Search

Electrical Impedance Tomography (EIT) is an ill-posed problem whereby there are insufficient measured data to solve for a large amount of unknowns (finite elements). Conventionally, EIT measurements are performed on the boundary of an object or a process vessel. This results in a lower spatial resolution in central regions far off the conventional periphery electrodes. This paper presents the development of a self-sufficient EIT sensor with an aim to obtain EIT measurements from any locality within the object or the process vessel. An ad hoc EIT sensor that performs the current injection and voltage measurement around two pairs of electrodes is developed. The sensor consists of a current source, voltage amplifier, multiplexers, and microcontroller. Tests were conducted on a phantom tank. The sensor successfully performs localized voltage measurements from the interior of the imaged space with channel SNR average of 15dB.

Following another vehicle too close is known as tailgating. Tailgater may not have enough space and time to avoid a collision. Thus there is a need for a fundamental understanding on factors affecting safe distance between vehicles. This paper aims to study such factors and to adopt certain rules and principles into the proposed traffic cellular automata model. Rule of seconds is applied and some deductions are made to attain a realistic traffic model. The simulation also entail human reaction time in perceiving safe distance with the leading vehicle and the simulation results are as expected. However there is a trade off between reaction time and an optimum safe following distance. Hence ideal reaction time of 0.75s is selected to emulate real life traffic flow without deteriorating traffic stability.

The increases of road vehicles also causes a higher chances of car accidents happened and more severe traffic congestion. Many researches have been done to relieve such situation including altering with traffic signal timing plan, either in single intersection or in multi-agent system. Another research area will be the wireless communication in vehicular network. In this study, the focus will be on modelling a vehicular ad hoc network (VANET) for data scavenging. Traffic Control Interface for MATLAB (TraCI4Matlab) is implemented to allow communication among Simulation of Urban Mobility (SUMO) and MATLAB, so that to achieve a vehicular network platform. SUMO is used to generate vehicles trace which will be used as data for later protocol assessment in MATLAB. Results from this study showed some of the features in TraCI4Matlab. Using the traffic control interface commands, properties of vehicles such as position, speed, acceleration, vehicle length, vehicle color, etc. can be retrieved into MATLAB. With the details obtained, routing protocol can be computed and assessed through the vehicular network platform.

Instead of using classical offline data-driven optimization technique in traffic network signal control, this work aims to explore the potential of implementing an online data-driven optimization technique. A dynamic modeling technique is proposed using Q-learning (QL) algorithm to online observe and learn the inflow-outflow traffic behaviors and extract the model parameters to update the evaluation model used in the fitness function of genetic algorithm (GA). The proposed GA with dynamic modeling is known as dyna- GA. Dyna-GA is then integrated into a hierarchical-based multi-agent traffic signal control system which consists of two layers. The lower-layer consists of several local agents that have autonomy in controlling their local intersection, whereas the upper-layer consists of one supervisory agent that has jurisdiction on all the local agents. The supervisory agent has the superiority in overwriting the local control decision if conflict occurred. The robustness of the proposed dyna-GA under several traffic scenarios is tested using a simulated arterial traffic network. The simulation results show the proposed dyna-GA has better performances in minimizing travel delay as compared to the classical GA which does not have the dynamic model.

The implementation of information technology in transportation system is becoming a leading trend nowadays due to alleviating the traffic problems such as traffic congestions and accidents are targeted as primary concerns by the traffic operators. Thus, monitoring the traffic scene serves as basis for the traffic operators especially at traffic intersection. Extracted traffic data from the monitoring system is often massive which requires efforts in searching for significant patterns in it. These patterns describe the vehicle movements are useful for observation of any abnormal behavior that leads to traffic conflicts. However, it will be a tremendous work for traffic operators to observe the vehicle flows manually where thousands of vehicles may travel through an intersection. Hence, the clustering of vehicle trajectory dataset for similar patterns identification is implemented with k-means and fuzzy c-means (FCM) clustering algorithm. As these clustering algorithms require the number of clusters as input parameter of the algorithms, the study of number of clusters for the clustering is served as focus in this paper. The evaluation of clustering performance with different input parameter of number of clusters is discussed in this paper.

This work aims to minimize average delay for an urban signalized intersection under oversaturated condition using genetic algorithm (GA). Relieving urban traffic congestion is an urgent call for traffic engineering. The effectiveness of traffic signalization is one of the key solutions to reduce congestion, but regrettably the current traffic signal control system is not fully optimized for handling oversaturated condition. Therefore, this work proposes GA to optimize traffic signals for reducing average delay at a signalized crossed intersection under oversaturated condition. A comprehensive traffic model based on Public Works Department, Malaysia has been developed as the platform. The average delay experienced by vehicles to traverse the crossed intersection is used as the performance metric to evaluate performances of the proposed algorithm. Simulation results show GA is able to control the traffic signals for minimizing the average delay to 55 sec/veh or equivalent to level of service (LOS) D.

