Multi-scale label interaction to improve object detection and segmentation

The project aims at advancing the state of the art in the use of context information for classification of image and video data. The use of context in the classification of images has been showed of great importance to improve the performance of actual object recognition systems. In our project we proposed the concept of Multi-scale Feature Labels as a general and compact method to exploit the local and global context. The feature extraction from the discriminative probability or classification confidence label field is of great novelty. Moreover the use of a multi-scale representation of the feature labels lead to a compact and efficient description of the context. The goal of the project has been also to provide a general-purpose method and prove its suitability in different image/video analysis problem. The two-year project generated 5 journal publications (plus 2 under submission), 10 conference publications (plus 2 under submission) and one patent (plus 1 pending). Of these publications, a relevant number make use of the main result of this project to improve the results in detection and/or segmentation of objects.

Systematic Identification of High Crash Locations Final Report, 2001

Federal and state policy makers increasingly emphasize the need to reduce highway crash rates. This emphasis is demonstrated in Iowa’s recently released draft Iowa Strategic Highway Safety Plan and by the U.S. Department of Transportation’s placement of “improved transportation safety” at the top of its list of strategic goals. Thus, finding improved methods to enhance highway safety has become a top priority at highway agencies. The objective of this project is to develop tools and procedures by which Iowa engineers can identify potentially hazardous roadway locations and designs, and to demonstrate the utility of these tools by developing candidate lists of high crash locations in the State. An initial task, building an integrated database to facilitate the tools and procedures, is an important product, in and of itself. Accordingly, the Iowa Department of Transportation (Iowa DOT) Geographic Information Management System (GIMS) and Geographic Information System Accident Analysis and Location System (GIS-ALAS) databases were integrated with available digital imagery. (The GIMS database contains roadway characteristics, e.g., lane width, surface and shoulder type, and traffic volume, for all public roadways. GIS-ALAS records include data, e.g., vehicles, drivers, roadway conditions, and the crash severity, for crashes occurring on public roadways during then past 10 years.)

Evaluation of Different Methods to Calculate Heavy-Truck VMT, Final Report, December 2004

Reliable estimates of heavy-truck volumes are important in a number of transportation applications. Estimates of truck volumes are necessary for pavement design and pavement management. Truck volumes are important in traffic safety. The number of trucks on the road also influences roadway capacity and traffic operations. Additionally, heavy vehicles pollute at higher rates than passenger vehicles. Consequently, reliable estimates of heavy-truck vehicle miles traveled (VMT) are important in creating accurate inventories of on-road emissions. This research evaluated three different methods to calculate heavy-truck annual average daily traffic (AADT) which can subsequently be used to estimate vehicle miles traveled (VMT). Traffic data from continuous count stations provided by the Iowa DOT were used to estimate AADT for two different truck groups (single-unit and multi-unit) using the three methods. The first method developed monthly and daily expansion factors for each truck group. The second and third methods created general expansion factors for all vehicles. Accuracy of the three methods was compared using n-fold cross-validation. In n-fold cross-validation, data are split into n partitions, and data from the nth partition are used to validate the remaining data. A comparison of the accuracy of the three methods was made using the estimates of prediction error obtained from cross-validation. The prediction error was determined by averaging the squared error between the estimated AADT and the actual AADT. Overall, the prediction error was the lowest for the method that developed expansion factors separately for the different truck groups for both single- and multi-unit trucks. This indicates that use of expansion factors specific to heavy trucks results in better estimates of AADT, and, subsequently, VMT, than using aggregate expansion factors and applying a percentage of trucks. Monthly, daily, and weekly traffic patterns were also evaluated. Significant variation exists in the temporal and seasonal patterns of heavy trucks as compared to passenger vehicles. This suggests that the use of aggregate expansion factors fails to adequately describe truck travel patterns.

Synthesis of Best Practice for Increasing Protection and Visibility of Highway Maintenance Vehicles, CTRE Final Report Iowa DOT Project TR-475, August 2002

