- Tactile and Sensory Interactions
- Hand Gesture Recognition Systems
- Remote Sensing and LiDAR Applications
- COVID-19 diagnosis using AI
- Interactive and Immersive Displays
- Remote Sensing in Agriculture
- Smart Agriculture and AI
- Advanced Vision and Imaging
- Radiomics and Machine Learning in Medical Imaging
- Gaze Tracking and Assistive Technology
- Leaf Properties and Growth Measurement
- Image Processing Techniques and Applications
- Forest ecology and management
- Advanced Image and Video Retrieval Techniques
- Robotics and Sensor-Based Localization
- Augmented Reality Applications
- AI in cancer detection
- Sugarcane Cultivation and Processing
- Spectroscopy and Chemometric Analyses
- Advanced Image Processing Techniques
- Image Retrieval and Classification Techniques
- Lung Cancer Diagnosis and Treatment
- Digital Accessibility for Disabilities
- Stock Market Forecasting Methods
- Educational Games and Gamification
Universidade Federal de Goiás
2015-2024
Southern Oregon University
2019-2020
Ashland (United States)
2019-2020
Institute of Informatics of the Slovak Academy of Sciences
2020
Instituto Federal Goiano
2018
Universidade Federal de Uberlândia
2015
This work extends PneumoCAD, a Computer-Aided Diagnosis system for detecting pneumonia in infants using radiographic images [1], with the aim of improving system's accuracy and robustness. We implement compare three contemporary machine learning classifiers, namely: Näıve Bayes, K-Nearest Neighbor (KNN), Support Vector Machines (SVM). Results our experiments demonstrate that SVM classifier produces best overall results.
Sugarcane planting is an important and growing activity in Brazil. Thereupon, several techniques have been developed over the years to maximize crop productivity profit, amongst them, processing of sugarcane field images. In this sense, research aims identify analyze rows measure their gaps from aerial images fields. For this, a small Remotely Piloted Aircraft captured images, generating orthomosaics areas for analysis. Then, each orthomosaic classified with K-Nearest Neighbor algorithm...
Emerging technology on mobile and wearable market, smartwatches have embedded movement sensors whose potential is yet to be fully explored. This paper proposes an interaction method with smart TVs via gestures performed by person's wrist using a smartwatch. Detailed architecture implementation for complete prototype, named Wrist Player, presented. A user study also conducted, in order evaluate the prototype performance user's interest proposal. Results show that works very well, participants...
Due to the expansion of multimedia data leveraged by social networks and smartphone devices, large sets information are available increasing daily. In this context, retrieval is crucial open new opportunities individuals, governments, businesses. Therefore, we present CBIR-ANR software in which content-based image (CBIR) followed an accuracy noise reduction (ANR) strategy that adjusts query responses increases assertiveness retrieval. Also, combines three low-level features form a...
Doenças neurodegenerativas (DNDs) causam, dentre outros sintomas, o comprometimento da marcha. Diversos estudos analisam a marcha para, com auxílio inteligência artificial, auxiliar no diagnóstico de DNDs. Devido à dificuldade coleta novos dados, técnica sobreamostragem através do janelamento dados é frequentemente utilizada. No entanto, um estudo anterior apontou para possível enviesamento na fase treinamento algoritmos classificação utilizando técnicas janelamento. Este trabalho investiga...
Wheat is the third most produced grain in world after maize and rice. Determining protein concentration wheat one of major challenges for measuring its industrial quality. Samples can be collected using a spectrophotometer device. The challenge to associate energy absorbed by device with wheat. measures hundreds variable intensities that related physicochemical properties. selection subset uncorrelated variables has been shown fundamental establishing correct correlations reducing prediction...
Nowadays, due to touchscreen, mobile devices have become much more dynamic than in the past. However, same reason, those are less accessible for blind people. It is expected that 2018, over half of phone users will a smartphone, therefore researches about accessibility very important. So, aim this systematic review cooperate with new research methods braille text entry on smartphones. The searches 5 databases, resulted 11 papers answered questions grounded work.
This work presents the development and usability evaluation of MazeVR game, a maze game designed for Google Cardboard device. The allows interactions through head movements to control camera gestures on smartwatch perform additional actions, such as starting stopping walking, picking up discarding torches, clearing path. Gesture recognition is performed using continuous gesture algorithm. main objective was create an immersive challenging experience players, allowing them explore overcome...
Smartwatches are wearable devices of emerging mobile technology and increasingly in people's daily lives. They allow you to perform various tasks; however, the interaction with these still proves be a significant challenge. Several studies carried out smartwatches using gesture recognition. Thus, this work presents comprehensive Systematic Review Literature (SRL) on recognition, showing what has already been developed is state art. We searched four databases relevant scientific scope: ACM...
Leveraged by the production of grains, oilseeds, and fresh deciduous fruits, food has reached new heights, exceeding amount produced in previous years with an estimate records for coming years. In this sense, technological advances are essential to reduce costs increase quality productivity. paper, we present a novel method detect insect predation on plant leaves that uses geometric leaf properties digital image processing techniques construct models. Unlike other approaches, our detects...
Tuberculosis is a severe and contagious lung disease that kills more than one million people annually, representing real public health problem worldwide. Meanwhile, researchers industry have highlighted the potential of analyzing classifying chest radiographs (CXR) with artificial intelligence (AI). However, although high-performance solutions to aid in diagnosing become reality, vulnerable populations underdeveloped countries struggled access them. In this sense, accessible low-cost...
Objetivo: Este estudo investiga se o possível viés na sobreamostragem via janelamento de dados marcha em indivíduos com Doença Parkinson (DP) também ocorre sinais vocais. Um anterior levantou a hipótese que amostras distintas um mesmo indivíduo não devem ser tratadas independentemente, dado risco enviesamento dos modelos. Método: Usamos voz 24 DP e 8 saudáveis, os algoritmos K-Nearest Neighbors (KNN), Support Vector Machine (SVM) Random Forest (RF). A validação cruzada foi feita...
This work proposes a method that allows the entry of text in smartwatches using gestures based on geometric forms. For this it is proposed development prototype capable inserting letter with no more than two user interactions. Gesture recognition performed incremental algorithm. A set lines and curves were created to be recognized by algorithm, generated from reduced equation line circumference, respectively. After recognizing gestures, they are sent classifier Naïve Bayes which responsible...