Computer Engineering Commons^™

An Approach To Counting Vehicles From Pre-Recorded Video Using Computer Algorithms, Mishuk Majumder

LSU Master's Theses

One of the fundamental sources of data for traffic analysis is vehicle counts, which can be conducted either by the traditional manual method or by automated means. Different agencies have guidelines for manual counting, but they are typically prepared for particular conditions. In the case of automated counting, different methods have been applied, but You Only Look Once (YOLO), a recently developed object detection model, presents new potential in automated vehicle counting. The first objective of this study was to formulate general guidelines for manual counting based on experience gained in the field. Another goal of this study was to …

Tech Comm Eagle Eye-Tracking Control System, Gabiella Lail, Robert Shaw, Hunter Smatla, Matthew Gary

Discovery Day - Prescott

Mobile eye-tracking systems provide usability research support as well as access to a wide range of robotics and technical communication research opportunities. Optical tracking systems are often prohibitively expensive and do not provide the mobility or flexibility needed for a variety of research application possibilities. Our team proposes building a simple mobile eye-tracking system to be used in-house at ERAU for heat-mapping, robotics, control systems, and various technical communication applications in a structured research environment. The mobile eyetracking system will become part of a larger research and hands-on technical communication usability lab and research center. The research team intends to …

Desarrollo De Un Esquema De Gestión Hídrica En El Sistema Acuífero Sap 3.1 Apoyado De La Tipificación De Suelos Y El Modelo Conceptual De Thöt, Maria Camila Soriano Espinosa, Camilo José Rodríguez Carvajal

Ingeniería Ambiental y Sanitaria

El presente proyecto tiene como objetivo principal desarrollar un esquema de gestión hídrica (EGH) en el sistema acuífero SAP 3.1, provincia llanos orientales, con base en la tipificación de suelos y el modelo conceptual de Tӧth, partiendo de que las aguas subterráneas se consideran una fuente alternativa de abastecimiento por su mejor calidad y el bajo costo de manejo en comparación al agua superficial, y teniendo en cuenta que el Departamento del Meta conoce la riqueza hídrica que está en su jurisdicción, no cuenta con una regulación adecuada en pro de una gestión hídrica a nivel subterráneo. La metodología empleada …

Comparison Of Object Detection And Patch-Based Classification Deep Learning Models On Mid- To Late-Season Weed Detection In Uav Imagery, Arun Narenthiran Veeranampalayam Sivakumar, Jiating Li, Stephen Scott, Eric T. Psota, Amit J. Jhala, Joe D. Luck, Yeyin Shi

Biological Systems Engineering: Papers and Publications

Mid- to late-season weeds that escape from the routine early-season weed management threaten agricultural production by creating a large number of seeds for several future growing seasons. Rapid and accurate detection of weed patches in field is the first step of site-specific weed management. In this study, object detection-based convolutional neural network models were trained and evaluated over low-altitude unmanned aerial vehicle (UAV) imagery for mid- to late-season weed detection in soybean fields. The performance of two object detection models, Faster RCNN and the Single Shot Detector (SSD), were evaluated and compared in terms of weed detection performance using mean …

Improving The Sustainability Of The Built Environment By Training Its Workforce In More Efficient And Greener Ways Of Designing And Constructing Through The Horizon2020 Bimcert Project, Barry Mcauley, Avril Behan

Conference papers

The construction industry consumes up to 50% of mineral resources excavated from nature, generates about 33% of CO2 present in the atmosphere and is responsible for 40% of total global energy through both construction and operation of buildings. The realisation that current pervasive construction practices now face globalization, sustainability, and environmental concerns, as well as ever-changing legislation requirements and new skills needed for the information age has resulted in technologies such as Building Information Modelling (BIM) becoming a key enabler in navigating these barriers. To assist in overcoming these barriers, a number of funding initiatives have been put in place …

Centres Of Excellence And Roadmaps For Digital Transition: Lessons For Ireland’S Construction Industry, Barry Mcauley, Alan Hore, Roger West

Conference papers

Like most sectors in today’s working world, construction businesses are challenged to work in an increasingly digitised world with sophisticated demands from intelligent clients. So much has been written about the inefficiencies of the construction industry, its fragmentation, lack of collaboration, low margins, adversarial pricing, poor productivity, financial fragility, lack of research and development, poor industry image and relatively weak use of digital solutions. The Irish government recognises the importance of digital innovation to address many of the challenges the construction industry faces. With recent high profile reports of escalating spend on signature public sector projects and weak productivity performance …

