Search results for "machine learning."
showing 10 items of 1455 documents
Classifying DME vs Normal SD-OCT volumes: A review
2016
International audience; This article reviews the current state of automatic classification methodologies to identify Diabetic Macular Edema (DME) versus normal subjects based on Spectral Domain OCT (SD-OCT) data. Addressing this classification problem has valuable interest since early detection and treatment of DME play a major role to prevent eye adverse effects such as blindness. The main contribution of this article is to cover the lack of a public dataset and benchmark suited for classifying DME and normal SD-OCT volumes, providing our own implementation of the most relevant methodologies in the literature. Subsequently, 6 different methods were implemented and evaluated using this comm…
Multi-Criteria Decision Making support system for pancreatic islet transplantation
2011
Pancreatic islet transplantation consists of replacing insulin-producing cells to restore normal glycemia in diabetic patients. This is a minimal invasive procedure that has been proved successful. Unfortunately unpredictability of islet transplant outcome remains a frustrating and costly issue limiting the clinical implementation of this procedure. Multiple variables are involved in the procedure and assessment is subjective to individual operators. The aim of this study was to generate a system expressing the probability of transplant success in relation to four classes of identified variables (donor, organ, isolation and recipient). We have proposed the utilization of Multi-Criteria Deci…
Modern Multispectral Sensors Help Track Explosive Eruptions
2013
Due to its massive air traffic impact, the 2010 eruption of Eyjafjallajokull was felt by millions of people and cost airlines more than U.S. $1.7 billion. The event has, thus, become widely cited in renewed efforts to improve real-time tracking of volcanic plumes, as witnessed by special sections published last year in Journal of Geophysical Research, (117, issues D20 and B9).
Mapping lava flows at Etna Volcano using Google Earth Engine, open-access satellite data, and machine learning
2021
Estimating eruptive parameters is fundamental to assess the volcanic hazards posed to the community living at the edge of active volcanoes. Here, we analyzed satellite remote sensing data by using machine learning unsupervised and supervised techniques and analytical approaches, i.e., mathematical-physics and statistics formulations, to map lava flows emitted during the long sequences of short-lived, violent eruptions occurred at Etna volcano between December 2020 and March 2021. Satellite observations allowed to follow the evolution of eruptions thanks to their capability to survey large areas with frequent revisit time and accurate spatial resolution. We quantified the areal coverage of l…
Description of movement sensor dataset for dog behavior classification
2022
The description and results of the original investigation are found in: Dog behaviour classification with movement sensors placed on the harness and the collar, Kumpulainen, P., Valldeoriola Cardó, A., Somppi, S., Törnqvist, H., Väätäjä, H., Majaranta, P., Gizatdinova, Y., Antink, C. H., Surakka, V., V. Kujala, M., Vainio, O. & Vehkaoja, A., Aug 2021, In: Applied Animal Behaviour Science. 241, 7 p., 105393. Movement sensor data from seven static and dynamic dog behaviors (sitting, standing, lying down, trotting, walking, playing, and (treat) searching i.e. sniffing) was collected from 45 middle to large sized dogs with six degree-of-freedom movement sensors attached to the collar and the ha…
Time Unification on Local Binary Patterns Three Orthogonal Planes for Facial Expression Recognition
2019
International audience; Machine learning has known a tremendous growth within the last years, and lately, thanks to that, some computer vision algorithms started to access what is difficult or even impossible to perceive by the human eye. While deep learning based computer vision algorithms have made themselves more and more present in the recent years, more classical feature extraction methods, such as the ones based on Local Binary Patterns (LBP), still present a non negligible interest, especially when dealing with small datasets. Furthermore, this operator has proven to be quite useful for facial emotions and human gestures recognition in general. Micro-Expression (ME) classification is…
A method for anomaly detection in hyperspectral images, using deep convolutional autoencoders
2017
Menetelmä poikkeavuuksien havaitsemiseen hyperspektrikuvista käyttäen syviä konvolutiivisia autoenkoodereita. Poikkeavuuksien havaitseminen kuvista, erityisesti hyperspektraalisista kuvista, on hankalaa. Kun ongelmaan yhdistetään ennalta tuntematon data ja poikkeavuudet, muodostuu ongelma vielä laajemmaksi. Spektraalisten poikkeavuuksien havaitsemiseen on kehitetty useita eri menetelmiä, mutta spatiaalisten poikkeavuuksien havaitseminen on huomattavasti hankalempaa. Tässä työssä esitellään uudenkaltainen menetelmä sekä spatiaalisten että spektraalisten poikkeavuuksien samanaikaiseen havaitsemiseen. Menetelmä on suunniteltu erityisesti spektraaliselle datalle, mutta soveltuu myös perinteisil…
Can Individual Movement Characteristics Across Different Throwing Disciplines Be Identified in High-Performance Decathletes?
2020
Although the individuality of whole-body movements has been suspected for years, the scientific proof and systematic investigation that individuals possess unique movement patterns did not manifest until the introduction of the criteria of uniqueness and persistence from the field of forensic science. Applying the criteria of uniqueness and persistence to the individuality of motor learning processes requires complex strategies due to the problem of persistence in the learning processes. One approach is to examine the learning process of different movements. For this purpose, it is necessary to differentiate between two components of movement patterns: the individual-specific component and …
Desafíos y oportunidades de Sentinel-2 en la monitorización de las aguas continentales
2023
En los ecosistemas de agua dulce, la escasez y la contaminación de este recurso está promoviendo que los organismos gubernamentales incluyan en sus agendas estrategias para mitigar esta situación a través de una gestión sostenible. La Directiva Marco del Agua establece entre sus requerimientos la monitorización del estado ecológico de las aguas continentales para determinar su calidad. Las imágenes satelitales ofrecen una visión sinóptica y continua a partir de la que es posible derivar métricas del estado ecológico. Esas métricas son un complemento a los tradicionales muestreos ya que se incrementa la cobertura espacial y la periodicidad en la monitorización. Sentinel-2, con su sensor Mult…
Large-scale nonlinear dimensionality reduction for network intrusion detection
2017
International audience; Network intrusion detection (NID) is a complex classification problem. In this paper, we combine classification with recent and scalable nonlinear dimensionality reduction (NLDR) methods. Classification and DR are not necessarily adversarial, provided adequate cluster magnification occurring in NLDR methods like $t$-SNE: DR mitigates the curse of dimensionality, while cluster magnification can maintain class separability. We demonstrate experimentally the effectiveness of the approach by analyzing and comparing results on the big KDD99 dataset, using both NLDR quality assessment and classification rate for SVMs and random forests. Since data involves features of mixe…