C-BER - Indexed Articles in Conferences

Permanent URI for this collection

http://localhost:4000/handle/123456789/331

Browse

Browsing C-BER - Indexed Articles in Conferences by Issue Date

Jump to a point in the index:
  • Item
    Single-pixel hyperspectral camera based on compressive sensing
    ( 2012) Francisco Araújo ; Filipe Tiago Magalhães ; Faramarz Farahi ; Mehrdad Abolbashari ; Miguel Velhote Correia
  • Item
    Biological imaging with high dynamic range using compressive imaging technique
    ( 2012) Gelareh Babaie ; Faramarz Farahi ; Mehrdad Abolbashari ; Filipe Tiago Magalhães ; Miguel Velhote Correia ; Francisco Araújo ; Awad Gerges
    Scenes in real world have dynamic range of radiation that cannot be captured by conventional cameras. High dynamic range imaging is a technique to capture detail images where, in the field of image, intensity variation is extreme. This technique is very useful for biological imaging where the samples have very bright and very dark regions and both parts have useful information. In this article we propose a novel high dynamic range imaging technique based on compressive imaging that uses one single detector instead of camera (array of detectors) to capture an image. Combination of high dynamic range imaging and compressive imaging benefits from imaging with high dynamic range of radiation and advantages of compressive sampling; namely, imaging at regions of optical spectrum where conventional cameras are not readily available and single detectors are available. Additionally, as its name suggests, this technique requires less number of samples (compared to raster scanning). Our experimen
  • Item
    MicroEye - Imager with compressive sensing capability
    ( 2012) Filipe Tiago Magalhães ; Francisco Araújo ; Miguel Velhote Correia ; Vítor Grade Tavares ; Hugo Rodrigues Gonçalves
  • Item
    Compressive Sensing Based Face Detection without Explicit Image Reconstruction Using Support Vector Machines
    ( 2013) Magalhaes,F ; Sousa,R ; Araujo,FM ; Miguel Velhote Correia
    The novel theory of compressive sensing takes advantage of the sparsity or compressibility of a signal in a specific domain allowing the assessment of its full representation from fewer measurements. In this work we tailored the concept of compressive sensing to assess the intrinsic discriminative capability of this method to distinguish human faces from objects. Afterwards we enrolled through a feature selection study to empirically determine the minimum amount of measurements required to properly detect human faces. This work was concluded with a comparative experiment against the SIFT descriptor. We determined that using only 40 measurements conducted by compressing sensing one is capable of capturing the relevant information that enable one to properly discriminate human faces from objects.
  • Item
    Monitoring of bedridden patients: Development of a fall detection tool
    ( 2013) Carmo Vilas Boas ; Silva,P ; Correia,MV ; Correia,MV ; Miguel Velhote Correia ; Cunha,SR ; Cunha,SR ; Cunha,SR
    Falls of patients are an important issue in hospitals, it causes severe injuries to the patients, increases hospitalization time and treatment costs. The detection of a fall, in time, provides faster rescue to the patient, preventing more serious injuries, as well as saving nursing time. The MovinSense (R) is an electronic device designed for monitoring patients to prevent pressure sores, and the main goal of this work was to develop a new tool for this device, with the purpose of detecting if the patient has fallen from the hospital bed, without changing any of the device original features. Experiments for gathering data samples of inertial signals of falling from the bed were obtained using the device. For fall detection a sensitivity of 72% and specificity of 100% were reached. Another algorithm was developed to detect if the patient got out of his/her bed.
  • Item
    Wearable sensors for the prophylaxis of lower limb pathologies
    ( 2013) Abreu,MJ ; Catarino,A ; Rocha,AM ; Derogarian,F ; Dias,R ; Da Silva,JM ; João Canas Ferreira ; Vítor Grade Tavares ; Miguel Velhote Correia
    In this paper a new wearable locomotion data capture system for gait analysis is presented. The system under development intends to help clinicians to detect and identify mobility impairments as well as to evaluate the effectiveness of surgical or rehabilitation intervention. The proposed system allows the measurement of kinematic and biomechanical parameters in a practical and comfortable weft knitted legging, in which the sensors are incorporated.
  • Item
    Monitoring of bedridden patients: Development of a fall detection tool
    ( 2013) Vilas Boas,M ; Silva,P ; Cunha,SR ; Miguel Velhote Correia
    Falls of patients are an important issue in hospitals nowadays; it causes severe injuries, increases hospitalization time and treatment costs. The detection of a fall, in time, provides faster rescue to the patient, preventing more serious injuries, as well as saving nursing time. The MovinSense (R) is an electronic device designed for monitoring patients to prevent pressure sores, and the main goal of this work was to develop a new tool for this device, with the purpose of detecting if the patient has fallen from the hospital bed, without changing any of the device's original features. Experiments for gathering data samples of inertial signals of falling from the bed were obtained using the device. For fall detection a sensitivity of 72% and specificity of 100% were reached. Another algorithm was developed to detect if the patient got out of his/her bed.
  • Item
    ECG Delineation and Morphological Analysis for Firefighters Tasks Differentiation
