HongBin Lin

Bio: HongBin Lin is an academic researcher from IBM. The author has contributed to research in topics: Software quality & Heuristics. The author has an hindex of 3, co-authored 5 publications receiving 43 citations.

Public bus arrival time prediction based on traffic information management system

Abstract: This paper presents a statistical approach to predict the public bus arrival time based on traffic information management system. It considers a number of factors affecting bus travel time, such as departure time, work day, current bus location, number of links, number of intersections, passenger demand at each stop and traffic status of the urban network, etc. A linear model is given to describe the bus arrival time. The parameters of the model are trained by the historical bus arrival times. A prototype system is built to verify the practicability and efficiency of the approach. The approach has been proved relatively accurate and efficient by experiments.

Access request authentication and authorization information generation

Abstract: An access request authentication method, an authorization information generation method, an access request authentication system, and a hardware device. The access request authentication method includes: obtaining the current clock information; receiving a first access request, where the first access request includes a first input code; and determining whether to authorize the first access request based on the current clock information and the first input code.

Self-adapting task allocation approach for software outsourcing services

Abstract: Task allocation problem plays a key role in software outsourcing services. In this paper, a self-adapting task allocation approach is presented to provide optimal task assignment strategy in the project management of software outsourcing services. The approach is constituted by preparation, task allocation, evaluation, and evolution part. In the core part, task allocation, several mathematical models for different objectives are built to determine the optimal task allocation solutions, and heuristics are proposed to solve them. The proposed approach was proved by numerical examples to be efficient, practical and helpful for improving enterprise project management level and sources code quality.

Access request verification method and system, authorization information generation method, hardware equipment

Abstract: The enforcement mode of the invention relates to the field of information processing on the whole, and further relates to an access request verification method, an authorization information generation method, an access request verification system and hardware equipment. The access request verification method comprises the following steps: acquiring current clock information; receiving a first access request, wherein the first access request comprises a first input code; and judging whether to authorize the first access request according to the current clock information and the first input code. Compared with the prior art, the access request verification method and system, the authorization information generation method and the hardware equipment at least have two advantages as follows: at first, more fine-grained and flexible control to the authorization can be carried out, and then the first input code or a code for verification is generated on the basis of clock information. Therefore, the off-line verification management can be realized.

Bus Arrival Prediction and Trip Planning for Better User Experience and Services

Abstract: Public transport is regarded as one of the most efficient means to confront the explosively growing city traffic problems such as congestion and pollution. Generally, public transport is hard to be more adopted by citizens, because of its poor service. In order to provide good bus services and improve user experiences, in this chapter, we will focus on the technologies for bus arrival prediction and bus trip planning, which are the two key components for public transport system. First, a statistical approach is presented to predict the public bus arrival time. It describes the bus arrival time as a linear model while considering a number of factors such as departure time, work day, current bus location, number of links, number of intersections, passenger demand at each stop, traffic status of the urban network, and so on. The parameters of the model are trained by the historical traffic information. Second, a system of bus trip planning service is proposed, which can help public transport users choose the most appropriate bus lines and transfers based on real time and predicted bus arrival time. Because of the large scale of the data size, a two-step combination of K -transfer and Multiobjective algorithms is used to optimize user-traveling route. Finally, a prototype is built to verify the practicability and efficiency of the proposed approaches. Experimental results on real transport networks of large cities proved that the system is efficient and practical.

Demo: how long to wait?: predicting bus arrival time with mobile phone based participatory sensing

Abstract: The bus arrival time is primary information to most city transport travelers. Excessively long waiting time at bus stops often discourages the travelers and makes them reluctant to take buses. In this paper, we present a bus arrival time prediction system based on bus passengers' participatory sensing. With commodity mobile phones, the bus passengers' surrounding environmental context is effectively collected and utilized to estimate the bus traveling routes and predict bus arrival time at various bus stops. The proposed system solely relies on the collaborative effort of the participating users and is independent from the bus operating companies, so it can be easily adopted to support universal bus service systems without requesting support from particular bus operating companies. Instead of referring to GPS enabled location information, we resolve to more generally available and energy efficient sensing resources, including cell tower signals, movement statuses, audio recordings, etc., which bring less burden to the participatory party and encourage their participation. We develop a prototype system with different types of Android based mobile phones and comprehensively experiment over a 7 week period. The evaluation results suggest that the proposed system achieves outstanding prediction accuracy compared with those bus company initiated and GPS supported solutions. At the same time, the proposed solution is more generally available and energy friendly.

How Long to Wait? Predicting Bus Arrival Time With Mobile Phone Based Participatory Sensing

Abstract: The bus arrival time is primary information to most city transport travelers. Excessively long waiting time at bus stops often discourages the travelers and makes them reluctant to take buses. In this paper, we present a bus arrival time prediction system based on bus passengers' participatory sensing. With commodity mobile phones, the bus passengers' surrounding environmental context is effectively collected and utilized to estimate the bus traveling routes and predict bus arrival time at various bus stops. The proposed system solely relies on the collaborative effort of the participating users and is independent from the bus operating companies, so it can be easily adopted to support universal bus service systems without requesting support from particular bus operating companies. Instead of referring to GPS-enabled location information, we resort to more generally available and energy efficient sensing resources, including cell tower signals, movement statuses, audio recordings, etc., which bring less burden to the participatory party and encourage their participation. We develop a prototype system with different types of Android-based mobile phones and comprehensively experiment with the NTU campus shuttle buses as well as Singapore public buses over a 7-week period. The evaluation results suggest that the proposed system achieves outstanding prediction accuracy compared with those bus operator initiated and GPS supported solutions. We further adopt our system and conduct quick trial experiments with London bus system for 4 days, which suggests the easy deployment of our system and promising system performance across cities. At the same time, the proposed solution is more generally available and energy friendly.

Online Bus Arrival Time Prediction Using Hybrid Neural Network and Kalman filter Techniques

Abstract: The ability to obtain accurate predictions of bus arrival time on a real time basis is vital to both bus operations control and passenger information systems. Several studies have been devoted to this arrival time prediction problem in many countries; however, few resulted in completely satisfactory algorithms. This paper presents an effective method that can be used to predict the expected bus arrival time at individual bus stops along a service route. This method is a hybrid scheme that combines a neural network (NN) that infers decision rules from historical data with Kalman filter (KF) that fuses prediction calculations with current GPS measurements. The proposed algorithm relies on real-time location data and takes into account historical travel times as well as temporal and spatial variations of traffic conditions. A case study on a real bus route is conducted to evaluate the performance of the proposed algorithm in terms of prediction accuracy. The results indicate that the system is capable of achieving satisfactory performance and accuracy in predicting bus arrival times for Egyptian environments.