Exploring Weather Data to Predict Activity Attendance in Event-based Social Network

2021 ◽  
Vol 15 (2) ◽  
pp. 1-25
Author(s):  
Jifeng Zhang ◽  
Wenjun Jiang ◽  
Jinrui Zhang ◽  
Jie Wu ◽  
Guojun Wang
Keyword(s):  
Real Life ◽  
Prediction Performance ◽  
Weather Data ◽  
Gradient Boosting ◽  
User Interest ◽  
Weather Factors ◽  
Event Duration ◽  
Outdoor Activities ◽  
Weather Factor ◽  
Event Based

Event-based social networks (EBSNs) connect online and offline lives. They allow online users with similar interests to get together in real life. Attendance prediction for activities in EBSNs has attracted a lot of attention and several factors have been studied. However, the prediction accuracy is not very good for some special activities, such as outdoor activities. Moreover, a very important factor, the weather, has not been well exploited. In this work, we strive to understand how the weather factor impacts activity attendance, and we explore it to improve attendance prediction from the organizer’s view. First, we classify activities into two categories: the outdoor and the indoor activities. We study the different ways that weather factors may impact these two kinds of activities. We also introduce a new factor of event duration. By integrating the above factors with user interest and user-event distance, we build a model of attendance prediction with the weather named GBT-W , based on the Gradient Boosting Tree. Furthermore, we develop a platform to help event organizers estimate the possible number of activity attendance with different settings (e.g., different weather, location) to effectively plan their events. We conduct extensive experiments, and the results show that our method has a better prediction performance on both the outdoor and the indoor activities, which validates the reasonability of considering weather and duration.

scholarly journals An Empirical Note on Delhi Weather Effects in the Indian Stock Market

2019 ◽  
Vol 8 (4) ◽  
pp. 1203-1208
Keyword(s):  
Stock Market ◽  
Stock Price ◽  
Weather Data ◽  
Weather Factors ◽  
Stock Market Returns ◽  
Weather Factor ◽  
Stock Indices ◽  
Daily Weather Data ◽  
Empirical Note ◽  
Indian Stock Market

This research paper investigates the dynamic linkage, between three weather factors and two top stock Indices in India, namely, BSE SENSEX and NSE NIFTY. In order to study the weather factor on stock indices, daily weather data of Delhi and daily closing stock price of BSE SENSEX and NSE NIFTY, from January 1st 2001 to 31st December 2017, were collected and analyzed. The study found that the Delhi weather namely humidity influence BSE Sensex returns. The investing community may note the findings, for making intelligent investment decisions. The findings would be useful to investors, speculators and officials managing the Indian Securities Exchanges. This is the first empirical study testing the relationship between stock market returns and weather factors in the City of Delhi in India

scholarly journals Prediction of Healing Performance of Autogenous Healing Concrete Using Machine Learning

Materials ◽  
2021 ◽  
Vol 14 (15) ◽  
pp. 4068
Author(s):  
Xu Huang ◽  
Mirna Wasouf ◽  
Jessada Sresakoolchai ◽  
Sakdirat Kaewunruen
Keyword(s):  
Machine Learning ◽  
Search Algorithm ◽  
Weather Conditions ◽  
Prediction Performance ◽  
Machine Learning Algorithms ◽  
Coefficient Of Determination ◽  
Gradient Boosting ◽  
Support Vector ◽  
Self Healing ◽  
Artificial Neural Network Ann

Cracks typically develop in concrete due to shrinkage, loading actions, and weather conditions; and may occur anytime in its life span. Autogenous healing concrete is a type of self-healing concrete that can automatically heal cracks based on physical or chemical reactions in concrete matrix. It is imperative to investigate the healing performance that autogenous healing concrete possesses, to assess the extent of the cracking and to predict the extent of healing. In the research of self-healing concrete, testing the healing performance of concrete in a laboratory is costly, and a mass of instances may be needed to explore reliable concrete design. This study is thus the world’s first to establish six types of machine learning algorithms, which are capable of predicting the healing performance (HP) of self-healing concrete. These algorithms involve an artificial neural network (ANN), a k-nearest neighbours (kNN), a gradient boosting regression (GBR), a decision tree regression (DTR), a support vector regression (SVR) and a random forest (RF). Parameters of these algorithms are tuned utilising grid search algorithm (GSA) and genetic algorithm (GA). The prediction performance indicated by coefficient of determination (R2) and root mean square error (RMSE) measures of these algorithms are evaluated on the basis of 1417 data sets from the open literature. The results show that GSA-GBR performs higher prediction performance (R2GSA-GBR = 0.958) and stronger robustness (RMSEGSA-GBR = 0.202) than the other five types of algorithms employed to predict the healing performance of autogenous healing concrete. Therefore, reliable prediction accuracy of the healing performance and efficient assistance on the design of autogenous healing concrete can be achieved.

