Publications | Paola Pesantez-Cabrera

2023

AIAFS (accepted)

Multi-Task Learning for Budbreak Prediction

Aseem Saxena, Paola Pesantez-Cabrera, Rohan Ballapragada, Markus Keller, and Alan Fern

2023

@article{saxena_grape_budbreak_2023,
  title = {Multi-Task Learning for Budbreak Prediction},
  publisher = {arXiv},
  author = {Saxena, Aseem and Pesantez-Cabrera, Paola and Ballapragada, Rohan and Keller, Markus and Fern, Alan},
  year = {2023},
  keywords = {Computer Science - Machine Learning},
  annote = {Comment: 4 pages, submitted to 2023 AAAI Workshop on Agriculture and Food Systems (AIAFS)},
}

AIAFS (accepted)

Persistent Homology to Study Cold Hardiness of Grape Cultivars

Welankar Sejal, Paola Pesantez-Cabrera, Bala Krishnamoorthy, Lynn Mills, Markus Keller, and Ananth Kalyanaraman

2023

Bib

@article{welankar_grape_2023,
  title = {Persistent Homology to Study Cold Hardiness of Grape Cultivars},
  url = {https://doi.org/10.48550/arXiv.2302.05600},
  publisher = {arXiv},
  author = {Sejal, Welankar and Pesantez-Cabrera, Paola and Krishnamoorthy, Bala and Mills, Lynn and Keller, Markus and Kalyanaraman, Ananth},
  year = {2023},
  keywords = {Computer Science - Machine Learning},
  annote = {Comment: 4 pages, submitted to 2023 AAAI Workshop on Agriculture and Food Systems (AIAFS)},
}

AAAI (accepted)

Grape Cold Hardiness Prediction via Multi-Task Learning

Aseem Saxena, Paola Pesantez-Cabrera, Rohan Ballapragada, Kin-Ho Lam, Markus Keller, and Alan Fern

2023

Bib

@article{saxena_grape_coldhardiness_2023,
  doi = {10.48550/ARXIV.2209.10585},
  author = {Saxena, Aseem and Pesantez-Cabrera, Paola and Ballapragada, Rohan and Lam, Kin-Ho and Keller, Markus and Fern, Alan},
  keywords = {Machine Learning (cs.LG), FOS: Computer and information sciences, FOS: Computer and information sciences},
  title = {Grape Cold Hardiness Prediction via Multi-Task Learning},
  publisher = {arXiv},
  year = {2023},
  copyright = {Creative Commons Attribution 4.0 International},
}

2021

Transactions GIS
A scoping review on the use, processing and fusion of geographic data in virtual assistants

Carlos Granell, Paola G. Pesántez-Cabrera, Luis M. Vilches-Blázquez, Rosario Achig, Miguel R. Luaces, Alejandro Cortiñas-Álvarez, Carolina Chayle, and Villie Morocho

Transactions in GIS 2021

Abs Bib

Virtual assistants are a growing area of research in academia and industry, with an impact on people’s daily lives. Many disciplines in science are moving towards the incorporation of intelligent virtual assistants in multiple scenarios and application domains, and GIScience is not external to this trend since they may be connected to intelligent spatial decision support systems. This article presents a scoping review to indicate relevant literature pertinent to intelligent virtual assistants and their usage of geospatial information and technologies. In particular, the study was designed to find critical aspects of GIScience and how to contribute to the development of virtual assistants. Moreover, this work explores the most prominent research lines as well as relevant technologies/platforms to determine the main challenges and current limitations regarding the use and implementation of virtual assistants in geospatial-related fields. As a result, this review shows the current state of geospatial applications regarding the use of intelligent virtual assistants, as well as revealing gaps and limitations in the use of spatial methods, standards, and resources available in spatial data infrastructures to develop intelligent decision systems based on virtual assistants for a wide array of application domains.
@article{granell_scoping_2021, title = {A scoping review on the use, processing and fusion of geographic data in virtual assistants}, volume = {25}, issn = {1467-9671}, url = {https://onlinelibrary.wiley.com/doi/abs/10.1111/tgis.12720}, doi = {10.1111/tgis.12720}, language = {en}, number = {4}, urldate = {2022-10-17}, journal = {Transactions in GIS}, author = {Granell, Carlos and Pesántez-Cabrera, Paola G. and Vilches-Blázquez, Luis M. and Achig, Rosario and Luaces, Miguel R. and Cortiñas-Álvarez, Alejandro and Chayle, Carolina and Morocho, Villie}, year = {2021}, pages = {1784--1808}, }

