<p> This project presents the design, implementation and experimental demonstration of an intensity control system for highway lighting. High Intensity Discharge lights (HID) are replaced by the White Light Emitting diodes (LED) in highway lighting systems in order to incorporate the dimming feature and conserve energy. The intensity is controlled by utilizing a micro controller that belongs to the 8051 family by generating pulse width modulated signals that energize a metal-oxide-semiconductor field effect transistor (MOSFET) to switch the LEDs to accomplish the desired operation. </p><p> A working model using ATMEL has been developed in which an array of LEDs are connected in series and parallel to control the light intensity applicable to the highway lights, which makes it a real time system. The micro controller is programmed to keep light intensity high during peak traffic hours, and gradually reduce it as traffic decreases, until dawn when lights are turned off to save energy.</p>

<p> This paper proposes an in-node microprocessor-based vehicle classification approach to analyze and determine the types of vehicles passing over a 3-axis magnetometer sensor. The approach for vehicle classification utilizes J48 classification algorithm implemented in Weka (a machine learning software suite). J48 is Quinlan's C4.5 algorithm, an extension of decision tree machine learning based on an ID3 algorithm. The decision tree model is generated from a set of features extracted from vehicles passing over the 3-axis sensor. The features are attributes provided with correct classifications to the J48 training algorithm to generate a decision tree model with varying degrees of classification rates based on cross-validation. Ideally, using fewer attributes to generate the model allows for the highest computational efficiency due to fewer features needed to be calculated while minimalizing the tree with fewer branches. The generated tree model can then be easily implemented using nested if-loops in any language on a multitude of microprocessors. Also, setting an adaptive baseline to negate the effects of the background magnetic field allows reuse of the same tree model in multiple environments. The result of the experiment shows that the vehicle classification system is effective and efficient.</p>

<p> Intelligent transportation systems use in-pavement inductive loop sensors to collect real time traffic data. This method is very expensive in terms of installation and maintenance. Our research is focused on developing advanced algorithms capable of generating high amounts of energy that can charge a battery. This electromechanical energy conversion is an optimal way of energy scavenging that makes use of piezoelectric sensors. The power generated is sufficient to run the vehicle detection module that has several sensors embedded together. To achieve these goals, we have developed a simulation module using software&rsquo;s like LabVIEW and Multisim. The simulation module recreates a practical scenario that takes into consideration vehicle weight, speed, wheel width and frequency of the traffic.</p>

<p> In this thesis, path planning for an autonomous ground vehicle (AGV) in an urban environment is considered. The following problem is considered. starting from an initial location, the AGV desires to reach a final location by taking the shortest distance, while minimizing the AGVs position estimation error and guaranteeing that the AGVs position estimation uncertainty is below a desired threshold. The AGV is assumed to be equipped with receivers capable of producing pseudodange measurements on Global Navigation Satellite System (GNSS) satellites and cellular long-term evolution (LTE) towers. Using a geographic information system (GIS) three-dimensional (3-D) building map of the urban environment, a signal reliability map is introduced, which provides information about regions where large errors due to cellular signal multipath or poor GNSS line-of-sight (LOS) are expected. The vehicle uses the signal reliability map to calculate the position estimation mean-squared error (MSE). An analytical expression for the AGV's state estimates is derived for a weighted nonlinear least-squares (WNLS) estimator, which is used to find an analytical upper bound on the position bias due to multipath. A path planning approach based on Dijkstra's algorithm is proposed to optimize the AGV's path while minimizing the path length and the position estimation MSE, subject to keeping the position estimation uncertainty and position estimation bias due to multipath being below desired thresholds. The path planning approach yields the optimal path together with a list of feasible paths. Simulation results are presented demonstrating that utilizing ambient cellular LTE signals together with GNSS signals (1) reduces the uncertainty about the AGV's position, (2) increases the number of feasible paths to choose from, which could be useful if other considerations arise, e.g., traffic jams and road blockages due to construction, and (3) yields significantly shorter feasible paths, which would otherwise be infeasible with GNSS signals alone. Experimental results on a ground vehicle navigating in downtown Riverside, California, are presented demonstrating a close match between the simulated and experimental results.</p><p>