nan Hadiuzzaman

Bus service quality prediction and attribute ranking: a neural network approach

Evaluation of service quality (SQ) based on user preferences has become a primary concern for the transportation authorities. The most significant attributes of public transportation systems are revealed through service quality analysis. This information serves as valuable input in constantly updating the quality of public transportation services. An appropriate tool is therefore mandatory in this regard. This paper represents a comparative study on the bus SQ prediction capabilities of three effective Artificial Neural Network (ANN) approaches, namely: Generalized Regression Neural Network (GRNN), Probabilistic Neural Network (PNN) and Pattern Recognition Neural Network (PRNN). To calibrate the parameters of the developed ANN models, data on users’ perception toward bus services of Dhaka city, Bangladesh, have been used. Taking the public opinion as baseline, GRNN and PNN have proven to be better prediction models since both have achieved higher accuracy compared to PRNN. Among 22 selected SQ attributes, the most significant attributes have been ranked according to their influence on the users’ decision making process. According to the GRNN and PNN models, punctuality and reliability, service frequency, seat availability and commuting experience are found to be the most significant attributes, which support the user-stated preferences.

Driver Compliance Analysis of Variable Speed Limit Based Freeway Traffic Control

In recent years, Variable Speed Limit (VSL) has been emerged as an effective mean of traffic control strategy to improve the mobility and traffic safety. This study analyzed the effects of driver response to VSL on a freeway corridor in the City of Edmonton, Alberta, Canada using VISSIM. A previously developed modified 2 nd order METANET model was adopted to implement the VSL control strategy. Various levels of speed compliance were assumed during the simulation. Finally, a simulation case study was analyzed based on the field collected data for drivers response towards posted speed limit. The study findings suggested that even with the lower speed compliance, VSL can still be effective for a traffic stream with lower speed variance. The simulation results also suggested that the adopted VSL control strategy overestimates the VSL effectiveness. BACKGROUND Increased travel demand in past 10-15 years together with technological advancement have led to the phenomenal development in the field of Intelligent Transportation System (ITS). To minimize congestion and to ensure safe traffic operation, there are number of dynamic traffic control strategies such as ramp metering (RM), variable speed limits (VSL), route guidance (RG), and lane management (LM) that have been implemented elsewhere under the umbrella of ITS. In this paper, we concentrate on driver perspective side of the VSL to evaluate its effectiveness on freeway operation. VSL is a dynamic traffic control strategy in ITS, where speed limit on freeway is altered to reduce the traffic stream speed, to increase the traffic flow, and to eliminate the risk of potential flow break down in response to traffic incident, or severe weather conditions. A typical VSL system architecture consists of traffic sensors to collect real time traffic related data, a communication protocol to communicate with the Traffic Management Centre (TMC), and the dynamic messages signs for displays.

H-CTM for simulating non-lane-based heterogeneous traffic

Abstract This paper developed a first-order deterministic macroscopic model H-CTM (heterogeneous cell transmission model) based on basic cell transmission model (CTM). The methodological calibration of the model considers the aggregate behavior of heterogeneous traffic under weak lane discipline. H-CTM incorporates a nonlinear fundamental diagram (FD), modeled for non-lane-based heterogeneous traffic, instead of traditional piecewise linear FD. For validating the model performance, high resolution traffic data were collected from a major arterial roadway (N3-Highway) of Dhaka city covering both peak and off-peak periods. Subsequently, the calibrated FD parameters were incorporated in the newly developed H-CTM to simulate the traffic. The estimated traffic states by the proposed model were then compared with basic model of CTM. Model performances, calculated in terms of mean absolute error based on ground truth values show that the H-CTM can be used to describe the traffic dynamics in the stated traffic system better than the basic model.

