scholarly journals The Mechanism Analysis of the Accelerator for Support Vector Regression Based on Data Partition

2020 ◽  
Author(s):  
Yunsheng Song ◽  
Fangyi Li ◽  
Jianyu Liu ◽  
Juao Zhang
Keyword(s):  
Support Vector Regression ◽  
Large Scale ◽  
Real Life ◽  
Support Vector ◽  
Mechanism Analysis ◽  
Data Partition ◽  
Price Forecast ◽  
Before And After ◽  
Important Solution ◽  
The Difference

Support vector regression is an important algorithm in machine learning, and it is widely used in real life for its good performance, such as house price forecast, disease prediction, weather forecast, and so on. However, it cannot efficiently process large-scale data, because it has a high time complexity in the training process. Data partition as an important solution to solve the large-scale learning problem mainly focuses on the classification task, it trains the classifiers over the divided subsets produced by data partition and obtain the final classifier by combining those classifiers. Meanwhile, the most existing method rarely study the influence of data partition on the regressor performance, so that it is difficult to keep its generation ability. To solve this problem, we obtain the estimation of the difference in objective function before and after the data partition. Mini-Batch K-Means clustering is adopted to largely reduce this difference, and an improved algorithm is proposed. This proposed algorithm includes training stage and prediction stage. In training stag, it uses Mini-Batch K-Means clustering to divide the input space into some disjoint sub-regions of equal sample size, then it trains the regressor on each divided sub-region using support vector regression algorithm. In the prediction stage, the regressor merely offers the predicted label for the unlabeled instances that are in the same sub-region. Experiment results on real datasets illustrate that the proposed algorithm obtains the similar generation ability as the original algorithm, but it has less execution time than other acceleration algorithms.

scholarly journals Large-Scale Landslide Displacement Rate Prediction Based on Multi-Factor Support Vector Regression Machine

2021 ◽  
Vol 11 (4) ◽  
pp. 1381
Author(s):  
Xiuzhen Li ◽  
Shengwei Li
Keyword(s):  
Support Vector Regression ◽  
Water Level ◽  
Large Scale ◽  
Displacement Rate ◽  
Support Vector ◽  
Single Factor ◽  
Reservoir Water ◽  
Reservoir Water Level ◽  
Depth Analysis ◽  
Three Factor

Forecasting the development of large-scale landslides is a contentious and complicated issue. In this study, we put forward the use of multi-factor support vector regression machines (SVRMs) for predicting the displacement rate of a large-scale landslide. The relative relationships between the main monitoring factors were analyzed based on the long-term monitoring data of the landslide and the grey correlation analysis theory. We found that the average correlation between landslide displacement and rainfall is 0.894, and the correlation between landslide displacement and reservoir water level is 0.338. Finally, based on an in-depth analysis of the basic characteristics, influencing factors, and development of landslides, three main factors (i.e., the displacement rate, reservoir water level, and rainfall) were selected to build single-factor, two-factor, and three-factor SVRM models. The key parameters of the models were determined using a grid-search method, and the models showed high accuracies. Moreover, the accuracy of the two-factor SVRM model (displacement rate and rainfall) is the highest with the smallest standard error (RMSE) of 0.00614; it is followed by the three-factor and single-factor SVRM models, the latter of which has the lowest prediction accuracy, with the largest RMSE of 0.01644.

scholarly journals Impact of Stem Education on Academic Achievement of Elementary School Students‟ of Delhi

2019 ◽  
Vol 9 (2) ◽  
pp. 3275-3278
Keyword(s):  
Academic Achievement ◽  
Stem Education ◽  
Teaching Methods ◽  
Life Experiences ◽  
Real Life ◽  
Traditional Teaching ◽  
School Students ◽  
Traditional Teaching Methods ◽  
Before And After ◽  
The Difference

STEM education does not follow traditional teaching methods but is based on interesting and critical thinking activities. It is important to increase students' interest and awareness of STEM educational activities to encourage them to learn STEM. STEM-based education can help students or children learn and participate in activities based on real-life experiences. We need to let them know that what they learned in STEM today is not only building their own future, but also the cornerstone of the country. Since no study has been done to know the difference in the academic achievement and basic attitude of the students towards this approach based on gender school types (government and private); before and after the conduction of STEM programme this study will give STEM practitioners strategies to design and integrate STEM content purposefully for the students ; so that students can develop a positive attitude towards STEM programme which will in turn help them to acquire higher academic achievement and make study more effective. This study will also through light on the teachers to make STEM programme more effective. This study will also be of immense help to the school authorities while opting for better STEM programme

scholarly journals Photogrammetric avalanche volume measurements at Vallée de la Sionne, Switzerland

