Abstract: Asset management of urban infrastructures faces a multitude of challenges that need to be overcome to obtain a reliable measurement of performances. Predicting the performance of slowly aging systems is one of those challenges, which helps the asset manager to investigate specific failure modes and to undertake the appropriate maintenance and rehabilitation interventions to avoid catastrophic failures as well as to optimize the maintenance costs. This article presents a methodology for modeling the deterioration of slowly degrading assets based on an operating history. It consists of extracting degradation profiles by grouping together assets that exhibit similar degradation sequences using an unsupervised classification technique derived from artificial intelligence. The obtained clusters are used to build the performance prediction models. This methodology is applied to a sample of a stormwater drainage culvert dataset.
Abstract: Research in predictive maintenance modeling has improved in the recent years to predict failures and needed maintenance with high accuracy, saving cost and improving manufacturing efficiency. However, classic prediction models provide little valuable insight towards the most important features contributing to the failure. By analyzing and quantifying feature importance in predictive maintenance models, cost saving can be optimized based on business goals. First, multiple classifiers are evaluated with cross-validation to predict the multi-class of failures. Second, predictive performance with features provided by different feature selection algorithms are further analyzed. Third, features selected by different algorithms are ranked and combined based on their predictive power. Finally, linear explainer SHAP (SHapley Additive exPlanations) is applied to interpret classifier behavior and provide further insight towards the specific roles of features in both local predictions and global model behavior. The results of the experiments suggest that certain features play dominant roles in predictive models while others have significantly less impact on the overall performance. Moreover, for multi-class prediction of machine failures, the most important features vary with type of machine failures. The results may lead to improved productivity and cost saving by prioritizing sensor deployment, data collection, and data processing of more important features over less importance features.
Abstract: The emergence of digital twin technology, a digital replica of physical world, has improved the real-time access to data from sensors about the performance of buildings. This digital transformation has opened up many opportunities to improve the management of the building by using the data collected to help monitor consumption patterns and energy leakages. One example is the integration of predictive models for anomaly detection. In this paper, we use the GAM (Generalised Additive Model) for the anomaly detection of Air Handling Units (AHU) power consumption pattern. There is ample research work on the use of GAM for the prediction of power consumption at the office building and nation-wide level. However, there is limited illustration of its anomaly detection capabilities, prescriptive analytics case study, and its integration with the latest development of digital twin technology. In this paper, we applied the general GAM modelling framework on the historical data of the AHU power consumption and cooling load of the building between Jan 2018 to Aug 2019 from an education campus in Singapore to train prediction models that, in turn, yield predicted values and ranges. The historical data are seamlessly extracted from the digital twin for modelling purposes. We enhanced the utility of the GAM model by using it to power a real-time anomaly detection system based on the forward predicted ranges. The magnitude of deviation from the upper and lower bounds of the uncertainty intervals is used to inform and identify anomalous data points, all based on historical data, without explicit intervention from domain experts. Notwithstanding, the domain expert fits in through an optional feedback loop through which iterative data cleansing is performed. After an anomalously high or low level of power consumption detected, a set of rule-based conditions are evaluated in real-time to help determine the next course of action for the facilities manager. The performance of GAM is then compared with other approaches to evaluate its effectiveness. Lastly, we discuss the successfully deployment of this approach for the detection of anomalous power consumption pattern and illustrated with real-world use cases.
Abstract: The impact the climate change is not recent, the main variable in the hydrological cycle is the sequence and shortage of a drought, which has a significant impact on the socioeconomic, agricultural and environmental spheres. This study aims to characterize and quantify, based on precipitation climatic projections, the rainy and dry events in the region of the Uruguay River Basin, through the Standardized Precipitation Index (SPI). The database is the image that is part of the Intercomparison of Model Models, Phase 5 (CMIP5), which provides condition prediction models, organized according to the Representative Routes of Concentration (CPR). Compared to the normal set of climates in the Uruguay River Watershed through precipitation projections, seasonal precipitation increases for all proposed scenarios, with a low climate trend. From the data of this research, the idea is that this article can be used to support research and the responsible bodies can use it as a subsidy for mitigation measures in other hydrographic basins.
Abstract: Crop yield prediction is a paramount issue in
agriculture. The main idea of this paper is to find out efficient
way to predict the yield of corn based meteorological records.
