scholarly journals A Real Data-Driven Analytical Model to Predict Happiness

2021 ◽  
Vol 8 (3) ◽  
pp. 45-61
Author(s):  
  Aditya Chakraborty ◽  
Dr. Chris P. Tsokos
Keyword(s):  
Analytical Model ◽  
Real Data ◽  
Data Driven

scholarly journals A Real Data-Driven Analytical Model for Testing for the Novel Coronavirus Disease, COVID-19

2021 ◽  
Vol 5 (8) ◽  
Author(s):  
Chris P. Tsokos ◽  
Lohuwa Mamudu
Keyword(s):  
Risk Factors ◽  
Analytical Model ◽  
Nasal Congestion ◽  
Real Data ◽  
The United States ◽  
Data Driven ◽  
World Health ◽  
Medical Evaluation ◽  
Control And Prevention ◽  
Novel Coronavirus

To address the testing of the horrific pandemic disease that has terrified our global society, COVID-19, we have developed an analytical model that an individual can easily apply to determine if he or she tested positive or negative with a very high degree of accuracy. Our analytical model is real data-driven utilizing data obtained from the World Health Organization, WHO, and the United States Center for Disease Control and Prevention, CDC guidelines. Both WHO and CDC have identified several symptoms or risk factors from individuals diagnosed with the disease, COVID-19. They have identified and published nine symptoms that are associated with the disease, COVID-19. However, our structured analytical model identified only seven of the nine symptoms to statistically significantly contribute to the subject disease. They are fever, tiredness, dry cough, difficulty in breathing, sore throat, pain, and nasal congestion. Each of the symptoms shows highly likelihood of having COVID-19. Our analytical model was carefully developed, very well-validated, and statistically tested to achieve a 93% accuracy in the testing result. If a person is tested positive, we recommend that he/she seek medical evaluation and treatment. That is, once we receive the categorical data from a given individual, and we input into the proposed model, the output result will be the individual is tested positive or negative for COVID-19. The developed model identifies (estimated) the different weights of each of the seven symptoms or risk factors that play a major role in the decision process of the testing results. Our findings seek to enhance testing efficiency, treatment, control, and prevention strategy for the COVID-19 disease.

Data-Driven Cash Replenishment Planning of Recycling ATMs with Out-of-Cash and Full-of-Cash Risks

2020 ◽  
Vol 13 (2) ◽  
pp. 77-96
Author(s):  
Yongwu Zhou ◽  
Qiran Wang ◽  
Yongzhong Wu ◽  
Mianmian Huang
Keyword(s):  
Real Data ◽  
Service Level ◽  
Inventory Model ◽  
Data Driven ◽  
Safety Stocks ◽  
Automated Teller Machines ◽  
Operational Costs

When banks replenish the cash held in automated teller machines (ATMs) it is crucial for them to reduce operational costs while maintaining service level. This article studies the replenishment planning for recycling ATMs, which allow cash deposits to be made as well as withdrawals. The problem is formulated as a special (s, S) inventory model with two safety stocks corresponding to out-of-stock and full-of-stock risks, based on which the ATMs to be replenished each day and the replenishment amount are determined. Experiments with real data show that the model can significantly reduce costs and improve the overall service level.

scholarly journals Comparative Evaluation of Control-Oriented Zone Temperature Prediction Modeling Strategies in Buildings

2015 ◽  
Author(s):  
Venkatesh Chinde ◽  
Jeffrey C. Heylmun ◽  
Adam Kohl ◽  
Zhanhong Jiang ◽  
Soumik Sarkar ◽  
...  
Keyword(s):  
Comparative Evaluation ◽  
Performance Monitoring ◽  
Control Strategies ◽  
Critical Role ◽  
Energy Resource ◽  
Real Data ◽  
Data Driven ◽  
Monitoring And Control ◽  
Test Bed ◽  
Occupant Comfort

