels (RCAs). The model integrated multiple parameters, including the material composition (matrix material type and proportions), modification design (modifier type and content), optical properties (solar reflectance and infrared emissivity), and environmental factors (solar irradiance and ambient temperature) to achieve accurate cooling performance predictions. A comparative analysis of various machine learning algorithms revealed that an optimized XGBoost model demonstrated superior predictive performance, achieving an R2 value of 0.943 and an RMSE of 1.423 for the test dataset. An interpretability analysis using Shapley additive explanations (SHAPs) identified a ZnO modifier (SHAP value, 1.523) and environmental parameters (ambient temperature, 1.299; solar irradiance, 0.979) as the most significant determinants of cooling performance. A feature interaction analysis further elucidated the complex interplay between the material composition and environmental conditions, providing theoretical guidance for material optimization.
| S-EPMC11765191 | biostudies-literature
Project description:Proactive detection of hemodynamic shock can prevent organ failure and save lives. Thermal imaging is a non-invasive, non-contact modality to capture body surface temperature with the potential to reveal underlying perfusion disturbance in shock. In this study, we automate early detection and prediction of shock using machine learning upon thermal images obtained in a pediatric intensive care unit of a tertiary care hospital. 539 images were recorded out of which 253 had concomitant measurement of continuous intra-arterial blood pressure, the gold standard for shock monitoring. Histogram of oriented gradient features were used for machine learning based region-of-interest segmentation that achieved 96% agreement with a human expert. The segmented center-to-periphery difference along with pulse rate was used in longitudinal prediction of shock at 0, 3, 6 and 12 hours using a generalized linear mixed-effects model. The model achieved a mean area under the receiver operating characteristic curve of 75% at 0 hours (classification), 77% at 3 hours (prediction) and 69% at 12 hours (prediction) respectively. Since hemodynamic shock associated with critical illness and infectious epidemics such as Dengue is often fatal, our model demonstrates an affordable, non-invasive, non-contact and tele-diagnostic decision support system for its reliable detection and prediction.
| S-EPMC6331545 | biostudies-literature
Project description:Chromatin interactions play important roles in regulating gene expression. However, the availability of genome-wide chromatin interaction data is limited. Various computational methods have been developed to predict chromatin interactions. Most of these methods rely on large collections of ChIP-Seq/RNA-Seq/DNase-Seq datasets and predict only enhancer-promoter interactions. Some of the ‘state-of-the-art’ methods have poor experimental designs, leading to over-exaggerated performances and misleading conclusions. Here we developed a computational method, Chromatin Interaction Neural Network (CHINN), to predict chromatin interactions between open chromatin regions by using only DNA sequences of the interacting open chromatin regions. CHINN is able to predict CTCF-, RNA polymerase II- and HiC-associated chromatin interactions between open chromatin regions. CHINN also shows good across-sample performances and captures various sequence features that are predictive of chromatin interactions. We applied CHINN to 90 chronic lymphocytic leukemia (CLL) samples and detected systematic differences in the chromatin interactome between IGVH-mutated and IGVH-unmutated CLL samples.
2021-07-09 | GSE163896 | GEO
Project description:Thermal boundary resistance (TBR) is a key property for the thermal management of high power micro- and opto-electronic devices and for the development of high efficiency thermal barrier coatings and thermoelectric materials. Prediction of TBR is important for guiding the discovery of interfaces with very low or very high TBR. In this study, we report the prediction of TBR by the machine learning method. We trained machine learning models using the collected experimental TBR data as training data and materials properties that might affect TBR as descriptors. We found that the machine learning models have much better predictive accuracy than the commonly used acoustic mismatch model and diffuse mismatch model. Among the trained models, the Gaussian process regression and the support vector regression models have better predictive accuracy. Also, by comparing the prediction results using different descriptor sets, we found that the film thickness is an important descriptor in the prediction of TBR. These results indicate that machine learning is an accurate and cost-effective method for the prediction of TBR.
| S-EPMC5540921 | biostudies-literature
Project description:Interfacial thermal resistance (ITR) is a critical property for the performance of nanostructured devices where phonon mean free paths are larger than the characteristic length scales. The affordable, accurate and reliable prediction of ITR is essential for material selection in thermal management. In this work, the state-of-the-art machine learning methods were employed to realize this. Descriptor selection was conducted to build robust models and provide guidelines on determining the most important characteristics for targets. Firstly, decision tree (DT) was adopted to calculate the descriptor importances. And descriptor subsets with topX highest importances were chosen (topX-DT, X = 20, 15, 10, 5) to build models. To verify the transferability of the descriptors picked by decision tree, models based on kernel ridge regression, Gaussian process regression and K-nearest neighbors were also evaluated. Afterwards, univariate selection (UV) was utilized to sort descriptors. Finally, the top5 common descriptors selected by DT and UV were used to build concise models. The performance of these refined models is comparable to models using all descriptors, which indicates the high accuracy and reliability of these selection methods. Our strategy results in concise machine learning models for a fast prediction of ITR for thermal management applications.