2001 ◽  
Vol 32 ◽  
pp. 141-146 ◽  
Author(s):  
Juauien Vallet ◽  
Urs Gruber ◽  
François Dufour
Keyword(s):  
Large Scale ◽  
Field Experiments ◽  
Test Site ◽  
Deposition Zone ◽  
Before And After ◽  
Large Scale Field ◽  
Volume Measurements ◽  
Snow Distribution ◽  
The Mean ◽  
The Difference

AbstractDuring winter 1999 three large avalanche events were triggered by explosives at SLF’s avalanche test site, Vallée de la Sionne, canton Valais, Switzerland. One important goal of these large-scale field experiments was to measure the release and deposition volumes of avalanches by photogrammetric methods. In this paper, the photogrammetric measurements of all three avalanches are summarized. For one avalanche event it was possible to realize the whole measuring procedure as planned, and to obtain volume measurements before and after the avalanche triggering In the other two avalanche events, the photographs before the triggering of the avalanche failed. Nevertheless the photographs taken after the avalanche provide valuable information on the fracture depth at the fracture line. The mean fracture depth of the largest avalanche was about 2.10 m, varying between 1 and 3.5 m over a width of > 1000 m. The total volume of the deposition of all three avalanche events was about 1300 000 m3. The deposits are distributed over a length of > 1000 m with depths up to 30 m. The difference between the released and deposited volumes proved that avalanches entrain a large amount of snow along the avalanche track. Furthermore, the snow distribution in the deposition zone provides important information about the behaviour of a dense flowing avalanche in the runout zone.

scholarly journals Development of an SVR Model for the Fault Diagnosis of Large-Scale Doubly-Fed Wind Turbines Using SCADA Data

Energies ◽  
2019 ◽  
Vol 12 (17) ◽  
pp. 3396 ◽  
Author(s):  
Mingzhu Tang ◽  
Wei Chen ◽  
Qi Zhao ◽  
Huawei Wu ◽  
Wen Long ◽  
...  
Keyword(s):  
Fault Diagnosis ◽  
Wind Turbine ◽  
Support Vector Regression ◽  
Confidence Intervals ◽  
Wind Turbines ◽  
Large Scale ◽  
Support Vector ◽  
Effective Response ◽  
Support Vector Regression Model ◽  
Doubly Fed

Fault diagnosis and forecasting contribute significantly to the reduction of operating and maintenance associated costs, as well as to improve the resilience of wind turbine systems. Different from the existing fault diagnosis approaches using monitored vibration and acoustic data from the auxiliary equipment, this research presents a novel fault diagnosis and forecasting approach underpinned by a support vector regression model using data obtained by the supervisory control and data acquisition system (SCADA) of wind turbines (WT). To operate, the extraction of fault diagnosis features is conducted by measuring SCADA parameters. After that, confidence intervals are set up to guide the fault diagnosis implemented by the support vector regression (SVR) model. With the employment of confidence intervals as the performance indicators, an SVR-based fault detecting approach is then developed. Based on the WT SCADA data and the SVR model, a fault diagnosis strategy for large-scale doubly-fed wind turbine systems is investigated. A case study including a one-year monitoring SCADA data collected from a wind farm in Southern China is employed to validate the proposed methodology and demonstrate how it works. Results indicate that the proposed strategy can support the troubleshooting of wind turbine systems with high precision and effective response.

scholarly journals Metode Kerja Berorientasi Ergonomi pada Proses Pengelapan Kaleng Sarden Menurunkan Keluhan Muskuloskeletal dan Kelelahan Pekerja di PT. BMP Negara, Bali

2019 ◽  
Vol 5 (1) ◽  
pp. 16
Author(s):  
Ni Luh Gede Aris Maytadewi Negara ◽  
I Dewa Putu Sutjana ◽  
Luh Made Indah Sri Handari Adiputra
Keyword(s):  
Large Scale ◽  
Test Group ◽  
Total Sample ◽  
Musculoskeletal Complaints ◽  
Fatigue Score ◽  
Before And After ◽  
Post Test ◽  
The Difference ◽  
The Right ◽  
A Company

Industrial activities developed from households to large-scale industries, including the development of industries in the field of canning fish. Worker health is one of the important things in a company, can be achieved by choosing the right work method. This study was conducted to determine whether ergonomic oriented working methods in the process of wiping canned sardines can reduce musculoskeletal complaints and fatigue in workers. The study design was two period cross over pre and post-test group desig). The research was conducted at PT. BMP Negara. It was held in December 2016. Total sample were 18 workers who wiping cans of sardines. The difference in conditions between before and after activities using ergonomic un-oriented working methods and ergonomic oriented working methods are compared and tested statistically. Comparison tests were carried out on scores of musculoskeletal complaints and worker fatigue. The results showed that ergonomic oriented working methods decreased of musculoskeletal complaints 17.82% (p<0.05) and fatigue score of 11.86% (p<0.05). The conclusion of this study is that ergonomic oriented working methods in the process of wiping sardine cans reduce musculoskeletal complaints and work fatigue of workers in PT. BMP Negara.

