scholarly journals A geostationary lightning pseudo-observation generator utilizing low frequency ground-based lightning observations

2021 ◽  
Author(s):  
Felix Erdmann ◽  
Olivier Caumont ◽  
Eric Defer
Keyword(s):  
Machine Learning ◽  
Data Assimilation ◽  
Low Frequency ◽  
Optical Signal ◽  
Support Vector ◽  
Flash Duration ◽  
Local Maxima ◽  
Visual Comparison ◽  
Lightning Detection ◽  
Support Vector Regressor

AbstractCoincident Geostationary Lightning Mapper (GLM) and National Lightning Detection Network (NLDN) observations are used to build a generator of realistic lightning optical signal in the perspective to simulate Lightning Imager (LI) signal from European NLDN-like observations. Characteristics of GLM and NLDN flashes are used to train different machine learning (ML) models, that predict simulated pseudo-GLM flash extent, flash duration, and event number per flash (targets) from several NLDN flash characteristics. Comparing statistics of observed GLM targets and simulated pseudo-GLM targets, the most suitable ML-based target generators are identified. The simulated targets are then further processed to obtain pseudo-GLM events and flashes. In the perspective of lightning data assimilation, Flash Extent Density (FED) is derived from both observed and simulated GLM data. The best generators simulate accumulated hourly FED sums with a bias of 2% to the observation, while cumulated absolute differences remain of about 22 %. A visual comparison reveals that hourly simulated FED features local maxima at the similar geolocations as the FED derived from GLM observations. However, the simulated FED often exceeds the observed FED in regions of convective cores and high flash rates. The accumulated hourly area with FED>0 flashes per 5 km×5 km pixel simulated by some pseudo-GLM generators differs by only 7% to 8% from the observed values. The recommended generator uses a linear Support Vector Regressor (linSVR) to create pseudo-GLM FED. It provides the best balance between target simulation, hourly FED sum, and hourly electrified area.

scholarly journals Danger-Pose Detection System Using Commodity Wi-Fi for Bathroom Monitoring

Sensors ◽  
2019 ◽  
Vol 19 (4) ◽  
pp. 884 ◽  
Author(s):  
Zizheng Zhang ◽  
Shigemi Ishida ◽  
Shigeaki Tagashira ◽  
Akira Fukuda
Keyword(s):  
Machine Learning ◽  
Anomaly Detection ◽  
Detection Method ◽  
Detection System ◽  
Wearable Sensors ◽  
Low Frequency ◽  
Training Data ◽  
Support Vector ◽  
Dynamic Features ◽  
Pose Detection

A bathroom has higher probability of accidents than other rooms due to a slippery floor and temperature change. Because of high privacy and humidity, we face difficulties in monitoring inside a bathroom using traditional healthcare methods based on cameras and wearable sensors. In this paper, we present a danger-pose detection system using commodity Wi-Fi devices, which can be applied to bathroom monitoring, preserving privacy. A machine learning-based detection method usually requires data collected in target situations, which is difficult in detection-of-danger situations. We therefore employ a machine learning-based anomaly-detection method that requires a small amount of data in anomaly conditions, minimizing the required training data collected in dangerous conditions. We first derive the amplitude and phase shift from Wi-Fi channel state information (CSI) to extract low-frequency components that are related to human activities. We then separately extract static and dynamic features from the CSI changes in time. Finally, the static and dynamic features are fed into a one-class support vector machine (SVM), which is used as an anomaly-detection method, to classify whether a user is not in bathtub, bathing safely, or in dangerous conditions. We conducted experimental evaluations and demonstrated that our danger-pose detection system achieved a high detection performance in a non-line-of-sight (NLOS) scenario.

scholarly journals Development of novel hybrid machine learning models for monthly thunderstorm frequency prediction over Bangladesh

2021 ◽  
Author(s):  
Md. Abul Kalam Azad ◽  
A R M Towfiqul Islam ◽  
Md. Siddiqur Rahman ◽  
Kurratul Ayen
Keyword(s):  
Machine Learning ◽  
Moving Average ◽  
Input Parameter ◽  
Low Frequency ◽  
Climate Extremes ◽  
Ensemble Empirical Mode Decomposition ◽  
Hybrid Models ◽  
Support Vector ◽  
Hybrid Machine ◽  
Conventional Models