The prediction models used in this paper can be classified into
model-driven approaches and data-driven approaches, according to
the different modeling methodologies. The model-driven approaches are based on crop mechanistic
modeling. They describe crop growth in interaction with their
environment as dynamical systems. But the calibration process of
the dynamic system comes up with much difficulty, because it
turns out to be a multidimensional non-convex optimization problem.
An original contribution of this paper is to propose a statistical
methodology, Multi-Scenarios Parameters Estimation (MSPE), for the
parametrization of potentially complex mechanistic models from a
new type of datasets (climatic data, final yield in many situations).
It is tested with CORNFLO, a crop model for maize growth. On the other hand, the data-driven approach for yield prediction
is free of the complex biophysical process. But it has some strict
requirements about the dataset.
A second contribution of the paper is the comparison of these
model-driven methods with classical data-driven methods. For this
purpose, we consider two classes of regression methods, methods
derived from linear regression (Ridge and Lasso Regression, Principal
Components Regression or Partial Least Squares Regression) and
machine learning methods (Random Forest, k-Nearest Neighbor,
Artificial Neural Network and SVM regression).
The dataset consists of 720 records of corn yield at county scale
provided by the United States Department of Agriculture (USDA) and
the associated climatic data. A 5-folds cross-validation process and
two accuracy metrics: root mean square error of prediction(RMSEP),
mean absolute error of prediction(MAEP) were used to evaluate the
crop prediction capacity.
The results show that among the data-driven approaches, Random
Forest is the most robust and generally achieves the best prediction
error (MAEP 4.27%). It also outperforms our model-driven approach
(MAEP 6.11%). However, the method to calibrate the mechanistic
model from dataset easy to access offers several side-perspectives.
The mechanistic model can potentially help to underline the stresses
suffered by the crop or to identify the biological parameters of interest
for breeding purposes. For this reason, an interesting perspective is
to combine these two types of approaches.
Abstract: The design of accurate and reliable mobile communication systems depends majorly on the suitability of path loss prediction methods and the adaptability of the methods to various environments of interest. In this research, the results of the adaptability of radio channel behavior are presented based on practical measurements carried out in the 1800 MHz frequency band. The measurements are carried out in typical urban, suburban and rural environments in Ekiti State, Southwestern part of Nigeria. A total number of seven base stations of MTN GSM service located in the studied environments were monitored. Path loss and break point distances were deduced from the measured received signal strength (RSS) and a practical path loss model is proposed based on the deduced break point distances. The proposed two slope model, regression line and four existing path loss models were compared with the measured path loss values. The standard deviations of each model with respect to the measured path loss were estimated for each base station. The proposed model and regression line exhibited lowest standard deviations followed by the Cost231-Hata model when compared with the Erceg Ericsson and SUI models. Generally, the proposed two-slope model shows closest agreement with the measured values with a mean error values of 2 to 6 dB. These results show that, either the proposed two slope model or Cost 231-Hata model may be used to predict path loss values in mobile micro cell coverage in the well-considered environments. Information from this work will be useful for link design of microwave band wireless access systems in the region.
Abstract: In order to study the impact of various factors on the housing price, we propose to build different prediction models based on deep learning to determine the existing data of the real estate in order to more accurately predict the housing price or its changing trend in the future. Considering that the factors which affect the housing price vary widely, the proposed prediction models include two categories. The first one is based on multiple characteristic factors of the real estate. We built Convolution Neural Network (CNN) prediction model and Long Short-Term Memory (LSTM) neural network prediction model based on deep learning, and logical regression model was implemented to make a comparison between these three models. Another prediction model is time series model. Based on deep learning, we proposed an LSTM-1 model purely regard to time series, then implementing and comparing the LSTM model and the Auto-Regressive and Moving Average (ARMA) model. In this paper, comprehensive study of the second-hand housing price in Beijing has been conducted from three aspects: crawling and analyzing, housing price predicting, and the result comparing. Ultimately the best model program was produced, which is of great significance to evaluation and prediction of the housing price in the real estate industry.
