A5002484344- Business Process Modeling and Analysis
- Service-Oriented Architecture and Web Services
- Semantic Web and Ontologies
- Retinal Imaging and Analysis
- Multi-Agent Systems and Negotiation
- Logic, Reasoning, and Knowledge
- Machine Learning and Data Classification
- Retinal Diseases and Treatments
- Software System Performance and Reliability
- Distributed and Parallel Computing Systems
- Biomedical Text Mining and Ontologies
- Digital Imaging for Blood Diseases
- Quantum and electron transport phenomena
- Imbalanced Data Classification Techniques
- Usability and User Interface Design
- Anomaly Detection Techniques and Applications
- Scientific Computing and Data Management
- Electronic Health Records Systems
- AI-based Problem Solving and Planning
- Access Control and Trust
- Advancements in Semiconductor Devices and Circuit Design
- Cryptography and Data Security
- Scheduling and Optimization Algorithms
- Medical Image Segmentation Techniques
- scientometrics and bibliometrics research
Hospital de Clínicas da Unicamp
1996-2023
Fractyl (United States)
2023
Universidade Estadual de Campinas (UNICAMP)
2012-2021
Fundação de Apoio à Universidade Federal de São Paulo
2012
Universidade Federal de São Paulo
2003-2007
Universidade Federal do Pará
2003
University of Colorado System
2000
Carnegie Mellon University
1995
Saarland University
1995
University of Colorado Boulder
1992
This paper discusses a conceptual model of groupware consisting three complementary components or models: description the objects and operations on these available in system; activities (and their orderings) that users system can perform; interface with system, other users.
In this paper, we present an algorithm to detect the presence of diabetic retinopathy (DR)-related lesions from fundus images based on a common analytical approach that is capable identifying both red and bright without requiring specific pre- or postprocessing. Our solution constructs visual word dictionary representing points interest (PoIs) located within regions marked by specialists contain associated with DR classifies absence these PoIs as normal DR-related pathology. The novelty our...
In recent years, software-based face presentation attack detection (PAD) methods have seen a great progress. However, most existing schemes are not able to generalize well in more realistic conditions. The objective of this competition is evaluate and compare the generalization performances mobile PAD techniques under some real-world variations, including unseen input sensors, instruments (PAI) illumination conditions, on larger scale OULU-NPU dataset using its standard evaluation protocols...
This paper presents a pair of role-based access control models for workflow systems, collectively known as the W-RBAC models. The first these models, W0-RBAC is based on framework that couples powerful RBAC-based permission service and component with clear separation concerns ease administration authorizations. focus work, providing an expressive logic-based language selection users authorized to perform tasks, preference ranking. W1-RBAC extends basic model by incorporating exception...
The focus of traditional workflow management systems is on control flow within one process definition. definition describes how a single case (i.e. instance) in isolation handled. For many applications this paradigm inadequate. Interaction between cases to support communication and collaboration at least as important. This paper introduces advocates the use interacting proclets, i.e. lightweight processes. By promoting interactions first-class citizens it possible model complex workflows...
Measurements of the temperature and carrier-density dependence strongly localized conductance short silicon inversion layers are reported. At lowest temperatures we observe well-isolated, large peaks whose width only consistent with resonant tunneling inconsistent Mott hopping. Several new features observed which believe may be result Coulomb interactions.
Diabetic Retinopathy (DR) is a complication of diabetes that can lead to blindness if not readily discovered. Automated screening algorithms have the potential improve identification patients who need further medical attention. However, lesions must be accurate useful for clinical application. The bag-of-visual-words (BoVW) algorithm employs maximum-margin classifier in flexible framework able detect most common DR-related such as microaneurysms, cotton-wool spots and hard exudates. BoVW...
Diabetic retinopathy (DR) is the leading cause of blindness in adults, but can be managed if detected early. Automated DR screening helps by indicating which patients should referred to doctor. However, current techniques automated still depend too much on detection individual lesions. In this study, we bypass lesion detection, and directly train a classifier for referral. Additional novelties are use state-of-the-art mid-level features retinal images: BossaNova Fisher Vector. Those extend...
Breast parenchymal density is considered a strong indicator of breast cancer risk and therefore useful for preventive tasks. Measurement often qualitative requires the subjective judgment radiologists. Here we explore an automatic composition classification workflow based on convolutional neural networks feature extraction in combination with support vector machines classifier. This compared to assessments seven experienced The experiments yielded average kappa value 0.58 when using mode...
We have made extensive studies of the temperature, gate voltage, and electric field dependences conductance peaks in small silicon inversion layers order to distinguish between resonant-tunneling models a hopping model. find that many are consistent only with model, whereas some could be an early None our structure is resonant tunneling if recent formulation Stone Lee correct.
Emerging technologies in health care aim at reducing unnecessary visits to medical specialists, minimizing overall cost of treatment and optimizing the number patients seen by each doctor. This paper explores image recognition for screening diabetic retinopathy, a complication diabetes that can lead blindness if not discovered its initial stages. Many previous reports on DR imaging focus segmentation retinal image, quality assessment, analysis presence DR-related lesions. Although this study...
We tested 14 very different classification algorithms (random forest, gradient boosting machines, SVM - linear, polynomial, and RBF 1-hidden-layer neural nets, extreme learning k-nearest neighbors a bagging of knn, naive Bayes, vector quantization, elastic net logistic regression, sparse linear discriminant analysis, classifiers) on 115 real life binary datasets. followed the Demsar analysis found that three best classifiers gbm SVM) are not significantly from each other. also discuss change...
We review some recent results on the low-temperature transport properties (T < 4K) of very small silicon metal-oxide field-effect transistors in insulating regime conduction. Our devices are lithographically patterned to have widths as 0.05 µm and lengths short 0.06 µm. These exhibit new unexpected sample-specific fluctuation behavior gate voltage, temperature, magnetic field dependence conductance. discuss both resonant tunneling Mott variable-range hopping, two main mechanisms these at low...