Master of Regional and Community Planning / Department of Landscape Architecture/Regional and Community Planning / Ray B. Weisenburger / This research explores the challenges related to the visual image of a city situated in a developing country. Originated as the colonial capital of British India, Kolkata faces new urban challenges in the post colonial world. This report intends to answer questions of imageability of the city as relevant to the Third World countries. Empathizing on the issues of scarcity of land, traffic congestion, accumulation of the urban poor, inadequacies in infrastructure and the organic expansion of fluid city boundaries under the neo-ideological globalization and liberal economic policies – Kolkata faces a host of urban problems. Imageability of the city usually tries to define the positive image of a city. The question here is, should the notions of imageability be confined to cities that inherently have succeeded in maintaining an appealing public image or should it be applied to the potential qualities of visual appropriateness to cities that have historically remained unattractive? This research intends to explore the visual quality of an area surrounding the five point intersection at Shyambazar, Kolkata, India. This study will be based on a number of observations and the different visual analysis techniques applicable in critically analyzing the visual conditions of an urban street pattern of a megacity in India. The main objective of this study is to find an appropriate visual quality for Kolkata, a megacity in the tropics – considering various related factors like – historical significance, demographic trends, geographical and climatological influences, transportation pattern, existing land use, socio-economic structure and inherent or associated urban problems of planning in developing nations.

Indiana University-Purdue University Indianapolis (IUPUI) / With the increasing number of vehicles on the road and the amount of time people spend driving their vehicles, traffic control and management has become an important part within logistics. Effective traffic control would involve traffic signal control and control over vehicle movement. Since Petri nets are versatile enough to represent traffic signals and traffic flow, it has become an important tool in urban traffic control. Many traffic systems are modeled using hybrid Petri nets. Chapter 1 briefly talks about traffic management systems and previous related work in the area of traffic control. Chapter 2 is a basic background on various Petri nets used in the study. The section also uses examples to demonstrate the working of Petri nets. Chapter 3 introduces the need for optimization in various industry. And then, it discusses different steps involved in optimizing a process. Chapter 4 discusses the existing model of two one-way intersection. In an effort to understand the model better, simulations are also carried out. Then, drawbacks of the existing model are discussed. This paves way for a new, improved, and realistic version of two one-way intersection. Various optimization steps discussed in Chapter 3 is used to optimize traffic light of the improved model. And then, a comparison between existing model and improved model is carried out. Chapter 5 expands the study of traffic models by connecting two different one-way intersection through a road (thus making it a network). Optimization and simulation of the connected-intersection model is also carried out. Chapter 6 is the summary which will provide a brief overview about each chapter.

Data-driven intelligent transportation systems (ITS) are increasingly playing a critical role in improving the efficiency of the existing transportation network and addressing traffic challenges in large cities, such as safety and road congestion. This dissertation employs data dimensionality reduction, reinforcement learning, and discrete outcome models to improve traffic flow and transportation safety. First, we propose a novel data-driven technique based on Koopman operator theory and dynamic mode decomposition (DMD) to address the complex nonlinear dynamics of signalized intersections. This approach not only provides a better understanding of intersection behavior but also offers faster computation times, making it a valuable tool for system identification and controller design. It represents a significant step towards more efficient and effective traffic management solutions. Second, we propose an innovative phase-switching approach for traffic light control using deep reinforcement learning, enhancing the efficiency of signalized intersections. The novel reward function, based on speed, waiting time, deceleration, and time to collision (TTC) for each vehicle, maximizes traffic flow and safety through real-time optimization. Finally, we introduce a mixed spline indicator pooled model, an approach for multivariate crash severity prediction, addressing the limitations of previous models by capturing temporal instability. It carefully incorporates additional independent variables to measure parameter slope changes over time, enhancing data fit and predictive accuracy. The developed models are estimated and validated using data from the Central Florida region.

This project deals with monitoring cars approaching the crossroads. Describes various methods of detection and discussing their problems. Primary goal is surveillance during the day in different weather conditions, but method of detection cars during the night and low light is also introduced. The most widely used algorithms are implemented using the OpenCV library. Important part is testing different algorithms and also variety of lighting conditions, camera locations and settings.

No description available.