Performance Of Optimization Model Research Articles

Real-time prediction model for indoor temperature in a commercial building

Indoor environmental parameters have significant influence on commercial building energy consumption and indoor thermal comfort. Prediction of these parameters, especially that of indoor air temperature, along with continuous monitoring and control of real world parameters can aid in the management of energy consumption and thermal comfort levels in existing buildings. An accurate indoor temperature prediction model assists in achieving an effective energy management strategy such as resetting air temperature set-points in commercial buildings. This study examines the real indoor environmental data for multiple adjacent zones in a commercial building in the context of thermal comfort and identifies the possibility of resetting air temperature set-point without compromising the occupant comfort level. Also, the value of predicting the indoor temperature accurately in such a building is established through this case study. This study presents a nonlinear autoregressive network with exogenous inputs-based system identification method to predict indoor temperature. During model development efforts have been paid to optimize the performance of the model in terms of complexity, prediction results and ease of application to a real system. The performance of single-zone and multi-zone prediction models is evaluated using different combinations and sizes of training data-sets. This study confirms that evaluating the performance of the model in the context of major contributing aspects such as optimal input parameters and network size, optimum size of training data, etc. offers optimized model performance. Thus, when the developed model is used for long-term prediction, it provides better prediction performance for an extended time span compared to existing studies. Therefore, it is anticipated that implementation of this long-term prediction model will offer greater energy savings and improved indoor environmental conditions through optimizing the set-point temperatures.

Methodological issues for measuring pharmacotherapy treatment and its calibration with patient outcomes using real-world data

IntroductionHealth system and administrative data sources, although collected for process/procedural healthcare use, have recently been leveraged for research purposes. Complex methodologies such as data linkages, defined algorithms, and proxy measures are needed to validate the use of these data. Alberta has exceptionally rich health system data to be explored.
 Objectives and ApproachOur objectives were to explore data sources in Alberta regarding pharmacotherapy treatments, patient outcomes, and develop methods to calibrate associations. We scoped data sources for pharmacotherapy treatment and patient outcomes in Alberta, Canada. Using a cohort of patients with multiple sclerosis (MS) as an example, we developed algorithms to measure medication possession ratio (MPR), proportion of days covered (PDC), and treatment discontinuation (TD). Patient outcomes included: ambulatory care visits, physician claims and hospitalizations. We explored different algorithms for statistical modeling of patient treatments and outcomes. Optimal cut-points and statistical model performance of MPR/PDC and TD with patient outcomes were evaluated.
 ResultsWe utilized six Albertan data sources to examine treatment patterns and patient outcomes. From the year 2000, the pharmaceutical information network (PIN) and Alberta Blue Cross drug datasets collected: service dates, dosages, drug identification numbers, anatomical therapeutic chemical classification codes, and days of supplies; which were used to calculate MPR, PDC and TD. MPR and PDC were calculated using three different methods: (1) fixed follow-up period; (2) with and without last fill; and (3) adjustment for hospitalization periods. No significant differences between methods were found. In addition, TD using 60- and 90-day gaps, while considering the medication day supplies, were calculated. Adherence with optimal cut-point 0.8 of MPR/PDC and TD were significantly associated with ambulatory care visits, physician claims, and hospitalizations (p=0.000; C-statistic range: 0.78-0.89).
 Conclusion/ImplicationsThe PIN data can be utilized for measuring pharmacotherapy treatment in patient outcomes research. To understand the impact of therapies on outcomes in a real-world setting, however, comprehensive methods for measuring treatment indicators as well as patient outcomes should be developed to control for inherent biases in observational data.