Relieving traffic congestion is an urgent call for traffic engineering. Although various adaptive control strategies have been reported in literature to reduce the travel delay, most of them are not tested under oversaturated condition, where the traffic demand is higher than the road capacity. Therefore, this work proposes genetic algorithm (GA) to optimize the traffic signals for reducing the average delay at the at-grade crossed intersection under oversaturated condition. A comprehensive traffic model has been dexeloped as the testbed. The average delay experienced by every vehicle to traverse the intersection is taken as performance metric to evaluate the performances of the formulated GA. The simulation results show the formulated GA is able to optimize the traffic signals and minimize the average delay of the intersection to 55.2 sec or equivalent to level-of-service (LOS) D.

The emerging of the intelligent transportation system especially in the research area of traffic surveillance and solving traffic congestions, become notably crucial for traffic operators in the aim of achieving efficient vehicle flow. However, behavioural manoeuvres that describe the pattern of vehicles movements and change of the vehicle flow are not sufficiently modeled based on the conventional inductive-loop traffic sensors. These behavioural manoeuvres are useful for interpreting the indepth study of traffic pattern in a traffic network. Hence, with the advancement of the available vehicle tracking system, vehicle trajectory dataset is selected as suitable candidate input for the traffic pattern extraction. The implementation of k-means and fuzzy c-means (FCM) clustering algorithm for vehicle flow analyzing task is served as focus in this paper. Similarity function based on Longest Common Subsequence (LCSS) is implemented to measure the similarity among the trajectories before clustering is performed. Rand Index (RI) is computed to evaluate the clustering performance of two sets trajectories with two different traffic scenes by comparing the simulated clustering result with the ground-truth result.

Vehicles have become a daily needs for all of us and it is normal that every family is having at least one vehicle at their home. This leads to the increased of accidents and vehicular ad hoc network (VANET) is an approach invented to tackle with this problem. In order to study the algorithm in VANET, a mobility simulator is needed for simulation. SUMO is proved to be a good simulation tool for VANET while MATLAB is good for future algorithm development. To develop a good simulation platform, modification on SUMO files are necessary. This paper discusses on the steps for creating a left-hand traffic (LHT) simulation file that is suitable to be used in Malaysia. Most of the hard work in creating LHT simulation is to modify the road connection and traffic light files. This paper also showed the results of the simulation after SUMO files modification. It is recommended that user make a good decision in deciding the map for simulation. Smaller map is easier to modify, while maintaining the same map for the whole VANET development can prevent a start over on the SUMO files modification process.

This paper presents a method of gesture recognition using Hidden Markov Model (HMM). Gesture itself is based on the movement of each right hand (RH) and left hand (LH), which represents the word intended by the signer. The feature vector selected, gesture path, hand distance and hand orientations are obtained from RH and LH then trained using HMM to produce the respective gesture class. While training, in handling HMM state, we introduce fixed state and variable state, where in fixed state, the numbers of state is generally fixed for all gestures and while the number of state in variable state is determined by the movement of the gesture. It was found that fixed state gave the highest rate of recognition achieving 83.1%.

Recently, surveillance on moving vehicles for traffic flow monitoring has emerging in rapid rate. A comprehensive traffic data, that is vehicle trajectory, is selected as reliable data for discovering the underlying pattern via trajectory mining. As the task of monitoring moving vehicles via vehicle trajectory dataset can be tedious, researchers are keen to provide solutions that reducing the tedious task performed by the traffic operators. One of the solutions is to group the vehicle trajectory data according to the shape of the patterns. This grouping task is called as clustering. Each of the clusters formed represents a pattern. In this paper, the analysis of the implemented clustering algorithm on the trajectory data with similarity function is presented. Discussion on the issues concerning the trajectory clustering is also presented.

Project-based learning (PBL) has been shown to be an effective tool in engineering education. Thus, in this paper a framework for integrating PBL into the curriculum to enable the delivery and the assessment of the necessary knowledge, skills, and attitudes required by three generic program outcomes required for accreditation of engineering programs in countries that signatories to the Washington Accord. The breadth and depth required by these outcomes and how it is implemented in this framework is also highlighted. It is believed that this framework is general enough to be implemented in any engineering program.

The development of an efficient traffic flow monitoring system has been the main focus for many researchers working in the field. Due to the rapid development in urbanization, the complexity of traffic intersections provides challenges for researchers to detect the underlying traffic scenes. With the emerging video based surveillance system, vehicle trajectory can be extracted for observation and prediction via behavioral pattern learning. Prior to the learning, clustering of the extracted vehicle trajectory data is performed to group the data based on similarity measures. In this paper, the implementation of clustering algorithm on the trajectory data is analyzed and issues concerning the trajectory clustering are discussed.