2020

Springer Intern.
A Software Architecture Proposal for a Data Platform on Active Mobility and Urban Environment

Christian Quinde, David Guillermo, Lorena Siguenza-Guzman, Daniel Orellana, and Paola Pesántez-Cabrera

In Information and Communication Technologies 2020

Abs Bib

Over time Geographic Information Systems (GIS) have evolved from monolithic software to dynamic platforms interacting with other systems. Consequently, characteristics such as availability, scalability, interoperability, and failure handling have become essential. Due to the vast diversity of applications and user levels, and the growing complexity of data types and models handling geospatial data, information management has developed into a complex, often overlooked task, leading to delayed results and/or disorganization of information. The goal of this paper is to propose a software architecture design to support mobility data collection, analysis, and visualization. The proposal is based on the process for software architectures stated by Bredemeyer Consulting, comprising five stages: commit, requirements, design, validation, and deployment. Likewise, the Attribute Driven Design (ADD) method has been used for the design stage where the selected architectural pattern was Service Oriented Architecture (SOA) since it provides the scalability and interoperability attributes required for this study. The Architecture Tradeoff Analysis Method (ATAM) has been chosen to identify the risks of the proposal and to evaluate the architecture to ensure that all requirements have been satisfactorily met. The model was validated using the data and projects of the LlactaLAB research group.
@inproceedings{quinde_software_2020, address = {Cham}, series = {Communications in {Computer} and {Information} {Science}}, title = {A {Software} {Architecture} {Proposal} for a {Data} {Platform} on {Active} {Mobility} and {Urban} {Environment}}, isbn = {978-3-030-62833-8}, doi = {10.1007/978-3-030-62833-8_37}, language = {en}, booktitle = {Information and {Communication} {Technologies}}, publisher = {Springer International Publishing}, author = {Quinde, Christian and Guillermo, David and Siguenza-Guzman, Lorena and Orellana, Daniel and Pesántez-Cabrera, Paola}, editor = {Rodriguez Morales, Germania and Fonseca C., Efraín R. and Salgado, Juan Pablo and Pérez-Gosende, Pablo and Orellana Cordero, Marcos and Berrezueta, Santiago}, year = {2020}, keywords = {Architecture balance analysis method, Attribute Driven Design, Geographic Information System, Geospatial information, Software architecture}, pages = {501--515}, }
LACLO
Proposal for the Design and Evaluation of a Dashboard for the Analysis of Learner Behavior and Dropout Prediction in Moodle

Edisson Sigua, Bryan Aguilar, Paola Pesántez-Cabrera, and Jorge Maldonado-Mahauad

In 2020 XV Conferencia Latinoamericana de Tecnologias de Aprendizaje (LACLO) Oct 2020