Abstract Accurate thunderstorm frequency (TSF) prediction is of great significance under climate extremes for reducing potential damages. However, TSF prediction has received little attention because a thunderstorm event is a combination of intricate and unique weather scenarios with high instability, making it difficult to predict. To close this gap, we proposed a novel hybrid machine learning model through hybridization of data pre-processing Ensemble Empirical Mode Decomposition (EEMD) with two state-of-arts models namely artificial neural network (EEMD-ANN), support vector machine (EEMD-SVM) for TSF prediction at three categories of yearly frequencies over Bangladesh. We were demarcated the yearly TSF datasets into three categories for the period 1981–2016 recorded at 28 sites; high (March-June), moderate (July-October), and low (November-February) TSF months. The performance of the proposed EEMD-ANN and EEMD-SVM hybrid models was compared with classical ANN, SVM, Autoregressive Integrated Moving Average (ARIMA). EEMD-ANN and EEMD-SVM hybrid models showed 8.02%-22.48% higher performance precision in terms of root mean square error (RMSE) compared to other models at high, moderate and low-frequency categories. Eleven out of 21 input parameters were selected based on the Random Forest (RF) variable importance analysis. The sensitivity analysis results showed that each input parameter was positively contributed to building the best model of each category and thunderstorm days are the most contributing parameters influencing TSF prediction. The proposed hybrid models outperformed the conventional models where EEMD-ANN is the most skillful for high TSF prediction, and EEMD-SVM is for moderate and low TSF prediction. The findings indicate the potential of hybridization of EEMD with the conventional models for improving prediction precision. The hybrid model developed in this work can be adopted for TSF prediction in Bangladesh as well as different parts of the world.

scholarly journals Comparing lightning observations of the ground-based EUCLID network and the space-based ISS-LIS

2020 ◽  
Author(s):  
Dieter R. Poelman ◽  
Wolfgang Schulz
Keyword(s):  
Scattered Light ◽  
Space Station ◽  
Low Frequency ◽  
The Other ◽  
Sensor Technology ◽  
Flash Duration ◽  
Other Hand ◽  
Lightning Detection ◽  
Lightning Discharges ◽  
Full Domain

Abstract. The Lightning Imaging Sensor (LIS) on the International Space Station (ISS) detects lightning from space by capturing the optical scattered light emitted from the top of the clouds. On the other hand, the ground-based European Cooperation for Lightning Detection (EUCLID) makes use of the low-frequency electromagnetic signals generated by lightning discharges to locate those accordingly. The objective of this work is to quantify the similarities and contrasts between the latter two distinct lightning detection technologies by comparing the EUCLID cloud-to-ground strokes and intracloud pulses to the ISS-LIS groups, in addition to the correlation at the flash level. The analysis is based on the observations made during March 01, 2017 and March 31, 2019 within the EUCLID network and limited to 54° north. A Bayesian approach is adopted to determine the relative and absolute detection efficiencies (DE) of each system. It is found that the EUCLID relative and absolute flash DE improves by approximately 10 % towards the center of the EUCLID network up to a value of 50.3 % and 69.4 %, respectively, compared to the averaged value over the full domain, inherent to the network geometry and sensor technology. On the other hand, the relative and absolute ISS-LIS flash DE over the full domain is 49 % and 68.9 %, respectively, and is somewhat higher than the values obtained in the centre of the EUCLID network. The behavior of the relative DE of each system in terms of the flash characteristics of the other reveals that the greater the value the more likely the other system detects the flash. For instance, when the ISS-LIS flash duration is smaller or equal to 200 ms, the EUCLID relative flash DE drops below 50 %, whereas this increases up to 80 % for ISS-LIS flashes with a duration longer than 750 ms. Finally, the distribution of the diurnal DE indicates higher (lower) ISS-LIS (EUCLID) DE at night, related to an increased ISS-LIS:EUCLID flash ratio at night.

scholarly journals Machine-Learning-Enabled Virtual Screening for Inhibitors of Lysine-Specific Histone Demethylase 1

Molecules ◽  
2021 ◽  
Vol 26 (24) ◽  
pp. 7492
Author(s):  
Jiajun Zhou ◽  
Shiying Wu ◽  
Boon Giin Lee ◽  
Tianwei Chen ◽  
Ziqi He ◽  
...  
Keyword(s):  
Machine Learning ◽  
Virtual Screening ◽  
Structural Information ◽  
Coefficient Of Determination ◽  
Support Vector ◽  
Molecular Fingerprints ◽  
Lysine Specific Demethylase ◽  
Zinc Database ◽  
Machine Learning Approach ◽  
Support Vector Regressor

A machine learning approach has been applied to virtual screening for lysine specific demethylase 1 (LSD1) inhibitors. LSD1 is an important anti-cancer target. Machine learning models to predict activity were constructed using Morgan molecular fingerprints. The dataset, consisting of 931 molecules with LSD1 inhibition activity, was obtained from the ChEMBL database. An evaluation of several candidate algorithms on the main dataset revealed that the support vector regressor gave the best model, with a coefficient of determination (R2) of 0.703. Virtual screening, using this model, identified five predicted potent inhibitors from the ZINC database comprising more than 300,000 molecules. The virtual screening recovered a known inhibitor, RN1, as well as four compounds where activity against LSD1 had not previously been suggested. Thus, we performed a machine-learning-enabled virtual screening of LSD1 inhibitors using only the structural information of the molecules.

