Hand gesture recognition system based in computer vision and machine learning

"Lecture notes in computational vision and biomechanics series, ISSN 2212-9391, vol. 19"

Vision-based portuguese sign language recognition system

Vision-based hand gesture recognition is an area of active current research in computer vision and machine learning. Being a natural way of human interaction, it is an area where many researchers are working on, with the goal of making human computer interaction (HCI) easier and natural, without the need for any extra devices. So, the primary goal of gesture recognition research is to create systems, which can identify specific human gestures and use them, for example, to convey information. For that, vision-based hand gesture interfaces require fast and extremely robust hand detection, and gesture recognition in real time. Hand gestures are a powerful human communication modality with lots of potential applications and in this context we have sign language recognition, the communication method of deaf people. Sign lan- guages are not standard and universal and the grammars differ from country to coun- try. In this paper, a real-time system able to interpret the Portuguese Sign Language is presented and described. Experiments showed that the system was able to reliably recognize the vowels in real-time, with an accuracy of 99.4% with one dataset of fea- tures and an accuracy of 99.6% with a second dataset of features. Although the im- plemented solution was only trained to recognize the vowels, it is easily extended to recognize the rest of the alphabet, being a solid foundation for the development of any vision-based sign language recognition user interface system.

Detection of dangerous situations using a smart internet of things system

The Internet of Things (IoT) is a concept that can foster the emergence of innovative applications. In order to minimize parents’s concerns about their children’s safety, this paper presents the design of a smart Internet of Things system for identifying dangerous situations. The system will be based on real time collection and analysis of physiological signals monitored by non-invasive and non-intrusive sensors, Frequency IDentification (RFID) tags and a Global Positioning System (GPS) to determine when a child is in danger. The assumption of a state of danger is made taking into account the validation of a certain number of biometric reactions to some specific situations and according to a self-learning algorithm developed for this architecture. The results of the analysis of data collected and the location of the child will be able in real time to child’s care holders in a web application.

Logic programming and artificial neural networks in breast cancer detection

About 90% of breast cancers do not cause or are capable of producing death if detected at an early stage and treated properly. Indeed, it is still not known a specific cause for the illness. It may be not only a beginning, but also a set of associations that will determine the onset of the disease. Undeniably, there are some factors that seem to be associated with the boosted risk of the malady. Pondering the present study, different breast cancer risk assessment models where considered. It is our intention to develop a hybrid decision support system under a formal framework based on Logic Programming for knowledge representation and reasoning, complemented with an approach to computing centered on Artificial Neural Networks, to evaluate the risk of developing breast cancer and the respective Degree-of-Confidence that one has on such a happening.

Structural analysis of the masonry envelope of Ica Cathedral, Peru

Dissertação de mestrado em Structural Analysis of Monuments and Historical Constructions

The influence of nitrogen and oxygen additions on the thermal characteristics of aluminium-based thin films

The ternary aluminium oxynitride (AlNxOy) system offers the possibility to obtain a wide range of properties by tailoring the ratio between pure Al, AlNx and AlOy and therefore opening a significant number of possible applications. In this work the thermal behaviour of AlNxOy thin films was analysed by modulated infrared radiometry (MIRR), taking as reference the binary AlOy and AlNx systems. MIRR is a non-contact and non-destructive thermal wave measurement technique based on the excitation, propagation and detection of temperature oscillations of very small amplitudes. The intended change of the partial pressure of the reactive gas (N2 and/or O2) influenced the target condition and hence the deposition characteristics which, altogether, affected the composition and microstructure of the films. Based on the MIRR measurements and their qualitative and quantitative interpretation, some correlations between the thermal transport properties of the films and their chemical/physical properties have been found. Furthermore, the potential of such technique applied in this oxynitride system, which present a wide range of different physical responses, is also discussed. The experimental results obtained are consistent with those reported in previous works and show a high potential to fulfil the demands needed for the possible applications of the systems studied. They are clearly indicative of an adequate thermal response if this particular thin film system is aimed to be applied in small sensor devices or in electrodes for biosignal acquisition, such as those for electroencephalography or electromyography as it is the case of the main research area that is being developed in the group.