Bim In Ireland 2019: A Study Of Bim Maturity And Diffusion In Ireland, Barry Mcauley, Alan Hore, Roger West

Conference papers

In 2017, the BIM Innovation Capability Programme team applied five macro BIM maturity conceptual models to capture the capability of the Irish construction industry and assess its BIM maturity. The results found that while Ireland is mature for modelling processes, it is less developed with regards to collaboration processes and policies. Ireland also ranked poorly when it came to regulatory frameworks, measurements and benchmarks compared to a number of countries which also applied the same conceptual models. At the time, the findings highlighted that Ireland’s diffusion dynamic was middle out, meaning that larger organisations or industry associations were pushing the …

An Investigation Into Current Procurement Strategies That Promote Collaboration Through Early Contractor Involvement With Regards To Their Suitability For Irish Public Work Projects, Barry Mcauley, Frederic Lefebvre

Conference papers

Previous research has established that multi-disciplinary collaboration will benefit a construction project throughout its lifecycle. While Lean Construction, Building Information Modelling (BIM), and Integrated Project Delivery (IPD) can all be viewed as separate processes which add independent value to a project, they are more effective when used in partnership with each other. In order to ensure the high levels of collaboration expected for these processes to work in unison, the early involvement of the Contractor is paramount. Early contractor involvement within the design process can ensure a more focused integrated project team, improvement of both constructability and cost certainty, as …

From Roadmap To Implementation: Lessons For Ireland’S Digital Construction Programme, Barry Mcauley, Alan Hore, Roger West

Conference papers

As part of their Future of Construction initiative in 2018 the World Economic Forum published an action plan to accelerate Building Information Modelling adoption. The WEF report highlighted actions that companies, industry organisations and governments are advised to implement to accelerate BIM adoption and better capitalise on delivering better project outcomes. According the authors of the report BIM is seen as the centrepiece of the construction industry’s digital transformation, however they acknowledged that BIM adoption globally remain slow. Anecdotal experience would suggest that BIM usage in Ireland is also very low and that a similar initiative or an adaptation of …

Data Provisioning For The Object Modeling System (Oms), Jack R. Carlson, Olaf David, Wes J. Lloyd, George H. Leavesley, Ken W. Rojas, Timothy R. Green, Mazdak Arabi, Lucas Yaege, Hom Kipka

Wes Lloyd

The Object Modelling System (OMS) platform supports initiatives to build or re-factor agro-environmental models and deploy them in different business contexts as model services on cloud computing platforms. Whether traditional desktop, client-server, or emerging cloud deployments, success especially at the enterprise level relies on stable and efficient data provisioning to the models. In this paper we describe recent experience and trends with tools and services deployed to cloud platforms. Also, systematic, sustained data stewardship and alignment with standards organizations impart stability to data provisioning efforts.

The Virtual Machine (Vm) Scaler: An Infrastructure Manager Supporting Environmental Modeling On Iaas Clouds, Wes J. Lloyd, Olaf David, Mazdak Arabi, James C. Ascough Ii, Timothy R. Green, Jack R. Carlson, Ken W. Rojas

Wes Lloyd

Infrastructure-as-a-service (IaaS) clouds provide a new medium for deployment of environmental modeling applications. Harnessing advancements in virtualization, IaaS clouds can provide dynamic scalable infrastructure to better support scientific modeling computational demands. Providing scientific modeling “as-a-service” requires dynamic scaling of server infrastructure to adapt to changing user workloads. This paper presents the Virtual Machine (VM) Scaler, an autonomic resource manager for IaaS Clouds. We have developed VM-Scaler, a REST/JSON-based web services application which supports infrastructure provisioning and management to support scientific modeling for the Cloud Services Innovation Platform (CSIP) [Lloyd et al. 2012]. VM-Scaler harnesses the Amazon Elastic Compute Cloud (EC2) …

Fire-Spotting Modelling And Parametrisation For Wild-Land Fires, Inderpreet Kaur, Gianni Pagnini

International Congress on Environmental Modelling and Software

This article describes a mathematical formulation for simulating the effects of firebrands on the propagation of the wild-land fires. Among the different approaches available in literature, this formulation is defined in a way to provide a versatile approach for application to operational wildfire models. Most of the operational wildfire models like WRF-SFIRE and ForeFire model only the evolution of the fire-line according to the definition of the rate of spread, fuel characterisation and the average fire properties and concurrent atmospheric conditions. But this information is not enough to simulate the effects of turbulence and fire-spotting. The formulation presented here can …