Abs Bib

The rapid development of technology has meant that over the past two decades Information and Communications Technologies (ICT) become increasingly involved in the teaching process and seek to change traditional learning models. With the support of modern technology, virtual platforms that encourage the adoption of a new learning paradigm in which geographical/temporal limitations no longer pose a difficulty have been developed and refined. These virtual learning platforms, also known as Learning Management Systems (LMS), store student and teacher interactions with course resources, and these interactions are stored in database engines. However, all the information generated by LMS has not been processed in a way that is helpful for the use of teachers and students, mainly because in most cases, students’ interactions with these systems focus on downloading class material, delivering assignments, and reading announcements, leaving aside indicators that can be presented in the form of visualizations that allow actions to be taken during the development of the learning process. Thus, this study proposes the design, implementation, and evaluation of a dashboard for the analysis of learner behavior and prediction of dropout on the Moodle platform. The proposed tool will help students to manage their learning process, easily and effectively monitor their progress in an online course, and teachers to know what students do before, during and after a virtual class. The latter for the purpose of being able to detect early students at risk of dropping out.
@inproceedings{sigua_proposal_2020, title = {Proposal for the {Design} and {Evaluation} of a {Dashboard} for the {Analysis} of {Learner} {Behavior} and {Dropout} {Prediction} in {Moodle}}, doi = {10.1109/LACLO50806.2020.9381148}, booktitle = {2020 {XV} {Conferencia} {Latinoamericana} de {Tecnologias} de {Aprendizaje} ({LACLO})}, author = {Sigua, Edisson and Aguilar, Bryan and Pesántez-Cabrera, Paola and Maldonado-Mahauad, Jorge}, month = oct, year = {2020}, keywords = {Dashboard, Dropout, Engines, Information and communication technology, Learning Analytics, Learning management systems, Monitoring, Moodle, Prediction, Proposals, Tools, Visualization}, pages = {1--6}, }
IEEE SCC
Towards a Methodology for creating Internet of Things (IoT) Applications based on Microservices

Edwin Cabrera, Paola Cárdenas, Priscila Cedillo, and Paola Pesántez-Cabrera

In 2020 IEEE International Conference on Services Computing (SCC) Nov 2020

Abs Bib

The Internet of Things (IoT) represents the new industrial revolution, in which physical and virtual objects are interconnected. On the other hand, microservices architectures have broken the monolithic and centralized way to build software, and provide systems with high-quality characteristics (e.g., resilience, availability, modularity, and portability). Therefore, the idea of merging those technologies can constitute a powerful strategy to be applied in environments that demand the distribution and management of many IoT devices using high-quality software. In this context, several studies that integrate IoT with microservices solutions have been analyzed. However, most of these studies aim to satisfy the functional requirements related to software and hardware, without taking into account software engineering methodologies and good practices that allow the creation of software for IoT devices considering their distributed nature. Thus, this paper presents the first approach to an agile methodology that i) contemplates the main characteristics of the IoT and ii) guides the development of appropriate software solutions based on microservices architectures to manage IoT environments acknowledging the serious difficulties that microservices imply.
@inproceedings{cabrera_towards_2020, title = {Towards a {Methodology} for creating {Internet} of {Things} ({IoT}) {Applications} based on {Microservices}}, doi = {10.1109/SCC49832.2020.00072}, booktitle = {2020 {IEEE} {International} {Conference} on {Services} {Computing} ({SCC})}, author = {Cabrera, Edwin and Cárdenas, Paola and Cedillo, Priscila and Pesántez-Cabrera, Paola}, month = nov, year = {2020}, note = {ISSN: 2474-2473}, keywords = {Agile, Computer architecture, Domain-Driven Design, Internet of Things, Merging, Methodology, MicroIoT, Microservices, Resilience, Service computing, Software, Software engineering}, pages = {472--474}, }
IEEE SeGAH
Towards an evaluation method of how accessible serious games are to older adults

Paola Pesántez-Cabrera, María Inés Acosta, Verónica Jimbo, Pablo Sinchi, and Priscila Cedillo

In 2020 IEEE 8th International Conference on Serious Games and Applications for Health (SeGAH) Aug 2020

