Improving Forecasting Performance by Exploiting Expert Knowledge: Evidence from Guangzhou Port

2016 ◽  
Vol 15 (02) ◽  
pp. 387-401 ◽  
Author(s):  
Anqiang Huang ◽  
Han Qiao ◽  
Shouyang Wang ◽  
John Liu
Keyword(s):  
Expert Knowledge ◽  
Constraint Equation ◽  
Positive Contribution ◽  
New Approach ◽  
Subjective Judgment ◽  
Forecasting Performance ◽  
Predicted Values

Expert knowledge has been proved by substantial studies to be contributory to higher forecasting performance; meanwhile, its application is criticized and opposed by some groups for biases and inconsistency inherent in experts’ subjective judgment. This paper proposes a new approach to improving forecasting performance, which takes advantage of expert knowledge by constructing a constraint equation rather than directly adjusting the predicted values by experts. For the comparison purpose, the proposed approach, together with several widely used models including ARIMA, BP-ANN and the judgment model (JM), is applied to forecasting the container throughput of Guangzhou Port, which is one of the most important ports of China. Forecasting performances of the above models are compared and the results clearly show superiority of the proposed approach over its rivals, which implies that expert knowledge will make positive contribution as long as it is used in a right way.

A new approach to bracket prediction in the NCAA Men’s Basketball Tournament based on a dual-proportion likelihood

2015 ◽  
Vol 11 (1) ◽  
Author(s):  
Ajay Andrew Gupta
Keyword(s):  
National Collegiate Athletic Association ◽  
Expert Knowledge ◽  
Probability Model ◽  
Expected Value ◽  
Division I ◽  
Prediction System ◽  
New Approach ◽  
Men's Basketball ◽  
Popular Interest ◽  
The One

AbstractThe widespread proliferation of and interest in bracket pools that accompany the National Collegiate Athletic Association Division I Men’s Basketball Tournament have created a need to produce a set of predicted winners for each tournament game by people without expert knowledge of college basketball. Previous research has addressed bracket prediction to some degree, but not nearly on the level of the popular interest in the topic. This paper reviews relevant previous research, and then introduces a rating system for teams using game data from that season prior to the tournament. The ratings from this system are used within a novel, four-predictor probability model to produce sets of bracket predictions for each tournament from 2009 to 2014. This dual-proportion probability model is built around the constraint of two teams with a combined 100% probability of winning a given game. This paper also performs Monte Carlo simulation to investigate whether modifications are necessary from an expected value-based prediction system such as the one introduced in the paper, in order to have the maximum bracket score within a defined group. The findings are that selecting one high-probability “upset” team for one to three late rounds games is likely to outperform other strategies, including one with no modifications to the expected value, as long as the upset choice overlaps a large minority of competing brackets while leaving the bracket some distinguishing characteristics in late rounds.

An Automated Layout Design System for Industrial Plant Piping

1991 ◽  
Author(s):  
N. Narikawa ◽  
S. Fujimoto ◽  
N. Sasaki ◽  
S. Azuma
Keyword(s):  
Expert Knowledge ◽  
Routing Algorithm ◽  
Layout Design ◽  
Memory Storage ◽  
Industrial Plant ◽  
Design System ◽  
Small Computer ◽  
Phase Step ◽  
New Approach ◽  
Weak Constraints

Abstract This paper describes a new approach to an automated layout design system for industrial plant piping. The routing system, which is the main part of this layout system, is composed of three steps, according to the practical layout design process. By dividing the layout design into the optimal routing phase (Step 1, Step 2) and the arrangement phase (Step 3), it is possible to design without depending on the routing order, and with small computer memory storage capacities. The optimal route is obtained by using the routing algorithm and heuristic search, based on expert knowledge. The arrangements are made by applying the enumeration method, taking the strong and weak constraints into account.

