Filters








5,404 Hits in 6.5 sec

Modeling correlated human dynamics [article]

Peng Wang, Tao Zhou, Xiao-Pu Han, Bing-Hong Wang
2010 arXiv   pre-print
This work helps in understanding both the temporal regularities and the predictability of human behaviors.  ...  We empirically study the activity patterns of individual blog-posting and find significant memory effects. The memory coefficient first decays in a power law and then turns to an exponential form.  ...  The memory or correlation of human behavior have much to do with the predictability.  ... 
arXiv:1007.4440v3 fatcat:rvvsmznayjdfdol3mcadf7lq44

Robust Online Model Adaptation by Extended Kalman Filter with Exponential Moving Average and Dynamic Multi-Epoch Strategy [article]

Abulikemu Abuduweili, Changliu Liu
2020 arXiv   pre-print
High fidelity behavior prediction of intelligent agents is critical in many applications.  ...  Inspired by Extended Kalman Filter (EKF), this paper introduces a series of online adaptation methods, which are applicable to neural network-based models.  ...  Behavior prediction is a sub-topic of time series prediction Weigend (2018), which includes but is not limited to vehicle trajectory prediction during autonomous driving Lefèvre et al. (2014) and human-motion  ... 
arXiv:1912.01790v3 fatcat:vd6auauztfdltndtw4ou2wg7ze

iJADE Stock Advisor: An Intelligent Agent Based Stock Prediction System Using Hybrid RBF Recurrent Network

R.S.T. Lee
2004 IEEE transactions on systems, man and cybernetics. Part A. Systems and humans  
With the rapid growth of Internet technology in recent years, e-finance has become a vital application of e-commerce.  ...  Financial predictions, such as stock forecasts, is always one of the hottest topics for research studies and commercial applications.  ...  In a typical time series prediction problem, given a series of past observations of n time-steps starting at t, i.e., [x t 1 ; x t01 1 ; x t02 1 ; x t03 1 ; ...; x t0n+1 1 ], with the predictive time-step  ... 
doi:10.1109/tsmca.2004.824871 fatcat:sre4hnv3pvad5jpasiyotyvoea

An Agent-Based Modeling Framework for Online Collective Emotions [chapter]

David Garcia, Antonios Garas, Frank Schweitzer
2016 Understanding Complex Systems  
Modeling Real-Time Online Emotional Interaction Another application of our modeling framework provides insights on the nature of human communication in real-time online discussions, i.e. chatrooms.  ...  We can formalize this asymmetry of agent perception through an exponential function with a cubic decay, as explained in Garcia and Schweitzer (2011) .  ... 
doi:10.1007/978-3-319-43639-5_10 fatcat:xfer76vq2ffhpnwfiyw76vh4gu

A stochastic differential equation approach to the analysis of the UK 2017 and 2019 general election polls [article]

Mark Levene, Trevor Fenner
2021 arXiv   pre-print
The method uses the Euler-Maruyama method to simulate the time series, measuring the prediction error with the mean absolute error and the root mean square error, and as such could be used as part of a  ...  time series.  ...  A generative model for time series with application to polls Stochastic differential equations can provide effective generative models for time series.  ... 
arXiv:2005.11953v2 fatcat:e3r6uzocergjhmyhe6bsrovceq

Dynamical and bursty interactions in social networks

Juliette Stehlé, Alain Barrat, Ginestra Bianconi
2010 Physical Review E  
Different distributions of contact times and inter-contact times between individuals are obtained by considering transition probabilities with memory effects, i.e. the transition probabilities for each  ...  At each time a random agent can make a transition from being isolated to being part of a group, or vice-versa.  ...  If for instance f is a constant, it is easy to see that the ͕N p ͖ pN decay exponentially with time so that the ͕P p ͖͑͒ pϾ0 are as well exponentially decaying functions.  ... 
doi:10.1103/physreve.81.035101 pmid:20365802 fatcat:ukuo5qby7zftjfuanofporr66m

Dynamical Signatures of Collective Quality Grading in a Social Activity: Attendance to Motion Pictures

Juan Valentin Escobar, Didier Sornette
2014 Social Science Research Network  
This corresponds to an epidemic branching model comprised of a decaying exponential function determining the time between cause and action, and a cascade of actions triggered by previous ones.  ...  From our results, we are able to translate a subjective concept such as movie quality into a probability of the deriving individual activity, and from it we build concrete quantitative predictions.  ...  keeping the exponential shape of the decay of attendance as a function of time elapsed since the peak.  ... 
doi:10.2139/ssrn.2465011 fatcat:izup5blnqbgbblkkoskkr34wfu

Dynamical Signatures of Collective Quality Grading in a Social Activity: Attendance to Motion Pictures

Juan V. Escobar, Didier Sornette, Dante R. Chialvo
2015 PLoS ONE  
This corresponds to an epidemic branching model comprised of a decaying exponential function determining the time between cause and action, and a cascade of actions triggered by previous ones.  ...  From our results, we are able to translate a subjective concept such as movie quality into a probability of the deriving individual activity, and from it we build concrete quantitative predictions.  ...  keeping the exponential shape of the decay of attendance as a function of time elapsed since the peak.  ... 
doi:10.1371/journal.pone.0116811 pmid:25612292 pmcid:PMC4303319 fatcat:ed43o42fjrexlnfqftj4plpkhm