    ( 2013) Bras,S ; Fernandes,JM ; João Paulo Cunha
    Between first responder professionals, firefighters registered the highest number of deaths on duty. An abnormal high proportion is associated with cardiovascular events. Our main goal is to identify fatigue/stress during daily routine activities, focusing on the cardiovascular analysis. To accomplish this purpose, ECG wave morphological alterations are analyzed. It was observed that the RR, PP and ST segment significantly differentiate the most stressful tasks from the others.
  • Item
    FIREMAN
    ( 2013) Marques,F ; Azevedo,P ; João Paulo Cunha ; Cunha,MB ; Brás,S ; Fernandes,JM
  • Item
    FIREMAN: Firefighter team breathing management system using android
    ( 2013) Marques,F ; Azevedo,P ; João Paulo Cunha ; Cunha,MB ; Bras,S ; Fernandes,JM
    In this paper we propose FIREMAN, a low cost system for online monitoring of firefighters ventilation patterns when using Self-Contained Breathing Apparatus (SCBA), based on a specific hardware device attached to SCBA and a Smartphone application. The system implementation allows the detection of relevant ventilation patterns while providing feasible and accurate estimation of SCBA air consumption.
  • Item
    MonitorMe: Online video monitoring for first responders using a smartphone
    ( 2013) Rocha,AP ; Pereira,O ; Ribeiro,D ; Fernandes,JM ; João Paulo Cunha
    Video can be a valuable source of information for monitoring first responders during operations in the field. In this paper we propose the MonitorMe, an application that supports online video monitoring of first responders. MonitorMe allows capturing video from a personal perspective, using a smartphone camera, and sending it to a remote observer. In order to reduce battery consumption and bandwidth usage, MonitorMe modulates the video frame rate according to the user activity/speed. The latter are estimated using the smartphone built-in accelerometer. The results have shown the potential of MonitorMe as a reliable non-GPS solution, which can be used for remote online monitoring of first responders in action. © 2013 IEEE.
  • Item
    ECG delineation and morphological analysis for firefighters tasks differentiation
    ( 2013) Bras,S ; Fernandes,JM ; João Paulo Cunha
    Between first responder professionals, firefighters registered the highest number of deaths on duty. An abnormal high proportion is associated with cardiovascular events. Our main goal is to identify fatigue/stress during daily routine activities, focusing on the cardiovascular analysis. To accomplish this purpose, ECG wave morphological alterations are analyzed. It was observed that the RR, PP and ST segment significantly differentiate the most stressful tasks from the others. © 2013 IEEE.
  • Item
    An I2C Based Mixed-Signal Test and Measurement Infrastructure
    ( 2014) Salazar Escobar,AJS ; José Machado da Silva ; Miguel Velhote Correia
    The framework being proposed addresses the test and measurement of circuits and systems populated with varying types of sensors and functional blocks, among which one can find embedded test instruments. Its conceptual functionality is based on four types of operations: setup, capture, process, and scan (SCPS), and aims to provide a unifying methodology for managing and synchronizing test operations and instruments. The generalized physical structure and examples of operating commands are described. An application illustrates its use in a particular case.
  • Item
    Optic Disk Localization for Gray-Scale Retinal Images Based on Patch Filtering
    ( 2014) Sattar,F ; Aurélio Campilho ; Kamel,M
    In this paper, an optic disk (OD) localization method is proposed for the retinal images based on a novel patch filtering approach. The patch filtering has been performed sequentially based on clustering in two stages. In the first stage, the patches are selected exploiting an 'isotropic' measure based on the ratio of maximum and minimum eigenvalues of the moment matrix representing the structure tensor. In the second stage, the patch filtering is based on the saliency measure. Finally, the optic disk is located from the centroids of the selected patches. Promising results are obtained for the low-contrast pathological retinal images using STARE database providing high localization accuracy.
  • Item
    Monitoring of plantar forces and surfboard's movement: Alternative to understand the injuries mechanism
    ( 2014) De Bona,DD ; Marques,MA ; Borgonovo Santos,M ; Miguel Velhote Correia
    The concern about injuries in sport are evident due to the implications it carries. To have the knowledge of the mechanisms of injuries is important either to prevent and recovery. This context generates the appropriate scenario to develop an electronic solution to measure dynamically the Center of Pressure (CoP) and surfboard's movement and support the understanding of the mechanisms responsible for the occurrence of injuries. Two matrices composed by 24 force sensors and Inertial Measurement Unit (IMU) controlled by ATEMEGA1280 microcontroller were developed. This system was tested using a dynamic protocol using one unstable structure at the bottom of the surfboard. The results have shown that the CoP displacement was largest during the tests that presented great rotation changes. Furthermore, the power oscillations were greater during transition moments. The proposed system is able to measure biomechanical variables dynamically, i.e., force, and surfboard's angle pitch and roll. This report reviews the surf injuries in literature and describes the electronic device used beyond to present the results of the tests performed. © 2014 IEEE.