A Generator Of Landuse Application For Complex And Heterogeneous Agricultural Practices, Odile Leccia-Phelpin, Jean-Marie Lescot, Françoise Vernier

International Congress on Environmental Modelling and Software

Non-point source pollution from agriculture has become a major concern for water managers and institutional stakeholders. To reduce diffuse pollution, agricultural conservation measures are widely used with efficiency. On non-monitored territories environmental modelling enables the assessment of their long term impacts on water and soils and to evaluate land-use change scenarios. We developed an innovative Generator of Landuse (GenLU) application in order to build up multi-year spatial crop successions from identified crop rotations with their related management schedule s. GenLU can be used solely for generating landuse or coupled with the Soil and Water Assessment Tool (SWAT) model so as …

Water Supply System Classification For Water Quality Improvement, Bruno Melo Brentan, Gustavo Meirelles Lima, Edevar Luvizotto Junior, Joaquín Izquierdo, Rafael Pérez-García

International Congress on Environmental Modelling and Software

Universal access to drinkable water is a constitutional right guaranteed in Brazil. However, not all cities in this country are able to supply the population with the expected quality. Important actions should be taken to improve the supply of drinkable water. To define a strategic plan for this purpose, classification tools can facilitate the design of plans, by grouping cities with similar quality conditions. During the last decades, neural network approaches have been used in environmental models, allowing more accurate representation of some complex systems. This work proposes the use of self-organizing maps (SOM’s) coupled with the k-means algorithm …

Optimal Land Use?! – A Review On Optimization Techniques Used In Multi-Criteria Decision Analysis, Andrea Kaim, Anna Cord, Martin Volk

International Congress on Environmental Modelling and Software

Agriculture, forest management, conservation planning and other related disciplines have specific land use demands, and thus different perspectives on how land should be used in an “optimal way”. One way to solve arising land use conflicts is employing the ecosystem services concept together with methods from the field of multi-criteria decision analysis (MCDA). Especially optimization techniques provide the possibility to include socio-economic and ecological aspects as well as the protection of biodiversity. In this study, we give an overview of these methods, focusing especially on their application in agricultural areas. We explore their abilities for the identification of ecosystem service …

Data-Driven Wildfire Behaviour Modelling: Application Of Firefly To Field-Scale Grassland Controlled Burns, M. C. Rochoux, C. Zhang, D. Lucor, S. Ricci, A. Trouve

International Congress on Environmental Modelling and Software

Assessing epistemic uncertainties is now considered as a milestone for improving numerical predictions of a dynamically evolving system. The objective of this project is to demonstrate the benefits of data assimilation combined with sensor observations of the fire front position to both quantify and reduce the uncertainties in wildfire behaviour forecasting capability. The challenges found on the route to modelling wildfire behaviour are two-fold. There is the modelling challenge associated with providing accurate representations of the multi-scale multi-physics processes governing wildfire dynamics. There is also the data challenge associated with providing accurate estimates of the environmental conditions (biomass moisture, near-surface …

Atlas: A Tool To Model Spatial-Temporal Dynamics Of Processes Influencing Ecosystem Services, Hugo Thierry, Aude Vialatte, Claude Monteil, Annie Ouin

International Congress on Environmental Modelling and Software

Biodiversity provides various benefits to humankind throughout what is defined as ecosystem services. Within a specific ecosystem, a wide range of ecosystem services can be identified. During the past decades, human intervention has aimed to increase some services such as food production through agricultural intensification, at the expense of other services such as water regulation. Mapping, evaluating and quantifying each of these ecosystem services provided by biodiversity to crop production could help to increase the multi-functionality of agricultural landscapes. In this context, we developed a spatially-explicit model called ATLAS (AgriculTural LandscApe Simulator). ATLA …

Understanding The Relationships Between Sanitation And Health In Nicaragua And Honduras, Through Data Mining Tools, Ginevra Marina Lazerini, Josep Nualart, Sergio Ruiz-Cayuela, Maialen Urbina, Miquel Sànchez Marrè, Karina Gibert