Predictive modeling of zone environment plays a critical role in developing and deploying advanced performance monitoring and control strategies for energy usage minimization in buildings while maintaining occupant comfort. The task remains extremely challenging, as buildings are fundamentally complex systems with large uncertainties stemming from weather, occupants, and building dynamics. Over the past few years, purely data-driven various control-oriented modeling techniques have been proposed to address different requirements, such as prediction accuracy, flexibility, computation and memory complexity. In this context, this paper presents a comparative evaluation among representative methods of different classes of models, such as first principles driven (e.g., lumped parameter autoregressive models using simple physical relationships), data-driven (e.g., artificial neural networks, Gaussian processes) and hybrid (e.g., semi-parametric). Apart from quantitative metrics described above, various qualitative aspects such as cost of commissioning, robustness and adaptability are discussed as well. Real data from Iowa Energy Center’s Energy Resource Station (ERS) test bed is used as the basis of evaluation presented here.

scholarly journals Recurrent Auto-Encoding Drift Diffusion Model

2017 ◽  
Author(s):  
Moens Vincent ◽  
Zenon Alexandre
Keyword(s):  
Diffusion Model ◽  
Real Data ◽  
Reaction Time Data ◽  
External Input ◽  
Current Data ◽  
Data Driven ◽  
Drift Diffusion Model ◽  
Time Data ◽  
Drift Diffusion ◽  
Modelling Framework

AbstractThe Drift Diffusion Model (DDM) is a popular model of behaviour that accounts for patterns of accuracy and reaction time data. In the Full DDM implementation, parameters are allowed to vary from trial-to-trial, making the model more powerful but also more challenging to fit to behavioural data. Current approaches yield typically poor fitting quality, are computationally expensive and usually require assuming constant threshold parameter across trials. Moreover, in most versions of the DDM, the sequence of participants’ choices is considered independent and identically distributed(i.i.d.), a condition often violated in real data.Our contribution to the field is threefold: first, we introduce Variational Bayes as a method to fit the full DDM. Second, we relax thei.i.d. assumption, and propose a data-driven algorithm based on a Recurrent Auto-Encoder (RAE-DDM), that estimates the local posterior probability of the DDM parameters at each trial based on the sequence of parameters and data preceding the current data point. Finally, we extend this algorithm to illustrate that the RAE-DDM provides an accurate modelling framework for regression analysis. An important result of the approach we propose is that inference at the trial level can be achieved efficiently for each and every parameter of the DDM, threshold included. This data-driven approach is highly generic and self-contained, in the sense that no external input (e.g. regressors or physiological measure) is necessary to fit the data. Using simulations, we show that this method outperformsi.i.d.-based approaches (either Markov Chain Monte Carlo ori.i.d.-VB) without making any assumption about the nature of the between-trial correlation of the parameters.

scholarly journals Feed-forward control of elastic-joint industrial robot based on hybrid inverse dynamic model

2021 ◽  
Vol 13 (9) ◽  
pp. 168781402110381
Author(s):  
Mei Zaiwu ◽  
Chen Liping ◽  
Ding Jianwan
Keyword(s):  
Dynamic Model ◽  
Analytical Model ◽  
Control Method ◽  
Data Driven ◽  
Parameter Uncertainties ◽  
Inverse Dynamic ◽  
Inverse Dynamic Model ◽  
Feed Forward ◽  
Elastic Joint ◽  
Feed Forward Control

A novel feedforward control method of elastic-joint robot based on hybrid inverse dynamic model is proposed in this paper. The hybrid inverse dynamic model consists of analytical model and data-driven model. Firstly, the inverse dynamic analytical model of elastic-joint robot is established based on Lie group and Lie algebra, which improves the efficiency of modeling and calculation. Then, by coupling the data-driven model with the analytical model, a feed-forward control method based on hybrid inverse dynamics model is proposed. This method can overcome the influence of the inaccuracy of the analytical inverse dynamic model on the control performance, and effectively improve the control accuracy of the robot. The data-driven model is used to compensate for the parameter uncertainties and non-parameter uncertainties of the analytical dynamic model. Finally, the proposed control method is proved to be stable and the multi-domain integrated system model of industrial robot is developed to verify the performance of the control scheme by simulation. The simulation results show that the proposed control method has higher control accuracy than the traditional torque feed-forward control method.