Abstract: Rail transport authorities around the world have been facing a significant challenge when predicting rail infrastructure maintenance work for a long period of time. Generally, maintenance monitoring and prediction is conducted manually. With the restrictions in economy, the rail transport authorities are in pursuit of improved modern methods, which can provide precise prediction of rail maintenance time and location. The expectation from such a method is to develop models to minimize the human error that is strongly related to manual prediction. Such models will help them in understanding how the track degradation occurs overtime under the change in different conditions (e.g. rail load, rail type, rail profile). They need a well-structured technique to identify the precise time that rail tracks fail in order to minimize the maintenance cost/time and secure the vehicles. The rail track characteristics that have been collected over the years will be used in developing rail track degradation prediction models. Since these data have been collected in large volumes and the data collection is done both electronically and manually, it is possible to have some errors. Sometimes these errors make it impossible to use them in prediction model development. This is one of the major drawbacks in rail track degradation prediction. An accurate model can play a key role in the estimation of the long-term behavior of rail tracks. Accurate models increase the track safety and decrease the cost of maintenance in long term. In this research, a short review of rail track degradation prediction models has been discussed before estimating rail track degradation for the curve sections of Melbourne tram track system using Adaptive Network-based Fuzzy Inference System (ANFIS) model.
Abstract: Rainfall is a major climatic parameter affecting
many sectors such as health, agriculture and water resources. Its
quantitative prediction remains a challenge to weather forecasters
although numerical weather prediction models are increasingly being
used for rainfall prediction. The performance of six convective
parameterization schemes, namely the Kain-Fritsch scheme, the
Betts-Miller-Janjic scheme, the Grell-Deveny scheme, the Grell-3D
scheme, the Grell-Fretas scheme, the New Tiedke scheme of the
weather research and forecast (WRF) model regarding quantitative
rainfall prediction over Uganda is investigated using the root mean
square error for the March-May (MAM) 2013 season. The MAM
2013 seasonal rainfall amount ranged from 200 mm to 900 mm over
Uganda with northern region receiving comparatively lower rainfall
amount (200–500 mm); western Uganda (270–550 mm); eastern
Uganda (400–900 mm) and the lake Victoria basin (400–650 mm). A
spatial variation in simulated rainfall amount by different convective
parameterization schemes was noted with the Kain-Fritsch scheme
over estimating the rainfall amount over northern Uganda (300–750
mm) but also presented comparable rainfall amounts over the eastern
Uganda (400–900 mm). The Betts-Miller-Janjic, the Grell-Deveny,
and the Grell-3D underestimated the rainfall amount over most
parts of the country especially the eastern region (300–600 mm).
The Grell-Fretas captured rainfall amount over the northern region
(250–450 mm) but also underestimated rainfall over the lake Victoria
Basin (150–300 mm) while the New Tiedke generally underestimated
rainfall amount over many areas of Uganda. For deterministic rainfall
prediction, the Grell-Fretas is recommended for rainfall prediction
over northern Uganda while the Kain-Fritsch scheme is recommended
over eastern region.
Abstract: To encourage building owners to purchase electricity at the wholesale market and reduce building peak demand, this study aims to develop models that predict day-ahead hourly electricity consumption and demand using artificial neural network (ANN) and support vector machine (SVM). All prediction models are built in Python, with tool Scikit-learn and Pybrain. The input data for both consumption and demand prediction are time stamp, outdoor dry bulb temperature, relative humidity, air handling unit (AHU), supply air temperature and solar radiation. Solar radiation, which is unavailable a day-ahead, is predicted at first, and then this estimation is used as an input to predict consumption and demand. Models to predict consumption and demand are trained in both SVM and ANN, and depend on cooling or heating, weekdays or weekends. The results show that ANN is the better option for both consumption and demand prediction. It can achieve 15.50% to 20.03% coefficient of variance of root mean square error (CVRMSE) for consumption prediction and 22.89% to 32.42% CVRMSE for demand prediction, respectively. To conclude, the presented models have potential to help building owners to purchase electricity at the wholesale market, but they are not robust when used in demand response control.
Abstract: The prediction models for the United States Medical Licensure Examination (USMLE) Steps 1 and 2 performances were constructed by the Monte Carlo simulation modeling approach via linear regression. The purpose of this study was to build robust simulation models to accurately identify the most important predictors and yield the valid range estimations of the Steps 1 and 2 scores. The application of simulation modeling approach was deemed an effective way in predicting student performances on licensure examinations. Also, sensitivity analysis (a/k/a what-if analysis) in the simulation models was used to predict the magnitudes of Steps 1 and 2 affected by changes in the National Board of Medical Examiners (NBME) Basic Science Subject Board scores. In addition, the study results indicated that the Medical College Admission Test (MCAT) Verbal Reasoning score and Step 1 score were significant predictors of the Step 2 performance. Hence, institutions could screen qualified student applicants for interviews and document the effectiveness of basic science education program based on the simulation results.