| S-EPMC7804206 | biostudies-literature
Project description:Although cities have risen to prominence as climate actors, emissions' data scarcity has been the primary challenge to evaluating their performance. Here we develop a scalable, replicable machine learning approach for evaluating the mitigation performance for nearly all local administrative areas in Europe from 2001-2018. By combining publicly available, spatially explicit environmental and socio-economic data with self-reported emissions data from European cities, we predict annual carbon dioxide emissions to explore trends in city-scale mitigation performance. We find that European cities participating in transnational climate initiatives have likely decreased emissions since 2001, with slightly more than half likely to have achieved their 2020 emissions reduction target. Cities who report emissions data are more likely to have achieved greater reductions than those who fail to report any data. Despite its limitations, our model provides a replicable, scalable starting point for understanding city-level climate emissions mitigation performance.
| S-EPMC9723121 | biostudies-literature
Project description: Not available
| S-EPMC11041458 | biostudies-literature
Project description:Predicting the dynamics of chaotic systems is crucial across various practical domains, including the control of infectious diseases and responses to extreme weather events. Such predictions provide quantitative insights into the future behaviors of these complex systems, thereby guiding the decision-making and planning within the respective fields. Recently, data-driven approaches, renowned for their capacity to learn from empirical data, have been widely used to predict chaotic system dynamics. However, these methods rely solely on historical observations while ignoring the underlying mechanisms that govern the systems' behaviors. Consequently, they may perform well in short-term predictions by effectively fitting the data, but their ability to make accurate long-term predictions is limited. A critical challenge in modeling chaotic systems lies in their sensitivity to initial conditions; even a slight variation can lead to significant divergence in actual and predicted trajectories over a finite number of time steps. In this paper, we propose a novel Physics-Guided Learning (PGL) method, aiming at extending the scope of accurate forecasting as much as possible. The proposed method aims to synergize observational data with the governing physical laws of chaotic systems to predict the systems' future dynamics. Specifically, our method consists of three key elements: a data-driven component (DDC) that captures dynamic patterns and mapping functions from historical data; a physics-guided component (PGC) that leverages the governing principles of the system to inform and constrain the learning process; and a nonlinear learning component (NLC) that effectively synthesizes the outputs of both the data-driven and physics-guided components. Empirical validation on six dynamical systems, each exhibiting unique chaotic behaviors, demonstrates that PGL achieves lower prediction errors than existing benchmark predictive models. The results highlight the efficacy of our design of data-physics integration in improving the precision of chaotic system dynamics forecasts.
| S-EPMC11782262 | biostudies-literature
Project description:Machine learning and genomic medicine are the mainstays of research in delivering personalized healthcare services for disease diagnosis, risk stratification, tailored treatment, and prediction of adverse effects. However, potential prediction errors in healthcare services can have life-threatening impact, raising reasonable skepticism about whether these applications have practical benefit in clinical settings. Conformal prediction offers a versatile framework for addressing these concerns by quantifying the uncertainty of predictive models. In this perspective review, we investigate potential applications of conformalized models in genomic medicine and discuss the challenges towards bridging genomic medicine applications with clinical practice. We also demonstrate the impact of a binary transductive model and a regression-based inductive model in predicting drug response as well as the performance of a multi-class inductive predictor in addressing distribution shifts in molecular subtyping. The main conclusion is that as machine learning and genomic medicine are increasingly infiltrating healthcare services, conformal prediction has the potential to overcome the safety limitations of current methods and could be effectively integrated into uncertainty-informed applications within clinical environments.
| S-EPMC11891349 | biostudies-literature
Project description:Humans are exposed to thousands of chemicals, including environmental chemicals. Unfortunately, little is known about their potential toxicity, as determining the toxicity remains challenging due to the substantial resources required to assess a chemical in vivo. Here, we present a novel hybrid neural network (HNN) deep learning method, called HNN-Tox, to predict chemical toxicity at different doses. To develop a hybrid HNN-Tox method, we combined two neural network frameworks, the Convolutional Neural Network (CNN) and the multilayer perceptron (MLP)-type feed-forward neural network (FFNN). Combining the CNN and FCNN in the field of environmental chemical toxicity prediction is a novel approach. We developed several binary and multiclass classification models to assess dose-range chemical toxicity that is trained based on thousands of chemicals with known toxicity. The performance of the HNN-Tox was compared with other machine-learning methods, including Random Forest (RF), Bootstrap Aggregation (Bagging), and Adaptive Boosting (AdaBoost). We also analyzed the model performance dependency on varying features, descriptors, dataset size, route of exposure, and toxic dose. The HNN-Tox model, trained on 59,373 chemicals annotated with known LD50 and routes of exposure, maintained its predictive ability with an accuracy of 84.9% and 84.1%, even after reducing the descriptor size from 318 to 51, and the area under the ROC curve (AUC) was 0.89 and 0.88, respectively. Further, we validated the HNN-Tox with several external toxic chemical datasets on a large scale. The HNN-Tox performed optimally or better than the other machine-learning methods for diverse chemicals. This study is the first to report a large-scale prediction of dose-range chemical toxicity with varying features. The HNN-Tox has broad applicability in predicting toxicity for diverse chemicals and could serve as an alternative methodology approach to animal-based toxicity assessment.
| S-EPMC9692315 | biostudies-literature