Hand gesture recognition system based in computer vision and machine learning: Applications on human-machine interaction

Tese de Doutoramento em Engenharia de Eletrónica e de Computadores

Modelação, simulação e implementação de agitação acústica para aplicações em microfluídica

Tese de Doutoramento (Programa Doutoral em Engenharia Biomédica)

A bio-inspired computational model for motion detection

Tese de Doutoramento (Programa Doutoral em Engenharia Biomédica)

A spectrophotometry based blood typing device

Blood typing is a crucial step before any blood transfusion. However, sometimes in emergency situations there is no time to determine the blood of the patient beforehand. In this cases, O negative blood type is administered, which has a lesser incompatibility risk to the patient. Nowadays, the “gold standard” blood typing devices cannot be used in emergency situations due to their high response time (about 30 minutes). This paper reports a blood typing device that determines the ABO and Rh human phenotypes. This device is fast (response time – 5 min), low-cost, and portable. Characteristics that make it suitable to be used in emergency situations, contributing to a higher efficiency and quality in healthcare.

Detection of incipient left ventricular hypertrophy in mild to moderate arterial hypertension with normal electrocardiogram and echocardiogram: a new use for signal-averaged electrocardiography

OBJECTIVE: To assess signal-averaged electrocardiogram (SAECG) for diagnosing incipient left ventricular hypertrophy (LVH). METHODS: A study with 115 individuals was carried out. The individuals were divided as follows: GI - 38 healthy individuals; GII - 47 individuals with mild to moderate hypertension and normal findings on echocardiogram and ECG; and GIII - 30 individuals with hypertension and documented LVH. The magnitude vector of the SAECG was analyzed with the high-pass cutoff frequency of 40 Hz through the bidirectional four-pole Butterworth high-pass digital filter. The mean quadratic root of the total QRS voltage (RMST) and the two-dimensional integral of the QRS area of the spectro-temporal map were analyzed between 0 and 30 Hz for the frequency domain (Int FD), and between 40 and 250 Hz for the time domain (Int TD). The electrocardiographic criterion for LVH was based on the Cornell Product. Left ventricular mass was calculated with the Devereux formula. RESULTS: All parameters analyzed increased from GI to GIII, except for Int FD (GII vs GIII) and RMST log (GII vs GIII). Int TD showed greater accuracy for detecting LVH with an appropriate cutoff > 8 (sensitivity of 55%, specificity of 81%). Positive values (> 8) were found in 56.5% of the G II patients and in 18.4% of the GI patients (p< 0.0005). CONCLUSION: SAECG can be used in the early diagnosis of LVH in hypertensive patients with normal ECG and echocardiogram.

A novel gene expression signature in peripheral blood mononuclear cells for early detection of colorectal cancer.

BACKGROUND: Early detection and treatment of colorectal adenomatous polyps (AP) and colorectal cancer (CRC) is associated with decreased mortality for CRC. However, accurate, non-invasive and compliant tests to screen for AP and early stages of CRC are not yet available. A blood-based screening test is highly attractive due to limited invasiveness and high acceptance rate among patients. AIM: To demonstrate whether gene expression signatures in the peripheral blood mononuclear cells (PBMC) were able to detect the presence of AP and early stages CRC. METHODS: A total of 85 PBMC samples derived from colonoscopy-verified subjects without lesion (controls) (n = 41), with AP (n = 21) or with CRC (n = 23) were used as training sets. A 42-gene panel for CRC and AP discrimination, including genes identified by Digital Gene Expression-tag profiling of PBMC, and genes previously characterised and reported in the literature, was validated on the training set by qPCR. Logistic regression analysis followed by bootstrap validation determined CRC- and AP-specific classifiers, which discriminate patients with CRC and AP from controls. RESULTS: The CRC and AP classifiers were able to detect CRC with a sensitivity of 78% and AP with a sensitivity of 46% respectively. Both classifiers had a specificity of 92% with very low false-positive detection when applied on subjects with inflammatory bowel disease (n = 23) or tumours other than CRC (n = 14). CONCLUSION: This pilot study demonstrates the potential of developing a minimally invasive, accurate test to screen patients at average risk for colorectal cancer, based on gene expression analysis of peripheral blood mononuclear cells obtained from a simple blood sample.