A Forecasting Methodology Using Support Vector Regression and Dynamic Feature Selection

2006 ◽  
Vol 05 (04) ◽  
pp. 329-335 ◽  
Author(s):  
José Guajardo ◽  
Richard Weber ◽  
Jaime Miranda
Keyword(s):  
Neural Networks ◽  
Time Series ◽  
Feature Selection ◽  
Support Vector Regression ◽  
Support Vector ◽  
Time Series Models ◽  
Dynamic Feature ◽  
Real World Applications ◽  
Alternative Approaches ◽  
The Difference

Various techniques have been proposed to forecast a given time series. Models from the ARIMA family have been successfully used, as well as regression approaches based on e.g. linear, non-linear regression, neural networks, and Support Vector Regression. What makes the difference in many real-world applications, however, is not the technique but an appropriate forecasting methodology. Here, we propose such a methodology for the regression-based forecasting approach. A hybrid system is presented that iteratively selects the most relevant features and constructs the regression model optimizing its parameters dynamically. We develop a particular technique for feature selection as well as for model construction. The methodology, however, is a generic one providing the opportunity to employ alternative approaches within our framework. The application to several time series underlines its usefulness.

Speeding up reactive transport simulations: statistical surrogates and caching of simulation results in lookup tables

2020 ◽  
Author(s):  
Marco De Lucia ◽  
Robert Engelmann ◽  
Michael Kühn ◽  
Alexander Lindemann ◽  
Max Lübke ◽  
...  
Keyword(s):  
Reactive Transport ◽  
Large Scale ◽  
Computing Time ◽  
Real Life ◽  
Data Driven ◽  
Support Vector ◽  
Coupled Transport ◽  
Charge Balance ◽  
Lookup Tables ◽  
Simulation Results

&lt;p&gt;A successful strategy for speeding up coupled reactive transport simulations at price of acceptable accuracy loss is to compute geochemistry, which represents the bottleneck of these simulations, through data-driven surrogates instead of &amp;#8216;full physics&amp;#8216; equation-based models [1]. A surrogate is a multivariate regressor trained on a set of pre-calculated geochemical simulations or potentially even at runtime during the coupled simulations. Many available algorithms and implementations are available from the thriving Machine Learning community: tree-based regressors such as Random Forests or xgboost, Artificial Neural Networks, Gaussian Processes and Support Vector Machines just to name a few. Given the &amp;#8216;black-box&amp;#8216; nature of the surrogates, however, they generally disregard physical constraints such as mass and charge balance, which are of course of paramount importance for coupled transport simulations. A runtime check of error of balances in the surrogate outcomes is therefore necessary: predictions offending a given tolerance must be rejected and the full physics chemical simulations run instead. Thus the practical speedup of this strategy is a tradeoff between careful training of the surrogate and run-time efficiency.&lt;/p&gt;&lt;p&gt;&lt;br&gt;In this contribution we demonstrate that the use of surrogates can lead to a dramatic decrease of required computing time, with speedup factors in the order of 10 or even 100 in the most favorable cases. Thus, large scale simulations with some 10&lt;sup&gt;6&lt;/sup&gt; grid elements are feasible on common workstations without requiring computation on HPC clusters [2].&lt;/p&gt;&lt;p&gt;&lt;span&gt;&lt;br&gt;Furthermore, we showcase our implementation of Distributed Hash Tables caching geochemical simulation results for further reuse in subsequent time steps. The computational advantage here stems from the fact that query and retrieval from lookup tables is much faster than both full physics geochemical simulations and surrogate predictions. Another advantage of this algorithm is that virtually no loss of accuracy is introduced in the simulations. Enabling the caching of geochemical simulations through DHT speeds up large scale reactive transport simulations up to a factor of four even when computing on several hundred &lt;/span&gt;&lt;span&gt;cores&lt;/span&gt;&lt;span&gt;.&lt;/span&gt;&lt;/p&gt;&lt;p&gt;&lt;br&gt;These algorithmical developments are demonstrated in comparison with published reactive transport benchmarks and on a real-life scenario of CO&lt;sub&gt;2&lt;/sub&gt; storage.&lt;/p&gt;&lt;p&gt;&amp;#160;&lt;/p&gt;&lt;p&gt;&amp;#160;&lt;/p&gt;&lt;p&gt;&lt;span&gt;[1] &lt;/span&gt;&lt;span&gt;Jatnieks, J., De Lucia, M., Dransch, D., Sips, M. (2016): Data-driven surrogate model approach for improving the performance of reactive transport simulations. Energy Procedia &lt;/span&gt;&lt;span&gt;97&lt;/span&gt;&lt;span&gt;, pp. 447-453. DOI: 10.1016/j.egypro.2016.10.047&lt;/span&gt;&lt;/p&gt;&lt;p&gt;[2] De Lucia, M., Kempka, T., Jatnieks, J., K&amp;#252;hn, M. (2017): Integrating surrogate models into subsurface simulation framework allows computation of complex reactive transport scenarios. Energy Procedia 125, pp. 580-587. DOI: 10.1016/j.egypro.2017.08.200&lt;/p&gt;

