Cookies Policy
The website need some cookies and similar means to function. If you permit us, we will use those means to collect data on your visits for aggregated statistics to improve our service. Find out More
Accept Reject
  • Menu
Publications

Publications by Luís Filipe Teixeira

2015

Automatic Analysis of Lung Function Based on Smartphone Recordings

Authors
Teixeira, JF; Teixeira, LF; Fonseca, J; Jacinto, T;

Publication
BIOMEDICAL ENGINEERING SYSTEMS AND TECHNOLOGIES, BIOSTEC 2015

Abstract
Over 250 million people, worldwide, are affected by chronic lung conditions such as Asthma and COPD. These can cause breathlessness, a harsh decrease in quality of life and, if left undetected or not properly managed, even death. In this paper, we approached part of the lines of development suggested upon earlier work. This concerned the development of a system design for a smartphone lung function classification app, which would only use recordings from the built-in microphone. A more systematic method to evaluate the relevant combinations of methods was devised and an additional set of 44 recordings was used for testing purposes. The previous 101 were kept for training the models. The results enabled to further reduce the signal processing pipeline leading to the use of 6 envelopes, per recording, half of the previous amount. An analysis of the classification performances is provided for both previous tasks: differentiation into Normal from Abnormal lung function, and between multiple lung function patterns. The results from this project encourage further development of the system.

2015

Learning from evolving video streams in a multi-camera scenario

Authors
Khoshrou, S; Cardoso, JS; Teixeira, LF;

Publication
MACHINE LEARNING

Abstract
Nowadays, video surveillance systems are taking the first steps toward automation, in order to ease the burden on human resources as well as to avoid human error. As the underlying data distribution and the number of concepts change over time, the conventional learning algorithms fail to provide reliable solutions for this setting. In this paper, we formalize a learning concept suitable for multi-camera video surveillance and propose a learning methodology adapted to that new paradigm. The proposed framework resorts to the universal background model to robustly learn individual object models from small samples and to more effectively detect novel classes. The individual models are incrementally updated in an ensemble-based approach, with older models being progressively forgotten. The framework is designed to detect and label new concepts automatically. The system is also designed to exploit active learning strategies, in order to interact wisely with operator, requesting assistance in the most ambiguous to classify observations. The experimental results obtained both on real and synthetic data sets verify the usefulness of the proposed approach.

2015

Lung Function Classification of Smartphone Recordings - Comparison of Signal Processing and Machine Learning Combination Sets

Authors
Teixeira, JF; Teixeira, LF; Fonseca, J; Jacinto, T;

Publication
HEALTHINF 2015 - Proceedings of the International Conference on Health Informatics, Lisbon, Portugal, 12-15 January, 2015.

Abstract
Worldwide, over 250 million people are affected by chronic lung conditions such as Asthma and COPD. These can cause breathlessness, a harsh decrease in quality of life and, if not detected and duly managed, even death. In this paper, we aim to find the best and most efficient combination of signal processing and machine learning approaches to produce a smartphone application that could accurately classify lung function, using microphone recordings as the only input. A total of 61 patients performed the forced expiration maneuver providing a dataset of 101 recordings. The signal processing comparison experiments were conducted in a backward selection approach, reducing from 54 to 12 final envelopes, per recording. The classification experiments focused first on differentiating Normal from Abnormal lung function, and second in multiple lung function patterns. The results from this project encourage further development of the system.

2014

Active Learning from Video Streams in a Multi-Camera Scenario

Authors
Khoshrou, S; Cardoso, JS; Teixeira, LF;

Publication
2014 22ND INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR)

Abstract
While video surveillance systems are spreading everywhere, extracting meaningful information from what they are recording is still prohibitively expensive. There is a major effort under way in order to make this process economical by including an intelligent software that eases the burden of the system. In this paper, we introduce an incremental learning framework to classify parallel data streams generated in a multi-camera surveillance scenario. The framework exploits active learning strategies in order to interact wisely with operators to address various problems that exist in such non-stationary environments, such as concept drift and concept evolution. If we look at the problem as mining parallel streams, the framework can address learning from uneven parallel streams applying a class-based ensemble, a problem that has not been addressed before. Favourable results indicate the success of the framework.

2013

Analysis of object description methods in a video object tracking environment

Authors
Carvalho, P; Oliveira, T; Ciobanu, L; Gaspar, F; Teixeira, LF; Bastos, R; Cardoso, JS; Dias, MS; Corte Real, L;

Publication
MACHINE VISION AND APPLICATIONS

Abstract
A key issue in video object tracking is the representation of the objects and how effectively it discriminates between different objects. Several techniques have been proposed, but without a generally accepted method. While analysis and comparisons of these individual methods have been presented in the literature, their evaluation as part of a global solution has been overlooked. The appearance model for the objects is a component of a video object tracking framework, depending on previous processing stages and affecting those that succeed it. As a result, these interdependencies should be taken into account when analysing the performance of the object description techniques. We propose an integrated analysis of object descriptors and appearance models through their comparison in a common object tracking solution. The goal is to contribute to a better understanding of object description methods and their impact on the tracking process. Our contributions are threefold: propose a novel descriptor evaluation and characterisation paradigm; perform the first integrated analysis of state-of-the-art description methods in a scenario of people tracking; put forward some ideas for appearance models to use in this context. This work provides foundations for future tests and the proposed assessment approach contributes to the informed selection of techniques more adequately for a given tracking application context.

2015

Spatio-Temporal Fusion for Learning of Regions of Interests Over Multiple Video Streams

Authors
Khoshrou, S; Cardoso, JS; Granger, E; Teixeira, LF;

Publication
ADVANCES IN VISUAL COMPUTING, PT II (ISVC 2015)

Abstract
Video surveillance systems must process and manage a growing amount of data captured over a network of cameras for various recognition tasks. In order to limit human labour and error, this paper presents a spatial-temporal fusion approach to accurately combine information from Region of Interest (RoI) batches captured in a multi-camera surveillance scenario. In this paper, feature-level and score-level approaches are proposed for spatial-temporal fusion of information to combine information over frames, in a framework based on ensembles of GMM-UBM (Universal Background Models). At the feature-level, features in a batch of multiple frames are combined and fed to the ensemble, whereas at the score-level the outcome of ensemble for individual frames are combined. Results indicate that feature-level fusion provides higher level of accuracy in a very efficient way.

  • 1
  • 11