The purpose of this research project is to study current practices in enhancing visibility and protection of highway maintenance vehicles involved in moving operations such as snow removal and shoulder operations, crack sealing, and pothole patching. The results will enable the maintenance staff to adequately assess the applicability and impact of each strategy to their use and budget. The report’s literature review chapter examines the use of maintenance vehicle warning lights, retroreflective tapes, shadow vehicles and truck-mounted attenuators, and advanced vehicle control systems, as well as other practices to improve visibility for both snowplow operators and vehicles. The chapter concludes that the Manual on Uniform Traffic Control Devices does not specify what color or kind of warning lights to use. Thus, a wide variety of lights are being used on maintenance vehicles. The study of the relevant literatures also suggests that there are no clear guidelines for moving work zones at this time. Two types of surveys were conducted to determine current practices to improve visibility and safety in moving work zones across the country and in the state of Iowa. In the first survey of state departments of transportation, most indicated using amber warning lights on their maintenance vehicles. Almost all the responding states indicated using some form of reflective material on their vehicles to make them more visible. Most participating states indicated that the color of their vehicles is orange. Most states indicated using more warning lights on snow removal vehicles than their other maintenance vehicles. All responding state agencies indicated using shadow vehicles and/or truck-mounted attenuators during their moving operations. In the second survey of Iowa counties, most indicated using very similar traffic control and warning devices during their granular road maintenance and snow removal operations. Mounting warning signs and rotating or strobe lights on the rear of maintenance vehicles is common for Iowa counties. The most common warning devices used during the counties’ snow removal operations are reflective tapes, warning flags, strobe lights, and auxiliary headlamps.

FY04 Enrich Iowa: State Funding for Iowa Libraries, 2004

In accordance with 2004 IOWA ACTS Chapter 182 (5)(5)(b), the State Library of Iowa submits this report on the uses and impact of state funding provided to Iowa libraries through the Enrich Iowa Program.

Final Report for the Iowa Livestock Industry Waste Characterization and Methane Recovery Information Dissemination Project, 2003

The Iowa livestock industry generates large quantities of manure and other organic residues; composed of feces, urine, bedding material, waste feed, dilution water, and mortalities. Often viewed as a waste material, little has been done to characterize and determine the usefulness of this resource. The Iowa Department of Natural Resources initiated the process to assess in detail the manure resource and the potential utilization of this resource through anaerobic digestion coupled with energy recovery. Many of the pieces required to assess the manure resource already exist, albeit in disparate forms and locations. This study began by interpreting and integrating existing Federal, State, ISU studies, and other sources of livestock numbers, housing, and management information. With these data, models were analyzed to determine energy production and economic feasibility of energy recovery using anaerobic digestion facilities on livestock faxms. Having these data individual facilities and clusters that appear economically feasible can be identified specifically through the use of a GIs system for further investigation. Also livestock facilities and clusters of facilities with high methane recovery potential can be the focus of targeted educational programs through Cooperative Extension network and other outreach networks, providing a more intensive counterpoint to broadly based educational efforts.

Asessing public policies. The case of education in Europe and the interaction between personal and institutional factors

The paper deals with the comparative study of European citizens' satisfaction with the state of education in their respective countries. Individual and contextual effects are tested applying multilevel analysis. The results show that educational public policies (level of decentralization, degree of comprehensiveness and public spending) as well as the students' social environment (socioeconomic and cultural status) have a sound impact on the opinions about the state of education.

Final Report of Emergency Services Interim Study Committee, February 2007

The Legislative Council established the Emergency Services Interim Study Committee in 2006 and authorized the Committee to meet for two days during the 2006 Legislative Interim. Upon request by the Committee, the Legislative Council subsequently approved a third meeting. The Committee was charged to study the governance, structure, and funding of the state's emergency services and available training for emergency services providers, and receive input from the Department of Public Defense's Division of Homeland Security and Emergency Management; Departments of Human Services, Public Health, and Public Safety, including the State Fire Marshal; and representatives of emergency services providers, including the Iowa Firemen's Association, Iowa Fire Chiefs' Association, Iowa Association of Professional Fire Chiefs, Iowa Professional Fire Fighters, Iowa Emergency Medical Services Association, and emergency room physicians.

Unmet Needs SFY 2004 Final Report, February 2005

Despite the successes of the Senior Living Program and other efforts of the Iowa Aging Network, there continue to be documented unmet needs throughout the state, in part because of general fund budget reductions. These are needs identified for elderly Iowans that the community service networks are unable to meet. The sources for this data are interdisciplinary teams with the Case Management Program for the Frail Elderly (CMPFE) and service providers under contract with the Area Agencies on Aging.

Unmet Needs SFY 2005 Final Report Version 2 10/26/2005

Despite the successes of the Senior Living Program and other efforts of the Iowa Aging Network, there continue to be documented unmet needs throughout the state, in part because of general fund budget reductions. These are needs identified for elderly Iowans that the community service networks are unable to meet. The sources for this data are interdisciplinary teams with the Case Management Program for the Frail Elderly (CMPFE) and service providers under contract with the Area Agencies on Aging.