Performance improvement of two-stage serial organic Rankine cycle (TSORC) driven by dual-level heat sources of geothermal energy coupled with solar energy

Solar energy is used as the supplementary heat source of geothermal energy. Based on two-stage serial organic Rankine cycle (TSORC) system driven by a single heat source (SHS), the TSORC driven by dual-level heat sources(DHS), geothermal energy as the low temperature heat source coupled with solar energy as the high temperature heat source, was proposed. A numerical model for performance optimization of combined system was constructed. A compound objective function was used to optimize the cycle parameters, such as the thermal efficiency, exergy efficiency, net output power, irreversible loss, thermal conductance, size parameter of turbine and the system performances. The TSORC driven by DHS were also compared with those driven by DHS, with the heat source ranging from 110 to 150℃. The results show that the TSORC driven by DHS can output more net power but the thermal efficiency is lower compared with the TSORC driven by SHS for heat source temperature below 140℃. Generally, the TSORC driven by DHS can improve the system performance, and it can be adopted in engineering application if there are dual-level heat sources.

River ice breakup timing prediction through stacking multi-type model trees

River ice breakup is an annual event with ecological and economic significance in the Northern Hemisphere. Breakup timing forecasting is critical for supporting emergency responses to river-ice related flooding. Little attention has been paid to applications of the classification and regression tree (CART) and M5 models as well as the stacking ensemble of multiple types of model trees to river ice forecasting problem. Thus, a framework of stacking ensemble tree models (SETM) is proposed, which consists of multiple types of model trees in a two-level structure: base and ensemble models. The Athabasca River at Fort McMurray is selected as the study area because the Athabasca River is the largest unregulated river in Alberta, Canada and ice jams frequently occur in the vicinity of Fort McMurray. To facilitate the comparison of models, the historical data in the past 36 years is collected and the leave-one-out cross validation method is employed. The results show that, the indicators influencing or corresponding with the breakup timing can be categorized as temperature and water flow conditions just before breakup (in March), during freeze-up (in last November and last December) and during middle winter (in January). The performance of optimal CART and M5 models are almost the same but the M5 model does simplify the tree structure. Although their performance can be further improved by the SETM framework, the structure of the base models can facilitate explicit explanations of the relations between indicators and the breakup date. In terms of validation performance (RMSEavg), the optimal ensemble model is the simple average method, which improves upon the two optimal base models (CART and M5) by 13.1% and 13.2%, respectively.

Radiotherapy dose–volume parameters predict videofluoroscopy-detected dysphagia per DIGEST after IMRT for oropharyngeal cancer: Results of a prospective registry

PurposeOur primary aim was to prospectively validate retrospective dose–response models of chronic radiation-associated dysphagia (RAD) after intensity modulated radiotherapy (IMRT) for oropharyngeal cancer (OPC). The secondary aim was to validate a grade ≥2 cut-point of the published videofluoroscopic dysphagia severity (Dynamic Imaging Grade for Swallowing Toxicity, DIGEST) as radiation dose-dependent. Material and methodsNinety-seven patients enrolled on an IRB-approved prospective registry protocol with stage I–IV OPC underwent pre- and 3–6 month post-RT videofluoroscopy. Dose–volume histograms (DVH) for swallowing regions of interest (ROI) were calculated. Dysphagia severity was graded per DIGEST criteria (dichotomized with grade ≥2 as moderate/severe RAD). Recursive partitioning analysis (RPA) and Bayesian Information Criteria (BIC) were used to identify dose–volume effects associated with moderate/severe RAD. Results31% developed moderate/severe RAD (i.e. DIGEST grade ≥2) at 3–6 months after RT. RPA found DVH-derived dosimetric parameters of geniohyoid/mylohyoid (GHM), superior pharyngeal constrictor (SPC), and supraglottic region were associated with DIGEST grade ≥2 RAD. V61 ≥ 18.57% of GHM demonstrated optimal model performance for prediction of DIGEST grade ≥2. ConclusionThe findings from this prospective longitudinal registry validate prior observations that dose to submental musculature predicts for increased burden of dysphagia after oropharyngeal IMRT. Findings also support dichotomization of DIGEST grade ≥2 as a dose-dependent split for use as an endpoint in trials or predictive dose–response analysis of videofluoroscopy results.