scholarly journals Improving the performance of a radio-frequency localization system in adverse outdoor applications

2021 ◽  
Vol 2021 (1) ◽  
Author(s):  
Marcelo N. de Sousa ◽  
Ricardo Sant’Ana ◽  
Rigel P. Fernandes ◽  
Julio Cesar Duarte ◽  
José A. Apolinário ◽  
...  
Keyword(s):  
Random Forest ◽  
Ray Tracing ◽  
Real World ◽  
Practical Implication ◽  
Real Life ◽  
Simulated Data ◽  
Real Data ◽  
Gradient Boosting ◽  
Real World Data ◽  
Localization Accuracy

AbstractIn outdoor RF localization systems, particularly where line of sight can not be guaranteed or where multipath effects are severe, information about the terrain may improve the position estimate’s performance. Given the difficulties in obtaining real data, a ray-tracing fingerprint is a viable option. Nevertheless, although presenting good simulation results, the performance of systems trained with simulated features only suffer degradation when employed to process real-life data. This work intends to improve the localization accuracy when using ray-tracing fingerprints and a few field data obtained from an adverse environment where a large number of measurements is not an option. We employ a machine learning (ML) algorithm to explore the multipath information. We selected algorithms random forest and gradient boosting; both considered efficient tools in the literature. In a strict simulation scenario (simulated data for training, validating, and testing), we obtained the same good results found in the literature (error around 2 m). In a real-world system (simulated data for training, real data for validating and testing), both ML algorithms resulted in a mean positioning error around 100 ,m. We have also obtained experimental results for noisy (artificially added Gaussian noise) and mismatched (with a null subset of) features. From the simulations carried out in this work, our study revealed that enhancing the ML model with a few real-world data improves localization’s overall performance. From the machine ML algorithms employed herein, we also observed that, under noisy conditions, the random forest algorithm achieved a slightly better result than the gradient boosting algorithm. However, they achieved similar results in a mismatch experiment. This work’s practical implication is that multipath information, once rejected in old localization techniques, now represents a significant source of information whenever we have prior knowledge to train the ML algorithm.

Geophysical Variables and Behavior: II. Weather Factors as Predictors of Local Social Indicators of Maladaptation in Two Non-Urban Areas

1978 ◽  
Vol 43 (2) ◽  
pp. 427-434 ◽  
Author(s):  
George Banziger ◽  
Karen Owens
Keyword(s):  
Urban Areas ◽  
Social Indicator ◽  
Social Indicators ◽  
Geographical Area ◽  
Drunk Driving ◽  
Medical Patient ◽  
Stepwise Multiple Regression ◽  
Weather Factors ◽  
Weather Factor ◽  
Telephone Hotline

The relative predictive strengths of eight weather factors were examined using as separate dependent variables monthly figures for community mental health intake, welfare caseload, calls to a telephone hotline, medical patient caseload, felony arrests, juvenile complaints, drunk-driving arrests, and mortality rates in two non-urban areas of Ohio. Z-score transformations of subjective discomfort of the weather factors as indicated by three independent samples were analyzed with a stepwise multiple regression. With the exception of hotline calls, each of the social indicators in the two localities was significantly predicted by a different weather factor, and the weather factors, taken together, accounted for about 10% of the variance of each social indicator. For each geographical area, combined weather factors accounted for no more than 30% of the variance of any local social indicator. Problems of overgeneralization and exaggeration of the effects of weather factors on social indicators in previous studies were discussed. A balanced approach to behavioral effects of geophysical variables must be achieved (Ammons, 1978).

scholarly journals Zooming into Real-Life Extraversion – How Personality and Situation Shape Sociability in Social Interactions

2016 ◽  
Author(s):  
Simon Mats Breil ◽  
Katharina Geukes ◽  
Robert Edmund Wilson ◽  
Steffen Nestler ◽  
Simine Vazire ◽  
...  
Keyword(s):  
Social Interactions ◽  
Specific Interaction ◽  
Real Life ◽  
Interaction Effects ◽  
Complex Interplay ◽  
Sampling Studies ◽  
Social Perspectives ◽  
Context Shape ◽  
Event Based ◽  
Main Effects