Abstract: Conical sections and shells of metal plates manufactured by 3-roller conical bending process are widely used in the industries. The process is completed by first bending the metal plates statically and then dynamic roller bending sequentially. It is required to have an analytical model to get maximum bending force, for optimum design of the machine, for static bending stage. Analytical models assuming various stress conditions are considered and these analytical models are compared considering various parameters and reported in this paper. It is concluded from the study that for higher bottom roller inclination, the shear stress affects greatly to the static bending force whereas for lower bottom roller inclination it can be neglected.
Abstract: The purpose of this study is to explore the different facets of growth among micro, small and medium-sized firms in Croatia and to analyze the differences between models designed for all micro, small and medium-sized firms and those in creative industries. Three growth prediction models were designed and tested using the growth of sales, employment and assets of the company as dependent variables. The key drivers of sales growth are: prudent use of cash, industry affiliation and higher share of intangible assets. Growth of assets depends on retained profits, internal and external sources of financing, as well as industry affiliation. Growth in employment is closely related to sources of financing, in particular, debt and it occurs less frequently than growth in sales and assets. The findings confirm the assumption that growth strategies of small and medium-sized enterprises (SMEs) in creative industries have specific differences in comparison to SMEs in general. Interestingly, only 2.2% of growing enterprises achieve growth in employment, assets and sales simultaneously.
Abstract: Enterprise growth is generally considered as a key driver of competitiveness, employment, economic development and social inclusion. As such, it is perceived to be a highly desirable outcome of entrepreneurship for scholars and decision makers. The huge academic debate resulted in the multitude of theoretical frameworks focused on explaining growth stages, determinants and future prospects. It has been widely accepted that enterprise growth is most likely nonlinear, temporal and related to the variety of factors which reflect the individual, firm, organizational, industry or environmental determinants of growth. However, factors that affect growth are not easily captured, instruments to measure those factors are often arbitrary, causality between variables and growth is elusive, indicating that growth is not easily modeled. Furthermore, in line with heterogeneous nature of the growth phenomenon, there is a vast number of measurement constructs assessing growth which are used interchangeably. Differences among various growth measures, at conceptual as well as at operationalization level, can hinder theory development which emphasizes the need for more empirically robust studies. In line with these highlights, the main purpose of this paper is twofold. Firstly, to compare structure and performance of three growth prediction models based on the main growth measures: Revenues, employment and assets growth. Secondly, to explore the prospects of financial indicators, set as exact, visible, standardized and accessible variables, to serve as determinants of enterprise growth. Finally, to contribute to the understanding of the implications on research results and recommendations for growth caused by different growth measures. The models include a range of financial indicators as lag determinants of the enterprises’ performances during the 2008-2013, extracted from the national register of the financial statements of SMEs in Croatia. The design and testing stage of the modeling used the logistic regression procedures. Findings confirm that growth prediction models based on different measures of growth have different set of predictors. Moreover, the relationship between particular predictors and growth measure is inconsistent, namely the same predictor positively related to one growth measure may exert negative effect on a different growth measure. Overall, financial indicators alone can serve as good proxy of growth and yield adequate predictive power of the models. The paper sheds light on both methodology and conceptual framework of enterprise growth by using a range of variables which serve as a proxy for the multitude of internal and external determinants, but are unlike them, accessible, available, exact and free of perceptual nuances in building up the model. Selection of the growth measure seems to have significant impact on the implications and recommendations related to growth. Furthermore, the paper points out to potential pitfalls of measuring and predicting growth. Overall, the results and the implications of the study are relevant for advancing academic debates on growth-related methodology, and can contribute to evidence-based decisions of policy makers.
Abstract: The development of change prediction models can help the software practitioners in planning testing and inspection resources at early phases of software development. However, a major challenge faced during the training process of any classification model is the imbalanced nature of the software quality data. A data with very few minority outcome categories leads to inefficient learning process and a classification model developed from the imbalanced data generally does not predict these minority categories correctly. Thus, for a given dataset, a minority of classes may be change prone whereas a majority of classes may be non-change prone. This study explores various alternatives for adeptly handling the imbalanced software quality data using different sampling methods and effective MetaCost learners. The study also analyzes and justifies the use of different performance metrics while dealing with the imbalanced data. In order to empirically validate different alternatives, the study uses change data from three application packages of open-source Android data set and evaluates the performance of six different machine learning techniques. The results of the study indicate extensive improvement in the performance of the classification models when using resampling method and robust performance measures.