Bond Portfolio Optimization in the Presence of Duration Constraints

Although there exists an abundant literature on the benefits and limits of scientific diversification in the equity universe, little is known about the out-of-sample performance of portfolio optimization models in the fixed-income universe. In this article, the authors address two key challenges that are specific to bond portfolio optimization, namely, the presence of duration constraints and the presence of no-arbitrage restrictions on risk parameter estimates, for which no equivalent exists in the equity universe. In an application to sovereign bonds in the eurozone, they find that the use of portfolio optimization techniques based on robust estimators for risk parameters generates an improvement in investor welfare compared with the use of ad hoc bond benchmarks such as equally weighted or cap-weighted portfolios. These results are robust with respect to changes in the number of constituents in the portfolio and the rebalancing period, and in the presence of duration or weight constraints. <b>TOPICS:</b>Fixed income and structured finance, fixed-income portfolio management, statistical methods

An Effective Ensemble Model for Performance Optimization and Predictive Analytics in the Healthcare

An Effective Ensemble Model for Performance Optimization and Predictive Analytics in the Healthcare

Developing a grouped random parameters multivariate spatial model to explore zonal effects for segment and intersection crash modeling

It is acknowledged that crash occurrence on segments and intersections could be affected by multilevel factors. Omission of important explanatory variables could result in biased and inconsistent parameter estimates. This paper contributes to the literature by examining the zonal effects which are always excluded or ignored in traffic safety research for segments and intersections. A grouped random parameters multivariate spatial model is proposed to identify both observable zonal effects and unobserved heterogeneity at the zonal level by considering the heterogeneous and spatial correlations. The proposed model is evaluated by comparing it with its three counterparts: a fixed parameters univariate spatial model without zonal factors, a random parameters univariate spatial model without zonal factors, and a random parameters univariate spatial model with zonal factors. The results indicate that the three random parameters models could consistently provide better performance than the fixed parameters model and the models including zonal factors outperform the models without zonal factors. Besides, the proposed model has the optimal model performance compared with its counterparts, which validates the concept of adopting the multivariate modeling framework to identify the heterogeneous and spatial correlations of zonal effects. The results confirm the significantly correlated heterogeneous residuals in modeling zonal factors on crash occurrence on segments and intersections. However, the spatial correlations of zonal effects on different types of road entities (segments and intersections) in adjacent zones are not statistically significant. Furthermore, the proposed model provides more valuable insights about the crash occurrence on segments and intersections by revealing segment-/intersection-level factors together with zonal factors.

Random subset feature selection for ecological niche models of wildfire activity in Western North America

Variable selection in ecological niche modelling can influence model projections to a degree comparable to variations in future climate scenarios. Consequently, it is important to select feature (variable) subsets for optimizing model performance and characterizing variability. We utilize a novel random subset feature selection algorithm (RSFSA) for niche modelling to select an ensemble of optimally sized feature subsets of limited correlation (|r| < 0.7) from 90 climatic, topographic and anthropogenic indices, generating wildfire activity models for western North America with higher performance. Monitoring Trends in Burn Severity and LANDFIRE wildfire data were used to develop thousands of MaxEnt, GLM and Glmnet models. The RSFSA-selected models performed better than random models, having higher accuracy (Area Under the Curve statistic; AUC), lower complexity (corrected Akaike Information Criterion; AICc), and, in some cases, lower overfitting (AUCdiff). The RSFSA-selected MaxEnt quadratic/hinge (β-regularization 2) feature models generally had higher AUC and lower AICc, outperforming other niche model parameterizations and methods. Feature subset ensembles of RSFSA-selected 15-variable MaxEnt quadratic/hinge models were used to characterize variability in projected areas of large wildfires for three burn severities under current, 2050, and 2070 climate scenarios. Expert screening of variables before RSFSA did not improve model performance. Widespread contemporary wildfire deficits and projected regional changes in wildfires highlight the need to manage fuel loads and restore natural fire regimes. The RSFSA is valuable for optimizing niche model performance and generating feature subset ensembles to characterize model variability across niche models of various feature subset sizes, modelling methods, and climate scenarios.