Abs Bib

The loss of cognitive and motor functions in humans increases with age, and the aging population is expected to continue growing significantly in the following years. In this context, serious games have become a tool that supports health professionals in mitigating age-related cognitive problems. Additionally, the accessibility provided by those tools is a determinant factor when users need to adapt themselves to a particular technology. Therefore, this paper presents an accessibility model and an evaluation method useful for assessing how accessible serious games are to older adults, based on the Games Accessibility Guidelines (GAG) proposed by the International Game Developers Association and the ISO/IEC 25040. In order to validate and ensure the feasibility of this study, each activity of the proposed method has been applied to a real game that was created for improving certain cognitive functions (i.e., A Clockwork Brain suite of serious games).
@inproceedings{pesantez-cabrera_towards_2020, title = {Towards an evaluation method of how accessible serious games are to older adults}, doi = {10.1109/SeGAH49190.2020.9201655}, booktitle = {2020 {IEEE} 8th {International} {Conference} on {Serious} {Games} and {Applications} for {Health} ({SeGAH})}, author = {Pesántez-Cabrera, Paola and Acosta, María Inés and Jimbo, Verónica and Sinchi, Pablo and Cedillo, Priscila}, month = aug, year = {2020}, note = {ISSN: 2573-3060}, keywords = {Tools, Accessibility, Aging, Evaluation, Games, Guidelines, Measurement, Older Adults, Serious Games, Standards, Usability}, pages = {1--8}, }
Edu. Technology
Coordinating learning analytics policymaking and implementation at scale

Tom Broos, Isabel Hilliger, Mar Pérez-Sanagustín, Nyi-Nyi Htun, Martijn Millecamp, Paola Pesántez-Cabrera, Lizandro Solano-Quinde, Lorena Siguenza-Guzman, Miguel Zuñiga-Prieto, Katrien Verbert, and Tinne De Laet

British Journal of Educational Technology Aug 2020

Abs Bib

Many Latin-American institutions recognise the potential of learning analytics (LA). However, the number of actual LA implementations at scale remains limited, notwithstanding considerable effort made to formulate guidelines and frameworks to support the LA policy development. Guidance on how to coordinate the interaction between the LA policymaking and implementation is mostly missing, leaving a difficult challenge up to practitioners. In this study we propose a coordination model to support future LA initiatives at scale. We explore the problem by comparing two cases in Belgium and Ecuador. Following up we use the LA implementation timeline as a driver for planning the interaction between the policymaking and implementation. We continue by testing an application of the model with LA experts predominantly from Latin-American institutions, asking them to map low-level items of the SHEILA policy framework to four implementation phases. The results of this mapping support that LA policy building can be spread over time, that it can coincide with LA implementation at scale, and that both efforts can be coordinated. It is hoped that this study will provide additional guidance for future Latin-American and other LA initiatives.
@article{broos_coordinating_2020, title = {Coordinating learning analytics policymaking and implementation at scale}, volume = {51}, issn = {1467-8535}, url = {https://onlinelibrary.wiley.com/doi/abs/10.1111/bjet.12934}, doi = {10.1111/bjet.12934}, language = {en}, number = {4}, urldate = {2022-10-17}, journal = {British Journal of Educational Technology}, author = {Broos, Tom and Hilliger, Isabel and Pérez-Sanagustín, Mar and Htun, Nyi-Nyi and Millecamp, Martijn and Pesántez-Cabrera, Paola and Solano-Quinde, Lizandro and Siguenza-Guzman, Lorena and Zuñiga-Prieto, Miguel and Verbert, Katrien and De Laet, Tinne}, year = {2020}, keywords = {Learning Analytics, Global South, Higher Education, Organisational change, Policy}, pages = {938--954}, }
Edu. Technology
Towards learning analytics adoption: A mixed methods study of data-related practices and policies in Latin American universities

Isabel Hilliger, Margarita Ortiz-Rojas, Paola Pesántez-Cabrera, Eliana Scheihing, Yi-Shan Tsai, Pedro J. Muñoz-Merino, Tom Broos, Alexander Whitelock-Wainwright, Dragan Gašević, and Mar Pérez-Sanagustín

