Comparison of Machine Learning Models on Performance of Single- and Dual-Type Electrochromic Devices.
Ontology highlight
ABSTRACT:
SUBMITTER: Gok EC
PROVIDER: S-EPMC7495761 | biostudies-literature | 2020 Sep
REPOSITORIES: biostudies-literature
Publications
Comparison of Machine Learning Models on Performance of Single- and Dual-Type Electrochromic Devices.
Gok Elif Ceren EC Yildirim Murat Onur MO Eren Esin E Oksuz Aysegul Uygun AU
ACS omega 20200831 36
This study shows that the model fitting based on machine learning (ML) from experimental data can successfully predict the electrochromic characteristics of single- and dual-type flexible electrochromic devices (ECDs) by using tungsten trioxide (WO<sub>3</sub>) and WO<sub>3</sub>/vanadium pentoxide (V<sub>2</sub>O<sub>5</sub>), respectively. Seven different regression methods were used for experimental observations, which belong to single and dual ECDs where 80% percent was used as training data ...[more]
Similar Datasets
Project description:MXene, a 2D material, is used as a filler to manufacture polymer electrolytes with high ionic conductivity because of its unique sheet shape, large specific surface area and high aspect ratio. Because MXene has numerous -OH groups on its surface, it can cause dehydration and condensation reactions with poly(4-styrenesulfonic acid) (PSSA) and consequently create pathways for the conduction of cations. The movement of Grotthuss-type hydrogen ions along the cation-conduction pathway is promoted and a high ionic conductivity can be obtained. In addition, when electrolytes composed of a conventional acid or metal salt alone is applied to an electrochromic device (ECD), it does not bring out fast response time, high coloration efficiency and transmittance contrast simultaneously. Therefore, dual-cation electrolytes are designed for high-performance ECDs. Bis(trifluoromethylsulfonyl)amine lithium salt (LiTFSI) was used as a source of lithium ions and PSSA crosslinked with MXene was used as a source of protons. Dual-Cation electrolytes crosslinked with MXene was applied to an indium tin oxide-free, all-solution-processable ECD. The effect of applying the electrolyte to the device was verified in terms of response time, coloration efficiency and transmittance contrast. The ECD with a size of 5 × 5 cm2 showed a high transmittance contrast of 66.7%, fast response time (8 s/15 s) and high coloration efficiency of 340.6 cm2/C.
| S-EPMC8065717 | biostudies-literature
Project description:The spread of Covid-19 has resulted in worldwide health concerns. Social media is increasingly used to share news and opinions about it. A realistic assessment of the situation is necessary to utilize resources optimally and appropriately. In this research, we perform Covid-19 tweets sentiment analysis using a supervised machine learning approach. Identification of Covid-19 sentiments from tweets would allow informed decisions for better handling the current pandemic situation. The used dataset is extracted from Twitter using IDs as provided by the IEEE data port. Tweets are extracted by an in-house built crawler that uses the Tweepy library. The dataset is cleaned using the preprocessing techniques and sentiments are extracted using the TextBlob library. The contribution of this work is the performance evaluation of various machine learning classifiers using our proposed feature set. This set is formed by concatenating the bag-of-words and the term frequency-inverse document frequency. Tweets are classified as positive, neutral, or negative. Performance of classifiers is evaluated on the accuracy, precision, recall, and F1 score. For completeness, further investigation is made on the dataset using the Long Short-Term Memory (LSTM) architecture of the deep learning model. The results show that Extra Trees Classifiers outperform all other models by achieving a 0.93 accuracy score using our proposed concatenated features set. The LSTM achieves low accuracy as compared to machine learning classifiers. To demonstrate the effectiveness of our proposed feature set, the results are compared with the Vader sentiment analysis technique based on the GloVe feature extraction approach.
| S-EPMC7906356 | biostudies-literature
Project description:The androgen receptor (AR) is a target of interest for endocrine disruption research, as altered signaling can affect normal reproductive and neurological development for generations. In an effort to prioritize compounds with alternative methodologies, the U.S. Environmental Protection Agency (EPA) used in vitro data from 11 assays to construct models of AR agonist and antagonist signaling pathways. While these EPA ToxCast AR models require in vitro data to assign a bioactivity score, Bayesian machine learning methods can be used for prospective prediction from molecule structure alone. This approach was applied to multiple types of data corresponding to the EPA's AR signaling pathway with proprietary software, Assay Central. The training performance of all machine learning models, including six other algorithms, was evaluated by internal 5-fold cross-validation statistics. Bayesian machine learning models were also evaluated with external predictions of reference chemicals to compare prediction accuracies to published results from the EPA. The machine learning model group selected for further studies of endocrine disruption consisted of continuous AC50 data from the February 2019 release of ToxCast/Tox21. These efforts demonstrate how machine learning can be used to predict AR-mediated bioactivity and can also be applied to other targets of endocrine disruption.
