Development of prediction models for freeway incident durations using data mining techniques

The nation's freeway systems are becoming increasingly congested. A major contribution to traffic congestion on freeways is due to traffic incidents. Traffic incidents are non-recurring events such as accidents or stranded vehicles that cause a temporary roadway capacity reduction, and they can account for as much as 60 percent of all traffic congestion on freeways. One major freeway incident management strategy involves diverting traffic to avoid incident locations by relaying timely information through Intelligent Transportation Systems (ITS) devices such as dynamic message signs or real-time traveler information systems. The decision to divert traffic depends foremost on the expected duration of an incident, which is difficult to predict. In addition, the duration of an incident is affected by many contributing factors. Determining and understanding these factors can help the process of identifying and developing better strategies to reduce incident durations and alleviate traffic congestion. A number of research studies have attempted to develop models to predict incident durations, yet with limited success. ^ This dissertation research attempts to improve on this previous effort by applying data mining techniques to a comprehensive incident database maintained by the District 4 ITS Office of the Florida Department of Transportation (FDOT). Two categories of incident duration prediction models were developed: "offline" models designed for use in the performance evaluation of incident management programs, and "online" models for real-time prediction of incident duration to aid in the decision making of traffic diversion in the event of an ongoing incident. Multiple data mining analysis techniques were applied and evaluated in the research. The multiple linear regression analysis and decision tree based method were applied to develop the offline models, and the rule-based method and a tree algorithm called M5P were used to develop the online models. ^ The results show that the models in general can achieve high prediction accuracy within acceptable time intervals of the actual durations. The research also identifies some new contributing factors that have not been examined in past studies. As part of the research effort, software code was developed to implement the models in the existing software system of District 4 FDOT for actual applications. ^

A scalable multimedia content processing framework with application to TV shopping

The advent of smart TVs has reshaped the TV-consumer interaction by combining TVs with mobile-like applications and access to the Internet. However, consumers are still unable to seamlessly interact with the contents being streamed. An example of such limitation is TV shopping, in which a consumer makes a purchase of a product or item displayed in the current TV show. Currently, consumers can only stop the current show and attempt to find a similar item in the Web or an actual store. It would be more convenient if the consumer could interact with the TV to purchase interesting items. ^ Towards the realization of TV shopping, this dissertation proposes a scalable multimedia content processing framework. Two main challenges in TV shopping are addressed: the efficient detection of products in the content stream, and the retrieval of similar products given a consumer-selected product. The proposed framework consists of three components. The first component performs computational and temporal aware multimedia abstraction to select a reduced number of frames that summarize the important information in the video stream. By both reducing the number of frames and taking into account the computational cost of the subsequent detection phase, this component component allows the efficient detection of products in the stream. The second component realizes the detection phase. It executes scalable product detection using multi-cue optimization. Additional information cues are formulated into an optimization problem that allows the detection of complex products, i.e., those that do not have a rigid form and can appear in various poses. After the second component identifies products in the video stream, the consumer can select an interesting one for which similar ones must be located in a product database. To this end, the third component of the framework consists of an efficient, multi-dimensional, tree-based indexing method for multimedia databases. The proposed index mechanism serves as the backbone of the search. Moreover, it is able to efficiently bridge the semantic gap and perception subjectivity issues during the retrieval process to provide more relevant results.^

Tree Islands in the Shark Slough Landscape: Interactions of Vegetation, Hydrology, and Soils

Executive Summary: This report presents what we have learned about tree islands of Shark Slough and adjacent marshes of Everglades National Park (ENP), based on ecological studies carried out in these wetlands during the period 2000-2003. The tree islands of Shark Slough share many features with tree islands elsewhere in the Everglades. Their current composition and community structure is determined to a large extent by recent hydrology, as well as by disturbances (fire, freezes, hurricanes, man). Tree islands have historical, cultural, and biological values that are recognized by nearly all parties to the Comprehensive Everglades Restoration Plan (CERP). Maintaining and/or restoring the health of tree islands are major objectives of CERP. Consequently, there is a need within CERP for tools to assess the health of tree islands, and to relate these measures to the hydrologic regime to which they are exposed.

