Tracking and modeling huge amount of users’ movement in a multi-floor building by using wireless devices is a challenging task, due to crowd movement complexity and signal sensing accuracy. In this paper, we use Layered Hidden Markov Model (LHMM) to fit the spatial-temporal trajectories (with large number of missing values). We decompose the problem into distinct layers that Hidden Markov Models (HMMs) are operated at different spatial granularities separately. Baum-Welch algorithm and Viterbi algorithm are used for finding the probable location sequences at each layer. By measuring the predicted result of trajectories, we compared the predicted results of both single standards HMM and multiple levels LHMM though 2D/3D path plotting, execution time and trajectory distance. The results indicate that LHMMs are better than HMMs for modeling and predicting the incomplete, long- distance temporal-spatial trajectories data.

We are concerned with the routine crowd management problem after a major event at a known venue. Without properly design com- plementary transport services, such sudden crowd build-ups will over- whelm the existing infrastructure. In this paper, we introduce a novel flow-rate based model to model the dynamic movement of passenger- s over the transportation flow network. Based on this basic model, an integer linear programming model is proposed to solve the bus transit problem permanently. We validate our model against a real scenario in Singapore, where a newly constructed mega-stadium hosts various large events regularly. The results show that the proposed approach effectively enables routine crowd, and achieves almost 24.1% travel time reduction with an addition of 40 buses serving 18.7% of the passengers.

This paper reviews the logistics challenges of a decentralization strategy in Singapore. The main purpose of an urban decentralization, where the commercial hubs and retail clusters are distributed in several regional centers is to relieve congestion from the city center and to move business closer to home. However, this approach can also create congestion in regional centers due to the rapid flow of public, private and freight vehicles in and out of regional centers. This paper identifies three major challenges and proposes Retail Precinct Management (RPM) which consists of four inter-related approaches to overcome these challenges.

A number of cities around the world have adopted urban consolidation centers (UCCs) to address challenges of last-mile deliveries. At the UCC, goods are consolidated based on their destinations prior to their deliveries into city centers. Typically, a UCC owns a fleet of eco- friendly vehicles to carry out such deliveries. Shippers/carriers that make use of the UCC’s service hence no longer need to be restricted by time- window and vehicle-type regulations. As a result, they retain the ability to deploy large trucks for the economies of scale from the source to the UCC which is located outside the city center. Furthermore, the resources which would otherwise be spent in the city center can then be utilized for other purposes. With possibly tighter regulation and thinning profit margin in near future, requests for UCC’s services will become more and more common, and there is a need for a market mechanism to allocate UCC’s resources to provide sustainable services for shippers/carriers in a win-win fashion. An early work of our research team (Handoko et al., 2014) proposed a profit-maximizing auction mechanism for the use of UCC’s last-mile delivery service. In this paper, we extend this work with an idea of rolling horizon to give bidders more flexibility in competing for the UCC’s resources in advance. In particular, it addresses the needs of many shippers/carriers to be able both plan deliveries weeks ahead and at the same time bid for the UCC’s service at the last minute. Under our rolling horizon framework, the capacity of the same truck is up for bid in several successive auctions. To allocate truck capacities among these auctions under future demand uncertainty, we propose a virtual pricing mechanism which makes use of Target-oriented Robust Optimization techniques.

Less-than-truckload deliveries is known to be a source of inefficiency in last-mile logistics leading to high transport costs, environmental pollution, traffic jam, partic- ularly in urban settings. An Urban Consolidation Center (UCC) provides a platform to consolidate freights from various sources before delivering into the city. The operations of UCCs consist of 2 interrelated phases, consolidating freights and scheduling trucks into the city center. This problem is computationally challenging because of large urban freight volumes, which prohibits optimal solutions of conventional integer programming models to be found efficiently. In this paper, we propose two novel decomposition schemes: a vertical decomposition based on dynamic programming can achieve optimal consolidation for the single-period problem, and the horizontal decomposition based on a Lagrangian Relaxation can achieve good approximate solution for the multi-period problem. The combination of these two decompositions yield an efficient approach for dealing with large-scale problems.

Last-mile logistics is vital to keep the economy of a city going. At the same time, however, the last-mile deliveries exert enormous pressures on the economic, environmental, and social well-being of the city. Delivery vehicles often remain for prolonged period of time traveling on congested roads around the city center. This drives up the delivery cost and contributes excessively to the carbon footprint. As loading/unloading bays inside the city are plagued with long queues, direct deliveries to multiple destinations (referred to as fragmented deliveries) not only diminish the delivery efficiency but also worsen the traffic condition, causing further inconveniences to the local residents. Order sharing is a plausible solution to such issue as it creates more consolidated deliveries, but not all orders can actually be shared. Carriers might have private orders they need to fulfill themselves. Herein, we introduce an order sharing mechanism in the form of a double auction with split delivery to facilitate an efficient collaboration among carriers while simultaneously preserving some degree of privacy. Computational experiments confirm the efficacy of our proposed mechanism in producing cost savings and reducing environmental impacts.

Collective graphical models (CGMs) are a for- malism for inference and learning about a popu- lation of independent and identically distributed individuals when only noisy aggregate data are available. We highlight a close connection be- tween approximate MAP inference in CGMs and marginal inference in standard graphical models. The connection leads us to derive a novel Belief Propagation (BP) style algorithm for collective graphical models. Mathematically, the algorithm is a strict generalization of BP—it can be viewed as an extension to minimize the Bethe free energy plus additional energy terms that are non-linear functions of the marginals. For CGMs, the al- gorithm is much more efficient than previous ap- proaches to inference. We demonstrate its perfor- mance on two synthetic experiments concerning bird migration and collective human mobility.

A recent exploratory study on the collaborative urban logistics in Singapore suggests that cost reduction and privacy preservation are two main drivers that would motivate the participation of carriers in consolidating their last mile deliveries. With Singapore's mild restrictions on the vehicle types or the time windows for the last-mile delivery, we believe that with proper technology in place, an Urban Consolidation Center like the Tenjin Joint Distribution System in Fukuoka Japan may be implemented to achieve cost reduction with some degree of privacy preservation. Participating carriers keep their respective private orders and have the option to get their remaining shareable orders consolidated with those from the other carriers' fleet. To this end, we propose in this paper a double auction mechanism that enables such consolidation with an objective to maximize the total cost savings attained by all participating carriers. Our experimental results on 5 zones of delivery in Singapore CBD demonstrate that the proposed double auction is able to bring about reductions in the number of inter-zone travels, thereby producing cost savings to the participating carriers.

This paper reviews the logistics challenges of a decentralization strategy in Singapore. The main purpose of an urban decentralization, where the commercial hubs and retail clusters are distributed in several regional centers is to relieve congestion from the city center and to move business closer to home. However, this approach can also create congestion in regional centers due to the rapid flow of public, private and freight vehicles in and out of regional centers. This paper identifies three major challenges and proposes Retail Precinct Management (RPM) which consists of four inter-related approaches to overcome these challenges.