| S-EPMC8243727 | biostudies-literature
Project description:Transcriptome prediction methods such as PrediXcan and FUSION have become popular in complex trait mapping. Most transcriptome prediction models have been trained in European populations using methods that make parametric linear assumptions like the elastic net (EN). To potentially further optimize imputation performance of gene expression across global populations, we built transcriptome prediction models using both linear and non-linear machine learning (ML) algorithms and evaluated their performance in comparison to EN. We trained models using genotype and blood monocyte transcriptome data from the Multi-Ethnic Study of Atherosclerosis (MESA) comprising individuals of African, Hispanic, and European ancestries and tested them using genotype and whole-blood transcriptome data from the Modeling the Epidemiology Transition Study (METS) comprising individuals of African ancestries. We show that the prediction performance is highest when the training and the testing population share similar ancestries regardless of the prediction algorithm used. While EN generally outperformed random forest (RF), support vector regression (SVR), and K nearest neighbor (KNN), we found that RF outperformed EN for some genes, particularly between disparate ancestries, suggesting potential robustness and reduced variability of RF imputation performance across global populations. When applied to a high-density lipoprotein (HDL) phenotype, we show including RF prediction models in PrediXcan revealed potential gene associations missed by EN models. Therefore, by integrating other ML modeling into PrediXcan and diversifying our training populations to include more global ancestries, we may uncover new genes associated with complex traits.
| S-EPMC8087249 | biostudies-literature
Project description:ObjectiveTo compare machine learning methods for predicting inpatient seizures risk and determine the feasibility of 1-h screening EEG to identify low-risk patients (<5% seizures risk in 48 h).MethodsThe Critical Care EEG Monitoring Research Consortium (CCEMRC) multicenter database contains 7716 continuous EEGs (cEEG). Neural networks (NN), elastic net logistic regression (EN), and sparse linear integer model (RiskSLIM) were trained to predict seizures. RiskSLIM was used previously to generate 2HELPS2B model of seizure predictions. Data were divided into training (60% for model fitting) and evaluation (40% for model evaluation) cohorts. Performance was measured using area under the receiver operating curve (AUC), mean risk calibration (CAL), and negative predictive value (NPV). A secondary analysis was performed using Monte Carlo simulation (MCS) to normalize all EEG recordings to 48 h and use only the first hour of EEG as a "screening EEG" to generate predictions.ResultsRiskSLIM recreated the 2HELPS2B model. All models had comparable AUC: evaluation cohort (NN: 0.85, EN: 0.84, 2HELPS2B: 0.83) and MCS (NN: 0.82, EN; 0.82, 2HELPS2B: 0.81) and NPV (absence of seizures in the group that the models predicted to be low risk): evaluation cohort (NN: 97%, EN: 97%, 2HELPS2B: 97%) and MCS (NN: 97%, EN: 99%, 2HELPS2B: 97%). 2HELPS2B model was able to identify the largest proportion of low-risk patients.InterpretationFor seizure risk stratification of hospitalized patients, the RiskSLIM generated 2HELPS2B model compares favorably to the complex NN and EN generated models. 2HELPS2B is able to accurately and quickly identify low-risk patients with only a 1-h screening EEG.
| S-EPMC6649418 | biostudies-literature
Project description:Graphene emerges as a viable material for optoelectronics because of its broad optical response and gate-tunable properties. For practical applications, however, single layer graphene has performance limits due to its small optical absorption defined by fundamental constants. Here, we demonstrated a new class of flexible electrochromic devices using multilayer graphene (MLG) which simultaneously offers all key requirements for practical applications; high-contrast optical modulation over a broad spectrum, good electrical conductivity and mechanical flexibility. Our method relies on electro-modulation of interband transition of MLG via intercalation of ions into the graphene layers. The electrical and optical characterizations reveal the key features of the intercalation process which yields broadband optical modulation up to 55 per cent in the visible and near-infrared. We illustrate the promises of the method by fabricating reflective/transmissive electrochromic devices and multi-pixel display devices. Simplicity of the device architecture and its compatibility with the roll-to-roll fabrication processes, would find wide range of applications including smart windows and display devices. We anticipate that this work provides a significant step in realization of graphene based optoelectronics.
| S-EPMC4180825 | biostudies-other
Project description:BackgroundMachine learning may be a useful tool for predicting metabolic syndrome (MetS), and previous studies also suggest that the risk of MetS differs according to Sasang constitution type. The present study investigated the development of MetS prediction models utilizing machine learning methods and whether the incorporation of Sasang constitution type could improve the performance of those prediction models.MethodsParticipants visiting a medical center for a health check-up were recruited in 2005 and 2006. Six kinds of machine learning were utilized (K-nearest neighbor, naive Bayes, random forest, decision tree, multilayer perceptron, and support vector machine), as was conventional logistic regression. Machine learning-derived MetS prediction models with and without the incorporation of Sasang constitution type were compared to investigate whether the former would predict MetS with higher sensitivity. Age, sex, education level, marital status, body mass index, stress, physical activity, alcohol consumption, and smoking were included as potentially predictive factors.ResultsA total of 750/2,871 participants had MetS. Among the six types of machine learning methods investigated, multiplayer perceptron and support vector machine exhibited the same performance as the conventional regression method, based on the areas under the receiver operating characteristic curves. The naive-Bayes method exhibited the highest sensitivity (0.49), which was higher than that of the conventional regression method (0.39). The incorporation of Sasang constitution type improved the sensitivity of all of the machine learning methods investigated except for the K-nearest neighbor method.ConclusionMachine learning-derived models may be useful for MetS prediction, and the incorporation of Sasang constitution type may increase the sensitivity of such models.
