Search results

The purpose of this paper is to propose an optimal predictive model for the short-term forecast of real-time non-stationary machine variables by combining time series prediction with adaptive algorithms to minimize the error and to improve the prediction accuracy.

The proposed model is applied for prediction of speed and controller set point of three-phase induction motor operating on closed loop speed control with AC drive and PI controller. At Stage 1, the trend of the machine variables has been extracted and added to auto-regressive moving average (ARMA) time series prediction. ARMA prediction has been carried out using different combinations of AR and MA methods in order to make prediction with less Mean Squared Error (MSE).

The prediction error indicates the inadequacy of the model to estimate the data characteristics, which has been resolved at the subsequent stage by cascading an adaptive least mean square finite impulse response filter to the time series model. The adaptive filter receives the predicted output including training data and iteratively adjusts its coefficients for zero error convergence.

The componentized data prediction based on time series and cascade adaptive filter algorithm decomposes the non-stationary data characteristics for predictive maintenance. Evaluation of the model with different combination of time series algorithms and parameter settings of adaptive filter has been carried out to illustrate the performance of the prediction model. This prediction accuracy is compared with existing linear adaptive filter prediction using MSE as comparison index. The wide margin in the MSE values substantiates the prediction efficiency of the proposed model for machine data.

This model predicts the dynamic machine data with component decomposition at high accuracy, which enables to interpret the system response under dynamic conditions efficiently.

In an increasingly dangerous era for brands because of the emergence of fake news on the internet, brand managers need to know what is happening with fake news. This study aims to present perspectives on how to cope in an era of fake news.

The author provides a general review of fake news and what its sudden rise means for brand managers.

The study highlights the importance of context for news and the role of institutions, such as businesses and governments. The study calls brand managers to slow down in the high-speed world of the infosphere to preserve the integrity of their brands.

The study is limited by its time frame as the internet continues to evolve. However, for times when fake news presents a threat to brands and other institutions, the study is relevant.

Brand managers need to slow down their activity levels just as savvy readers need to slow down their own reading on the internet. By doing this, brand managers will be better able to defend their brands in an era characterized by volatility, uncertainty, complexity and ambiguity (VUCA).

The study suggests that resistance to fake news and its pernicious effects can be improved by taking an approach to processing content on the internet characterized by the scientific method. In this way, a context for news can be derived and fake news can be identified. In this way, societal trust can be improved.

This study is original because it analyzes the implications of fake news for brand managers and presents the most workable steps for identifying fake news.

The demand for accurate property value estimation by valuation report end users has led to a shift towards advanced property valuation modelling techniques in some property markets and these require a sizeable number of data set to function. In a situation where there is a lack of a centralised transaction data bank, scholars and practitioners usually collect data from different sources for analysis, which could affect the accuracy of property valuation estimates. This study aims to establish the suitability of different data sources that are reliable for estimating accurate property values.

This study adopts the Lagos metropolis property market, Nigeria, as the study area. Transaction data of residential properties are collected from two sources, i.e. from real estate firms (selling price) and listing prices from an online real estate company. A portion of the collected data is fitted into the artificial neural network (ANN) model, which is used to predict the remaining property prices. The holdout sample data are predicted with the developed ANN models. Thereafter, the predicted prices and the actual prices are compared so as to establish which data set generates the most accurate property valuation estimates.

It is found that the listing data (listing prices) produced an encouraging mean absolute error (MAE), root mean square error (RMSE) and mean absolute percentage error (MAPE) values compared with the firms’ data (selling prices). An MAPE value of 26.93 and 29.96 per cent was generated from the listing and firms’ data, respectively. A larger proportion of the predicted listing prices had property valuation error of margin that is within the industry acceptable standard of between ±0 and 10 per cent, compared with the predicted selling prices. Also, a higher valuation accuracy was recorded in properties with lower values, compared with expensive properties.

The opaqueness in real estate transactions consummated in developing nations could be attributed to why selling prices (data) could not produce more accurate valuation estimates in this study than listing prices. Despite the encouraging results produced using listing prices, there is still an urgent need to maintain a robust and quality property data bank in developing nations, as obtainable in most developed nations, so as to achieve a sustainable global property valuation practice.

This study does not investigate the relationship between listing prices and selling prices, which has been conducted in previous studies, but examines their suitability to improve property valuation accuracy in an emerging property market. The findings of this study would be useful in property markets where property transaction data bank is not available.

This chapter will identify readily accessible existing sources of public data. Thechallenges of using that data are considerable and require extensive time to ensure validity for reporting purposes. Summaries of data field selection and data wrangling requirements are presented in conjunction with data aggregation strategies.

Knowledge of the effect of various cash-flow factors on expected project profit is important to effectively manage productivity on construction projects. This study was conducted to develop and test the sensitivity of a Machine Learning Support Vector Regression Algorithm (SVRA) to predict construction project profit in Ghana.

The study relied on data from 150 institutional projects executed within the past five years (2014–2018) in developing the model. Eighty percent (80%) of the data from the 150 projects was used at hyperparameter selection and final training phases of the model development and the remaining 20% for model testing. Using MATLAB for Support Vector Regression, the parameters available for tuning were the epsilon values, the kernel scale, the box constraint and standardisations. The sensitivity index was computed to determine the degree to which the independent variables impact the dependent variable.

