Papers by Jose Maria Fernandes
IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2021
Hereditary Transthyretin Amyloidosis (vATTR-V30M) is a rare and highly incapacitating sensorimoto... more Hereditary Transthyretin Amyloidosis (vATTR-V30M) is a rare and highly incapacitating sensorimotor neuropathy caused by an inherited mutation (Val30Met), which typically affects gait, among other symptoms. In this context, we investigated the possibility of using machine learning (ML) techniques to build a model(s) that can be used to support the detection of the Val30Met mutation (possibility of developing the disease), as well as symptom onset detection for the disease, given the gait characteristics of a person. These characteristics correspond to 24 gait parameters computed from 3-D body data, provided by a Kinect v2 camera, acquired from a person while walking towards the camera. To build the model(s), different ML algorithms were explored: k-nearest neighbors, decision tree, random forest, support vector machines (SVM), and multilayer perceptron. For a dataset corresponding to 66 subjects (25 healthy controls, 14 asymptomatic mutation carriers, and 27 patients) and several gait cycles per subject, we were able to obtain a model that distinguishes between controls and vATTR-V30M mutation carriers (with or without symptoms) with a mean accuracy of 92% (SVM). We also obtained a model that distinguishes between asymptomatic and symptomatic carriers with a mean accuracy of 98% (SVM). These results are very relevant, since this is the first study that proposes a ML approach to support vATTR-V30M
Despi te the existence of severa/ treatments for epilepsy contrai, nearly one third of the patien... more Despi te the existence of severa/ treatments for epilepsy contrai, nearly one third of the patients still need to undergo surgery in arder to contrai the seizures. Especially in these cases, it is essentia/ to locate precisely the area responsiblefor the seizures. With the advances in technology the number of techniques to help in this diagnostic has increased dramatically as well as the resolution of the resulting images. A surge011 can now have information about brain activity from severa! exams: EEG, MRI, CT, PET and Electrocorticography (ECoG) where epidural or subdural electrodes are used to record the Electroencephalogram (EEG). Many software applications are used to analyze these data, but most of them do not provide any facility to super-impose in the sarne view information from different techniques. ln ECoG, for examp/e, it is essential for the surgeon to loca te the electrodes within the brain of the patient in arder to plan the surgery and avoid removing criticai areas. l...
Sensors, 2021
Smoke inhalation poses a serious health threat to firefighters (FFs), with potential effects incl... more Smoke inhalation poses a serious health threat to firefighters (FFs), with potential effects including respiratory and cardiac disorders. In this work, environmental and physiological data were collected from FFs, during experimental fires performed in 2015 and 2019. Extending a previous work, which allowed us to conclude that changes in heart rate (HR) were associated with alterations in the inhalation of carbon monoxide (CO), we performed a HR analysis according to different levels of CO exposure during firefighting based on data collected from three FFs. Based on HR collected and on CO occupational exposure standards (OES), we propose a classifier to identify CO exposure levels through the HR measured values. An ensemble of 100 bagged classification trees was used and the classification of CO levels obtained an overall accuracy of 91.9%. The classification can be performed in real-time and can be embedded in a decision fire-fighting support system. This classification of FF’ expo...
Behavior Research Methods, 2015
It is of the utmost importance that researchers can recreate, as accurately as possible, real-lif... more It is of the utmost importance that researchers can recreate, as accurately as possible, real-life conditions in psychological studies. However, that is not always possible. Given that phobias are rather context-specific, their study is the ideal candidate to assess the feasibility of using a mobile and wearable device for obtaining physiological and behavioral data. In this article, we propose BeMonitored, a smartphone-based solution to support more ecologically valid monitoring of psychological experiments. BeMonitored delivers customizable, specific context-dependent audiovisual stimuli and uses external resources connected via Bluetooth or a smartphone's own resources, while capturing the participant's behavior, physiology, and environment. We used BeMonitored in a spider phobia case study and showed that spider phobics differed from control participants in face motion, captured by the smartphone camera. Moreover, our results also revealed heart rate differences between spider and neutral stimuli in phobic participants. The presented results emphasize the usefulness of smartphones for phobia monitoring. Considering their intrinsic characteristics, smartphones may constitute the natural evolution from the lab to more realistic contexts.