Input selection and data-driven model performance optimization to predict the Standardized Precipitation and Evaporation Index in a drought-prone region

Accurate predictions of drought events to plan and manage the adverse effects of drought on agriculture and the environment requires tools that precisely predict standardized drought metrics. Improving on the World Meteorological Organization approved Standardized Precipitation Index (SPI), the multi-scalar Standardized Precipitation and Evapotranspiration Index (SPEI), a variant of the SPI, is a relatively recent drought index, which takes into account the impacts of temperature change on overall dryness, along with precipitation and evapotranspiration effects. In this paper, an extreme learning machine (ELM) model was applied to predict SPEI in a drought-prone region in eastern Australia, and the quality of the model's performance was compared to that of a multiple linear regression (MLR), an artificial neural network (ANN), and a least support vector regression (LSSVR) model. The SPEI data were derived from climatic variables recorded at six weather stations between January 1915 and December 2012. Model performance was evaluated by means of the normalized root mean square error (NRMSE), normalized mean absolute error (NMAE), coefficients of determination (r2), and the Nash-Sutcliffe efficiency coefficient (NASH) in the testing period. Results showed that the ELM and ANN models outperformed the MLR and LSSVR models, and all four models revealed a greater predictive accuracy for the 12-month compared to the 3-month SPEI predictions. For the 12-month SPEI predictions, optimal models had r2 that ranged from 0.668 for the LSSVR model (Station 6) to 0.894 for the ANN model (Station 4). The good agreement between observed and predicted SPEI at different locations within the study region indicated the potential of the developed models to contribute to a more thorough understanding of potential future drought-risks in eastern Australia, and their applicability to drought assessments over multiple timescales. The models and findings have useful implications for water resources assessment in drought-prone regions.

An automated algorithm for mapping building impervious areas from airborne LiDAR point-cloud data for flood hydrology

Buildings, as impervious surfaces, are an important component of total impervious surface areas that drive urban stormwater response to intense rainfall events. Most stormwater models that use percent impervious area (PIA) are spatially lumped models and do not require precise locations of building roofs, as in other applications of building maps, but do require accurate estimates of total impervious areas within the geographic units of observation (e.g. city blocks or sub-watershed units). Two-dimensional mapping of buildings from aerial imagery requires laborious efforts from image analysts or elaborate image analysis techniques using high spatial resolution imagery. Moreover, large uncertainties exist where tall, dense vegetation obscures the structures. Analyzing LiDAR point-cloud data, however, can distinguish buildings from vegetation canopy and facilitate the mapping of buildings. This paper presents a new building extraction approach that is based on and optimized for estimating building impervious areas (BIA) for hydrologic purposes and can be used with standard GIS software to identify building roofs under tall, thick canopy. Accuracy assessment methods are presented that can optimize model performance for modeling BIA within the geographic units of observation for hydrologic applications. The Building Extraction from LiDAR Last Returns (BELLR) model, a 2.5D rule-based GIS model, uses a non-spatial, local vertical difference filter (VDF) on LiDAR point-cloud data to automatically identify and map building footprints. The model includes an absolute difference in elevation (AdE) parameter in the VDF that compares the difference between mean and modal elevations of last-returns in each cell.The BELLR model is calibrated for an extensive inner-city, highly urbanized small watershed in Columbia, South Carolina, USA that is covered by tall, thick vegetation canopy that obscures many buildings. The calibration of BELLR used a set of building locations compiled by photo-analysts, and validation used independent building reference data. The model is applied to two residential neighborhoods, one of which is a residential area within the primary watershed and the other is a younger suburban neighborhood with a less-well developed tree canopy used as a validation site. Performance results indicate that the BELLR model is highly sensitive to concavity in the lasboundary tool of LAStools® and those settings are highly site specific. The model is also sensitive to cell size and the AdE threshold values. However, properly calibrated the BIA for the two residential sites could be estimated within 1% error for optimized experiments.To examine results in a hydrologic application, the BELLR estimated BIAs were tested using two different types of hydrologic models to compare BELLR results with results using the National Land Cover Database (NLCD) 2011 Percent Developed Imperviousness data. The BELLR BIA values provide more accurate results than the use of the 2011 NLCD PIA data in both models. The VDF developed in this study to map buildings could be applied to LiDAR point-cloud filtering algorithms for feature extraction in machine learning or mapping other planar surfaces in more broad-based land-cover classifications.

