A5060005215- Complex Network Analysis Techniques
- Opinion Dynamics and Social Influence
- Species Distribution and Climate Change
- Advanced Graph Neural Networks
- Evolutionary Game Theory and Cooperation
- Data Visualization and Analytics
- Neural dynamics and brain function
- Wildlife Ecology and Conservation
- Functional Brain Connectivity Studies
- Genome Rearrangement Algorithms
- Cell Image Analysis Techniques
- Identification and Quantification in Food
- Genomics and Phylogenetic Studies
- Primate Behavior and Ecology
- Video Surveillance and Tracking Methods
- Advanced Graph Theory Research
- Complexity and Algorithms in Graphs
- Bioinformatics and Genomic Networks
- Topic Modeling
- Advanced Image and Video Retrieval Techniques
- Animal Vocal Communication and Behavior
- Big Data and Business Intelligence
- Gene Regulatory Network Analysis
- Animal Behavior and Reproduction
- Peer-to-Peer Network Technologies
The Ohio State University
2020-2025
University of Illinois Chicago
2013-2023
Mpala Research Center and Wildlife Foundation
2023
Princeton University
2023
Wild Salmon Center
2023
The London College
2023
Rensselaer Polytechnic Institute
2023
Carnegie Mellon University
2021
University of Illinois Urbana-Champaign
1999-2018
Bioengineering Center
2017-2018
We propose frameworks and algorithms for identifying communities in social networks that change over time. Communities are intuitively characterized as "unusually densely knit" subsets of a network. This notion becomes more problematic if the interactions Aggregating time can radically misrepresent existing changing community structure. Instead, we an optimization-based approach modeling dynamic prove finding most explanatory structure is NP-hard APX-hard, based on programming, exhaustive...
Finding patterns of social interaction within a population has wide-ranging applications including: disease modeling, cultural and information transmission, behavioral ecology. Social interactions are often modeled with networks. A key characteristic is their continual change. However, most past analyses networks essentially static in that all about the time take place discarded. In this paper, we propose new mathematical computational framework enables analysis dynamic explicitly makes use...
We propose a novel method, based on concepts from expander graphs, to sample communities in networks. show that our sampling unlike previous techniques, produces subgraphs representative of community structure the original network. These generated may be viewed as stratified samples they consist members most or all Using produced by we problem detection recast into case statistical relational learning. empirically evaluate approach against several real-world datasets and demonstrate method...
We present HotSpotter, a fast, accurate algorithm for identifying individual animals against labeled database. It is not species specific and has been applied to Grevy's plains zebras, giraffes, leopards, lionfish. describe two approaches, both based on extracting matching keypoints or "hotspots". The first tests each new query image sequentially database image, generating score in isolation, ranking the results. second, building recent techniques instance recognition, matches using fast...
We present the first method to perform automatic 3D pose, shape and texture capture of animals from images acquired in-the-wild. In particular, we focus on problem capturing information about Grevy's zebras a collection images. The zebra is one most endangered species in Africa, with only few thousand individuals left. Capturing pose these can provide biologists conservationists animal health behavior. contrast research human estimation, training data for limited, are complex natural scenes...
High uptake of vaccinations is essential in fighting infectious diseases, including severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) that causes the ongoing disease 2019 (COVID-19) pandemic. Social media play a crucial role propagating misinformation about vaccination, through conspiracy theories and can negatively impact trust vaccination. Users typically engage with multiple social platforms; however, little known content cross-platform use spreading vaccination-related...
We present a novel dataset for animal behavior recognition collected in-situ using video from drones flown over the Mpala Research Centre in Kenya. Videos DJI Mavic 2S January 2023 were acquired at 5.4K resolution accordance with IACUC protocols, and processed to detect track each frames. An image subregion centered on was extracted combined sequence form "mini-scene". Be-haviors then manually labeled frame of mini-scene by team annotators overseen an expert behavioral ecologist. The...
From social networks to P2P systems, network sampling arises in many settings. We present a detailed study on the nature of biases strategies shed light how best sample from networks. investigate connections between specific and various measures structural representativeness. show that certain are, fact, beneficial for applications, as they "push" process towards inclusion desired properties. Finally, we describe these can be exploited several, real-world applications including disease...
Social interactions that occur regularly typically correspond to significant yet often infrequent and hard detect interaction patterns. To identify such regular behavior, we propose a new mining problem of finding periodic or near subgraphs in dynamic social networks. We analyze the computational complexity problem, showing that, unlike any related subgraph problems, it is polynomial. practical, efficient scalable algorithm find takes imperfect periodicity into account. demonstrate...