Endurance vs. strength training: comparison of cardiac structures using normal predicted values

1988 ◽  
Vol 64 (6) ◽  
pp. 2552-2557 ◽  
Author(s):  
A. Roy ◽  
M. Doyon ◽  
J. G. Dumesnil ◽  
J. Jobin ◽  
F. Landry
Keyword(s):  
Individual Differences ◽  
Strength Training ◽  
Body Surface ◽  
Normal Values ◽  
Volume Overload ◽  
Left Ventricular ◽  
New Approach ◽  
Lv Mass ◽  
Lv Volume ◽  
Predicted Values

There are still disagreements concerning the adaptation of cardiac structures in relation to different training stimuli. To eliminate some of the variance due to individual differences in body surface area, we utilized a new approach based on the calculation of the percentages of each individual's normal predicted values (%NPV). We studied 46 strength (S, bodybuilders) and 57 endurance (E, runners) athletes. Left ventricular (LV) mass was 143.8 +/- 21.9 %NPV (mean +/- SD) in E vs. 134.3 +/- 23.4 %NPV in S (P less than 0.05), and LV volume was 131.0 +/- 24.0 %NPV in E vs. 120.0 +/- 25.5 %NPV in S (P less than 0.05). Moreover, the LV wall thickness-to-radius ratio did not differ from normal values in either group. From these data we conclude that 1) cardiac modifications are greater in E than S, 2) the predominant stimulus is a volume overload type in both groups, and 3) concentric LV hypertrophy may not be as prevalent in S as previously suggested.

scholarly journals Fuzzy Filtering of Sensors Signals in Manufacturing Systems with Time Constraints

2010 ◽  
Vol 5 (3) ◽  
pp. 362 ◽  
Author(s):  
Anis M’halla ◽  
Nabil Jerbi ◽  
Simon Collart Dutilleul ◽  
Etienne Craye ◽  
Mohamed Benrejeb
Keyword(s):  
Fuzzy Systems ◽  
Manufacturing Systems ◽  
Knowledge Integration ◽  
Expert Knowledge ◽  
Time Constraints ◽  
Quality And Safety ◽  
Job Shops ◽  
New Approach ◽  
Robustness Property ◽  
Filtering Approach

The presented work is dedicated to the supervision of manufacturing job-shops with time constraints. Such systems have a robustness property towards time disturbances. The main contribution of this paper is a fuzzy filtering approach of sensors signals integrating the robustness values. This new approach integrates a classic filtering mechanism of sensors signals and fuzzy logic techniques. The strengths of these both techniques are taken advantage of the avoidance of control freezing and the capability of fuzzy systems to deal with imprecise information by using fuzzy rules. Finally, to demonstrate the effectiveness and accuracy of this new approach, an example is depicted. The results show that the fuzzy approach allows keeping on producing, but in a degraded mode, while providing the guarantees of quality and safety based on expert knowledge integration.

scholarly journals Prediction of vine vigor and precocity using data and knowledge-based fuzzy inference systems

OENO One ◽  
2012 ◽  
Vol 46 (3) ◽  
pp. 185 ◽  
Author(s):  
Cécile Coulon-Leroy ◽  
Brigitte Charnomordic ◽  
Dominique Rioux ◽  
Marie Thiollet-Scholtus ◽  
Serge Guillaume
Keyword(s):  
Expert System ◽  
Environmental Factors ◽  
Management Practices ◽  
Fuzzy Inference ◽  
Cultural Practices ◽  
Expert Knowledge ◽  
Scientific Evidence ◽  
Parent Rock ◽  
New Approach ◽  
Continuous Estimation

