Susana Baptista

A period vehicle routing case study

Abstract The period vehicle routing problem is a multilevel problem assembling two classical problems: the assignment problem and the vehicle routing problem. Collection days have to be assigned to each customer and vehicle routes have to be designed for each day of the period (time horizon) so that the total distribution cost is minimised. The interaction between the temporal and spatial aspects turns the problem into one of the most challenging variations of vehicle routing. In this paper, we present the study of a real period vehicle routing system: the collection of recycling paper containers in the City Council of Almada, Portugal.

Bioecology and Vectorial Capacity of Aedes albopictus (Diptera: Culicidae) in Macao, China, in Relation to Dengue Virus Transmission

Abstract Until 2001, the Chinese Territory of Macao had not registered any autochthonous dengue cases, despite the abundance of Aedes albopictus (Skuse), a known vector. This work describes a bioecological characterization of the local Ae. albopictus adult population, with the purpose of estimating the receptivity of Macao to dengue introduction. In the wet seasons of 1997 and 1998 and the dry season of 1998, Ae. albopictus was the most abundant human-biting mosquito. Daily biting rates of 314 mosquitoes per person were recorded in the wet season with a reduction to 94 in the dry season. Ae. albopictus was mainly exophagic and exophilic and had a human blood index of 44%. The parity rate of field-collected mosquitoes was 57%. Daily survival rate ranged from 91 to 97%. Estimates of vectorial capacity ranged from 144 to 880, depending on what parameter values were used. These estimates indicated a great receptivity for the introduction of dengue viruses, as the 2001 outbreak came to prove.

Lyme borreliosis spirochetes in questing ticks from mainland Portugal.

In Portugal, Ixodes ricinus ticks have been shown to contain DNA of several spirochetes belonging to the Borrelia burgdorferi sensu lato complex, with major differences in the genetic diversity between ecozones. Some isolates have been obtained since 1999, confirming the circulation of pathogenic strains in these ticks. Ixodes ricinus is considered to be a widespread species, however, in Portugal it is found only in a few habitats. Here we present preliminary results from a nationwide survey of questing I. ricinus (n = 4,001) and other Ixodidae (n = 1,534) in Portugal, initiated in 2001. The sampling points (so far 41) were selected using a Geographic Information System, according to the type of vegetation, accessibility and prevalence of human cases. The spatial and temporal of tick abundance and the infection of B. burgdorferi sensu lato in ticks were determined in selected areas. Ticks were examined for the presence of B. burgdorferi sensu lato by culturing (719 out of 4,001 I. ricinus), and direct PCR amplification of the 5S-23S intergenic spacer region (1,870 out of 5,535) followed by RFLP analysis, the reverse line blot assay and nucleotide sequencing of PCR amplicons. The most abundant tick genus was Rhipicephalus (53%), followed by Dermacentor (34%), I. ricinus and Hyalomma (7%, each). The Mafra and Grândola sites, where a more intensive study was carried out, were excellent habitats for I. ricinus. However, a clear difference of the prevalence of Borrelia infection and the genetic diversity of circulating spirochetes was observed in these two sites. Genotyping of all I. ricinus isolates revealed 5 B. garinii, 8 B. lusitaniae and 1 B. valaisiana strains, which were obtained for the first time in these regions along with a considerable percentage of tick-derived PCR amplicons. Two hard-tick species other than I. ricinus in Grândola were also B. lusitaniae positive, thus seeming to take part in the transmission cycle of Borrelia. The seasonal dynamics of I. ricinus in Mafra was bimodal, more pronounced in nymphs than in adults. The present findings indicate that B. burgdorferi sensu lato agents are differentially maintained in nature in local tick populations in different geographic areas across Portugal and that the risk of acquiring Lyme borreliosis in certain areas of Portugal is higher than previously assumed.

A case study on the application of an approximated hypercube model to emergency medical systems management

This paper describes an application of the approximated hypercube model to Lisbon emergency medical services (EMS) management, namely for assessing alternative dispatching rules for assigning ambulances to emergency calls. The approximated hypercube (A-hypercube) is a queuing theory model that computes several performance measures such as average response time, server workloads or the probability of all servers being busy (loss probability). The assumptions of the extended model are Poisson customer arrivals, general service time (customer and server dependent) and a fixed preference assignment rule of servers to customers. The fact that dispatching rules are precisely a model parameter, turn this model into a valuable tool in the definition of efficient operating rules. In this paper, we propose new expressions for the computation of system performance measures during periods in which the emergency call arrival process is not stationary. Different dispatching rules are evaluated by comparing the system performance measures obtained from the extended A-hypercube model and a simulation model, using data collected from the Lisbon EMS Department.

A Metaheuristic for Solving Large-Scale Two-Stage Stochastic Mixed 0-1 Programs with the Time Stochastic Dominance Risk Averse Strategy

Abstract Supply Chain Design problems often result into multiperiod stochastic mixed integer problems that are hard to solve. In this paper we propose a metaheuristic algorithm as a specialization for two- stage problems of the so-named Fix-and-Relax Algorithm presented previously for solving large- scale multiperiod stochastic mixed 0–1 optimization problems under a time stochastic dominance risk averse strategy, so-named TSD. Some computational experience is presented.

On risk management of a two-stage stochastic mixed 0–1 model for the closed-loop supply chain design problem

Abstract In this work, the design and operation planning of a multi-period, multi-product closed-loop supply chain is addressed. Recovered end-of-life products from customers are evaluated in disassembly centers and accordingly are sent back to factories for remanufacturing, or leave the network either by being sold to third parties or by being sent to disposal. Typical uncertain parameters are product demand, production cost, and returned product volume and evaluation, among others. So, stochastic optimization approaches should be used for problem solving, where different topology decisions on the timing, location and capacity of some entities (factories, and distribution and sorting centers) are to be considered along a time horizon. A two-stage multi-period stochastic mixed 0–1 bilinear optimization model is introduced, where the combined definition of the available entities at the periods and the products’ flow among the entities, maximizes the net present value of the expected total profit along the time horizon. A version of the mixture of chance-constrained and second order stochastic dominance risk averse measures is considered for risk management at intermediate periods of the time horizon. Given the high dimensions of the model it is unrealistic to look for the optimality of the solution in an affordable computing effort for current hardware and optimization software resources. So, a decomposition approach is considered, namely a Fix-and-Relax decomposition algorithm. For assessing the computational validation of the modeling and algorithmic proposals, pilot cases are taken from a real-life glass supply chain network whose main features are retained.

A Fix-and-Relax Algorithm for Solving Parallel and Sequential Versions of a Multi-period Multi-product Closed Loop Supply Chain Design and Operation Planning Model

In this work we present the sequential and parallel versions of a heuristic algorithm for the solution of a two-stage stochastic mixed 0-1 model for closed loop supply chain planning problem along a time horizon. Some computational experience conducted on randomly generated networks shows the quality of the proposed approach.