International Congress on Environmental Modelling and Software

The aim of this work is to analyze water and sanitation supply data from Nicaragua and Honduras by using different data mining tools. The data has been provided by SIASAR (Rural Water and Sanitation Information System), which is a water and sanitation management and information platform created through the joint effort of different Central American Governments and the World Bank. In the study data from a survey performed in all the rural communities in Nicaragua and in a sample of the rural communities in Honduras from 2012 to 2015 is analyzed. Database contains 10206 communities described by 23 numerical variables …

Resilience Of Punta S’Aliga Barrier Beach To Storm Impacts, Andrea Sulis

International Congress on Environmental Modelling and Software

Beach and dune provide natural defense against erosion and flooding, and associated mitigation measures are classical coastal engineering problems studied by many researchers. Winter storms cause severe erosion leading to dune breaching and then flooding of the hinterland areas. Resiliency of a barrier beach depends on the ability of the dune (resistor) to recover in height and extent following storms. Whereas erosion of the beach and dune occurs over hours and days, it can be years to decades before the beach and dune are able to recover to their pre-storm state. In the last two decades, numerical modelling methods have …

The Economics Of Agricultural Water Productivity In The Blue Nile, Imeshi Weerasinghe, James Booker, Wim Bastiaanssen, Lisa-Marie Rebelo, Ann Van Griensven

International Congress on Environmental Modelling and Software

Agricultural Water Productivity (AWP) is often simplified as the ‘crop per drop’, described as the output in terms of yield or biomass per unit of water input. This purely physical measure of Water Productivity (WP) using only a single factor input (water) does not consider: (1) the level of other inputs used in conjunction with water, (2) the opportunity cost of water as an input, (3) the value of the output and (4) the costs of production for different crops. This study presents a justification and methodology for incorporating these factors into WP indicators. The application of these extensions to …

E3.Pt – An E3 Portabledyme Model For Portugal, Anett Großmann, Frank Hohmann

International Congress on Environmental Modelling and Software

E3 models are environmentally extended economic models. They are extensively used for impact assessment of energy, climate and resource policies at national and international level. E3 models have proven to be suitable tools for quantifying effects on the economy, environment and energy system. Usually, the structure and documentation of such models are only accessible by the model builders. They are facing the allegation to be a "black box" meaning that only their creators are able to operate and fully understand the model system. Decision makers are often only engaged at the end of the model building process to discuss the …

A Markov Decision Process Model To Compare Ecosystem Services Provided By Agricultural Landscapes, Sabrina Gaba, Nathalie Peyrard, Régis Sabbadin, Julia Radoszyckic

International Congress on Environmental Modelling and Software

One current challenge in managing agricultural landscapes, is to reach a trade-off between provision of food and biodiversity conservation. Two extreme land-use strategies, land sharing and land sparing, are often discussed. The design of decision rules for allocating crops and lands for biodiversity conservation (e.g. grasslands) can be formalized as an optimization problem. However the target to optimize, representing the trade-off between ecosystem services (ES) can be complex to model since ES are usually not defined on comparable scales and may rely on different sides of biodiversity. Here, we will investigate how landscape composition and structure affect the magnitude of …

Sectorization Of Intermittent Water Supply Networks Based On Graph Theory And Clustering Techniques, Amilkar E. Ilaya-Ayza, David Ayala-Cabrera, Joaquín Izquierdo, Enrique Campbell, Rafael Pérez-García

International Congress on Environmental Modelling and Software

Intermittent water supply is the form of access to water in many countries around the world. It is very common that design, operation, maintenance and, in general, decision-making in these systems are performed using tools originally developed for systems with continuous supply, which are not adequate. However, these tools can be reasonably applied to network sectorization of intermittent supply networks. We propose a sectorization methodology for networks that do not have the possibility of working with continuous supply. In addition, to ensure sufficient pressure, sector design must guarantee equity in the supply. Furthermore, it is not enough to establish sector …

A Mathematical Model For Ghg From Sb-Mbr: Calibration By An Innovative Protocol, Giorgio Mannina, Alida Cosenza

International Congress on Environmental Modelling and Software

A mathematical model to quantify greenhouse gases (GHG) (carbon dioxide, CO₂ and nitrous oxide, N₂O) for a membrane bioreactor (MBR) is presented. The model has been applied to a pilot plant with a pre-denitrification MBR scheme. The pilot plant was cyclically filled with real saline wastewater according to the fill-draw-batch operation. The model was calibrated by adopting a specific protocol based on extensive field dataset. Standardised Regression Coefficient (SRC) method was adopted to select the most influential model factors to be calibrated. Results related to SRC method show that among the important model factors a key role …