Application of Artificial Fish Swarm Algorithm for Synchronous Selection of Wavelengths and Spectral Pretreatment Methods in Spectrometric Analysis of Beef Adulteration

In this paper, we proposed artificial fish swarm algorithm (AF) for synchronous selection of wavelengths and pretreatment methods during quantification of beef adulteration with spoiled beef based on the analysis of ultraviolet (UV), visible and near-infrared (Vis-NIR), and UV-Vis-NIR spectra. The best partial least squares regression model was obtained when the wavelength-then-pretreatment scheme was adopted in the Vis-NIR range where 11 wavelengths were utilized to produce an RPD value of 2.68. The coefficients of determination R2 and root mean squared errors of the model were 0.91 and 0.08 as well as 0.87 and 0.11 for calibration and prediction, respectively. It was demonstrated that AF was a useful tool for model optimization as compared with genetic algorithm. Moreover, the sequence for selecting wavelengths and spectral pretreatment methods had great influence in model performance and could be decided by try-out approach since the performance due to selection sequence was sensitive to spectral range and optimization algorithm employed. Nevertheless, wavelength-then-pretreatment scheme was preferred due to simpler model structure and reduced computation loads. It was shown that Vis-NIR spectroscopy was feasible in quantifying beef adulteration, and AF was an advance method for optimizing model performance. Moreover, AF could be expended in more studies for optimizing food quality and safety analysis.

Identifying musical pieces from fMRI data using encoding and decoding models

Encoding models can reveal and decode neural representations in the visual and semantic domains. However, a thorough understanding of how distributed information in auditory cortices and temporal evolution of music contribute to model performance is still lacking in the musical domain. We measured fMRI responses during naturalistic music listening and constructed a two-stage approach that first mapped musical features in auditory cortices and then decoded novel musical pieces. We then probed the influence of stimuli duration (number of time points) and spatial extent (number of voxels) on decoding accuracy. Our approach revealed a linear increase in accuracy with duration and a point of optimal model performance for the spatial extent. We further showed that Shannon entropy is a driving factor, boosting accuracy up to 95% for music with highest information content. These findings provide key insights for future decoding and reconstruction algorithms and open new venues for possible clinical applications.

Optimizing ensembles of small models for predicting the distribution of species with few occurrences

AbstractEnsembles of Small Models (ESM) represent a novel strategy for species distribution modelling with few observations.ESMs are built by calibrating many small models and then averaging them into an ensemble model where the small models are weighted by their cross‐validated scores of predictive performance. In a previous paper (Breiner, Guisan, Bergamini, &amp; Nobis,Methods in Ecology and Evolution,6, 1210–1218, 2015), we reported two major findings. First,ESMs proved largely superior to standard models in terms of model performance and transferability. Second,ESMs including different modelling techniques did not clearly improve model performance compared to single‐techniqueESMs. However,ESMs often require a large computation effort, which can become problematic when modelling large numbers of species. Given the appealing new perspectives offered byESMs, it is especially important to investigate if some techniques yield increased performance while saving computation time and thus could be predominantly used for buildingESMs.Here, we present results from a reanalysis of a subset of the data used in Breiner et al. (2015). More specifically, we ranESMs: (1) fitted with 10 modelling techniques separately (in Breiner et al., 2015 we used only three techniques); and (2) using various parameter options for each modelling technique (i.e., model tuning).We show thatESMs vary in model performance and computation time across techniques, and some techniques are advantageous in terms of optimizing model performance and computation time (i.e.,GLM,CTAandANN). Including one of these modelling techniques could thus optimize computation time compared to using more computing‐intensive techniques likeGBM. Next, we show that parameter tuning can improve performance and transferability ofESMs, but often at the cost of computation time. Parameter tuning could therefore be used when computing resources are not a limiting factor.These findings help improve the applicability and performance ofESMs when applied to large numbers of species.

