Browsing by Author "Lan, LW"

Now showing 1 - 12 of 12

A novel model for quick response to disaster relief distribution
(2005)
Sheu, JB
;
Chen, YH
;
Lan, LW
;
運輸與物流管理系註：原交通所+運管所
;
Department of Transportation and Logistics Management
This paper presents a hybrid fuzzy-optimization methodology to solve the large-scale disaster relief distribution problem with the main goal of minimizing the total number of fatalities. The proposed method mainly contains a three-stage operational algorithm. Here fuzzy clustering techniques are used in the first stage to classify the damaged areas based on respective relief demand attributes and priority, followed by the second and the third stage, where fuzzy linear programming is employed to deal with the situation when the demand for victims is greater than the available resources. Results of a numerical study are illustrated to demonstrate the applicability of the proposed method.
Color image vehicular detection systems with and without fuzzy neural network: A comparison
(2003-09-01)
Lan, LW
;
Kuo, AY
;
Huang, YC
;
運輸與物流管理系註：原交通所+運管所
;
Department of Transportation and Logistics Management
This paper develops a color image vehicular detection (CIVD) system in which background differencing technique is employed to detect whether a vehicle passes through the detecting points equally spaced out on a pseudo line detector. Two methods (interval search and regression) are tried to determine the optimal crisp threshold values to cope with various lighting conditions. To compare the detection performance with and without incorporating a fuzzy neural network (FNN), a three-layer FNNCIVD system is further designed with trapezoidal membership function and network parameters trained by back propagation algorithm. Under different environments (freeway and urban street) with various lighting conditions (daytime and nighttime), it is found that the detection success rates for interval-search CIVD and regression CIVD are about the same. However, both perform worse than the FNNCIVD system in which about 90% success rates are reported with seven detection points. Compared with the interval-search CIVD system, the FNNCIVD system can increase the success rates at a range of 14% to 22% on the freeway mainline and 18% to 26% on the urban street. It is also found that daytime detection performance is slightly better than nighttime detection. Possible reasons for missed detection and false detection are discussed.
Development and deployment of public transport policy and planning in Taiwan
(2006-03-01)
Lan, LW
;
Wang, MT
;
Kuo, AY
;
運輸與物流管理系註：原交通所+運管所
;
Department of Transportation and Logistics Management
Over the past decade, the escalating roadway congestion and environmental deterioration due to heavy use of private vehicles have provoked the Taiwan government to realize the importance of public transport systems. Under the "carrot-and-stick" rationales, the government has formulated public transport policies and exercised a series of related initiatives by providing sufficient and higher quality of public transport services so as to attract more private vehicle users. In this paper, the planning philosophy and policy formulation of Taiwan's public transport development are highlighted. The most important initiatives, including the Five-year Enhancement of Mass Transportation Program and the upgrading public transport schemes in the National Development Plan are examined. Based on previous experience and lessons, we point out the most challenging issues that the government will encounter. Suggestions for the future of public transport planning are also addressed.
Development of a fuzzy neural network color image vehicular detection (FNNCIVD) system
(2002)
Lan, LW
;
Kuo, AY
;
運輸與物流管理系註：原交通所+運管所
;
Department of Transportation and Logistics Management
This paper develops a fuzzy neural network color image vehicular detection (FNNCIVD) system to detect the multiple-lane traffic flows. A pseudo line detector with fourteen detection points is placed on the monitor to detect the two-lane traffic images. On each detection point, the differencing of R, G and B pixel values between background Image and, Instantaneous Image are Inputted every one-tenth second Into a four-layer fuzzy neural network trained by the backpropagation algorithm. Traffic scenes in the daytime and nighttime are both experimented. The experiment results show that the success rates for traffic counting In different lighting conditions can be as high as 90%. in the mean time, the success rates for vehicle classification can reach 100%.
Fuzzy neural incident detection algorithms with rolling training procedure
(2003)
Lan, LW
;
Huang, YC
;
運輸與物流管理系註：原交通所+運管所
;
Department of Transportation and Logistics Management
This paper attempts to establish a fuzzy neural automatic incident detection (FNAID) algorithm, using back-propagation training procedures. A rolling training procedure continuously updating the traffic flow parameters is proposed to enhance the adaptability of FNAID to different traffic flow conditions. A real incident case is deliberately generated to calibrate the traffic simulator-Paramics. To validate the FNAID with and without rolling training procedure, the calibrated Paramics is used to simulate sufficient incident samples. The off-line tests and statistic tests conclude that under various traffic flow conditions, the FNAID with rolling training procedure has better detection performance than the one without rolling.
Genetic clustering algorithms
(2001-12-01)
Chiou, YC
;
Lan, LW
;
運輸與物流管理系註：原交通所+運管所
;
Department of Transportation and Logistics Management
This study employs genetic algorithms to solve clustering problems. Three models, SICM, STCM, CSPM, are developed according to different coding/decoding techniques. The effectiveness and efficiency of these models under varying problem sizes are analyzed in comparison to a conventional statistics clustering method (the agglomerative hierarchical clustering method). The results for small scale problems (10-50 objects) indicate that CSPM is the most effective but least efficient method, STCM is second most effective and efficient, SICM is least effective because of its long chromosome. The results for medium-to-large scale problems (50-200 objects) indicate that CSPM is still the most effective method. Furthermore, we have applied CSPM to solve an exemplified p-Median problem. The good results demonstrate that CSPM is usefully applicable. (C) 2001 Elsevier Science B.V. All rights reserved.