The developed model's predictions perfectly fitted the data and explained all the variability of the response data around its mean. Average predictive accuracy of 73.66% was achieved with all the variables on the different projects in validation. The developed SVR model was sensitive to labour and loan.

The developed SVRA combines variation, defective works and labour with other financial constraints, which have been the variables used in previous studies. It will aid contractors in predicting profit on completion at commencement and also provide information on the effect of changes to cash-flow factors on profit.

The purpose of this paper is to study the effect of copper concentration in near‐eutectic liquid SAC solders on their thermophysical properties: viscosity, surface tension, density; as well as wetting behavior on copper substrates at 523 K.

Viscosity, surface tension, and density were studied over a broad range of temperatures with the recently developed Roach‐Henein method. The obtained results were compared with the data from modified capillary, maximum bubble pressure, wetting balance and dilatometric measurements. Wetting angles measured with wetting balance method were compared with the results of sessile drop measurements.

The results obtained indicate that increasing concentration of copper in the alloy results in higher density, surface tension and viscosity, but differences resulting from copper concentration on wettability are relatively small. At 523 K, the density is: 7.097, 7.186, 7.232 g cm⁻³, the surface tension is: 538.1, 553.5, 556.7 m Nm⁻¹, the viscosity is: 2.173, 2.227, 2.467 mPas, respectively, for alloys containing 0.41, 1.01 and 1.61 wt% of Cu. Wetting angles on copper substrates are similar within a margin of error for all compositions. The results of present study are compared with the available literature data and a relatively good agreement is observed.

This paper provides the data of thermophysical properties of widely‐used SAC solders including viscosity, of which there is little data in the literature. It is confirmed that the increased copper concentration increases viscosity, yet this effect is small and does not correlate with the wetting behavior.

Prediction markets are techniques to aggregate dispersed public opinions via market mechanisms to predict uncertain future events’ outcome. Many experiments have shown that prediction markets outperform other traditional forecasting methods in terms of accuracy. Logarithmic market scoring rules (LMSR) is one of the most simple and widely used market mechanisms; however, market makers have to confront crucial design decisions including the setting of the parameter “b” or the “liquidity parameter” in the price functions. As the liquidity parameter has significant effects on the market performance, this paper aims to provide a comprehensive basis for the setting of the parameter.

The analyses include the effects of the liquidity parameter on the forecast standard error and the amount of time for the market price to converge to the true value. These experiments use artificial prediction markets, the proposed simulation models that mimic real prediction markets.

The simulation results indicate that prediction market’s forecast standard error decreases as the value of the liquidity parameter increases. Moreover, for any given number of traders in the market, there exists an optimal liquidity parameter value that yields appropriate price adaptability and leads to the fastest price convergence.

Understanding these tradeoffs, the market makers can effectively determine the liquidity parameter value under various objectives on the standard error, the time to convergence and cost.

The purpose of this paper is to propose a simple, fast, and effective method for detecting measurement errors in data collected with low-cost environmental sensors typically used in building monitoring, evaluation, and automation applications.

The method combines two unsupervised learning techniques: a distance-based anomaly detection algorithm analyzing temporal patterns in data, and a density-based algorithm comparing data across different spatially related sensors.

Results of tests using 60,000 observations of temperature and humidity collected from 20 sensors during three weeks show that the method effectively identified measurement errors and was not affected by valid unusual events. Precision, recall, and accuracy were 0.999 or higher for all cases tested.

The method is simple to implement, computationally inexpensive, and fast enough to be used in real-time with modest open-source microprocessors and a wide variety of environmental sensors. It is a robust and convenient approach for overcoming the hardware constraints of low-cost sensors, allowing users to improve the quality of collected data at almost no additional cost and effort.

The paper aims to examine fall armyworm's (FAW) effect on Ghana's farming households' income and food security status.

A sample of 225 farmers, including FAW-infested households and non-FAW-infested households, were interviewed. Gross margin (GM) analysis was used to estimate farmers' farm revenues, and the Household Food Insecurity Access Scores (HFIAS) was employed to measure the food security status of the households. The seemingly unrelated regression (SUR) was adopted to investigate the effect of FAW infestation on gross income and food security.

From the study, FAW attack is predominant during the vegetative stage of the maize plant. The empirical results revealed that FAW-infested farms incur loss, whereas non-FAW-infested farmers gained profit. Also, FAW-infested households were mildly food insecure, while non-FAW-infested households were food secured. The results of SUR analysis reveal that FAW infestation decreased farmers' income from maize production and rendered them food insecure.

One limitation of this study is that it largely depended on a survey; however, future studies can combine both survey and experimental data from the farmers' fields during minor and major growing seasons of maize.

Given the negative consequences of FAW, studies have been conducted across Africa and globally. However, most of these studies concentrated on using geographic information system (GIS) and descriptive statistics without necessarily quantifying the effect of FAW on food security and the profit margins of farming households. Therefore, this study adds to the little literature on the effect of FAW on food security and GM from maize production, which has received less attention in Ghana to the authors' best knowledge.