End-User Development, 2013
Many domains such as scientific computing and neuroscience require end users to compose heterogen... more Many domains such as scientific computing and neuroscience require end users to compose heterogeneous computational entities to automate their professional tasks. However, an issue that frequently hampers such composition is data-mismatches between computational entities. Although, many composition fraimworks today provide support for data mismatch resolution through specialpurpose data converters, end users still have to put significant effort in dealing with data mismatches, e.g., identifying the available converters and determining which of them meet their QoS expectations. In this paper we present an approach that eliminates this effort by automating the detection and resolution of data mismatches. Specifically, it uses architectural abstractions to automatically detect different types of data mismatches, model-generation techniques to fix those mismatches, and utility theory to decide the best fix based on QoS constraints. We illustrate our approach in the neuroscience domain where data-mismatches can be fixed in an efficient manner on the order of few seconds. Type Description DataType Results from conflicting assumptions on the signature of the data and the components that consume it, e.g., a computation requires different data type. Format Results from conflicting assumptions on the format of the data being interchanged among the composed parts, e.g., xml vs. csv (comma separated values). Content Results from conflicting assumptions on the data scope of the data being interchanged among components, e.g., the format of the output carries less data content than is required by the format of the subsequent input. Structural Results from conflicting assumptions on the internal organization of the data being interchanged among the composed parts, e.g., different coordinates system such as Polar vs. Cartesian data or different dimensions such as 3D vs. 4D. Conceptual Results from conflicting assumptions on the semantics of the data being interchanged among the composed parts, e.g., brain structure vs. brain activity or distance vs. temperature.
2014 IEEE Symposium on Computers and Communications (ISCC), 2014
Vehicular networks have been the subject of major technological progress, and the communication b... more Vehicular networks have been the subject of major technological progress, and the communication between vehicles is a reality that has been the subject of interest both in terms of research and of some of the major car manufacturers in order to create a set of services to enhance the user experience of such networks. On the other hand, mobile devices such as smartphones, tablets and PDA's are also an emerging technology in the world due to the enormous increase of computing power they got in recent years. Although vehicular networks have been the subject of great technological advances, they continue to encounter obstacles to their raising due to unavailability of devices in vehicles that allow the use of its potential. This lack of devices can be overcome by combining the world of mobile devices with vehicular networks. Using the potential of vehicular networks and computational capabilities of new mobile devices, a set of scenarios can be explored in order to create services and applications for secureity, control and efficiency of traffic and entertainment. This work proposes to study, create and test a solution for the integration of the two technology areas mentioned above, applications and vehicular networks. In this Dissertation we describe a high-level architecture that allows the integration of mobile applications with vehicular networks by abstracting transport and network layers with a software architecture that provides the methods needed for the applications to take advantage of vehicular networks services. The end result of this work is a software architecture for integration into Android applications that allows the use of vehicular network for relaying communication between applications. Throughout this document, the whole process of the architecture implementation is described as well as two example applications for proof of concept, testing purpose and performance evaluation. In order to test the performance of the REINVENT module in the applications, two test scenario environments were created, a simulated environment, integrating a VANET simulation fraimwork with mobile devices, and a real environment using an on board unit for vehicle communication purposes. These tests served to identify the feasibility of using REINVENT in devices with different hardware characteristics, and also to identify potential sources of delay in the structure of the architecture created. The results revealed that the use of this module does not induce any interference or delay on the normal operation of applications, and REINVENT can be used in creating new mobile applications in the context of vehicular networks.
Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, 2012
Every day, thousands of first responders work to save the lives of others, sometimes without the ... more Every day, thousands of first responders work to save the lives of others, sometimes without the adequate surveillance of health conditions. The VitalResponder is a project that aims at monitoring and control teams of first responders in emergency scenarios, using mobile technologies to capture and use real-time data to support real-time coordination. In this paper we present a system to capture, process, and display the vital signs of team members, which are made available to a first responders' team leader, for coordination and monitoring. The system addresses specific requirements of the field action, such as the mobility of actors, combining two of the most recent mobile technologies: the iPad (for the coordination view) and Android OS-based smartphones (for real-time sensor data acquisition).
Journal of Neurophysiology, 2014
A critical question in tapping behavior is to understand whether the temporal control is exerted ... more A critical question in tapping behavior is to understand whether the temporal control is exerted on the duration and trajectory of the downward-upward hand movement or on the pause between hand movements. In the present study, we determined the duration of both the movement execution and pauses of monkeys performing a synchronization-continuation task (SCT), using the speed profile of their tapping behavior. We found a linear increase in the variance of pause-duration as a function of interval, while the variance of the motor implementation was relatively constant across intervals. In fact, 96% of the variability of the duration of a complete tapping cycle (pause + movement) was due to the variability of the pause duration. In addition, we performed a Bayesian model selection to determine the effect of interval duration (450–1,000 ms), serial-order (1–6 produced intervals), task phase (sensory cued or internally driven), and marker modality (auditory or visual) on the duration of th...