A Framework For Decision-Making In Cases Of Invasive Species, Peter A. Khaiter, Marina G. Erechtchoukova, Sina Roushan

International Congress on Environmental Modelling and Software

Invasion of nonindigenous species is one of the most pressing global challenges, causing substantial environmental, economic and social harm. Invasion of alien species alters the composition, structure and functioning of invaded ecosystems as well as the services they generated before the invasion. Decisions about the management of invasive cases are inherently difficult because of the multifactorial and multiattribute scope of the problem. In particular, the resilience limits of invaded ecosystems to fully recover original, pre-invaded states remain unclear. To facilitate management efforts, decision-makers and environmental practitioners require a framework integrating relevant knowledge and acting as a supporting expert system. The …

Cool Farm Tool (Cft) Water: Novel Tool For Water Resource Assessment On Field Scale, Benjamin Kayatz, Gabriele Baroni, Benjamin Kuster, Stefan Lüdtke, Daniella Malin, Richard Heathcote, Carl Von Tonder, Martin Wattenbach

International Congress on Environmental Modelling and Software

At the global scale over 70 % of all fresh water used is consumed by the agricultural sector. For this reason a sustainable water management at the basin level often requires the assessment of water that is used for crop production. In this context, the characterization of green and blue water footprint showed to be a useful and efficient approach to support analysis and decisions.

However determining the water footprint is cumbersome and often linked to additional data acquisition efforts. Furthermore the water footprint is often not revealing the basin impact of crop production. To overcome these limitations we developed …

Metadata For Describing Water Models, Mohamed M. Morsy, Jonathan L. Goodall, Christina Bandaragoda, Anthony M. Castronova, Jane Greenberg

Anthony Castronova

Computer models are widely used in hydrology and water resources management. A large variety of models exist, each tailored to address specific challenges related to hydrologic science and water resources management. When scientists and engineers apply one of these models to address a specific question, they must devote significant effort to set up, calibrate, and evaluate that model instance built for some place and time. In many cases, there is a benefit to sharing these computer models and associated datasets with the broader scientific community. Core to model reuse in any context is metadata describing the model. A standardized metadata …

Small Farms Dams Modelling In Highly Anthropized Basins: Case Of The Garonne Catchment In The South-West Of France, François Moussu, Pierre Le Moigne, Pierre Le Cointe, Camille Truche, Olivier Therond, Eric Martin, Florence Habets

International Congress on Environmental Modelling and Software

One of the aims of the REGARD project is to evaluate the influence of human activities in the modelling of water resources in the South-West of France, at the scale of the Garonne Watershed (~55 000 km²). Since 2009 the French government introduced a new regulation of agricultural water withdrawals, to avoid regular crisis due to water resources issues.Our approach consists in accounting for small farm dams in the Safran-Isba-Modcou (SIM) model and to evaluate their impact on river discharges. Several scenarios with different volume capacities, filling catchment sizes and filling periods were tested to assess how the …

Bayesian Estimation Of Source Term Of Atmospheric Radiation Release With Interval Prior, O. Tichý, V. Šmídl, R. Hofman

International Congress on Environmental Modelling and Software

Detection of release of an atmospheric pollutant is a problem of interest in environmental sciences. We are concerned with estimation of unknown source term of the release. Formally, the problem is formulated as a linear model where measurements are explained using source-receptor- sensitivity matrix obtained from atmospheric transport model and source term vector which has to be estimated. Specifically, we estimate the release of radioactivity from measurements of gamma dose rate (GDR). The problem of isolation of activity of individual nuclides is poorly conditioned. We propose a probabilistic model with the prior information on intervals of nuclide ratios. The model …

A Simulation Platform To Assess Forest Landscape Resilience, Werner Rammer, Rupert Seidl

International Congress on Environmental Modelling and Software

Forest ecosystems suffer increasingly from pressures such as anthropogenic climatic change, while at the same time being subject to an increasing societal demand for ecosystem services. In addition to direct climate effects on tree growth and regeneration recent research suggests that climate-induced changes in disturbance regimes will likely increase the volatility of future forest trajectories. Addressing these challenges requires a coupled human and natural systems perspective, as most of Europe’s forests are heavily influenced by management, and forests are a crucial component in the emerging bioeconomy. Methodologically, assessments of the long-term socio-ecological resilience of forest ecosystems require approaches that combine …