scholarly journals Modelling wine astringency from its chemical composition using machine learning algorithms

OENO One ◽  
2019 ◽  
Vol 53 (3) ◽  
Author(s):  
Maria P Sáenz-Navajas ◽  
Sara Ferrero-del-Teso ◽  
Miguel Romero ◽  
Darío Pascual ◽  
David Diaz ◽  
...  
Keyword(s):  
Machine Learning ◽  
Chemical Composition ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
Wine Production ◽  
Polyphenolic Composition ◽  
Trained Panel ◽  
Production Stages ◽  
The Mean ◽  
Support Vector Regressor

Aims: The present work aims to predict sensory astringency from wine chemical composition using machine learning algorithms.Material and results: Moristel grapes from different vineblocks and at different stages of ripening were collected. Eleven different wines were produced in 75 L tanks in triplicate, and further sensory factors were described by the rate-all-that-apply method with a trained panel of participants. The polyphenolic composition was characterised in wines by measuring the concentration and activity of tannins using UHPLC-UV/VIS, the mean degree of polymerisation (mDP. and the composition of tannins using thiolysis followed by UHPLC-MS. Conventional oenological parameters were analysed using FTIR and UV-Vis. Machine learning was applied to build models for predicting a wines astringency from its chemical composition. The best model was obtained using the support vector regressor (radial kernel) algorithm presenting a root-mean-square error (RMSE) value of 0.190.Conclusions: The main variables of the astringency model were the % of procyanidins constituting tannins and ethanol content, followed by other eight variables related to tannin structure and acidity.Significance of the study: These results increase the knowledge of chemical variables related to the perception of wine astringency and provide tools to control and optimise grape and wine production stages to modulate astringency and maximise quality and the consumer appeal of wines.

scholarly journals Exploring the long-term changes in the Madden Julian Oscillation using machine learning

2020 ◽  
Vol 10 (1) ◽  
Author(s):  
Panini Dasgupta ◽  
Abirlal Metya ◽  
C. V. Naidu ◽  
Manmeet Singh ◽  
M. K. Roxy
Keyword(s):  
Machine Learning ◽  
Twentieth Century ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
Madden Julian Oscillation ◽  
Multilinear Regression ◽  
The Pacific ◽  
Long Term Changes ◽  
Support Vector Regressor

Abstract The Madden Julian Oscillation (MJO), the dominant subseasonal variability in the tropics, is widely represented using the Real-time Multivariate MJO (RMM) index. The index is limited to the satellite era (post-1974) as its calculation relies on satellite-based observations. Oliver and Thompson (J Clim 25:1996–2019, 2012) extended the RMM index for the twentieth century, employing a multilinear regression on the sea level pressure (SLP) from the NOAA twentieth century reanalysis. They obtained an 82.5% correspondence with the index in the satellite era. In this study, we show that the historical MJO index can be successfully reconstructed using machine learning techniques and improved upon. We obtain a significant improvement of up to 4%, using the support vector regressor (SVR) and convolutional neural network (CNN) methods on the same set of predictors used by Oliver and Thompson. Based on the improved RMM indices, we explore the long-term changes in the intensity, phase occurrences, and frequency of the winter MJO events during 1905–2015. We show an increasing trend in MJO intensity (22–27%) during this period. We also find a multidecadal change in MJO phase occurrence and periodicity corresponding to the Pacific Decadal Oscillation (PDO), while the role of anthropogenic warming cannot be ignored.

scholarly journals Abnormal Low-Frequency Oscillations Reflect Abnormal Eye Movement and Stereovision in Patients With Comitant Exotropia

2021 ◽  
Vol 15 ◽  
Author(s):  
Juan Chen ◽  
Han Jin ◽  
Yu-Lin Zhong ◽  
Xin Huang
Keyword(s):  
Machine Learning ◽  
Eye Movements ◽  
Supplementary Motor Area ◽  
Low Frequency ◽  
Motor Area ◽  
Frequency Fluctuation ◽  
Support Vector ◽  
Machine Learning Method ◽  
Learning Method ◽  
The Right

