Search results

Hardgrove grindability index (HGI) is an important physical parameter used to demonstrate the relative hardness of coal particles. Modeling of HGI based on coal conventional properties is a quite complicated procedure. The paper aims to develop a new accurate model for prediction of HGI that is called optimized evolutionary neural network (OPENN).

The procedure for generation of the proposed OPENN predictive model was performed in two stages. In the first stage, as the high dimensionality involved in the input space, a correlation-based feature selection (CFS) algorithm was used to select the most important influencing variables for HGI prediction. In the second stage, a combination of differential evolution (DE) and biography-based optimization (BBO) algorithms as a global search method were applied to evolve weights of a multi-layer perception neural network.

The proposed OPENN was examined and compared with other typical models using a wide range of Kentucky coal samples. The testing results showed that the accuracy of the proposed OPENN model is significantly better than the other typical models and can be considered as a promising alternative for HGI prediction.

As HGI test is relatively expensive procedure, there is an economical interest on HGI modeling based on coal conventional properties (proximate, ultimate and petrography); the proposed OPENN model to estimate HGI would be a valuable and practical tool for coal industry.

The primary goal of this research is to introduce a data-driven Problem-Solving Approach for Performance Improvement in Healthcare Systems (DPAPIH). This approach combines process mining and data mining techniques to enhance operational efficiency by identifying bottlenecks in Coronary Artery Bypass Grafting (CABG) procedures, particularly focusing on variability in Length of Stay (LOS) in the Intensive Care Unit (ICU). The study, implemented at Tehran Heart Center, aims to optimize patient flow, reduce ICU congestion and improve hospital efficiency by predicting and managing the occurrence of postoperative Atrial Fibrillation (AF), a significant cause of prolonged ICU stays.

The study introduces a data-driven problem-solving approach that integrates process mining and data mining techniques to improve performance in healthcare systems. Focusing on coronary artery bypass grafting (CABG) at Tehran Heart Center, the approach identifies bottlenecks, particularly variability in ICU length of stay (LOS) and predicts postoperative atrial fibrillation (AF). A mixed-methods approach is employed, combining quantitative process mining analyses with qualitative insights from expert consultations. The CHAID decision tree algorithm, alongside other models, is used to predict AF, enabling preemptive interventions, improving patient flow and optimizing resource allocation to reduce hospital congestion and costs.

The study reveals that postoperative Atrial Fibrillation (AF) significantly increases the length of stay (LOS) in the Intensive Care Unit (ICU), creating bottlenecks that delay subsequent surgeries and elevate hospital costs. A predictive model developed using CHAID decision tree algorithms achieved a prediction accuracy of 71.4%, allowing healthcare providers to anticipate AF occurrences. This capability enables proactive measures to reduce ICU congestion, improve patient flow and optimize resource allocation. The findings emphasize the importance of AF management in enhancing operational efficiency and improving patient outcomes in Coronary Artery Bypass Grafting (CABG) procedures.

This study presents an innovative integration of fuzzy process mining and data mining algorithms to address performance bottlenecks in healthcare systems, specifically within the coronary artery bypass surgery process. By identifying atrial fibrillation as a key factor in length of stay fluctuations and developing a robust predictive model, the research offers a novel, data-driven approach to performance improvement. The implementation at Tehran Heart Center validates the model’s practical applicability, demonstrating significant potential for enhancing patient outcomes, optimizing resource allocation and informing decision-making in healthcare management.

In shopping, for selecting the appropriate garments, people have to try on multiple garments. This problem is due to lack of a sizing system based on updated anthropometric data and the classification system that introduces the appropriate size from the sizing chart to each person. To solve this problem, as a first study in the literature, a hybrid intelligent classification model as a size recommendation expert system is proposed. The paper aims to discuss these issues.

Three stages for developing a hybrid intelligent classification system based on data clustering and probabilistic neural network (PNN) are proposed. In the first stage, the clustering algorithm is used for specifying the sizing chart. In the second stage, the resulting sizing chart is used as a reference for developing a new intelligent classification system by using a PNN. At the last stage, the accuracy of the proposed model is evaluated by using the Iranian male's body type data set.

Experimental results show that the proposed model has a good accuracy and can be used as a size recommendation expert system to specify the right size for the customers. By using the proposed model and designing an interface for it, a decision support system was developed as a size recommendation expert system that was used by an apparel sales store. The results were time saving and more satisfying for the customers by selecting the appropriate apparel size for them.

In this paper, as a first study in literature, a hybrid intelligent model for developing a size recommendation expert system based on data clustering and a PNN to enable the salesperson to help the consumer in choosing the right size is proposed. In the first stage, the clustering algorithm is used for specifying the sizing chart. In the second stage, the resulting sizing chart is used as a reference to develop a new intelligent classification system by using a PNN. In the last stage, the accuracy of the proposed model is evaluated by using testing data. The proposed model achieved an 87.2 percent accuracy rate that is very promising.

The purpose of this paper is to estimate long‐run elasticities for housing prices in Tehran's (capital of Iran) 20 different zones relative to several explanatory variables available for use such as land price, total substructure area, material price, etc. Moreover, another goal of this paper is to propose a new approach to deal with problems which arise due to a lack of proper data.

The data set is gathered from “The Municipality of Tehran” and “The Central Bank of Islamic Republic of Iran (CBI)”. One‐way fixed effects and one‐way random effects approaches (which are panel data approaches) are applied to model housing price forecasting function in Tehran's 20 different zones. Results are compared with ordinary least squares approach which is a common approach in this field. Finally, outcomes of the preferred approach are discussed and analyzed with regard to the economic point of view.

Results show that one‐way fixed effects approach provides more accurate forecasts and can be considered as a suitable tool to deal with housing price forecasting problems in environments which are: uncertain, complex, and faced with a lack of proper data. Moreover, it is found that land price is the most effective factor that has impact on total housing cost in Tehran, i.e. the main portion of house prices in Tehran is affected by land price, so appropriate policies have to be made by the government to control fluctuations of this factor.

The proposed approach will supply policy makers with improved estimations with decreased errors in uncertain and complex environments which are faced with a lack of proper data, and it extracts valuable information which enables policy makers for handling non‐linearity, complexity, as well as uncertainty that may exist in actual data sets with respect to housing price forecasting. Moreover, the proposed approach can be applied to similar housing price case studies to obtain more accurate and more reliable outcomes.

Applying panel data approach for estimation of housing prices is relatively new in the field of housing economics. Moreover, this is the first study which employs panel data approach for analyzing the housing market in Tehran.