Self-organizing Ising model of financial markets

W.-X. Zhou, D. Sornette
2006 European Physical Journal B : Condensed Matter Physics  
We study a dynamical Ising model of agents' opinions (buy or sell) with coupling coefficients reassessed continuously in time according to how past external news (magnetic field) have explained realized  ...  We find that the stylized facts of financial markets are reproduced only when agents are over-confident and mis-attribute the success of news to predict return to herding effects, thereby providing positive  ...  and decay with the same characteristic time scale as a function of time lag.  ... 
doi:10.1140/epjb/e2006-00391-6 fatcat:pb2m4dkaqvfntoapinvm3gjniu

Empirical analysis of collective human behavior for extraordinary events in the blogosphere

Yukie Sano, Kenta Yamada, Hayafumi Watanabe, Hideki Takayasu, Misako Takayasu
2013 Physical Review E  
We focus on words that show dynamic growth and decay with a tendency to diverge on a certain day.  ...  After careful pretreatment and fitting method, we found power laws generally approximate the functional forms of growth and decay with various exponents values between -0.1 and -2.5.  ...  With this modification, we can determine the time-shifted time series.  ... 
doi:10.1103/physreve.87.012805 pmid:23410386 fatcat:f6wsp24e65h4ll2ri5we2nhlei

Online Multi-Agent Forecasting with Interpretable Collaborative Graph Neural Network [article]

Maosen Li, Siheng Chen, Yanning Shen, Genjia Liu, Ivor W. Tsang, Ya Zhang
2021 arXiv   pre-print
Extensive experiments are conducted on three tasks: online simulated trajectory prediction, online human motion prediction and online traffic speed prediction, and our methods outperform state-of-the-art  ...  Each collaborative predictor is trained to predict the status of an agent by considering the impact of another agent.  ...  PROBLEM FORMULATION With the time-series measurements collected by multiple agents in real-time, the task of online multi-agent forecasting essentially aims to predict the future statuses of each agent  ... 
arXiv:2107.00894v1 fatcat:4djnqe722vfx5d3xzn6oyig2by

Improving Artificial Teachers by Considering How People Learn and Forget [article]

Aurélien Nioche, Pierre-Alexandre Murena, Carlos de la Torre-Ortiz, Antti Oulasvirta
2021 arXiv   pre-print
The paper presents a novel model-based method for intelligent tutoring, with particular emphasis on the problem of selecting teaching interventions in interaction with humans.  ...  The approach is novel in its use of a cognitive model that can account for several key individual- and material-specific characteristics related to recall/forgetting, along with a planning technique that  ...  , and the Academy of Finland (projects 328813, "Human Automata," and 318559, "BAD").  ... 
arXiv:2102.04174v1 fatcat:s6fb74tbe5axdk6ecbhoqwes5q

Agent-Based Simulations of Emotional Dialogs in the Online Social Network MySpace [chapter]

Bosiljka Tadić, Milovan Šuvakov, David Garcia, Frank Schweitzer
2016 Understanding Complex Systems  
B.T. is grateful for support from the national program P1-0044 of the Research Agency of the Republic of Slovenia and COST-TD1210 action.  ...  M.Š. also thanks the national research projects ON171037 and III41011 of the Republic of Serbia.  ...  The exponential terms indicate the aging messages and the decay of the entire influence filed with the rate h , where t lm ji is the time of the last message arriving on the wall of agent i.  ... 
doi:10.1007/978-3-319-43639-5_11 fatcat:nyce446icbb5pnfgojuoud5q64

Agent-based simulations of emotion spreading in online social networks [article]

Milovan Šuvakov, David Garcia, Frank Schweitzer, Bosiljka Tadić
2012 arXiv   pre-print
Using agent-based computer simulations, in this paper we study dynamics of emotional communications in online social networks.  ...  High-resolution dynamics is implemented where each message carrying agent's emotion along the network link is identified and its effect on the recipient agent is considered as continuously aging in time  ...  B.T. thanks support from the national program P1-0044 of the research agency of the Republic of Slovenia and COST-MP0801 action.  ... 
arXiv:1205.6278v1 fatcat:x47gkboneffobincrtzivlioqi

Action Reaction Learning: Automatic Visual Analysis and Synthesis of Interactive Behaviour [chapter]

Tony Jebara, Alex Pentland
1999 Lecture Notes in Computer Science  
Using a time series of perceptual measurements, a system automatically uncovers correlations between past gestures from one human participant (an action) and a subsequent gesture ( a r eaction) from another  ...  Thus, after analyzing human interaction in a pair of participants, the system is able to replace one of them and interact with a single remaining user.  ...  The process is shown in Figure 7 where a window is placed over the time series, generating a short term memory Y . An exponential decay function is used to decay it and generates theŶ version.  ... 
doi:10.1007/3-540-49256-9_17 fatcat:rykslqvv4rcihpoc6xw3jn4smm
« Previous Showing results 1 — 15 out of 5,404 results