Using Florida Keys Reference Sites As a Standard for Restoration of Forest Structure in Everglades Tree Islands

In south Florida, tropical hardwood forests (hammocks) occur in Everglades tree islands and as more extensive forests in coastal settings in the nearby Florida Keys. Keys hammocks have been less disturbed by humans, and many qualify as “old-growth,” while Everglades hammocks have received much heavier use. With improvement of tree island condition an important element in Everglades restoration efforts, we examined stand structure in 23 Keys hammocks and 69 Everglades tree islands. Based on Stand Density Index and tree diameter distributions, many Everglades hammocks were characterized by low stocking and under-representation in the smaller size classes. In contrast, most Keys forests had the dense canopies and open understories usually associated with old-growth hardwood hammocks. Subject to the same caveats that apply to off-site references elsewhere, structural information from mature Keys hammocks can be helpful in planning and implementing forest restoration in Everglades tree islands. In many of these islands, such restoration might involve supplementing tree stocking by planting native trees to produce more complete site utilization and a more open understory.

Biogeochemical Contributions of Tree Islands to Everglades Wetland Landscape Nitrogen Cycling During Seasonal Inundation

In the Florida Everglades, tree islands are conspicuous heterogeneous elements in the herbaceous wetland landscape. We characterized the biogeochemical role of a seasonally flooded tree island during wet season inundation, specifically examining hydrologically mediated flows of nitrogen (N) and N retention by the tree island. We estimated ecosystem N standing stocks and fluxes, soil and litter N transformation rates, and hydrologic fluxes of N to quantify the net ecosystem N mass flux. Results showed that hydrologic sources of N were dominated by surface water loads of nitrate (NO3) and ammonium (NH4). Nitrate immobilization by soils and surficial leaf litter was an important sink for surface water dissolved inorganic N (DIN). We estimated that the net annual DIN retention by a seasonally flooded tree island was 20.5 ± 5.0 g m−2 during wet season inundation. Based on the estimated tree island surface water DIN loading rate, a seasonally flooded tree island retained 76% of imported DIN. As such, seasonally flooded tree islands have the potential to retain 55% of DIN entering the marsh landscape via upstream canal overland flow in the wet season. By increasing reactive surface area and DOC availability, we suggest that tree islands promote convergence of elements that enhance DIN retention. Tree islands of this region are thus important components of landscape-scale restoration efforts that seek to reduce sources of anthropogenic DIN to downstream estuaries.

Survival and growth responses of eight Everglades tree species along an experimental hydrological gradient on two tree island types

Questions: How are the early survival and growth of seedlings of Everglades tree species planted in an experimental setting on artificial tree islands affected by hydrology and substrate type? What are the implications of these responses for broader tree island restoration efforts? Location: Loxahatchee Impoundment Landscape Assessment (LILA), Boynton Beach, Florida, USA. Methods: An experiment was designed to test hydrological and substrate effects on seedling growth and survivorship. Two islands – a peat and a limestone-core island representing two major types found in the Everglades – were constructed in four macrocosms. A mixture of eight tree species was planted on each island in March of 2006 and 2007. Survival and height growth of seedlings planted in 2006 were assessed periodically during the next two and a half years. Results: Survival and growth improved with increasing elevation on both tree island substrate types. Seedlings' survival and growth responses along a moisture gradient matched species distributions along natural hydrological gradients in the Everglades. The effect of substrate on seedling performance showed higher survival of most species on the limestone tree islands, and faster growth on their peat-based counterparts. Conclusions: The present results could have profound implications for restoration of forests on existing landforms and artificial creation of tree islands. Knowledge of species tolerance to flooding and responses to different edaphic conditions present in wetlands is important in selecting suitable species to plant on restored tree islands