We describe an algorithmic and experimental approach to a fundamental problem in field ecology: computer-assisted individual animal identification. use database of noisy photographs taken the wild build biometric animals differentiated by their coat markings. A new image unknown can then be queried its markings against determine if has been observed identified before. Our algorithm, called StripeCodes, efficiently extracts simple features uses dynamic programming algorithm compare images....
Communities are natural structures observed in social networks and usually characterized as "relatively dense" subsets of nodes. Social change over time so do the underlying community structures. Thus, to truly uncover this structure we must take temporal aspect into consideration. Previously, have represented framework for finding dynamic communities using cost model formulated corresponding optimization problem [33], assuming that partitions individuals groups given each step. We also...
This paper proposes a 5-component detection pipeline for use in computer vision-based animal recognition system. The end result of our proposed is collection novel annotations interest (AoI) with species and view-point labels. These AoIs, example, could be fed as the focused input data into an appearance-based identification goal method to increase reliability automation censusing studies provide better ecological information conservationists. Our able achieve localization mAP 81.67%,...
Abstract Social network analysis is the study of patterns interaction between social entities. The field attracting increasing attention from diverse disciplines including sociology, epidemiology, and behavioral ecology. An important sociological phenomenon that draws analysts emergence communities, which tend to form, evolve, dissolve gradually over a period time. Understanding this evolution crucial sociologists domain scientists, often leads better appreciation system under study....
Researchers have long noted that individuals occupy consistent spatial positions within animal groups. However, an individual's position depends not only on its own behaviour, but also the behaviour of others. Theoretical models collective motion suggest global patterns assortment can arise from individual variation in local interaction rules. this prediction remains untested. Using high-resolution GPS tracking members a wild baboon troop, we identify inter-individual differences...
Graph representation learning for static graphs is a well studied topic. Recently, few studies have focused on temporal information in addition to the topology of graph. Most these relied represent nodes and substructures dynamic graphs. However, problem entire context yet be addressed. In this paper, we propose an unsupervised architecture graphs, designed learn both topological features that evolve over time. The approach consists sequence-to-sequence encoder-decoder model embedded with...
Abstract In many animal societies, groups of individuals form stable social units that are shaped by well-delineated dominance hierarchies and a range affiliative relationships. How do socially complex maintain cohesion achieve collective movement? Using high-resolution GPS tracking members wild baboon troop, we test whether movement in is governed interactions among local neighbours (commonly found with largely anonymous memberships), affiliates, and/or paying attention to global group...
Abstract Determining which species are at greatest risk, where they most vulnerable, and what the trajectories of their communities populations is critical for conservation management. Globally distributed, wide-ranging whales dolphins present a particular challenge in data collection because no single research team can record over biologically meaningful areas. Flukebook.org an open-source web platform that addresses these gaps by providing researchers with latest computational tools. It...
Abstract Reconstruction of sibling relationships from genetic data is an important component many biological applications. In particular, the growing application molecular markers (microsatellites) to study wild populations plant and animals has created need for new computational methods establishing pedigree relationships, such as sibgroups, among individuals in these populations. Most current sibship reconstruction microsatellite use statistical heuristic techniques that rely on a priori...
The understanding of dynamics data streams is greatly affected by the choice temporal resolution at which are discretized, aggregated, and analyzed. Our paper focuses explicitly on represented as dynamic networks. We propose a framework for identifying meaningful levels that best reveal critical changes in network structure, balancing reduction noise with loss information. demonstrate applicability our approach analyzing various statistics both synthetic real networks using those to detect...
Understanding why animal societies take on the form that they do has benefited from insights gained by applying social network analysis to patterns of individual associations. Such analyses typically aggregate data over long time periods even though most selective forces shape sociality have strong temporal elements. By explicitly incorporating signal in interaction we re-examine dynamics systems evolutionarily closely-related Grevy's zebras and wild asses show broadly similar organizations....
Granger causality is a fundamental technique for causal inference in time series data, commonly used the social and biological sciences. Typical operationalizations of make strong assumption that every point effect influenced by combination other with fixed delay. The delay also exists Transfer Entropy, which considered to be non-linear version causality. However, does not hold many applications, such as collective behavior, financial markets, natural phenomena. To address this issue, we...