British Journal of Educational Technology Aug 2020

Abs Bib

In Latin American universities, Learning Analytics (LA) has been perceived as a promising opportunity to leverage data to meet the needs of a diverse student cohort. Although universities have been collecting educational data for years, the adoption of LA in this region is still limited due to the lack of expertise and policies for processing and using educational data. In order to get a better picture of how existing data-related practices and policies might affect the incorporation of LA in Latin American institutions, we conducted a mixed methods study in four Latin American universities (two Chilean and two Ecuadorian). In this paper, the qualitative data were based on 37 interviews with managers and 16 focus groups with 51 teaching staff and 45 students; the quantitative data were collected through two surveys answered by 1884 students and 368 teachers, respectively. The findings reveal opportunities to incorporate LA services into existing data practices in the four case studies. However, the lack of reliable information systems and policies to regulate the use of data imposes challenges that need to be overcome for future LA adoption.
@article{hilliger_towards_2020, title = {Towards learning analytics adoption: {A} mixed methods study of data-related practices and policies in {Latin} {American} universities}, volume = {51}, issn = {1467-8535}, shorttitle = {Towards learning analytics adoption}, url = {https://onlinelibrary.wiley.com/doi/abs/10.1111/bjet.12933}, doi = {10.1111/bjet.12933}, language = {en}, number = {4}, urldate = {2022-10-17}, journal = {British Journal of Educational Technology}, author = {Hilliger, Isabel and Ortiz-Rojas, Margarita and Pesántez-Cabrera, Paola and Scheihing, Eliana and Tsai, Yi-Shan and Muñoz-Merino, Pedro J. and Broos, Tom and Whitelock-Wainwright, Alexander and Gašević, Dragan and Pérez-Sanagustín, Mar}, year = {2020}, keywords = {Learning Analytics, Higher Education, Data Management Practices, Data Protection Policies, Latin America, Mixed Methods}, pages = {915--937}, }
Internet Higher Edu
Identifying needs for learning analytics adoption in Latin American universities: A mixed-methods approach

Isabel Hilliger, Margarita Ortiz-Rojas, Paola Pesántez-Cabrera, Eliana Scheihing, Yi-Shan Tsai, Pedro J. Muñoz-Merino, Tom Broos, Alexander Whitelock-Wainwright, and Mar Pérez-Sanagustín

The Internet and Higher Education Apr 2020

Abs Bib

Learning Analytics (LA) is perceived to be a promising strategy to tackle persisting educational challenges in Latin America, such as quality disparities and high dropout rates. However, Latin American universities have fallen behind in LA adoption compared to institutions in other regions. To understand stakeholders’ needs for LA services, this study used mixed methods to collect data in four Latin American Universities. Qualitative data was obtained from 37 interviews with managers and 16 focus groups with 51 teaching staff and 45 students, whereas quantitative data was obtained from surveys answered by 1884 students and 368 teaching staff. According to the triangulation of both types of evidence, we found that (1) students need quality feedback and timely support, (2) teaching staff need timely alerts and meaningful performance evaluations, and (3) managers need quality information to implement support interventions. Thus, LA offers an opportunity to integrate data-driven decision-making in existing tasks.
@article{hilliger_identifying_2020, title = {Identifying needs for learning analytics adoption in {Latin} {American} universities: {A} mixed-methods approach}, volume = {45}, issn = {1096-7516}, shorttitle = {Identifying needs for learning analytics adoption in {Latin} {American} universities}, url = {https://www.sciencedirect.com/science/article/pii/S1096751620300026}, doi = {10.1016/j.iheduc.2020.100726}, language = {en}, urldate = {2022-10-17}, journal = {The Internet and Higher Education}, author = {Hilliger, Isabel and Ortiz-Rojas, Margarita and Pesántez-Cabrera, Paola and Scheihing, Eliana and Tsai, Yi-Shan and Muñoz-Merino, Pedro J. and Broos, Tom and Whitelock-Wainwright, Alexander and Pérez-Sanagustín, Mar}, month = apr, year = {2020}, keywords = {Latin America, Higher education, Institutional adoption, Learning analytics, Mixed methods, Stakeholder perspectives}, pages = {100726}, }
Assessing Risk in Learning Analytics Projects

Henrique Chevreux, Valeria Henriquez, Eliana Scheihing, Pedro Muñoz-Merino², Tinne De Laet, Mar Pérez-Sanagustín⁴, Isabel Hilliger, Jorge Maldonado, Paola Pesántez-Cabrera, and Margarita Ortiz