Field programmable gate array based target detection and gesture recognition

The move from Standard Definition (SD) to High Definition (HD) represents a six times increases in data, which needs to be processed. With expanding resolutions and evolving compression, there is a need for high performance with flexible architectures to allow for quick upgrade ability. The technology advances in image display resolutions, advanced compression techniques, and video intelligence. Software implementation of these systems can attain accuracy with tradeoffs among processing performance (to achieve specified frame rates, working on large image data sets), power and cost constraints. There is a need for new architectures to be in pace with the fast innovations in video and imaging. It contains dedicated hardware implementation of the pixel and frame rate processes on Field Programmable Gate Array (FPGA) to achieve the real-time performance. ^ The following outlines the contributions of the dissertation. (1) We develop a target detection system by applying a novel running average mean threshold (RAMT) approach to globalize the threshold required for background subtraction. This approach adapts the threshold automatically to different environments (indoor and outdoor) and different targets (humans and vehicles). For low power consumption and better performance, we design the complete system on FPGA. (2) We introduce a safe distance factor and develop an algorithm for occlusion occurrence detection during target tracking. A novel mean-threshold is calculated by motion-position analysis. (3) A new strategy for gesture recognition is developed using Combinational Neural Networks (CNN) based on a tree structure. Analysis of the method is done on American Sign Language (ASL) gestures. We introduce novel point of interests approach to reduce the feature vector size and gradient threshold approach for accurate classification. (4) We design a gesture recognition system using a hardware/ software co-simulation neural network for high speed and low memory storage requirements provided by the FPGA. We develop an innovative maximum distant algorithm which uses only 0.39% of the image as the feature vector to train and test the system design. Database set gestures involved in different applications may vary. Therefore, it is highly essential to keep the feature vector as low as possible while maintaining the same accuracy and performance^

Green tree frog

http://digitalcommons.fiu.edu/fce_lter_photos/1282/thumbnail.jpg

Calvin Liu measuring mangrove tree heights, Shark River Slough

This material is based upon work supported by the National Science Foundation through the Florida Coastal Everglades Long-Term Ecological Research program under Cooperative Agreements #DBI-0620409 and #DEB-9910514. This image is made available for non-commercial or educational use only.

Tagged tree damaged by Hurricane Wilma, Shark River Slough

This material is based upon work supported by the National Science Foundation through the Florida Coastal Everglades Long-Term Ecological Research program under Cooperative Agreements #DBI-0620409 and #DEB-9910514. This image is made available for non-commercial or educational use only.

Jay Sah measuring tree height in a mangrove forest impacted by Hurricane Wilma, Harney River

This material is based upon work supported by the National Science Foundation through the Florida Coastal Everglades Long-Term Ecological Research program under Cooperative Agreements #DBI-0620409 and #DEB-9910514. This image is made available for non-commercial or educational use only.

Tagged tree broken as result of Hurricane Wilma, Shark River Slough

This material is based upon work supported by the National Science Foundation through the Florida Coastal Everglades Long-Term Ecological Research program under Cooperative Agreements #DBI-0620409 and #DEB-9910514. This image is made available for non-commercial or educational use only.

Mike Ross inspecting mangrove tree canopy damage after Hurricane Wilma, Harney River

This material is based upon work supported by the National Science Foundation through the Florida Coastal Everglades Long-Term Ecological Research program under Cooperative Agreements #DBI-0620409 and #DEB-9910514. This image is made available for non-commercial or educational use only.

Left to right: Mike Ross and Nilesh Timilsina measuring mangrove tree height after Hurricane Wilma, Harney River

This material is based upon work supported by the National Science Foundation through the Florida Coastal Everglades Long-Term Ecological Research program under Cooperative Agreements #DBI-0620409 and #DEB-9910514. This image is made available for non-commercial or educational use only.

Jay Sah crossing tidal creek to measure tree damage by Hurricane Wilma, Harney River

This material is based upon work supported by the National Science Foundation through the Florida Coastal Everglades Long-Term Ecological Research program under Cooperative Agreements #DBI-0620409 and #DEB-9910514. This image is made available for non-commercial or educational use only.