<p style="text-align: justify;"><strong>Aims</strong>: The evolution of the economic and environmental context (low-input management practices, increase of energy cost and climate change) requires adaptation and/or optimization of winegrower’s practices in order to elaborate competitive and yet still qualitative wines. To adapt and sustain their practices at the plot scale (<em>e.g.</em>, rootstock selection or plantation density), winegrowers and viticultural consultants need indicators to predict vine development based on permanent environmental factors (soil, parent rock and landscape). As of today, such indicators are either nonexistent or too basic. The aim of this work is to develop operational and useful indicators based on strong scientific evidence.</p><p style="text-align: justify;"><strong>Methods and results</strong>: This paper proposes a new approach based on a computer model composed of a cascade of fuzzy expert systems to estimate the two variables that best characterize vine development: vigor (VIG) and precocity (PRE). This model combines pedological expertise and data analysis. Based on scientific literature, and in particular on a previous expert system using analytical equations (Morlat <em>et al.</em>, 2001), the new approach allows a continuous estimation of VIG and PRE imparted by soil, parent rock and landscape. Further, it avoids the drawbacks of the previous expert system, due to the use of traditional crisp partitions for continuous input variables. Another novel aspect is the parameter setting, which efficiently combines expert knowledge and data mining. Finally, the method is tuned and validated against two different databases.</p><p style="text-align: justify;"><strong>Conclusion</strong>: VIG and PRE imparted by environmental factors can now be evaluated more efficiently than with the former methods. The new method eliminates the need for post-evaluation correction by experts, which saves time. It also allows a continuous estimation of these variables. Each step can be controlled and analyzed during the design. Finally, the method is generic in the sense that the reasoning used to represent the relations between variables is not restricted to a given area. It can easily be customized and adapted to new areas by adjusting the parameters using local pedological knowledge and data.</p><p style="text-align: justify;"><strong>Significance and impact of the study</strong>: This work answers the significant problem of VIG and PRE assessment according to environmental factors, which is a prerequisite in order to best adapt long-term cultural practices.</p>

scholarly journals A new approach to integrating patient-generated data with expert knowledge for personalized goal setting: A pilot study

2020 ◽  
Vol 139 ◽  
pp. 104158
Author(s):  
Marissa Burgermaster ◽  
Jung H. Son ◽  
Patricia G. Davidson ◽  
Arlene M. Smaldone ◽  
Gilad Kuperman ◽  
...  
Keyword(s):  
Pilot Study ◽  
Goal Setting ◽  
Expert Knowledge ◽  
New Approach

scholarly journals Automated Prediction of the Liquid Paraffins Viscosity

2021 ◽  
Vol 2096 (1) ◽  
pp. 012084
Author(s):  
B A Grigoriev ◽  
D V Boldyrev
Keyword(s):  
Experimental Data ◽  
Control Systems ◽  
Raw Materials ◽  
Petroleum Products ◽  
Physicochemical Analysis ◽  
New Approach ◽  
Automatic Control Systems ◽  
Systems Software ◽  
Construction Of Self ◽  
Predicted Values

Abstract The article deals with an approach to the construction of self-adjusting automatic control systems, in which parametric adaptation occurs when the properties of technological raw materials change during its processing due to changes in the parameters of state. A new algorithm for predicting the viscosity of hydrocarbon liquids is proposed, which can be used as part of the control systems software. The main dependences are obtained on the basis of reliable experimental data on the viscosity of normal C8–C20 alkanes, which are similar in properties to commodity petroleum products. The data of physicochemical analysis are used as the initial data for the computation. Based on the theory of corresponding states, a new approach to scaling the viscosity using a set of characteristic parameters is developed and technique for their determination is proposed. The method is tested in the temperature range (0.4 – 0.7)TC at pressures up to 10 MPa. It is shown that the deviation of the predicted values from the experimental data is comparable to the error of the viscosity measurement.

New Approach for Calibration Transfer from a Local Database to a Global Database

1998 ◽  
Vol 6 (1) ◽  
pp. 55-60 ◽  
Author(s):  
Pierre Dardenne ◽  
Roland Welle
Keyword(s):  
Sample Selection ◽  
Maize Silage ◽  
Calibration Transfer ◽  
Mahalanobis Distances ◽  
New Approach ◽  
Global Database ◽  
Local Database ◽  
Whole Plant ◽  
Predicted Values ◽  
New Equation