Octopus Standard Automated Perimetry, Pulsar Perimetry, Moorfields Motion Displacement Test and Heidelberg Retinal Tomography in Glaucoma Detection - A Comparison of Diagnostic Accuracy

Purpose: To investigate the accuracy of 4 clinical instruments in the detection of glaucomatous damage. Methods: 102 eyes of 55 test subjects (Age mean = 66.5yrs, range = [39; 89]) underwent Heidelberg Retinal Tomography (HRTIII), (disc area<2.43); and standard automated perimetry (SAP) using Octopus (Dynamic); Pulsar (TOP); and Moorfields Motion Displacement Test (MDT) (ESTA strategy). Eyes were separated into three groups 1) Healthy (H): IOP<21mmHg and healthy discs (clinical examination), 39 subjects, 78 eyes; 2) Glaucoma suspect (GS): Suspicious discs (clinical examination), 12 subjects, 15 eyes; 3) Glaucoma (G): progressive structural or functional loss, 14 subjects, 20 eyes. Clinical diagnostic precision was examined using the cut-off associated with the p<5% normative limit of MD (Octopus/Pulsar), PTD (MDT) and MRA (HRT) analysis. The sensitivity, specificity and accuracy were calculated for each instrument. Results: See table Conclusions: Despite the advantage of defining glaucoma suspects using clinical optic disc examination, the HRT did not yield significantly higher accuracy than functional measures. HRT, MDT and Octopus SAP yielded higher accuracy than Pulsar perimetry, although results did not reach statistical significance. Further studies are required to investigate the structure-function correlations between these instruments.

Quantifying consistency of Event Related Potentials across subjects based on single-trial topographic analysis

Introduction: Non-invasive brain imaging techniques often contrast experimental conditions across a cohort of participants, obfuscating distinctions in individual performance and brain mechanisms that are better characterised by the inter-trial variability. To overcome such limitations, we developed topographic analysis methods for single-trial EEG data [1]. So far this was typically based on time-frequency analysis of single-electrode data or single independent components. The method's efficacy is demonstrated for event-related responses to environmental sounds, hitherto studied at an average event-related potential (ERP) level. Methods: Nine healthy subjects participated to the experiment. Auditory meaningful sounds of common objects were used for a target detection task [2]. On each block, subjects were asked to discriminate target sounds, which were living or man-made auditory objects. Continuous 64-channel EEG was acquired during the task. Two datasets were considered for each subject including single-trial of the two conditions, living and man-made. The analysis comprised two steps. In the first part, a mixture of Gaussians analysis [3] provided representative topographies for each subject. In the second step, conditional probabilities for each Gaussian provided statistical inference on the structure of these topographies across trials, time, and experimental conditions. Similar analysis was conducted at group-level. Results: Results show that the occurrence of each map is structured in time and consistent across trials both at the single-subject and at group level. Conducting separate analyses of ERPs at single-subject and group levels, we could quantify the consistency of identified topographies and their time course of activation within and across participants as well as experimental conditions. A general agreement was found with previous analysis at average ERP level. Conclusions: This novel approach to single-trial analysis promises to have impact on several domains. In clinical research, it gives the possibility to statistically evaluate single-subject data, an essential tool for analysing patients with specific deficits and impairments and their deviation from normative standards. In cognitive neuroscience, it provides a novel tool for understanding behaviour and brain activity interdependencies at both single-subject and at group levels. In basic neurophysiology, it provides a new representation of ERPs and promises to cast light on the mechanisms of its generation and inter-individual variability.

Multi-scale support vector algorithms for hot spot detection and modelling

The algorithmic approach to data modelling has developed rapidly these last years, in particular methods based on data mining and machine learning have been used in a growing number of applications. These methods follow a data-driven methodology, aiming at providing the best possible generalization and predictive abilities instead of concentrating on the properties of the data model. One of the most successful groups of such methods is known as Support Vector algorithms. Following the fruitful developments in applying Support Vector algorithms to spatial data, this paper introduces a new extension of the traditional support vector regression (SVR) algorithm. This extension allows for the simultaneous modelling of environmental data at several spatial scales. The joint influence of environmental processes presenting different patterns at different scales is here learned automatically from data, providing the optimum mixture of short and large-scale models. The method is adaptive to the spatial scale of the data. With this advantage, it can provide efficient means to model local anomalies that may typically arise in situations at an early phase of an environmental emergency. However, the proposed approach still requires some prior knowledge on the possible existence of such short-scale patterns. This is a possible limitation of the method for its implementation in early warning systems. The purpose of this paper is to present the multi-scale SVR model and to illustrate its use with an application to the mapping of Cs137 activity given the measurements taken in the region of Briansk following the Chernobyl accident.