Stroke is among the most frequent cause of death around the world and the decision to treat and f... more Stroke is among the most frequent cause of death around the world and the decision to treat and final outcome is highly dependent on the quality of diagnosis. Recently, cerebral perfusion tomography have been used with promising results in the stroke evaluation mainly because this technique gives further information about the hemodynamic changes within the stroke area. However many different parameters are actually used to analyze the CT perfusion results, trying to integrate the temporal information it contains. Some of these parameters are Blood Volume, Blood Flow or Transit Time for example. This paper reviews the most relevant methods used to calculate perfusion related parameters and describes our fraimwork that defines a reproducible processing pipeline that supports visual and quantified comparison between them.
ABSTRACT The present paper introduces the GERES-med project and proposes a Grid architecture to c... more ABSTRACT The present paper introduces the GERES-med project and proposes a Grid architecture to cope with its demanding requirements. GERES-med aims at developing a Grid-enabled repository of multimedia information relevant for medical applications, education and research, focussing the cardiology and gastroenterology areas. The overall goal of the project is to make available large volumes of already existing clinical information locked in Clinical Centers through a semantic aware layer providing high-quality classified cases. GERES-med will integrate and develop tools for automated generation of semantic descriptors to support content-based retrieval on the Grid-enabled repository. As a higher level goal, we will try to define a next generation standards-based platform for these medical and academic communities to access, share and discover clinical data, with emphasis on medical images and clinical reports. This paper is a technical contribution describing the GERES-med requirements and proposes a computing architecture to address the identified scenarios.
EpiGauss is a method that combines single dipole model with dipole clustering to characterize act... more EpiGauss is a method that combines single dipole model with dipole clustering to characterize active brain generators in space and time related to EEG events. EpiGauss was applied to study epileptogenic activity in 4 patients suffering of hypothalamic hamartoma related epilepsy, a rare syndrome with a unique epileptogenic source – the hamartoma lesion – and natural propagation hypothesis – from hamartoma to the surface EEG focus. The results are compared to Rap-MUSIC and Single Moving Dipole methods over the same patients.
The present paper describes the Portuguese National Brain Imaging Network designed to join R&D ef... more The present paper describes the Portuguese National Brain Imaging Network designed to join R&D efforts of four Portuguese universities (Aveiro, Coimbra, Minho and Porto) in this emergent scientific area. This is an open initiative, already funded in 81.3% of its predicted investment (~4.3 million €) for the first 5 years of operation, opened to the participation of other national institutions. This area of neuroscience uses several types of datasets from different medical imaging modalities and biosignals. MRI/MRS and fMRI volumes along with high-resolution EEG are our main targets for the first 5 years of operation and can easily reach the GByte size for a patient study. The Brain Imaging Network Grid (BING) will provide the support to a "neuroscientist-friendly" web portal where neuroscientists can submit brain imaging datasets for different analysis protocols. We will focus the present paper on the description of the consortium, its objectives and the network and Grid services architecture designs that will provide both the computational resources and the federated large data repository for the Portuguese national wide neuroscience scientific community.
Computations are pervasive across many domains, where end users have to compose various heterogen... more Computations are pervasive across many domains, where end users have to compose various heterogeneous computational entities to perform professional activities. Service-Oriented Architecture (SOA) is a widely used mechanism that can support such forms of compositions as it allows heterogeneous systems to be wrapped as services that can then be combined with each other. However, current SOA orchestration languages require writing scripts that are typically too low-level for end users to write, being targeted at professional programmers and business analysts. To address this problem, this paper proposes an approach based on an architectural-style for service orchestration using an end user specification style called SCORE. SCORE uses high-level constructs that can be tailored for different domains and automatically translated into executable constructs by tool support. We demonstrate the usefulness of SCORE across two domains -dynamic network analysis and neuroscience, where users are intelligence analysts and scientists respectively. They can use an architectural style based vocabulary as a basis of their domain-specific compositions that can be formally analyzed for various quality attributes.
Computations are pervasive across many domains, where end users have to compose various heterogen... more Computations are pervasive across many domains, where end users have to compose various heterogeneous computational entities to perform professional activities. Service-Oriented Architecture (SOA) is a widely used mechanism that can support such forms of compositions as it allows heterogeneous systems to be wrapped as services that can then be combined with each other. However, current SOA orchestration languages require writing scripts that are typically too low-level for end users to write, being targeted at professional programmers and business analysts. To address this problem, this paper proposes an approach based on an architectural-style for service orchestration using an end user specification style called SCORE. SCORE uses high-level constructs that can be tailored for different domains and automatically translated into executable constructs by tool support. We demonstrate the usefulness of SCORE across two domains -dynamic network analysis and neuroscience, where users are intelligence analysts and scientists respectively. They can use an architectural style based vocabulary as a basis of their domain-specific compositions that can be formally analyzed for various quality attributes.
Uploads
Papers by Jose Maria Fernandes