A5014336297- Complex Network Analysis Techniques
- Public Spaces through Art
- Urban Design and Spatial Analysis
- Land Use and Ecosystem Services
- Opinion Dynamics and Social Influence
- Automated Road and Building Extraction
- Image Enhancement Techniques
- Spatial Cognition and Navigation
- Video Surveillance and Tracking Methods
- Human Mobility and Location-Based Analysis
- Urban Transport and Accessibility
- COVID-19 epidemiological studies
- Data Management and Algorithms
- Digital Media Forensic Detection
- Advanced Image Processing Techniques
- Impact of Light on Environment and Health
- Data Visualization and Analytics
- Bioinformatics and Genomic Networks
- Vehicle License Plate Recognition
- Statistical Methods and Applications
- Traffic and Road Safety
- Advanced Clustering Algorithms Research
- Urban Heat Island Mitigation
- Plant and animal studies
- Urban Green Space and Health
Universidade de São Paulo
2018-2023
University of Oxford
2022-2023
Universidade Federal de São Carlos
2022-2023
Universidade Cidade de São Paulo
2019
Universidad San Pedro
2019
Hospital Universitário da Universidade de São Paulo
2018
Universidade Estadual de Campinas (UNICAMP)
2011-2013
We present a comprehensive study and evaluation of existing single image deraining algorithms, using new large-scale benchmark consisting both synthetic real-world rainy images.This dataset highlights diverse data sources contents, is divided into three subsets (rain streak, rain drop, mist), each serving different training or purposes. further provide rich variety criteria for dehazing algorithm evaluation, ranging from full-reference metrics, to no-reference subjective the novel...
Abstract Background Coffee is one of the world's most important crops; it consumed worldwide and plays a significant role in economy producing countries. Coffea arabica C. canephora are responsible for 70 30% commercial production, respectively. an allotetraploid from recent hybridization diploid species, eugenioides . has lower genetic diversity results higher quality beverage than Research initiatives have been launched to produce genomic transcriptomic data about spp. as strategy improve...
Inaccessible urban infrastructure creates and reinforces systemic exclusion of people with disabilities impacts public health, physical activity, quality life for all. To improve the design our cities to enable more equitable policies location-centric technology designs, we need new data collection techniques, standards, accessibility-infused analytic tools interactive maps focused on quality, safety, accessibility pathways, transit ecosystems, buildings. In this workshop, bring together...
Graffiti is a common phenomenon in urban scenarios. Differently from art, graffiti tagging vandalism act and many local governments are putting great effort to combat it. The map of region can be very useful resource because it may allow one potentially locations with high level also cleanup saturated regions discourage future acts. There currently no automatic way obtaining obtained by manual inspection the police or popular participation. In this sense, we describe an ongoing work where...
An understanding of pedestrian dynamics is indispensable for numerous urban applications including the design transportation networks and planing business development. Pedestrian counting often requires utilizing manual or technical means to count individuals in each location interest. However, such methods do not scale size a city new approach fill this gap here proposed. In project, we used large dense dataset images New York City along with computer vision techniques construct...
In this work we propose a semi-supervised learning approach for object detection where use detections from preexisting detector to train new detector. We differ previous works by coming up with relative quality metric which involves simpler labeling and proposing full framework of automatic generation improved detectors. To validate our method, collected comprehensive dataset more than two thousand hours streaming public traffic cameras that contemplates variations in time, location weather....
Several natural and theoretical networks can be broken down into smaller portions, or subgraphs corresponding to neighborhoods. The more frequent of these neighborhoods then understood as motifs the network, being therefore important for better characterizing understanding overall structure. developments in network science have relied on this interesting concept, with ample applications areas including systems biology, computational neuroscience, economy ecology. present work aims at...
Abstract Several natural and artificial structures systems are somehow optimized for performing specific functionalities. The structure topology of cities no exception, as it is critically important to ensure effective access the several resources well overall mobility. present work addresses subject improving plan a given city through incorporation avenues other expressways such bridges tunnels. More specifically, we start with real consider an expressway between any two locations in city,...
Abstract Several natural and theoretical networks can be broken down into smaller portions, henceforth called neighborhoods. The more frequent of these then understood as motifs the network, being therefore important for better characterizing understanding its overall structure. developments in network science have relied on this interesting concept, with ample applications areas including systems biology, computational neuroscience, economy ecology. present work aims at reporting a...
Graffiti tagging is a common issue in great cities an local authorities are on the move to combat it. The map of city can be useful tool as it may help clean-up highly saturated regions and discourage future acts neighbourhood currently there no way getting region automatic fashion manual inspection or crowd participation required. In this work, we describe work progress creating get region. It based use street view images detection graffiti tags images.
Characterizing the structure of cities constitutes an important task since identification similar can promote sharing respective experiences. In present work, we consider 20 European from 5 countries and with comparable populations, each which characterized in terms four topological as well one geometrical feature. These are then mapped into networks by considering their pairwise similarity gauged coincidence methodology, consists combining Jaccard interiority indices. The methodology...
Large-scale analysis of pedestrian infrastructures, particularly sidewalks, is critical to human-centric urban planning and design. Benefiting from the rich data set planimetric features high-resolution orthoimages provided through New York City Open Data portal, we train a computer vision model detect roads, buildings remote-sensing imagery achieve 83% mIoU over held-out test set. We apply shape techniques study different attributes extracted sidewalks. More specifically, do tile-wise...
In the big-data age, tabular data are being generated and analyzed everywhere. As a consequence, finding understanding relationships between features in these of great relevance. Here, to encompass relationships, we propose graph-based method that allows individual, group multi-scale analyses. The starts by mapping into weighted directed graph using Shapley additive explanations technique. With this show inference hierarchical modular structure obtained Nested Stochastic Block Model (nSBM)...
Knowledge networks have become increasingly important as a changing repository of data which can be represented, studied and modeled by using complex concepts methodologies. Here we report study knowledge corresponding to the areas Physics Theology, obtained from Wikipedia taken at two different dates separated 4 years. The respective versions these were characterized in terms their cross-relation signatures, being summarized modification indices for each nodes that are preserved among...