scholarly journals Distinct effects of single plant-based vs. animal-based meals on satiety and mood revealed by real-world smartphone-embedded studies

2021 ◽  
Author(s):  
Evelyn Medawar ◽  
Marie Zedler ◽  
Larissa de Biasi ◽  
Arno Villringer ◽  
A. Veronica Witte
Keyword(s):  
Protein Content ◽  
Large Scale ◽  
Model Comparison ◽  
Dietary Habits ◽  
Real Life ◽  
Obesity Prevalence ◽  
Single Plant ◽  
Psychological Determinants ◽  
Meal Intake ◽  
Before And After

Adopting plant-based diets high in fiber may reduce global warming and obesity prevalence. Physiological and psychological determinants of plant-based food decision-making remain unclear, particularly in real-life settings. As fiber has been linked with improved gut-brain signaling, we hypothesized that a single plant-based compared to an animal-based meal, would induce higher satiety, higher mood and less stress. In three smartphone-based studies adults (nall = 16,379) ranked satiety and mood on 5/10-point Likert scales before and after meal intake. Statistical analyses comprised linear mixed models, extended by nutrient composition, taste ratings, gender, social interaction, type of decision and dietary adherence to consider potential confounding. Overall, meal intake induced satiety and higher mood. Against our hypotheses, plant-based meal choice did not explain differences in hunger after the meal. Considering mood, individuals choosing a plant-based meal reported slightly higher mood before the meal and smaller mood increases after the meal compared to those choosing animal-based meals (post-meal*plant-based: b = -0.06 , t = -3.6, model comparison p < .001). Protein content marginally mediated post-meal satiety, while gender and taste ratings had a strong effect on satiety and mood in general. In this series of large-scale online studies, we could not detect profound effects of plant-based vs. animal-based meals on satiety and mood. Instead of meal category, satiety and mood depended on taste and protein content of the meal, as well as dietary habits and gender. Our findings might help to develop strategies to increase acceptability of healthy and sustainable plant-based food choices.

scholarly journals CIRCULATING LEUKOCYTES

2010 ◽  
Vol 17 (03) ◽  
pp. 455-458
Author(s):  
ISRAR AHMED AKHUND ◽  
IRSHAD ALI ALVI ◽  
GHULAM RASOOL BHURGRI ◽  
Muhammad Ali Qureshi ◽  
Haji Khan Khoharo
Keyword(s):  
Coronary Artery Disease ◽  
Coronary Artery ◽  
Life Stress ◽  
Venous Blood ◽  
Real Life ◽  
Medical College ◽  
Before And After ◽  
Leukocyte Counts ◽  
The Difference ◽  
Artery Disease

Objective: Evaluating circulating leukocytes in acute mental stress & relation with coronary artery disease. Design: Descriptive study Setting: Muhammad Medical College Mirpurkhas, Duration: from March 2007 to August 2007. Methods: Two hundred young healthy adults were studied for stress experiment. Venous blood samples were drawn before and after stress for estimation of leukocyte counts. Values were presented as mean ±standard error of mean (SEM). Results: The difference in Pre and during stress results of variables were TLC = - 4630.85 ± 140.65, N % = -11.8 ± 0.36, L% = 4.03 ± 0.14, M %= 5.48 ± 0.37, E % = 1.18 ± 0.07, B % = 1.11 ± 0.022. Highly significant p-values (≤ 0.001) were found among various parameters, in both groups of subjects. Conclusion: An increase in the number of circulating leukocytes was an important unexpected observation that was noted. We suggest that the real life stress induced leukocytes changes may warrant further investigation about its relation with the coronary artery disease (CAD).

Sign in / Sign up

Export Citation Format

Share Document