A multiobjective single bus corridor scheduling using machine learning-based predictive models

Abstract

Many real-life optimisation problems, including those in production and logistics, have uncertainties that pose considerable challenges for practitioners. In spite of considerable efforts, the current methods are still not satisfactory. This is primarily caused by a lack of effective methods to deal with various uncertainties. Existing literature comes from two isolated research communities, namely the operations research community and the machine learning community. In the operations research community, uncertainties are often modelled and solved through techniques like stochastic programming or robust optimisation, which are often criticised for their over conservativeness. In the machine learning community, the problem is formulated as a dynamic control problem and solved through techniques like supervised learning and/or reinforcement learning, which could suffer from being myopic and unstable. In this paper, we aim to fill this research gap and develop a novel framework that takes advantages of both short-term accuracy from mathematical models and high-quality future forecasts from machine learning modules. We demonstrate the practicality and feasibility of our approach for a real-life bus scheduling problem and two controlled bus scheduling instances that are generated artificially. To our knowledge, the proposed framework represents the first multi-objective bus-Contact R.

COVID-19 vaccine hesitancy: a social media analysis using deep learning

“…In this specific domain, people use ML/DL to search for new data patterns and generate predictive models. Such patterns are used to improve future operational decisions (Cohen, 2018;Chen et al, 2020;Kusiak, 2020). The success of this family of prediction techniques can be explained by factors such as the improvement of computational processing, the availability of massive sources of data; the growing demand of data-driven decision-making, and the need for automating decision processes.…”

Modelling and Optimisation of Resource Usage in an IoT Enabled Smart Campus

“…By considering historical origin-destination data, this study aims to minimise passenger wait time during transfer. Apart from optimising bus scheduling to improve passenger transit experience, other studies also aim to minimise costs of bus operations [168], improve on-time bus performance [169], and relieve unbalanced spatial and temporal distribution of buses in areas with less passenger demand [170].…”

“…Since scheduling buses involves multiple stakeholders who often have conflicting objectives, some studies have adopted multi-objectives optimisation approach to solve the problem. A study in [168] develop a model that aims to minimise bus operational cost while minimising passenger wait time and total bus overload by using predicted passenger arrival data for each time horizon. In this study, the problem has been solved using two popular evolutionary methods namely NSGA-II and MOED/D.…”

“…Several research works [167,171] have developed dynamic bus scheduling schemes to improve the transit experience of passengers, with the common objective being minimizing passenger wait times. However, many existing models estimate passenger wait time without considering the limited capacity of buses [168,219]. During peak hours particularly, certain passengers (depending on the queue length and their location in the queue) may need to wait for more than two buses before they get on board.…”

A QoS and Network Lifetime Aware Reliable Multicast Routing Protocol Using a Chaos Integrated Cuckoo Search Rider Optimization Algorithm

“…[16]. Generally, multicast routing problems includes the minimization of link delay, routing cost minimization, bandwidth maximization and link jitter minimization etc., By that, MR problem is considered as NP complexity for largescale and wide area network [17][18][19][20].…”