Here, we provide you with supplemental material (additional tables, data, R-Codes) and a Preprint to the manuscript "Zooming into Real-Life Extraversion - How Personality and Context Shape Sociability in Social Interactions" by Breil et al. (under review). Abstract:What predicts sociable behavior? While main effects of personality and situation characteristics on sociability are well established, the determinants of sociable behavior within real-life social interactions are understudied. Moreover, although such effects are often hypothesized, there is to date little evidence of person-situation interaction effects. Finally, previous research focused on self-reported behavior ratings, and less is known on the partner’s social perspective, i.e. how partners perceive and influence an actor’s behavior. In the current research we investigated predictors of sociable behavior in real-life social interactions across social perspectives, including person and situation main effects as well as person-situation interaction effects. In two experience-sampling studies (Study 1: N = 394, US, time-based; Study 2: N = 124, Germany, event-based), we assessed personality traits with self- and informant reports, self-reported sociable behavior during real-life social interaction, and corresponding information on the situation (dimensional ratings of situation characteristics and categorical situation classifications). In Study 2, we additionally assessed interaction partner-reported behavior. Multilevel analyses provided consistent evidence for main effects of personality and situation features, and for person-situation interaction effects. First, extraverts acted more sociable in general. Second, individuals behaved more sociable in hedonic/positive/low-duty situations (vs. eudaimonic/negative/high-duty situations). Third, the latter was particularly true for extraverts. Further specific interaction effects were found for the other social perspectives. These results are discussed regarding the complex interplay of persons and situations in shaping human behavior.

scholarly journals Association between weather factors and dengue in Dhaka: a time-series analysis

2021 ◽  
Vol 39 (1) ◽  
pp. 43-49
Author(s):  
Shafia Shaheen
Keyword(s):  
Time Series ◽  
Time Series Analysis ◽  
Incidence Rate ◽  
Negative Binomial ◽  
Weather Data ◽  
Negative Binomial Regression Model ◽  
Weather Factors ◽  
Average Temperature ◽  
Series Analysis ◽  
Average Maximum

Background: There was an epidemic of dengue fever that happened  in Bangladesh  in the year of 2019. Temperature of this country has been raising which leads to changing in rainfall pattern. This study was aimed to investigate the relationship of weather factors and dengue incidence in Dhaka. Methods: A time series analysis was carried out by using 10 years weather data as average , maximum and minimum monthly temperature, average monthly humidity and average and cumulative monthly rainfall. Reported number of dengue cases was extracted from January 2009 to July 2019. Firstly, dengue incidence rate was  calculated. Correlation analysis and negative binomial regression model was developed. Results: Dengue incidence rate had sharp upward trend. Dengue incidence and mean, maximum and minimum average temperature showed statistically significant negative correlation at 3 months' lag. Highest incidence Rate Ratio (IRR) of dengue was found at minimum average temperature at 0 and I-month lag. Average humidity showed positive and significant correlation with dengue incidence at 0-month lag. Average and cumulative rainfall also showed negative and significant correlation only at 3-months lag period. Conclusion: Weather variability influences dengue incidence and the association between the weather factors are non­ linear and not consistent. So the study findings should be evaluated area basis with other local factors to develop early warning for dengue epidemic prediction. JOPSOM 2020; 39(1): 43-49

scholarly journals Zooming into Real-Life Extraversion – how Personality and Situation Shape Sociability in Social Interactions

2019 ◽  
Vol 5 (1) ◽  
Author(s):  
Simon M. Breil ◽  
Katharina Geukes ◽  
Robert E. Wilson ◽  
Steffen Nestler ◽  
Simine Vazire ◽  
...  
Keyword(s):  
Social Interactions ◽  
Specific Interaction ◽  
Real Life ◽  
Interaction Effects ◽  
Behavioral Models ◽  
Social Perspective ◽  
Sampling Studies ◽  
Social Perspectives ◽  
Event Based ◽  
Main Effects

What predicts sociable behavior? While main effects of personality and situation characteristics on sociability are well established, there is little evidence for the existence of person-situation interaction effects within real-life social interactions. Moreover, previous research has focused on self-reported behavior ratings, and less is known about the partner’s social perspective, i.e. how partners perceive and influence an actor’s behavior. In the current research, we investigated predictors of sociable behavior in real-life social interactions across social perspectives, including person and situation main effects as well as person-situation interaction effects. In two experience-sampling studies (Study 1: N = 394, US, time-based; Study 2: N = 124, Germany, event-based), we assessed personality traits with self- and informant-reports, self-reported sociable behavior during real-life social interactions, and corresponding information on the situation (categorical situation classifications and dimensional ratings of situation characteristics). In Study 2, we additionally assessed interaction partner-reported actor behavior. Multilevel analyses provided evidence for main effects of personality and situation features, as well as small but consistent evidence for person-situation interaction effects. First, extraverts acted more sociable in general. Second, individuals behaved more sociable in low-effort/positive/low-duty situations (vs. high-effort/negative/high-duty situations). Third, the latter was particularly true for extraverts. Further specific interaction effects were found for the partner’s social perspective. These results are discussed regarding their accordance with different behavioral models (e.g., Trait Activation Theory) and their transferability to other behavioral domains.