Unmet Needs SFY 2006 Final Report, October 2006

Despite the successes of the Senior Living Program and other efforts of the Iowa Aging Network, there continue to be documented unmet needs throughout the state, in part because of general fund budget reductions. These are needs identified for elderly Iowans that the community service networks are unable to meet. The sources for this data are interdisciplinary teams with the Case Management Program for the Frail Elderly (CMPFE) and service providers under contract with the Area Agencies on Aging.

Unmet Needs SFY 2007 Final Report, October 2007

Despite the successes of the Senior Living Program and other efforts of the Iowa Aging Network, there continue to be documented unmet needs throughout the state, in part because of general fund budget reductions. These are needs identified for elderly Iowans that the community service networks are unable to meet. The sources for this data are interdisciplinary teams with the Case Management Program for the Frail Elderly (CMPFE) and service providers under contract with the Area Agencies on Aging.

Improving generalized regression analysis for the spatial prediction of forest communities

Aim This study used data from temperate forest communities to assess: (1) five different stepwise selection methods with generalized additive models, (2) the effect of weighting absences to ensure a prevalence of 0.5, (3) the effect of limiting absences beyond the environmental envelope defined by presences, (4) four different methods for incorporating spatial autocorrelation, and (5) the effect of integrating an interaction factor defined by a regression tree on the residuals of an initial environmental model. Location State of Vaud, western Switzerland. Methods Generalized additive models (GAMs) were fitted using the grasp package (generalized regression analysis and spatial predictions, http://www.cscf.ch/grasp). Results Model selection based on cross-validation appeared to be the best compromise between model stability and performance (parsimony) among the five methods tested. Weighting absences returned models that perform better than models fitted with the original sample prevalence. This appeared to be mainly due to the impact of very low prevalence values on evaluation statistics. Removing zeroes beyond the range of presences on main environmental gradients changed the set of selected predictors, and potentially their response curve shape. Moreover, removing zeroes slightly improved model performance and stability when compared with the baseline model on the same data set. Incorporating a spatial trend predictor improved model performance and stability significantly. Even better models were obtained when including local spatial autocorrelation. A novel approach to include interactions proved to be an efficient way to account for interactions between all predictors at once. Main conclusions Models and spatial predictions of 18 forest communities were significantly improved by using either: (1) cross-validation as a model selection method, (2) weighted absences, (3) limited absences, (4) predictors accounting for spatial autocorrelation, or (5) a factor variable accounting for interactions between all predictors. The final choice of model strategy should depend on the nature of the available data and the specific study aims. Statistical evaluation is useful in searching for the best modelling practice. However, one should not neglect to consider the shapes and interpretability of response curves, as well as the resulting spatial predictions in the final assessment.

Insects of forensic importance from Rio Grande do Sul state in southern Brazil

The experiment was conducted throughout the year 2005, at the Universidade Federal de Pelotas campus. The objectives of the study were to analyze the decomposition of rabbit (Oryctolagus cunniculus L.) with mean weight 2.67 Kg carcass and describe the interaction of insects acting on it, as well as the insect's potential use in legal medicine. We collected 5.239 insect specimens; 1.827 of them were obtained from larvae collected from carcasses and reared. The specimens were identified and 20 species were of forensic importance. The species Lucilia eximia (Wiedemann, 1819) and Chrysomya albiceps (Wiedemann, 1819) (Diptera, Calliphoridae) were better indicators of post-mortem interval (PMI) because they occurred in all seasons and were the first to reach the carcass. Hemilucilia semidiaphana (Rondani, 1850), H. segmentaria (Fabricius, 1805) (Diptera, Calliphoridae), Muscina stabulans (Fallén, 1817) and Synthesiomyia nudiseta (Wulp, 1883) (Diptera, Muscidae) can disclose death time because they occur only in certain months of the year. Oxyletrum discicolle (Brullé, 1840) (Coleoptera, Silphidae) and Dermestes maculates De Geer, 1774 (Coleoptera, Desmestidae) were found in advanced stages of decomposition.

Asessing public policies. The case of education in Europe and the interaction between personal and institutional factors

The paper deals with the comparative study of European citizens satisfaction with thestate of education in their respective countries. Individual and contextual effects aretested applying multilevel analysis. The results show that educational public policies(level of decentralization, degree of comprehensiveness and public spending) as well asthe students social environment (socioeconomic and cultural status) have a soundimpact on the opinions about the state of education.