The goal of the experiment is to transfer a local model to a global model for the prediction of a new parameter. Station de Haute Belgique (SHB) has developed an extensive spectral database to determine 10 parameters of whole plant maize silage samples. Pioneer has determined the Tilley and Terry digestibility (T&T) on a smaller set of samples. The analysis of the Mahalanobis distances between the two sets shows that Pioneer's set has a much smaller variation than SHB's set. Pioneer's set can be predicted by SHB's calibrations, but SHB's database cannot be predicted by Pioneer's calibration. The 10 parameters predicted on Pioneer's set are used to estimate the Tilley and Terry digestibility coefficient through a PLS model. The same model is then used to predict T&T on the large SHB set. The later predicted values are reported as references on SHB's set and a global T&T equation is developed after an adequate sample selection. The procedure shows that the new equation, applied on independent sets, is more accurate and more robust than the local one.

Does Interval Knowledge Sharpen Forecasting Models? Evidence from China’s Typical Ports

2018 ◽  
Vol 17 (02) ◽  
pp. 467-483 ◽  
Author(s):  
Anqiang Huang ◽  
Kin Keung Lai ◽  
Han Qiao ◽  
Shouyang Wang ◽  
Zhenji Zhang
Keyword(s):  
Expert System ◽  
Statistical Models ◽  
Expert Knowledge ◽  
Large Body ◽  
Interval Estimation ◽  
Point Estimation ◽  
Forecasting Models ◽  
Forecasting Performance ◽  
Good Potential ◽  
Economic Regions

Substantial studies integrating experts’ point knowledge with statistical forecasting modes have been implemented to investigate a long-lasting and disputing issue which is whether or not expert knowledge could improve forecasting performance. However, a large body of current forecasting studies neglect the application of experts’ interval knowledge where experts are expected to be more competent, considering that humans do much better in fuzzy calculation like interval estimation than in accurate computation like point estimation. To fill in this gap, this paper first proposes a novel forecasting paradigm incorporating interval knowledge generated by a Delphi-based expert system into the SARIMA and SVR models. For validation purposes, the proposed paradigm is applied to several representative seaports from the top three dynamic economic regions in China. The empirical results clearly show that interval knowledge, following the proposed paradigm, significantly improves the forecasting performance. This finding implies that the proposed forecasting paradigm has the good potential to be an effective method for sharpening the statistical models for container throughput forecasting.

Modified analytical method to calculate the assembly and separation forces of cantilever hook-type snap-fit

2019 ◽  
Vol 233 (14) ◽  
pp. 5074-5084 ◽  
Author(s):  
Bruno Robert Mose ◽  
In-Seo Son ◽  
Joon-Woo Bae ◽  
Hong-Geul Ann ◽  
Choon Yeol Lee ◽  
...  
Keyword(s):  
Finite Element Analysis ◽  
Finite Element ◽  
Analytical Method ◽  
Previous Method ◽  
Experimental Investigations ◽  
Element Analysis ◽  
New Approach ◽  
The Face ◽  
Predicted Values ◽  
Separation Force

In this study, a new analytical method to calculate the assembly force and separation force of cantilever hook type snap-fit was proposed. Finite element analysis and experimental measurement were performed to verify the new approach. It was found out that the conventional analytical method had a few limitations. The solution was only applicable when the retention face angle was small, and there existed a critical value of retention face angle where separation force unreasonably decreased with increase in deflection. The new approach considered large deflection of retention feature and resultant moment term in addition to the previous method, and the solution was obtained explicitly. The new analytical solution could be applied to large face angles without any divergence, and showed good agreement with finite element analysis results. When the face angle was relatively small, both conventional method and new method showed reasonable results; however, when the angle was large, only the new analytical method showed reasonable results. Experimental investigations of forces during assembly and separation showed that the measured forces were much smaller than the predicted values by analytical methods and finite element analysis. The forces were strongly dependent on the rigidity of the mating part and the magnitude of radius at the edges of beam and mating parts. It was found from experiment that the separation force nonlinearly increased as clearance decreased.

Sign in / Sign up

Export Citation Format

Share Document