Mar 2020

Abs Bib

Learning Analytics (LA) enables leaders to improve teaching, learning, organizational efficiency, and decision making. Nonetheless, LA initiatives often have difficulty to move out of prototype into real educational practice. As an emerging multidisciplinary field, we wonder how much its challenges are similar to other more mature related fields. This work assesses to which extent its risks are related to another well-established field as Enterprise Resource Planning (ERP) projects. Our findings show that risk factors and categories in ERP apply to LA projects and their top risks are considered very similar by LA experts. Therefore this work can help the LA community in the search for strategies to sustainable adoption.
@book{chevreux_assessing_2020, title = {Assessing {Risk} in {Learning} {Analytics} {Projects}}, author = {Chevreux, Henrique and Henriquez, Valeria and Scheihing, Eliana and Muñoz-Merino², Pedro and De Laet, Tinne and Pérez-Sanagustín⁴, Mar and Hilliger, Isabel and Maldonado, Jorge and Pesántez-Cabrera, Paola and Ortiz, Margarita}, month = mar, year = {2020}, doi = {10.13140/RG.2.2.31857.10083}, }

2019

IEEE/ACM
Efficient Detection of Communities in Biological Bipartite Networks

Paola Pesántez-Cabrera, and Ananth Kalyanaraman

IEEE/ACM Transactions on Computational Biology and Bioinformatics Jan 2019

Abs Bib

Methods to efficiently uncover and extract community structures are required in a number of biological applications where networked data and their interactions can be modeled as graphs, and observing tightly-knit groups of vertices (“communities”) can offer insights into the structural and functional building blocks of the underlying network. Classical applications of community detection have largely focused on unipartite networks - i.e., graphs built out of a single type of objects. However, due to increased availability of biological data from various sources, there is now an increasing need for handling heterogeneous networks which are built out of multiple types of objects. In this paper, we address the problem of identifying communities from biological bipartite networks - i.e., networks where interactions are observed between two different types of objects (e.g., genes and diseases, drugs and protein complexes, plants and pollinators, and hosts and pathogens). Toward detecting communities in such bipartite networks, we make the following contributions: i) (metric) we propose a variant of bipartite modularity; ii) (algorithms) we present an efficient algorithm called biLouvain that implements a set of heuristics toward fast and precise community detection in bipartite networks (https://github.com/paolapesantez/biLouvain); and iii) (experiments) we present a thorough experimental evaluation of our algorithm including comparison to other state-of-the-art methods to identify communities in bipartite networks. Experimental results show that our biLouvain algorithm identifies communities that have a comparable or better quality (as measured by bipartite modularity) than existing methods, while significantly reducing the time-to-solution between one and four orders of magnitude.
@article{pesantez-cabrera_efficient_2019, title = {Efficient {Detection} of {Communities} in {Biological} {Bipartite} {Networks}}, volume = {16}, issn = {1557-9964}, doi = {10.1109/TCBB.2017.2765319}, number = {1}, journal = {IEEE/ACM Transactions on Computational Biology and Bioinformatics}, author = {Pesántez-Cabrera, Paola and Kalyanaraman, Ananth}, month = jan, year = {2019}, note = {Conference Name: IEEE/ACM Transactions on Computational Biology and Bioinformatics}, keywords = {Biology, bipartite modularity, bipartite networks, community detection, Computational modeling, Data models, Diseases, Drugs, graph algorithms, Heterogeneous biological data, Heterogeneous networks, Heuristic algorithms}, pages = {258--271}, }
Assessing Institutional Needs for Learning Analytics Adoption in Latin American Higher Education

Isabel Hilliger, Mar Pérez-Sanagustín, Margarita Ortiz, Paola Pesántez-Cabrera, Eliana Scheihing, Yi-Shan Tsai, Yi-Shan Tsai@ed, Pedro Uk, Pedro Merino, and Tom Broos