scholarly journals Prediction and Analysis of Length of Stay Based on Nonlinear Weighted XGBoost Algorithm in Hospital

2021 ◽  
Vol 2021 ◽  
pp. 1-9
Author(s):  
Yong Chen
Keyword(s):  
Length Of Stay ◽  
Prediction Performance ◽  
Gradient Boosting ◽  
Distribution Law ◽  
Effective Technique ◽  
Weighting Method ◽  
Imbalance Data ◽  
Extreme Gradient Boosting ◽  
Hospital Beds ◽  
Log Likelihood

An improved nonlinear weighted extreme gradient boosting (XGBoost) technique is developed to forecast length of stay for patients with imbalance data. The algorithm first chooses an effective technique for fitting the duration of stay and determining the distribution law and then optimizes the negative log likelihood loss function using a heuristic nonlinear weighting method based on sample percentage. Theoretical and practical results reveal that, when compared to existing algorithms, the XGBoost method based on nonlinear weighting may achieve higher classification accuracy and better prediction performance, which is beneficial in treating more patients with fewer hospital beds.

An approach towards decentralized control of cooperating non-autonomous multiple robots

Robotica ◽  
2000 ◽  
Vol 18 (5) ◽  
pp. 495-504 ◽  
Author(s):  
Khalid Munawar ◽  
Masayoshi Esashi ◽  
Masaru Uchiyama
Keyword(s):  
Decentralized Control ◽  
Degrees Of Freedom ◽  
Real Life ◽  
Robotic Systems ◽  
Present System ◽  
Multiple Robots ◽  
Experimental Implementation ◽  
Control Scheme ◽  
The Common ◽  
Event Based

This paper introduces an event-based decentralized control scheme for the cooperation between multiple manipulators. This is in contrast to the common practice of using only centralized controls for such cooperation which, consequently, greatly limit the flexibility of robotic systems. The manipulators used in the present system are very simple with only two degrees of freedom, while even one of them is passive. Moreover these manipulators use very few and commonly available sensors only. Computer simulations indicated the applicability of the event-based decentralized control scheme for multi-manipulator cooperation, while real-life experimental implementation has proved that the proposed decentralized control scheme is fairly applicable for very simple and even under-actuated systems too. Hence, this work has opened new doors towards further research in this area. The proposed control scheme is expected to be equally applicable for any mobile or immobile multi-robotic system.

Changes in wind erosion climatic erosivity in northern China from 1981-2016: a comparison of two climate/weather factors of wind erosion models

2021 ◽  
Vol 83 ◽  
pp. 133-146
Author(s):  
F Zhang ◽  
J Wang ◽  
X Zou ◽  
R Mao ◽  
DY Gong ◽  
...  
Keyword(s):  
Wind Erosion ◽  
Qaidam Basin ◽  
Dust Emission ◽  
Northern China ◽  
Northwest China ◽  
Gobi Desert ◽  
Weather Factors ◽  
Weather Factor ◽  
Increasing Trend ◽  
Erosion Equation

Wind erosion is largely determined by wind erosion climatic erosivity. In this study, we examined changes in wind erosion climatic erosivity during 4 seasons across northern China from 1981-2016 using 2 models: the wind erosion climatic erosivity of the Wind Erosion Equation (WEQ) model and the weather factor from the Revised Wind Erosion Equation (RWEQ) model. Results showed that wind erosion climatic erosivity derived from the 2 models was highest in spring and lowest in winter with high values over the Kumtag Desert, the Qaidam Basin, the boundary between Mongolia and China, and the Hulunbuir Sandy Land. In spring and summer, wind erosion climatic erosivity showed decreasing trends in whole of northern China from 1981-2016, whereas there was an increasing trend in wind erosion climatic erosivity over the Gobi Desert from 1992-2011. For the weather factor of the RWEQ model, the difference between northern Northwest China and the Gobi Desert and eastern-northern China was much larger than that of the wind erosion climatic erosivity of the WEQ model. In addition, in contrast to a decreasing trend in the weather factor of the RWEQ model over southern Northwest China during spring and summer from 1981-2016, the wind erosion climatic erosivity of the WEQ model showed a decreasing trend for 1981-1992 and an increasing trend for 1992-2011 over southern Northwest China. According to a comparison between dust emission and wind erosion climatic erosivity, the 2 models have the ability to project changes in future wind erosion in northern China.

Sign in / Sign up

Export Citation Format

Share Document