Abstract: Different knitted structures and knitted parameters play a vital role in the stretch and recovery management of compression sportswear in addition to the materials use to generate this stretch and recovery behavior of the fabric. The present work was planned to predict the different performance indicators of a compression sportswear fabric with some ground parameters i.e. base yarn stitch length (polyester as base yarn and spandex as plating yarn involve to make a compression fabric) and linear density of the spandex which is a key material of any sportswear fabric. The prediction models were generated by response surface method for performance indicators such as stretch & recovery percentage, compression generated by the garment on body, total elongation on application of high power force and load generated on certain percentage extension in fabric. Certain physical properties of the fabric were also modeled using these two parameters.
Abstract: The work reported through this paper is an
experimental work conducted on High Performance Concrete (HPC)
with super plasticizer with the aim to develop some models suitable
for prediction of compressive strength of HPC mixes. In this study,
the effect of varying proportions of fly ash (0% to 50% @ 10%
increment) on compressive strength of high performance concrete has
been evaluated. The mix designs studied were M30, M40 and M50 to
compare the effect of fly ash addition on the properties of these
concrete mixes. In all eighteen concrete mixes that have been
designed, three were conventional concretes for three grades under
discussion and fifteen were HPC with fly ash with varying
percentages of fly ash. The concrete mix designing has been done in
accordance with Indian standard recommended guidelines. All the
concrete mixes have been studied in terms of compressive strength at
7 days, 28 days, 90 days, and 365 days. All the materials used have
been kept same throughout the study to get a perfect comparison of
values of results. The models for compressive strength prediction
have been developed using Linear Regression method (LR), Artificial
Neural Network (ANN) and Leave-One-Out Validation (LOOV)
methods.
Abstract: This paper presents a method of evaluating the effect
of aggregate angularity on hot mix asphalt (HMA) properties and its
relationship to the Permanent Deformation resistance. The research
concluded that aggregate particle angularity had a significant effect
on the Permanent Deformation performance, and also that with an
increase in coarse aggregate angularity there was an increase in the
resistance of mixes to Permanent Deformation. A comparison
between the measured data and predictive data of permanent
deformation predictive models showed the limits of existing
prediction models. The numerical analysis described the permanent
deformation zones and concluded that angularity has an effect of the
onset of these zones. Prediction of permanent deformation help road
agencies and by extension economists and engineers determine the
best approach for maintenance, rehabilitation, and new construction
works of the road infrastructure.
Abstract: Software fault prediction models are created by using
the source code, processed metrics from the same or previous version
of code and related fault data. Some company do not store and keep
track of all artifacts which are required for software fault prediction.
To construct fault prediction model for such company, the training
data from the other projects can be one potential solution. Earlier we
predicted the fault the less cost it requires to correct. The training
data consists of metrics data and related fault data at function/module
level. This paper investigates fault predictions at early stage using the
cross-project data focusing on the design metrics. In this study,
empirical analysis is carried out to validate design metrics for cross
project fault prediction. The machine learning techniques used for
evaluation is Naïve Bayes. The design phase metrics of other projects
can be used as initial guideline for the projects where no previous
fault data is available. We analyze seven datasets from NASA
Metrics Data Program which offer design as well as code metrics.
Overall, the results of cross project is comparable to the within
company data learning.
Abstract: The main objective of this paper is to provide a new
methodology for road safety assessment in Oman through the
development of suitable accident prediction models. GLM technique
with Poisson or NBR using SAS package was carried out to develop
these models. The paper utilized the accidents data of 31 un-signalized
T-intersections during three years. Five goodness-of-fit
measures were used to assess the overall quality of the developed
models. Two types of models were developed separately; the flow-based
models including only traffic exposure functions, and the full
models containing both exposure functions and other significant
geometry and traffic variables.
The results show that, traffic exposure functions produced much
better fit to the accident data. The most effective geometric variables
were major-road mean speed, minor-road 85th percentile speed,
major-road lane width, distance to the nearest junction, and right-turn
curb radius.
The developed models can be used for intersection treatment or
upgrading and specify the appropriate design parameters of T-intersections.
Finally, the models presented in this thesis reflect the intersection
conditions in Oman and could represent the typical conditions in
several countries in the middle east area, especially gulf countries.