Performance analysis of simulation-based optimization of construction projects using High Performance Computing

Abstract The complexity and uncertain nature of bridge construction projects require simulation for analyzing and planning these projects. On the other hand, optimization can be used to address the inverse relationship between the cost and time of a project and to find a proper trade-off between these two key elements. In addition, the large number of resources required in large-scale bridge construction projects results in a very large search space. Therefore, there is a need for using parallel computing to reduce the computational time of the simulation-based optimization problem. Another problem in this area is that most of the construction simulation tools need an integration platform to be combined with optimization techniques. To alleviate these limitations, an integrated simulation-based optimization framework is developed within one High Performance Computing (HPC) platform, and its performance is analyzed by carrying out a case study. A master-slave (or global) parallel Genetic Algorithm (GA) is used to decrease the computation time and to efficiently use the full capacity of the computer. In addition, sensitivity analysis is applied to identify the promising configuration for GA and the best number of cores used in parallel and to analyze the impact of GA parameters on the overall performance of the simulation-based optimization model. Using NSGA-ΙΙ as the optimization algorithm resulted in better near-optimal solutions compared to those of fast-messy GA. Moreover, performing the proposed framework on multiple nodes using the cluster system led to 31% saving in the computation time on average. Furthermore, the GA was tuned using sensitivity analyses, which resulted in the selection of the best parameters of the GA.

Variability of pCO2 in surface waters and development of prediction model

Inland waters are substantial sources of atmospheric carbon, but relevant data are rare in Asian monsoon regions including Korea. Emissions of CO2 to the atmosphere depend largely on the partial pressure of CO2 (pCO2) in water; however, measured pCO2 data are scarce and calculated pCO2 can show large uncertainty. This study had three objectives: 1) to examine the spatial variability of pCO2 in diverse surface water systems in Korea; 2) to compare pCO2 calculated using pH-total alkalinity (Alk) and pH-dissolved inorganic carbon (DIC) with pCO2 measured by an in situ submersible nondispersive infrared detector; and 3) to characterize the major environmental variables determining the variation of pCO2 based on physical, chemical, and biological data collected concomitantly. Of 30 samples, 80% were found supersaturated in CO2 with respect to the overlying atmosphere. Calculated pCO2 using pH-Alk and pH-DIC showed weak prediction capability and large variations with respect to measured pCO2. Error analysis indicated that calculated pCO2 is highly sensitive to the accuracy of pH measurements, particularly at low pH. Stepwise multiple linear regression (MLR) and random forest (RF) techniques were implemented to develop the most parsimonious model based on 10 potential predictor variables (pH, Alk, DIC, Uw, Cond, Turb, COD, DOC, TOC, Chla) by optimizing model performance. The RF model showed better performance than the MLR model, and the most parsimonious RF model (pH, Turb, Uw, Chla) improved pCO2 prediction capability considerably compared with the simple calculation approach, reducing the RMSE from 527–544 to 105μatm at the study sites.

An improved unit circuit model for transient heat conduction performance analysis and optimization in multi-layer materials

Transient heat conduction analysis and optimization in multi-layer thermal insulation materials (MLTIMs) requires an effective simplified model with certain accuracy. This paper proposes an improved unit circuit model (IUCM) based on the thermo-electrical analogy, where the interface nodes between every two adjacent layers are considered to describe the rapid variations of temperature gradients and heat fluxes at the interfaces. Then, the IUCM for three-layer materials is solved with jump and sinusoidal temperature boundaries, and the obtained temperatures and the outlet heat fluxes are compared to the solutions obtained by the finite volume method as well as other two existing lumped parameter models. The comparison shows that the IUCM reduces the relative mean outlet heat flux error by more than 50% compared to the other models in the studied cases. Applying the IUCM together with the genetic algorithm offers the optimal geometrical structures of three-layer materials, where the optimal structure reduced the outlet heat per unit area by more than 50% compared to the feasible structures. Meanwhile, arranging the mechanical layer with high thermal conductivity between two thermal insulation materials leads to a decrease of about 35% in the outlet heat during a certain time.