Study of Determinant Profiles of Cutaneous Tuberculosis in Bangladesh

The determinant spectra coupled with laboratory parameters of cutaneous tuberculosis in patients attending the Department of Dermatology and VD of the Community Based Medical College, Mymensingh, Bangladesh were studied for a period of over four years. A total of 110 patients (males, 75 and females, 35) having ages between 1 to 60 years were detected to infected. The result evidenced that skin tuberculosis is becoming mostly a disease of young patients between the ages of 16 to 30 years (44.55 %). There was a trend of appearance of Lupus vulgaris as the most common variant (49.09%) followed by Tuberculosis verrucosa cutis (29.09%). Skin tuberculosis was found more frequently in males than females (ratio 15: 7) and all patients belonged to lower socio-economic class. In 64 cases (58.18%) BCG vaccination coverage could not yield protection against cutaneous tuberculosis. Abnormal chest x-ray reports were available in 12 patients. It is interesting to note that enlargement of hilar lymph nodes, pleural effusion, ascites and generalized lymphadenopathy were not detected. Mantoux test revealed positive reactors in 100 patients (90.90%). Raised ESR (>20) was found in all patients. The validity of histopathology associated with FNAC was confirmed in 95 cases of patients (86.36%). There was evidence of Scrofuloderma in 20 patients and ICT indicated 74 positive cases. Bacteriological examination generated negative results in all cases. The response to antitubercular therapy was excellent except in 3 cases which required further monitoring of using additional drug and took much more time. The coexistence of pulmonary tuberculosis was determined in 2 patients. DOI: http://dx.doi.org/10.3329/cbmj.v1i1.13817 Community Based Medical Journal Vol.1(1) 2012 3-7

Real-time Traffic State Estimation and Prediction for Active Traffic and Demand Management: The Application of DynaTAM

Over the last decade, increased interests have been found in the field of Active Traffic and Demand Management (ATDM), and subsequently numerous simulation studies were devoted to see its effectiveness. Unfortunately, the real life benefits of ATDM application are not still apparent. This may be attributable to the following factors: (1) accuracy of traffic data obtained from the available field traffic sensors and failure to transmit the real-time and on-line data to the Traffic Management Centre (TMC); (2) absence of accurate traffic dynamics for the traffic state prediction; and (3) reliable field application software in the field of ATDM. To promise the above functions, in this research, DynaTAM―a field application tool is being developed by the authors. It can be used to analyze, simulate, and optimize traffic network in off-line or on-line mode. This paper presents the framework of DyanTAM and its communication protocol with the outer system, i.e. traffic control devices and field sensors. In the data management module, it has realized a practical data conditioning method which makes it suitable for ATDM application. The current version of this tool provides Variable Speed Limit (VSL) and Ramp Metering (RM) control as the start-up ATDM strategies with a hierarchical and coordinated control system. It evaluates the traffic states for roadway links by the well-known and parsimonious METANET and cell transmission model (CTM). Indeed, these macroscopic traffic models work as reference traffic simulators for traffic state prediction. As a preliminary evaluation, the VSL control module of DynaTAM will be tested this year on the Whitemud Drive (WMD), Edmonton. Therefore, the WMD project will be used in this paper as an exemplification, with some ideas and details given about the field test and application. . Author keywords: Active traffic and demand management; DynaTAM; Variable speed limit; Ramp metering; METANET; Cell transmission model.

Urban Traffic Collision Frequency Analysis and Modeling for Edmonton in Canada

Consistently higher number of traffic collisions was observed on Friday as compared to other days of the week in Edmonton, Canada. The collision data was investigated and a collision prediction model was formulated based on three contributing factors: 1) number of daylight hours, 2) number of snowfall hours, and; 3) visibility on daily basis. A negative binomial (NB) model was formulated to establish a relation between the collision frequency and the independent variables. The model accuracy test results were found good. Statistical measures indicate that increased traffic collision is significantly related with increased number of snowfall hours. The proposed NB model could provide a realistic estimate of expected collision frequency for a particular day as a function of number of hours of daylight, number of hours of snowfall and visibility. It is expected that predicted collision frequencies will help the decision maker to quantify the traffic safety of Edmonton.