Abstract:This research is dedicated to the modelling of decision process occurring during the implementation of construction projects. Recent studies generally do not assess the robustness of the decisions regarding the possible changes during the construction project implementation. However, such an assessment might increase the reliability of the decision-making process. We addressed this gap through a new model that combines the decision-making process modelling with the AHP method and includes the analysis of model… Show more
“…Meanwhile, the decision trees are used for prediction functions such as classification and regression. The nodes represent the data set features, and the branches represent the rules of the decisions [12]. This decision tree has two nodes: the decision node and the leaf node.…”
Section: Materials and Methods Supervised Learningmentioning
The airline business is one of the businesses determined by the quality of its services. Every airline creates its best service so that customers feel satisfied and loyal to using their services. Therefore, customer satisfaction is an essential metric to measure features and services provided. By having a database on customer satisfaction, the company can utilize the data for machine learning modelling. The model generated can predict customer satisfaction by looking at the existing feature criteria and becoming a decision support system for management. This article compares machine learning between Split Point and Attribute Reduced Classifier (SPAARC), Multilayer Perceptron (MLP), and Random Fores (RF) in predicting customer satisfaction. Based on the data testing, the Random Forest algorithm provides better results with the lowest training time compared to SPAARC and MLP. It has an accuracy of 95.827%, an F-score of 0.958, and a training time of 84.53 seconds.
“…Meanwhile, the decision trees are used for prediction functions such as classification and regression. The nodes represent the data set features, and the branches represent the rules of the decisions [12]. This decision tree has two nodes: the decision node and the leaf node.…”
Section: Materials and Methods Supervised Learningmentioning
The airline business is one of the businesses determined by the quality of its services. Every airline creates its best service so that customers feel satisfied and loyal to using their services. Therefore, customer satisfaction is an essential metric to measure features and services provided. By having a database on customer satisfaction, the company can utilize the data for machine learning modelling. The model generated can predict customer satisfaction by looking at the existing feature criteria and becoming a decision support system for management. This article compares machine learning between Split Point and Attribute Reduced Classifier (SPAARC), Multilayer Perceptron (MLP), and Random Fores (RF) in predicting customer satisfaction. Based on the data testing, the Random Forest algorithm provides better results with the lowest training time compared to SPAARC and MLP. It has an accuracy of 95.827%, an F-score of 0.958, and a training time of 84.53 seconds.
“…The AHP technique is a multi-criteria decision-making that assesses the weights of criteria and prioritizes options in a structured manner through pairwise comparisons (Bao et al, 2021). Considering that linguistic values and subjective judgments during comparisons can be imprecise, this study utilized fuzzy logic (Maceika et al, 2021). Buckley (1985) expanded Saaty's AHP by assigning precise ratios when comparing criteria and options, and by deriving their fuzzy weights using the geometric mean method.…”
Wetlands play a vital role as one of the most important natural habitats on our planet. However, the survival of these natural wetlands is threatened by various factors. The arrival of invasive and non-native aquatic ferns is one of these challenges. In this regard, Azolla filiculoides has become a severe problem for the Anzali wetland. Azolla, as an aquatic fern, has created numerous issues in aquatic habitats and paddy fields in recent decades. However, the valorization of Azolla can contribute to the establishment of a collection system for this invasive fern, which can consequently reduce the negative impact of this fern on the wetland, and it can serve as a free and available source of biomass. In this respect, a fuzzy multi-criteria decision-making approach was used to rank the valorization strategies of this invasive fern. Initially, through an in-depth literature review and expert opinions, four criteria were designated as indicators for research evaluation: 1) technical, 2) economic, 3) social, and 4) environmental. Six management options for Azolla were considered: 1) no collection, 2) collection and landfilling, 3) direct use as livestock and poultry feed, 4) composting, 5) biogas generation, and 6) biodiesel generation. The results revealed that "biodiesel generation," "biogas generation," and "composting" were ranked as the most effective management strategies for Azolla in the investigated wetland. This study suggests that bioenergy generation and compost production from Azolla are promising strategies towards mitigating the negative impact of this fern on the Anzali wetland.
“…The pairwise comparison matrix table is the output which is based on the criteria priority we have provided. In the pairwise comparison matrix, the diagonals always get values of only one [33]. Based on the pairwise comparison table, a standardized matrix has been obtained.…”
In the current era, there are a plethora of mobile phone companies rendering different features. It is challenging to distinguish the best and create correlations among them. However, this can be accomplished through crowdsourcing. Crowdsourcing is the process of gathering information from multiple sources, and we use the AHP (Analytic Hierarchy Process) process to determine which company’s model is the best among many. The weight value of each model is compared to the assigned values, and if one of the company product weights is greater than the assigned weight, that product is the best. Eventually, we can use this process to select the most preferred and best mobile phone model from among all other models. Gray Relational Analysis (GRA) is one of the most popular models, employing a grey co-efficient that estimates the data items by ranking. This model defines a process’s situation or state as black with no information and white with perfect information. In this work, AHP initially assumes criteria weights and assigns rank with the CR (Consistency Ratio) of 1.5%. The criteria weights are re-assigned based on the outcomes, and the CR remains constant as 1.5%. This work also provides an environmental-based attribute access control system, which adds the strength to the system by providing security and the integrity. So, this proposed work performs as a decision support system combined with the security enhancements, and hence it becomes a complete framework to provide a solution to a target application. The novelty of the proposed work is the combination of the crowdsourcing with the recommender system on a secured framework.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.