Optimization of Fuzzy Neural Networks using Mine Blast Algorithm for Classification Problem

The integration of Fuzzy Neural Networks (FNNs) with optimization techniques has not only solved the issues “black box” in Artificial Neural Networks (ANNs) but also has been effective in a wide variety of real-world applications. Adaptive Neuro-Fuzzy Inference System (ANFIS) still needs effective parameter training and rules optimization methods to perform efficiently when the number of inputs increases. ANFIS accuracy depends on the parameters it is trained with and the drawbacks of gradients based learning of ANFIS using gradient descent and least square methods in two-pass learning algorithm. Many researchers have trained ANFIS parameters using metaheuristic, however, very few have considered optimizing the ANFIS rule-base. We propose an effective technique for optimizing ANFIS rule-base and training the network parameters using newly Accelerated modified MBA (AMBA) to convergence the speed during exploitation phase. The AMBA optimized ANFIS was tested on real-world benchmark classification problems like Breast Cancer, Iris, and Glass. The AMBA optimized ANFIS has also been employed to model real datasets. The performance of the proposed AMBA optimized ANFIS model was compared with the ones optimized by Genetic Algorithm (GA), Particle Swarm Optimization (PSO), MBA and Improved MBA (IMBA), respectively. The results show that the proposed AMBA optimized ANFIS achieved better accuracy with optimized rule-set in less number of function evaluations. Moreover, the results also indicate that AMBA converges earlier than its other counterparts.

A Health Performance and Cost Optimization Model for Sustainable Healthy Buildings

To construct a sustainable and healthy building, it is necessary to build a system capable of efficiently analyzing, assessing and managing health performance data over the life cycle of a building. To fulfill such needs, health-friendly resources database, life cycle health-performance tree, health performance evaluation and health management concepts were suggested. Such studies focused on health performance. Selecting building materials based only on their health performance while ignoring cost is likely to lead to not only rapid construction cost increases, but also higher maintenance costs. For cost-benefit management, the health performance and cost management model was proposed. However, while the model can be used in decision-making, it is unable to suggest an optimization solution. To supplement this need, this study proposes a health performance and cost optimization model for sustainable healthy buildings. The model proposed here is composed of simulation and optimization modules for health performance and cost using the concepts mentioned above.

A multi-stage methodology for selecting input variables in ANN forecasting of river flows

&lt;p&gt;The scientific community has recognized the necessity for more efficiently selected inputs in artificial neural network models (ANNs) in river flows and has worked on this despite some shortcomings. Moreover, there is none or limited inclusion of ANN inputs coupled with atmospheric circulation under various patterns arising from the need of data downscaling for climate change predictions in hydrology domain. This paper presents the results of a novel multi-stage methodology for selecting input variables used in artificial neural network (ANN) models for river flow forecasting. The proposed methodology makes use of data correlations together with a set of crucial statistical indices for optimizing model performance, both in terms of ANN structure (e.g. neurons, momentum rate, learning rate, activation functions, etc), but also in terms of inputs selection. The latter include various previous time steps of daily areal precipitation and temperature data coupled with atmospheric circulation in the form of circulation patterns, observed river flow data and time expressed via functions of sine and cosine. Additionally, the no-linear behavior between river flow and the respective inputs is investigated by the ANN configuration itself and not only by correlation indices (or other equivalent contingency tools). The proposed methodology revealed the river flow of past four days, the precipitation of past three days and the seasonality as robust input variables. However, the temperature of three past days should be considered as an alternative against the seasonality. The produced models forecasting ability was validated by comparing its one-step ahead flow prediction ability to two other approaches (an auto regressive model and a genetic algorithm (GA)-optimized single input ANN).&amp;nbsp;&lt;/p&gt;