Background: Patients with comitant exotropia (CE) are accompanied by abnormal eye movements and stereovision. However, the neurophysiological mechanism of impaired eye movements and stereovision in patient with CE is still unclear.Purpose: The purpose of this study is to investigate spontaneous neural activity changes in patients with CE using the amplitude of low-frequency fluctuation (ALFF) method and the machine learning method.Materials and Methods: A total of 21 patients with CE and 21 healthy controls (HCs) underwent resting-state magnetic resonance imaging scans. The ALFF and fractional amplitude of low-frequency fluctuation (fALFF) values were chosen as classification features using a machine learning method.Results: Compared with the HC group, patients with CE had significantly decreased ALFF values in the right angular (ANG)/middle occipital gyrus (MOG)/middle temporal gyrus (MTG) and bilateral supplementary motor area (SMA)/precentral gyrus (PreCG). Meanwhile, patients with CE showed significantly increased fALFF values in the left putamen (PUT) and decreased fALFF values in the right ANG/MOG. Moreover, patients with CE showed a decreased functional connectivity (FC) between the right ANG/MOG/MTG and the bilateral calcarine (CAL)/lingual (LING) and increased FC between the left PUT and the bilateral cerebellum 8/9 (CER 8/9). The support vector machine (SVM) classification reaches a total accuracy of 93 and 90% and the area under the curve (AUC) of 0.93 and 0.90 based on ALFF and fALFF values, respectively.Conclusion: Our result highlights that patients with CE had abnormal brain neural activities including MOG and supplementary motor area/PreCG, which might reflect the neural mechanism of eye movements and stereovision dysfunction in patients with CE. Moreover, ALFF and fALFF could be sensitive biomarkers for distinguishing patients with CE from HCs.

Using Machine Learning Algorithms on Prediction of Stock Price

2020 ◽  
Vol 12 (2) ◽  
pp. 84-99
Author(s):  
Li-Pang Chen
Keyword(s):  
Machine Learning ◽  
Stock Price ◽  
Short Term Memory ◽  
Machine Learning Algorithms ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
Short Term ◽  
Learning Techniques ◽  
Historical Database ◽  
Long Short Term Memory

In this paper, we investigate analysis and prediction of the time-dependent data. We focus our attention on four different stocks are selected from Yahoo Finance historical database. To build up models and predict the future stock price, we consider three different machine learning techniques including Long Short-Term Memory (LSTM), Convolutional Neural Networks (CNN) and Support Vector Regression (SVR). By treating close price, open price, daily low, daily high, adjusted close price, and volume of trades as predictors in machine learning methods, it can be shown that the prediction accuracy is improved.

A Comparative Study of Different Machine Learning Algorithms for Disease Prediction

2017 ◽  
Vol 7 (7) ◽  
pp. 172
Author(s):  
Anantvir Singh Romana
Keyword(s):  
Machine Learning ◽  
Subsequent Treatment ◽  
Machine Learning Algorithms ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
Disease Prediction ◽  
Classification Problems ◽  
Learning Techniques ◽  
Neural Network Classifiers ◽  
Diagnostic Detection

Accurate diagnostic detection of the disease in a patient is critical and may alter the subsequent treatment and increase the chances of survival rate. Machine learning techniques have been instrumental in disease detection and are currently being used in various classification problems due to their accurate prediction performance. Various techniques may provide different desired accuracies and it is therefore imperative to use the most suitable method which provides the best desired results. This research seeks to provide comparative analysis of Support Vector Machine, Naïve bayes, J48 Decision Tree and neural network classifiers breast cancer and diabetes datsets.

Structure-Based Virtual Screening of Perfluoroalkyl and Polyfluoroalkyl Substances (PFASs) as Endocrine Disruptors of Androgen Receptor Activity Using Molecular Docking and Machine Learning

2020 ◽  
Author(s):  
Azhagiya Singam Ettayapuram Ramaprasad ◽  
Phum Tachachartvanich ◽  
Denis Fourches ◽  
Anatoly Soshilov ◽  
Jennifer C.Y. Hsieh ◽  
...  
Keyword(s):  
Machine Learning ◽  
Molecular Docking ◽  
Androgen Receptor ◽  
Endocrine Disruptors ◽  
Hormone Receptors ◽  
Steroid Hormone Receptors ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
Polyfluoroalkyl Substances ◽  
Perfluoroalkyl And Polyfluoroalkyl Substances

Perfluoroalkyl and Polyfluoroalkyl Substances (PFASs) pose a substantial threat as endocrine disruptors, and thus early identification of those that may interact with steroid hormone receptors, such as the androgen receptor (AR), is critical. In this study we screened 5,206 PFASs from the CompTox database against the different binding sites on the AR using both molecular docking and machine learning techniques. We developed support vector machine models trained on Tox21 data to classify the active and inactive PFASs for AR using different chemical fingerprints as features. The maximum accuracy was 95.01% and Matthew’s correlation coefficient (MCC) was 0.76 respectively, based on MACCS fingerprints (MACCSFP). The combination of docking-based screening and machine learning models identified 29 PFASs that have strong potential for activity against the AR and should be considered priority chemicals for biological toxicity testing.

Sign in / Sign up

Export Citation Format

Share Document