| S-EPMC7886522 | biostudies-literature
Project description:The search for new tuberculosis treatments continues as we need to find molecules that can act more quickly, be accommodated in multidrug regimens, and overcome ever increasing levels of drug resistance. Multiple large scale phenotypic high-throughput screens against Mycobacterium tuberculosis (Mtb) have generated dose response data, enabling the generation of machine learning models. These models also incorporated cytotoxicity data and were recently validated with a large external data set. A cheminformatics data-fusion approach followed by Bayesian machine learning, Support Vector Machine, or Recursive Partitioning model development (based on publicly available Mtb screening data) was used to compare individual data sets and subsequent combined models. A set of 1924 commercially available molecules with promising antitubercular activity (and lack of relative cytotoxicity to Vero cells) were used to evaluate the predictive nature of the models. We demonstrate that combining three data sets incorporating antitubercular and cytotoxicity data in Vero cells from our previous screens results in external validation receiver operator curve (ROC) of 0.83 (Bayesian or RP Forest). Models that do not have the highest 5-fold cross-validation ROC scores can outperform other models in a test set dependent manner. We demonstrate with predictions for a recently published set of Mtb leads from GlaxoSmithKline that no single machine learning model may be enough to identify compounds of interest. Data set fusion represents a further useful strategy for machine learning construction as illustrated with Mtb. Coverage of chemistry and Mtb target spaces may also be limiting factors for the whole-cell screening data generated to date.
| S-EPMC3910492 | biostudies-literature
Project description:The application of artificial intelligence enhances the ability of sensor and networking technologies to realize smart systems that sense, monitor and automatically control our everyday environments. Intelligent systems and applications often automate decisions based on the outcome of certain machine learning models. They collaborate at an ever increasing scale, ranging from smart homes and smart factories to smart cities. The best performing machine learning model, its architecture and parameters for a given task are ideally automatically determined through a hyperparameter tuning process. At the same time, edge computing is an emerging distributed computing paradigm that aims to bring computation and data storage closer to the location where they are needed to save network bandwidth or reduce the latency of requests. The challenge we address in this work is that hyperparameter tuning does not take into consideration resource trade-offs when selecting the best model for deployment in smart environments. The most accurate model might be prohibitively expensive to computationally evaluate on a resource constrained node at the edge of the network. We propose a multi-objective optimization solution to find acceptable trade-offs between model accuracy and resource consumption to enable the deployment of machine learning models in resource constrained smart environments. We demonstrate the feasibility of our approach by means of an anomaly detection use case. Additionally, we evaluate the extent that transfer learning techniques can be applied to reduce the amount of training required by reusing previous models, parameters and trade-off points from similar settings.
| S-EPMC7070423 | biostudies-literature
Project description:BackgroundCurrent atherosclerotic cardiovascular disease (ASCVD) predictive models have limitations; thus, efforts are underway to improve the discriminatory power of ASCVD models.ObjectiveWe sought to evaluate the discriminatory power of social media posts to predict the 10-year risk for ASCVD as compared to that of pooled cohort risk equations (PCEs).MethodsWe consented patients receiving care in an urban academic emergency department to share access to their Facebook posts and electronic medical records (EMRs). We retrieved Facebook status updates up to 5 years prior to study enrollment for all consenting patients. We identified patients (N=181) without a prior history of coronary heart disease, an ASCVD score in their EMR, and more than 200 words in their Facebook posts. Using Facebook posts from these patients, we applied a machine-learning model to predict 10-year ASCVD risk scores. Using a machine-learning model and a psycholinguistic dictionary, Linguistic Inquiry and Word Count, we evaluated if language from posts alone could predict differences in risk scores and the association of certain words with risk categories, respectively.ResultsThe machine-learning model predicted the 10-year ASCVD risk scores for the categories <5%, 5%-7.4%, 7.5%-9.9%, and ≥10% with area under the curve (AUC) values of 0.78, 0.57, 0.72, and 0.61, respectively. The machine-learning model distinguished between low risk (<10%) and high risk (>10%) with an AUC of 0.69. Additionally, the machine-learning model predicted the ASCVD risk score with Pearson r=0.26. Using Linguistic Inquiry and Word Count, patients with higher ASCVD scores were more likely to use words associated with sadness (r=0.32).ConclusionsLanguage used on social media can provide insights about an individual's ASCVD risk and inform approaches to risk modification.
| S-EPMC8411430 | biostudies-literature