Sarajane Marques Peres

ORCID: 0000-0003-3551-6480
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Business Process Modeling and Analysis
  • Hand Gesture Recognition Systems
  • Hearing Impairment and Communication
  • Data Quality and Management
  • Data Mining Algorithms and Applications
  • Topic Modeling
  • Service-Oriented Architecture and Web Services
  • Big Data and Business Intelligence
  • Education and Digital Technologies
  • Speech and dialogue systems
  • Data Stream Mining Techniques
  • Business and Management Studies
  • Neural Networks and Applications
  • Privacy, Security, and Data Protection
  • Tactile and Sensory Interactions
  • Semantic Web and Ontologies
  • Multi-Agent Systems and Negotiation
  • Face and Expression Recognition
  • Advanced Clustering Algorithms Research
  • Time Series Analysis and Forecasting
  • Text and Document Classification Technologies
  • Recommender Systems and Techniques
  • Image Retrieval and Classification Techniques
  • Fuzzy Logic and Control Systems
  • Ethics and Social Impacts of AI

Universidade de São Paulo
2015-2024

Centro Universitário Belas Artes de São Paulo
2022

University of Ontario Institute of Technology
2021

Universidad San Pedro
2018

Universidade Estadual Paulista (Unesp)
2008

Universidade Estadual de Maringá
2006

Universidade Estadual de Campinas (UNICAMP)
2003-2004

Western University
2004

Universidade Estadual do Oeste do Paraná
2002

Universidade Federal de Santa Catarina
1998

In this paper, the vision-based hand movement recognition problem is formulated for universe of discourse Brazilian Sign Language. order to analyze specific domain we have used artificial neural networks models based on distance, including neural-fuzzy models. The experiments explored here show usefulness these extract helpful knowledge about classes movements and support project adaptative recognizer modules Libras-oriented computational tools. Using architectures - Self Organizing Maps...

10.1109/ijcnn.2009.5178917 article EN 2009-06-01

This study systematically assesses the process mining scenario from 2005 to 2014. The analysis of 705 papers evidenced 'discovery' (71%) as main type addressed and 'categorical prediction' (25%) task solved. most applied traditional technique is 'graph structure-based' ones (38%). Specifically concerning computational intelligence machine learning techniques, we concluded that little relevance has been given them. are 'evolutionary computation' (9%) 'decision tree' (6%), respectively....

10.1080/17517575.2017.1402371 article EN Enterprise Information Systems 2017-11-20

Although large language models (LLMs) demonstrate strong text generation capabilities, they struggle in scenarios requiring access to structured knowledge bases or specific documents, limiting their effectiveness knowledge-intensive tasks. To address this limitation, retrieval-augmented (RAG) have been developed, enabling generative incorporate relevant document fragments into inputs. In paper, we design and evaluate a RAG-based virtual assistant specifically tailored for the University of...

10.48550/arxiv.2501.13880 preprint EN arXiv (Cornell University) 2025-01-23

10.24251/hicss.2025.211 article EN Proceedings of the ... Annual Hawaii International Conference on System Sciences/Proceedings of the Annual Hawaii International Conference on System Sciences 2025-01-01

10.24251/hicss.2025.139 article EN Proceedings of the ... Annual Hawaii International Conference on System Sciences/Proceedings of the Annual Hawaii International Conference on System Sciences 2025-01-01

Gesture analysis has been widely used for developing new methods of human-computer interaction. The advancement reached in the gesture area is also motivating its application to automate tasks related discourse analysis, such as phases segmentation task. In this paper, we present an initiative that aims at segmenting gestures, especially considering "units" -- larger grain involved segmentation. Thereunto, have captured gestures using a Xbox Kinect™ device, modeled problem classification...

10.1145/2480362.2480373 article EN 2013-03-18

A smart toy is defined as a device consisting of physical component that connects to one or more computing services facilitate gameplay in the cloud through networking and sensory technologies enhance functionality traditional toy. this context can be effectively considered an Internet Things (IoT) with Artificial Intelligence (AI) which provide Augmented Reality (AR) experiences users. In paper, first assumption children do not understand concept privacy know how protect themselves online,...

10.24251/hicss.2017.146 article EN cc-by-nc-nd Proceedings of the ... Annual Hawaii International Conference on System Sciences/Proceedings of the Annual Hawaii International Conference on System Sciences 2017-01-01

Purpose – Process mining is a research area used to discover, monitor and improve real business processes by extracting knowledge from event logs available in process-aware information systems. The purpose of this paper evaluate the application artificial neural networks (ANNs) support vector machines (SVMs) data tasks process context. goal was understand how these computational intelligence techniques are currently being applied mining. Design/methodology/approach authors conducted...

10.1108/bpmj-02-2015-0017 article EN Business Process Management Journal 2015-10-19

In the information systems development, software engineers seek to improve systems’ functionality and usability, which may require a review of their requirements. Considering teaching-learning process scenario, guaranteeing such goals demands comply with pedagogical rules satisfy student desires needs. This paper reports on an experiment in requirements refinement for Learning Management System, involving system’s users through application Design Thinking methodology. is human-centered set...

10.5753/sbsi.2013.5686 article EN 2013-05-22

In several countries, deaf communities adopt the sign language as their official and natural language. This fact inserts a new field for software application development that can improve dissemination social inclusion of people. Alphabetic character-based applications, like games educational softwares, be adapted to run fingerspelling-based in which inputs are signs (static images or videos) rather than letters (typed letters). this paper, we present Pattern Recognition Module, implemented...

10.1145/1774088.1774287 article EN 2010-03-22

Currently the demand for development of more precise and reliable methods person identification have received attention from academic community industry, with Biometrics being one these new approaches. The term 'Biometrics' is used to refer techniques based on physical or behavioural characteristics. As biometric recognition becomes increasingly popular, fear circumvention, obfuscation replay attacks a rising concern. Since traditional modalities (face, iris fingerprint) are not able supply...

10.1109/ijcnn.2017.7966216 article EN 2022 International Joint Conference on Neural Networks (IJCNN) 2017-05-01

Business processes are subject to changes over time due the need for adaptation and flexibility a complex environment. Detecting drift as soon possible identifying process elements involved, lead much better understanding of behavior, which can be competitive edge businesses. However, most existing approaches focus on each these two tasks separately. Isolated do not always have interfaces between them that allow you combine solutions effectively corresponding task. In such cases, using...

10.1145/3412841.3441918 article EN 2021-03-22
Coming Soon ...