scholarly journals Interpretable, Data-Efficient and Verifiable Autonomy with High-Level Knowledge

2020 ◽  
Author(s):  
Zhe Xu
Keyword(s):  
Artificial Intelligence ◽  
Neural Networks ◽  
Deep Neural Networks ◽  
Autonomous Systems ◽  
Real Data ◽  
Data Driven ◽  
Knowledge Representations ◽  
Limited Availability ◽  
High Level ◽  
Level Performance

<p>Despite the fact that artificial intelligence boosted with data-driven methods (e.g., deep neural networks) has surpassed human-level performance in various tasks, its application to autonomous</p> <p>systems still faces fundamental challenges such as lack of interpretability, intensive need for data and lack of verifiability. In this overview paper, I overview some attempts to address these fundamental challenges by explaining, guiding and verifying autonomous systems, taking into account limited availability of simulated and real data, the expressivity of high-level</p> <p>knowledge representations and the uncertainties of the underlying model. Specifically, this paper covers learning high-level knowledge from data for interpretable autonomous systems,</p><p>guiding autonomous systems with high-level knowledge, and</p><p>verifying and controlling autonomous systems against high-level specifications.</p>

scholarly journals Towards Data-Driven Vehicle Estimation for Signalised Intersections in a Partially Connected Environment

Sensors ◽  
2021 ◽  
Vol 21 (24) ◽  
pp. 8477
Author(s):  
Roozbeh Mohammadi ◽  
Claudio Roncoli
Keyword(s):  
Traffic Control ◽  
Partial Information ◽  
Control Strategies ◽  
Synthetic Data ◽  
Real Data ◽  
Significant Loss ◽  
Data Driven ◽  
Estimation Methods ◽  
Connected Vehicles ◽  
Vehicle Data

Connected vehicles (CVs) have the potential to collect and share information that, if appropriately processed, can be employed for advanced traffic control strategies, rendering infrastructure-based sensing obsolete. However, before we reach a fully connected environment, where all vehicles are CVs, we have to deal with the challenge of incomplete data. In this paper, we develop data-driven methods for the estimation of vehicles approaching a signalised intersection, based on the availability of partial information stemming from an unknown penetration rate of CVs. In particular, we build machine learning models with the aim of capturing the nonlinear relations between the inputs (CV data) and the output (number of non-connected vehicles), which are characterised by highly complex interactions and may be affected by a large number of factors. We show that, in order to train these models, we may use data that can be easily collected with modern technologies. Moreover, we demonstrate that, if the available real data is not deemed sufficient, training can be performed using synthetic data, produced via microscopic simulations calibrated with real data, without a significant loss of performance. Numerical experiments, where the estimation methods are tested using real vehicle data simulating the presence of various penetration rates of CVs, show very good performance of the estimators, making them promising candidates for applications in the near future.

scholarly journals An Evaluation of COVID-19 in Italy: A data-driven modeling analysis

2020 ◽  
Author(s):  
Yongmei Ding ◽  
Liyuan Gao
Keyword(s):  
Real Data ◽  
Data Driven ◽  
The Novel ◽  
State Variables ◽  
Infected People ◽  
Modeling Analysis ◽  
Travel Restrictions ◽  
Novel Coronavirus ◽  
Data Driven Modeling ◽  
Global Travel

Abstract The novel coronavirus (COVID-19) that has been spreading worldwide since December 2019 has sickened millions of people, shut down major cities and some countries, prompted unprecedented global travel restrictions. Real data-driven modeling is an effort to help evaluate and curb the spread of the novel virus. Lockdowns and the effectiveness of reduction in the contacts in Italy has been measured via our modified model, with the addition of auxiliary and state variables that represent contacts, contacts with infected, conversion rate, latent propagation. Results show the decrease in infected people due to stay-at-home orders and tracing quarantine intervention. The effect of quarantine and centralized medical treatment was also measured through numerical modeling analysis.

Sign in / Sign up

Export Citation Format

Share Document