A5033705237- Forensic Anthropology and Bioarchaeology Studies
- Dental Radiography and Imaging
- Orthodontics and Dentofacial Orthopedics
- Face recognition and analysis
- Embedded Systems Design Techniques
- Autopsy Techniques and Outcomes
- Interconnection Networks and Systems
- Date Palm Research Studies
- Nematode management and characterization studies
- Parallel Computing and Optimization Techniques
- Smart Agriculture and AI
- Data-Driven Disease Surveillance
- Medical Imaging and Analysis
- Spine and Intervertebral Disc Pathology
- Spinal Fractures and Fixation Techniques
- dental development and anomalies
- Forecasting Techniques and Applications
- Milk Quality and Mastitis in Dairy Cows
- Prostate Cancer Diagnosis and Treatment
- Biosensors and Analytical Detection
- Face and Expression Recognition
- COVID-19 epidemiological studies
- Connexins and lens biology
- Energy Load and Power Forecasting
- Urinary Bladder and Prostate Research
Instituto da Visão
2024
Universidade Federal de Mato Grosso
2024
Universidade de Brasília
2018-2024
University of Dundee
2022
Universidade de São Paulo
2020
Universidade Federal de São Carlos
2014-2015
Abstract Convolutional neural networks (CNN) led to important solutions in the field of Computer Vision. More recently, forensic sciences benefited from resources artificial intelligence, especially procedures that normally require operator-dependent steps. Forensic tools for sexual dimorphism based on morphological dental traits are available but have limited performance. This study aimed test application a machine learning setup distinguish females and males using dentomaxillofacial...
Abstract Using on-farm microbiological culture (OFC), based on chromogenic media, enables the identification of mastitis causing pathogens in about 24 h, allows rapid decision making selective treatment and control management measures cows with clinical (CM). However, accurate interpretation OFC results requires trained experienced operators, which could be a limitation for use dairy farms. Our hypothesis was that AI-based automated plate reading mobile application can analyze images...
Third molar development is used for dental age estimation when all the other teeth are fully mature. In most medicolegal facilities, an operator-dependent procedure. During examination of unaccompanied and undocumented minors, this procedure may lead to binary decisions around thresholds legal interest, namely ages 14, 16 18 years. This study aimed test performance artificial intelligence classify individuals below above years using third development. The sample consisted 11,640 panoramic...
TB/HIV coinfection poses a complex public health challenge. Accurate forecasting of future trends is essential for efficient resource allocation and intervention strategy development. This study compares classical statistical machine learning models to predict cases stratified by gender the general populations. We analyzed time series data using exponential smoothing ARIMA establish baseline trend seasonality. Subsequently, (SVR, XGBoost, LSTM, CNN, GRU, CNN-GRU, CNN-LSTM) were employed...
Abstract Convolutional neural networks (CNN) led to important solutions in the field of Computer Vision. More recently, forensic sciences benefited from resources artificial intelligence, especially procedures that normally require operator-dependent steps. Forensic tools for sexual dimorphism based on morphological dental traits are available but have limited performance. This study aimed test application a machine learning setup distinguish females and males using dentomaxillofacial...
We present a fully automatic system for the quantitative assessment of discs and vertebrae using convolutional neural networks. The proposed algorithm works in three stages: 1) segmentation/identification spinal anatomy; 2) curvature analysis; 3) detection pathological conditions intervertebral discs. validate approach on large dataset 1,500 subjects with sagittal T2-weighted whole spine MRI, obtained as part body MRI protocol preventative health screening program.
AI-assisted prostate whole-gland and zonal volume quantification enable quantitative reproducibility enhance read-time efficiency. Our AI-segmentation solution enhanced measurement accuracy by 23.59%, compared with traditional estimates. Zonal enabled us to generate population normative aging-curves we used a shallow classifier identify patients BPH. findings show the transitional zone grows 2.05 ml 3.58 per decade for entire BPH, respectively, while peripheral 0.70 decade. Further, zones...
<title>Abstract</title> Considering the complexity and severity of TB/HIV coinfection, accuracy in forecasting future trends is crucial for efficient allocation public health resources development intervention strategies. This study explores application predictive models, ranging from classical statistical approaches to machine learning techniques, analyze time series coinfection case notifications stratified men, women, general population. Traditional models using Exponential Smoothing...
Phytoparasitic nematodes (or phytonematodes) are causing severe damage to crops and generating large-scale economic losses worldwide. In soybean crops, annual estimated at 10.6% of world production. Besides, identifying these species through microscopic analysis by an expert with taxonomy knowledge is often laborious, time-consuming, susceptible failure. this perspective, robust automatic approaches necessary for phytonematodes capable providing correct diagnoses the classification...
Over the last years, facial landmarks techniques were first and main approach to solve biometric recognition they are still capable of achieving great results in controlled environments. However, there open problems be solved, such as how deal with twins, scale variation face growth. In this work, we propose a new method based on measured values (ratios) from cephalometric landmarks, which uses an iris size normalization factor influence (face growth) effect improving Equal Error Rates (EER)...
Compiladores de síntese alto nível vem se popularizando. Esses permitem transformar códigos em hardware maneira simples e rápida. As soluções atuais geram que não exploram as técnicas permitam melhorar o pipeline hardware. Este trabalho apresenta compilador LALPC utiliza para explorar paralelismo FPGAs a partir projetos descritos linguagem C. identificar aplicar otimizações acelerar trechos baseados loops. é capaz gerar sistemas desempenho, permitindo exploração espaço projeto pelo programador.
This study aimed to investigate the dynamics of facial aging from photographs individuals in different age groups and establish a pattern growth. The sample consisted digital standardly taken 1273 Brazilians aged between 2 24 years equally distributed by sex into 12 specific (2, 4, 6, 8, 10, 12, 14, 16, 18, 20, 22 years). SAFF-2D® (Forensic Facial Analysis System, Brazilian Federal Police, Brazil) software package was used for positioning 28 landmarks on each photograph. Two-hundred eight...
This paper presents LALPC, a prototype high-level synthesis tool, specialized in hardware generation for loop-intensive code segments. As demonstrated previous work, the underlying components target by LALPC are highly loop pipeline execution, resulting efficient implementations, both terms of performance and resources usage (silicon area). extends functionality tool using subset C language as input to describe computations, improving usability potential acceptance technique among...
Abstract Third molar development is used for dental age estimation when all the other teeth are fully mature. In most medicolegal facilities, an operator-dependent procedure. During examination of unaccompanied and undocumented minors, this procedure may lead to binary decisions around thresholds legal interest, namely ages 14, 16 18 years. This study aimed test performance artificial intelligence classify individuals below above years using third development. The sample consisted 11.640...
Facial landmarks are employed in many research areas such as facial recognition, craniofacial identification, age and sex estimation among the most important. In forensic field, focus is on analysis of a particular set landmarks, defined cephalometric landmarks. Previous works demonstrated that descriptive adequacy these anatomical references for an indirect application (photo-anthropometric description) increased marking precision points, contributing to greater reliability analyzes....
A tradução automática está intrinsecamente associada ao estudo e desenvolvimento de metodologias computadorizadas para a produção traduções idiomáticas. As abordagens mais utilizadas são as estatísticas baseadas em redes neurais. Uma das deficiências apontadas por estes métodos é possível falta coerência entre sentenças traduzidas. Neste projeto propomos utilização técnicas na Teoria Grafos conservar dos textos do Inglês o Português. O método estudado apresenta grande variabilidade...