Apr 2019

Abs Bib

In recent years, Learning Analytics (LA) has captured the attention of higher education managers who saw in this research field a means to optimize the process of teaching and learning on a large scale. So far, most studies in LA have concentrated on the development of tools to address educational challenges in the contexts of Europe, Australia, and U.S. However, tools and adoption frameworks developed in these contexts are not necessarily applicable for higher education institutions in the rest of the world. Given that there is no one-size-fits-all approach, this study aims to assess institutional needs for LA in the Latin American context by collecting and analyzing qualitative information obtained from managers, teaching staff and students at four universities (U1, U2, U3, and U4). Although most participants agreed that LA is a promising means to monitor students’ academic progress at a curriculum level, findings show specific needs and considerations that differentiate each university (U1: academic support for subgroups, U2: dropout indicators,
@book{hilliger_assessing_2019, title = {Assessing {Institutional} {Needs} for {Learning} {Analytics} {Adoption} in {Latin} {American} {Higher} {Education}}, author = {Hilliger, Isabel and Pérez-Sanagustín, Mar and Ortiz, Margarita and Pesántez-Cabrera, Paola and Scheihing, Eliana and Tsai, Yi-Shan and Tsai@ed, Yi-Shan and Uk, Pedro and Merino, Pedro and Broos, Tom}, month = apr, year = {2019}, }

2018

SIAM
Exploiting Intra-Type Information in Bipartite Community Detection

Paola Pesántez-Cabrera, Ananth Kalyanaraman, and Mahantesh Halappanavar

Jul 2018

Abs Bib

Classical bipartite community methods only take into account inter-type edge information-i.e., edges between vertices of two different types. We present a new form of bipartite modularity (as an objective function for community detection) that can enable methods to incorporate both intra-type and inter-type edge information. Preliminary results evaluating this new form are presented.
@misc{pesantez-cabrera_exploiting_2018, title = {Exploiting {Intra}-{Type} {Information} in {Bipartite} {Community} {Detection}}, publisher = {SIAM Workshop on Network Science}, author = {Pesántez-Cabrera, Paola and Kalyanaraman, Ananth and Halappanavar, Mahantesh}, month = jul, year = {2018}, doi = {10.13140/RG.2.2.23333.73444}, }

2016

Trust from the past: Bayesian Personalized Ranking based Link Prediction in Knowledge Graphs

Baichuan Zhang, Sutanay Choudhury, Mohammad Al Hasan, Xia Ning, Khushbu Agarwal, Sumit Purohit, and Paola Pesantez-Cabrera

Feb 2016

Abs Bib

Link prediction, or predicting the likelihood of a link in a knowledge graph based on its existing state is a key research task. It differs from a traditional link prediction task in that the links in a knowledge graph are categorized into different predicates and the link prediction performance of different predicates in a knowledge graph generally varies widely. In this work, we propose a latent feature embedding based link prediction model which considers the prediction task for each predicate disjointly. To learn the model parameters it utilizes a Bayesian personalized ranking based optimization technique. Experimental results on large-scale knowledge bases such as YAGO2 show that our link prediction approach achieves substantially higher performance than several state-of-art approaches. We also show that for a given predicate the topological properties of the knowledge graph induced by the given predicate edges are key indicators of the link prediction performance of that predicate in the knowledge graph.
@article{zhang_trust_2016, title = {Trust from the past: {Bayesian} {Personalized} {Ranking} based {Link} {Prediction} in {Knowledge} {Graphs}}, shorttitle = {Trust from the past}, doi = {10.48550/arXiv.1601.03778}, urldate = {2022-10-17}, publisher = {arXiv}, author = {Zhang, Baichuan and Choudhury, Sutanay and Hasan, Mohammad Al and Ning, Xia and Agarwal, Khushbu and Purohit, Sumit and Pesantez-Cabrera, Paola}, month = feb, year = {2016}, note = {arXiv:1601.03778 [cs]}, keywords = {Computer Science - Artificial Intelligence, Computer Science - Information Retrieval, Computer Science - Machine Learning}, annote = {Comment: SDM Workshop on Mining Networks and Graphs (MNG 2016), Miami, FL}, }
IntechOpen
Kinetic Model of Development and Aging of Artificial Skin Based on Analysis of Microscopy Data