  • Item
    Parkinson's Disease Assessment Based on Gait Analysis Using an Innovative RGB-D Camera System
    ( 2014) Rocha,AP ; Hugo Miguel Choupina ; Fernandes,JM ; Rosas,MJ ; Vaz,R ; João Paulo Cunha
    Movement-related diseases, such as Parkinson's disease (PD), progressively affect the motor function, many times leading to severe motor impairment and dramatic loss of the patients' quality of life. Human motion analysis techniques can be very useful to support clinical assessment of this type of diseases. In this contribution, we present a RGB-D camera (Microsoft Kinect) system and its evaluation for PD assessment. Based on skeleton data extracted from the gait of three PD patients treated with deep brain stimulation and three control subjects, several gait parameters were computed and analyzed, with the aim of discriminating between non-PD and PD subjects, as well as between two PD states (stimulator ON and OFF). We verified that among the several quantitative gait parameters, the variance of the center shoulder velocity presented the highest discriminative power to distinguish between non-PD, PD ON and PD OFF states (p = 0.004). Furthermore, we have shown that our low-cost portable system can be easily mounted in any hospital environment for evaluating patients' gait. These results demonstrate the potential of using a RGB-D camera as a PD assessment tool.
  • Item
    Precise 3D deep brain stimulation electrode location based on multimodal neuroimage fusion
    ( 2014) Nádia Moreira Silva ; Rozanski,VE ; Sérgio Miguel Tafula ; João Paulo Cunha
    The success of neurosurgery strongly depends on the pre-neurosurgical evaluation phase, in which the delineation of the areas to be removed or to be stimulated must be very accurate. For patients undergoing Deep Brain Stimulation (DBS) it is vital the delineation of the target area prior to surgery, and after the implantation of the DBS lead to confirm the electrodes positioning. In this paper we present a system to accurately determine the 3D position of DBS electrodes implanted within the brain of Parkinson and Dystonia patients. The system was tested using a multimodal dataset from 16 patients (8 with Parkinson's disease and 8 with dystonia) and, on average, the differences between the detected electrodes positions and the ones estimated manually by an experienced physician were less than a voxel in all cases. Copyright
  • Item
    Feature-based supervised lung nodule segmentation
    ( 2014) Campos,DM ; Simoes,A ; Ramos,I ; Aurélio Campilho
    Lung nodule segmentation allows for automatic measurement of the nodule's size or volume which is of utmost importance in lung cancer diagnosis. It is a challenging task since there are many different types of nodules (solid or non-solid, solitary or multiple, etc). A supervised lung nodule segmentation method uses a shape-based, contrast-based and intensity-based feature set to produce three preliminary segmentations and an artificial neural network to obtain a more accurate segmentation. This method was applied to 20 computer tomography studies, all containing nodules. The data has 10 images of solid nodules and 10 images of ground glass opacity nodules, all with ground-truth. The segmentation uses a region growing approach and the volumetric shape index is used for nodule detection and providing a seed point. In the first and second segmentation the probability of each neighbor belonging to the nodule is estimated using the volumetric shape index and the convergence index filter, respectively. The third segmentation is obtained using a feature set region regression method where for each neighbor the probability of belonging to the nodule or not is obtained using k nearest neighbor regression. Then, using a leave-one out method, an artificial neural network uses the three preliminary segmentations as input and is trained to obtain a more accurate segmentation. Results obtained a 12% relative volume error, 88% and 93% Jaccard and Dice coefficient respectively. © 2014, Springer International Publishing Switzerland.
  • Item
    Reliable Lung Segmentation Methodology by Including Juxtapleural Nodules
    ( 2014) Novo,J ; José Rouco Maseda ; Ana Maria Mendonça ; Aurélio Campilho
    In a lung nodule detection task, parenchyma segmentation is crucial to obtain the region of interest containing all the nodules. Thus, the challenge is to devise a methodology that includes all the lung nodules, particularly those close to the walls, as the juxtapleural nodules. In this paper, different region growing approaches are proposed for the automatic segmentation of the lung parenchyma. The methodology is organized in five different steps: first, the image intensity is corrected to improve the contrast of the lungs. With that, the fat area is obtained, automatically deriving the interior of the lung region. Then, the traquea is extracted by a 3D region growing, being subtracted from the lung region results. The next step is the division of the two lungs to guarantee that both are separated. And finally, the lung contours are refined to provide appropriate final results. The methodology was tested in 50 images taken from the LIDC image database, with a large variability and, specially, including different types of lung nodules. In particular, this dataset contains 158 nodules, from which 40 are juxtapleural nodules. Experimental results demonstrate that the method provides accurate lung regions, specially including the centers of 36 of the juxtapleural nodules. For the other 4, although the centers are not included, parts of their areas are retained in the segmentation, which is useful for lung nodule detection.
  • Item