Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

Highway Capacity Manual改訂の動向--テイラ-教授の講演より

In this paper, the analysis of recent advances in genetic algorithms is discussed. The genetic algorithms of great interest in research community are selected for analysis. This review will help the new and demanding researchers to provide the wider vision of genetic algorithms. The well-known algorithms and their implementation are presented with their pros and cons. The genetic operators and their usages are discussed with the aim of facilitating new researchers. The different research domains involved in genetic algorithms are covered. The future research directions in the area of genetic operators, fitness function and hybrid algorithms are discussed. This structured review will be helpful for research and graduate teaching.

/pdf/a-review-on-genetic-algorithm-past-present-and-future-2o5y8ru178.pdf

A review on genetic algorithm: past, present, and future

Integer programming formulations of discrete hub location problems

Computer Aided Civil and Infrastructure Engineering

SUMMARY

This paper addresses the toll pricing framework for the first-best pricing with logit-based stochastic user equilibrium (SUE) constraints. The first-best pricing is usually known as marginal-cost toll, which can be obtained by solving a traffic assignment problem based on the marginal cost functions. The marginal-cost toll, however, has rarely been implemented in practice, because it requires every specific link on the network to be charged. Thus, it is necessary to search for a substitute of the marginal cost pricing scheme, which can reduce the toll locations but still minimize the total travel time. The toll pricing framework is the set of all the substitute toll patterns of the marginal cost pricing. Assuming the users' route choice behavior following the logit-based SUE principle, this paper has first derived a mathematical expression for the toll pricing framework. Then, by proposing an origin-based variational inequality model for the logit-based SUE problem, another toll pricing framework is built, which avoids path enumeration/storage. Finally, the numerical test shows that many alternative pricing patterns can inherently reduce the charging locations and total toll collected, while achieving the same equilibrium link flow pattern. Copyright © 2013 John Wiley & Sons, Ltd.

/pdf/toll-pricing-framework-under-logit-based-stochastic-user-2h4c61nv6m.pdf

Toll pricing framework under logit-based stochastic user equilibrium constraints

Liner ship fleet deployment is the assignment of ships to liner service routes for delivering containers in a planning horizon. This paper first reformulates the maximum number of voyages that can be completed in the planning horizon, which is incorrectly defined by the existing studies on liner ship fleet deployment. It proceeds to remedy a constraint in Gelareh and Meng (Transp Res 46E:76–89 2010) such that the nonlinear programming model proposed by Gelareh and Meng (Transp Res 46E:76–89 2010) is equivalent to its linear formulation. Finally, a reformulation of the fleet deployment model is presented to eliminate the combinatorial behavior of the model proposed by Gelareh and Meng (Transp Res 46E:76–89 2010). Computational study demonstrates significant efficiency improvement of the reformulated model.

A note on liner ship fleet deployment

Station choice for Australian commuter rail lines: Equilibrium and optimal fare design

Maritime transport is the backbone of international trade and globalization. Maritime transport research can be roughly divided into two categories, namely the shipping side and the port side. Most of the classic approaches adopted to address practical problems in these research topics are based on long-term observations and expert knowledge, while few of them are based on historical data accumulated from practice. In recent years, emerging approaches, which we refer to as machine learning and deep learning techniques in this essay, have been receiving a wider attention to solve practical problems. As a relatively conservative industry, there are some initial trials of applying the emerging approaches to solve practical problems in the maritime sector. The objective of this essay is to review the application of emerging approaches to maritime transport research. The main research topics in maritime transport and classic methods developed to solve them are first presented. The introduction of emerging approaches and their suitability to be applied in maritime transport research is then discussed. Related existing studies are then reviewed according to problem settings, main data sources, and emerging approaches adopted. Challenges and solutions in the process are also discussed from the perspectives of data, model, users, and targets. Finally, promising future research directions are identified. This essay is the first to give a comprehensive review of existing studies on developing machine learning and deep learning models together with popular data sources used to address practical problems in maritime transport.

Emerging approaches applied to maritime transport research: Past and future

This paper aims to estimate capacity utilization of a liner ship route with a bounded polyhedral container shipment demand pattern, arising in the liner container shipping industry. The proposed maximum and minimum liner ship route capacity utilization problems are formulated as a linear programming model and a min–max model, respectively. We examine two fundamental properties of the min–max model. These two nice properties enable us to develop two e -optimal global optimization algorithms for solving the min–max model, which find a globally e -optimal solution by iteratively cutting off the bounded polyhedral container shipment demand set with a cut. The latter algorithm overcomes non-convexity of the remaining feasible demand set generated by the former algorithm via a novel hyperplane cut. Each hyperplane cut can assure that the current vertex of the polyhedral demand set is cut off, whereas solutions that may improve the current one by more than a factor of e are retained. Extensive numerical experiments for problems larger than those encountered in real applications demonstrate the computational efficacy of the latter algorithm.

Shuaian Wang

Papers

Toll pricing framework under logit-based stochastic user equilibrium constraints

A note on liner ship fleet deployment

Station choice for Australian commuter rail lines: Equilibrium and optimal fare design

Emerging approaches applied to maritime transport research: Past and future

Liner ship route capacity utilization estimation with a bounded polyhedral container shipment demand pattern