Paola Pesantez-Cabrera, Cläre von Neubeck, Marianne B. Sowa, John H. Miller, Paola Pesantez-Cabrera, Cläre von Neubeck, Marianne B. Sowa, and John H. Miller

Sep 2016

Abs Bib

Artificial human skin is available commercially or can be grown in the laboratory from established cell lines. Standard microscopy techniques show that artificial human skin has a fully developed basement membrane that separates an epidermis with the corneal, granular, spinosal, and basal layers from a dermis consisting of fibroblasts in an extracellular matrix. In this chapter, we show how modeling can integrate microscopy data to obtain a better understanding of the development and aging of artificial human skin. We use the time-dependent structural information predicted by our model to show how irradiation with an electron beam at different times in the life of artificial human skin affects the amount of energy deposited in different layers of the tissue. Experimental studies of this type will enable a better understanding of how different cell types in human skin contribute to overall tissue response to ionizing radiation.
@book{pesantez-cabrera_kinetic_2016, title = {Kinetic {Model} of {Development} and {Aging} of {Artificial} {Skin} {Based} on {Analysis} of {Microscopy} {Data}}, isbn = {978-953-51-2579-2}, url = {https://www.intechopen.com/state.item.id}, language = {en}, urldate = {2022-10-22}, publisher = {IntechOpen}, author = {Pesantez-Cabrera, Paola and Neubeck, Cläre von and Sowa, Marianne B. and Miller, John H. and Pesantez-Cabrera, Paola and Neubeck, Cläre von and Sowa, Marianne B. and Miller, John H.}, month = sep, year = {2016}, doi = {10.5772/63402}, note = {Publication Title: Microscopy and Analysis}, }
ACM
Detecting Communities in Biological Bipartite Networks

Paola Pesantez-Cabrera, and Ananth Kalyanaraman

In Proceedings of the 7th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics Oct 2016

Abs Bib

Methods to uncover and extract community structures are required in a number of biological applications where networked data and their interactions can be modeled as graphs, and observing tightly-knit groups of vertices ("communities") can offer insights into the structural and functional building blocks of the underlying network. While classical applications of community detection have focused largely on detecting molecular complexes from protein-protein networks and other similar graphs, there is an increasing need for extending the community detection operation to work for heterogeneous data sets — i.e., networks built out of multiple types of data. In this paper, we address the problem of identifying communities from biological bipartite networks — networks where interactions are observed between two different types of vertices (e.g., genes and diseases, drugs and protein complexes, plants and pollinators). Toward detecting communities in such bipartite networks, we make the following contributions: i) we define a variant of the bipartite modularity function defined by Murata to overcome one of its limitations; ii) we present an algorithm (biLouvain), building on an efficient heuristic that was originally developed for unipartite networks; and iii) we present a thorough experimental evaluation of our algorithm compared to other state-of-the-art methods to identify communities on bipartite networks. Experimental results show that our biLouvain algorithm identifies communities that have a comparable or better quality (bipartite modularity) than existing methods, while significantly reducing the time-to-solution between one and three orders of magnitude.
@inproceedings{pesantez-cabrera_detecting_2016, address = {New York, NY, USA}, series = {{BCB} '16}, title = {Detecting {Communities} in {Biological} {Bipartite} {Networks}}, isbn = {978-1-4503-4225-4}, url = {https://doi.org/10.1145/2975167.2975177}, doi = {10.1145/2975167.2975177}, urldate = {2022-10-21}, booktitle = {Proceedings of the 7th {ACM} {International} {Conference} on {Bioinformatics}, {Computational} {Biology}, and {Health} {Informatics}}, publisher = {Association for Computing Machinery}, author = {Pesantez-Cabrera, Paola and Kalyanaraman, Ananth}, month = oct, year = {2016}, keywords = {community detection, graph algorithms, Heterogeneous biological data, biological bipartite networks}, pages = {98--107}, }