“…As can be seen, in none of the above studies, the concepts of social network and the impact of driver's human role in a transportation network have been used to diffuse the information of shipping orders and maximize the profit of TSP system administrators. However, for the first time, the drivers' collaboration networks in two monoplex and multiplex perspectives presented by (Badiee et al, 2020). But, it did not consider the role of drivers in maximizing companies' profit, in TSP problem.…”
Section: Literature Reviewmentioning
confidence: 99%
“…The concepts of a drivers' collaboration network was presentedby Badiee et al, (2020), using the graph 𝐺 = (𝑉, 𝐸), in which V is the set of drivers, as graph nodes, and E is the set of edges, showing the "similarities" between nodes. Also, they introduced explanations of the edges, such as: working on a shared vehicle, shared origin, or destination.…”
“…In fact, what we are looking for in this problem is applying an algorithm to detect communities which should have the feature of overlapping communities, consider different connections between drivers and also different values of relation intensity between them. Therefore, by studying the literature of community detection methods, we select the OCDEM algorithm (Badiee et al, 2020) and develop it by improving the NCOS measure, using the relation intensity (RI) index for each two nodes, in the network. Some benefits of the OCDEM algorithm are as follows: the algorithm can determine the optimal number of the communities; considering the communities overlapping, so nodes can belong to more than one community; ability to solve edge-colored networks, and finally performing better than other algorithms.…”
Section: Extended Overlapping Community Detection Algorithm Based On ...mentioning
confidence: 99%
“…Lines 47 to 60 show the inter-layer community aggregating step. Badiee et al, (2020) proposed the "community fitness" measure, 𝑓 𝐶 𝑖 𝐶 𝑗 , as follows:…”
“…To extract the best results from these algorithms, the parameter value σ is set to 0.9. The OCDEM algorithm (Badiee et al, 2020) is also applied with the parameters α = 0.6, β = 0.35 and γ = 0.9.…”
One of the key issues in transportation systems is allocating shipping orders to the most appropriate drivers, in the shortest time and with the maximum profit. Many studies were carried out in the transportation service procurement process for allocating orders, but none of them considered driver-to-driver interactions and applied information diffusion concepts as a framework to maximize the profit, due to the lack of a framework to model the interactions. In this paper, we present a weighted drivers' collaboration network to form the interactions. To predict the behavior of drivers, a new community detection algorithm is developed to extract communities and their leaders, in terms of the speed and the power of receiving and diffusing shipping orders. Also, we present a profit maximization model using information diffusion power of community leaders. The results show the model is able to allocate shipping orders to the most suitable drivers, in the best possible time and with the highest profit. To demonstrate the performance of the developed algorithm, we present a numerical example. Finally, a case study is applied to solve the optimization problem. The results show that the optimized behavior of companies in allocating orders to drivers is based on their risk level, reputation, and the average number of their customers.
“…As can be seen, in none of the above studies, the concepts of social network and the impact of driver's human role in a transportation network have been used to diffuse the information of shipping orders and maximize the profit of TSP system administrators. However, for the first time, the drivers' collaboration networks in two monoplex and multiplex perspectives presented by (Badiee et al, 2020). But, it did not consider the role of drivers in maximizing companies' profit, in TSP problem.…”
Section: Literature Reviewmentioning
confidence: 99%
“…The concepts of a drivers' collaboration network was presentedby Badiee et al, (2020), using the graph 𝐺 = (𝑉, 𝐸), in which V is the set of drivers, as graph nodes, and E is the set of edges, showing the "similarities" between nodes. Also, they introduced explanations of the edges, such as: working on a shared vehicle, shared origin, or destination.…”
“…In fact, what we are looking for in this problem is applying an algorithm to detect communities which should have the feature of overlapping communities, consider different connections between drivers and also different values of relation intensity between them. Therefore, by studying the literature of community detection methods, we select the OCDEM algorithm (Badiee et al, 2020) and develop it by improving the NCOS measure, using the relation intensity (RI) index for each two nodes, in the network. Some benefits of the OCDEM algorithm are as follows: the algorithm can determine the optimal number of the communities; considering the communities overlapping, so nodes can belong to more than one community; ability to solve edge-colored networks, and finally performing better than other algorithms.…”
Section: Extended Overlapping Community Detection Algorithm Based On ...mentioning
confidence: 99%
“…Lines 47 to 60 show the inter-layer community aggregating step. Badiee et al, (2020) proposed the "community fitness" measure, 𝑓 𝐶 𝑖 𝐶 𝑗 , as follows:…”
“…To extract the best results from these algorithms, the parameter value σ is set to 0.9. The OCDEM algorithm (Badiee et al, 2020) is also applied with the parameters α = 0.6, β = 0.35 and γ = 0.9.…”
One of the key issues in transportation systems is allocating shipping orders to the most appropriate drivers, in the shortest time and with the maximum profit. Many studies were carried out in the transportation service procurement process for allocating orders, but none of them considered driver-to-driver interactions and applied information diffusion concepts as a framework to maximize the profit, due to the lack of a framework to model the interactions. In this paper, we present a weighted drivers' collaboration network to form the interactions. To predict the behavior of drivers, a new community detection algorithm is developed to extract communities and their leaders, in terms of the speed and the power of receiving and diffusing shipping orders. Also, we present a profit maximization model using information diffusion power of community leaders. The results show the model is able to allocate shipping orders to the most suitable drivers, in the best possible time and with the highest profit. To demonstrate the performance of the developed algorithm, we present a numerical example. Finally, a case study is applied to solve the optimization problem. The results show that the optimized behavior of companies in allocating orders to drivers is based on their risk level, reputation, and the average number of their customers.
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.