Genetic fuzzy logic controller: an iterative evolution algorithm with new encoding method
(2005-06-16)
Chiou, YC
;
Lan, LW
;
運輸與物流管理系註：原交通所+運管所
;
Department of Transportation and Logistics Management
Logic rules and membership functions are two key components of a fuzzy logic controller (FLC). If only one component is learned, the other one is often set subjectively thus can reduce the applicability of FLC. If both components are learned simultaneously, a very long chromosome is often needed thus may deteriorate the learning performance. To avoid these shortcomings, this paper employs genetic algorithms to learn both logic rules and membership functions sequentially. We propose a bi-level iterative evolution algorithm in selecting the logic rules and tuning the membership functions for a genetic fuzzy logic controller (GFLC). The upper level is to solve the composition of logic rules using the membership functions tuned by the lower level. The lower level is to determine the shape of membership functions using the logic rules learned from the upper level. We also propose a new encoding method for tuning the membership functions to overcome the problem of too many constraints. Our proposed GFLC model is compared with other similar GFLC, artificial neural network and fuzzy neural network models, which are trained and validated by the same examples with theoretical and field-observed car-following behaviors. The results reveal that our proposed GFLC has outperformed. © 2004 Elsevier B.V. All rights reserved.
Inhomogeneous cellular automata modeling for mixed traffic with cars and motorcycles
(2005-09-01)
Lan, LW
;
Chang, CW
;
運輸與物流管理系註：原交通所+運管所
;
Department of Transportation and Logistics Management
This paper develops inhomogeneous cellular automata models to elucidate the interacting movements of cars and motorcycles in mixed traffic contexts. The car and motorcycle are represented by non-identical particle sizes that respectively occupy 6x2 and 2x1 cell units, each of which is 1.25x1.25 meters. Based on the field survey, we establish deterministic cellular automata (CA) rules to govern the particle movements in a two-dimensional space. The instantaneous positions and speeds for all particles are updated in parallel per second accordingly. The deterministic CA models have been validated by another set of field observed data. To account for the deviations of particles' maximum speeds, we further modify the models with stochastic CA rules. The relationships between flow, cell occupancy (a proxy of density) and speed under different traffic mixtures and road (lane) widths are then elaborated.
Modeling bus drivers' aberrant behaviors and the influences on fuel and maintenance costs
(2003-12-01)
Lan, LW
;
Kuo, AY
;
運輸與物流管理系註：原交通所+運管所
;
Department of Transportation and Logistics Management
Bus drivers' aberrant behaviors such as errors and violations might bring about extra fuel consumption and mechanic abrading. To investigate how the aberrant behaviors affect the fuel and maintenance costs, seven indexes are proposed and their corresponding threshold values are determined through the field experiments. Nearly six months of en route data are collected from an intercity bus route and the raw data are converted into the proposed index values by a database management system. A collinearity test is performed and three different specifications of simultaneous-equation regression models are attempted. The results show that abnormal engine rotation, unstable speed gradient, remarkable jerk, and speeding are the four independent indexes which can significantly explain the effects of bus drivers' aberrant behaviors on fuel and maintenance costs. Based on the cost importance of these four indexes, the drivers are further clustered into five categories and some practical applications are addressed.
Provision of accessible transportation alternatives for the transportation handicapped in Taiwan
(1996-06-01)
Lan, LW
;
運輸與物流管理系註：原交通所+運管所
;
Department of Transportation and Logistics Management
Four transportation handicapped groups are identified in Taiwan (impaired ambulation, visually impaired, aged, and others) and nine accessible transportation alternatives are proposed. The costs and potential ridership for these nine alternatives in the Taipei area are estimated. Using analytic hierarchy process (AHP) and multicriteria evaluation with qualitative and quantitative data (MEQQD) methods, the most appropriate accessible transportation alternatives for each of the four handicap groups are selected. It is found that the best accessible transportation alternative for the impaired ambulation, the aged, and others would be a demand-responsive lift-equipped specialized van, while half-fare subsidized taxi would be the second-best option. By contrast, the best alternative for the visually impaired would be half-fare subsidized taxi, while conventional bus with broadcast equipment would be the second-best choice.
Self-organization phenomenon and the edge of chaos in traffic flow dynamics
(2003)
Lan, LW
;
Lin, FY
;
Wang, YP
;
運輸與物流管理系註：原交通所+運管所
;
Department of Transportation and Logistics Management
According to the complexity theory, a self-organization phenomenon might exist when the phase shifts from order (non-congested) to chaos (congested) state within a system. In this paper, cellular automaton (CA) traffic simulator is applied to investigate the self-organization forming process as the traffic density grows. Real traffic data are used to examine whether the power law, an indicator of self-organization phenomenon, exists or not. Our empirical evidence on a two-lane freeway shows that self-organization phenomenon appears when the density exceeds 45% (or 60 pcu/km); however, the edge of chaos is at a density level of 33.8% (or 45 pcu/km), which should be the starting control point (e.g., ramp metering) for recurrent congestion.
Structural equation modeling to determine passenger loyalty toward intercity bus services
(2005)
Wen, CH
;
Lan, LW
;
Cheng, HL
;
運輸與物流管理系註：原交通所+運管所
;
Department of Transportation and Logistics Management
This paper investigates passenger loyalty to intercity bus services and identifies important factors influencing loyalty. The relationships between passenger loyalty and other latent factors, including satisfaction, service value, service quality, sacrifice, switching costs, attractiveness of competitors, and trust are hypothesized and tested. Factor analysis is used to extract the latent service quality factors from a large number of service quality indicators. Structural equation models are then developed to elucidate the causal relationships of passenger loyalty and the latent factors. The empirical results have confirmed the proposed hypotheses. Satisfaction has the most significant influence on passenger loyalty. Service value, switching costs, and trust have direct and positive effects on loyalty, whereas attractiveness of competitors has a direct negative effect. The indirect effect of service quality, via service value and satisfaction, on passenger loyalty is also significant. From the empirical results, managerial implications for the bus carriers are addressed.