UMATUG: A dataset of inertial signals of older and young adults using a gerontologic simulator collected during instrumented Timed Up and Go (iTUG) tests.

Timed Up and Go (TUG) test is one of the most popular clinical tools aimed at the assessment of functional mobility and fall risk in older adults. The automation of the analysis of TUG movements is of great medical interest not only to speed up the test but also to maximize the information inferred from the subjects under study. In this context, this article describes a dataset collected from a cohort of 69 experimental subjects (including 30 adults over 60 years), during the execution of several repetitions of the TUG test. In particular, the dataset includes the measurements gathered with four wearables devices embedding four sensors (accelerometer, gyroscope magnetometer and barometer) located on four body locations (waist, wrist, ankle and chest). As a particularity, the dataset also includes the same measurements recorded when the young subjects repeat the test while wearing a commercial geriatric simulator, consisting of a set of weighted vests and other elements intended to replicate the limitations caused by aging. Thus, the generated dataset also enables the investigation into the potential of such tools to emulate the actual dynamics of older individuals.

Differentiation of Saccadic Eye Movement Signals.

Saccadic electrooculograms are discrete biosignals that contain the instantaneous angular position of the human eyes as a response to saccadic visual stimuli. These signals are essential to monitor and evaluate several neurological diseases, such as Spinocerebellar Ataxia type 2 (SCA2). For this, biomarkers such as peak velocity, latency and duration are computed. To compute these biomarkers, we need to obtain the velocity profile of the signals using numerical differentiation methods. These methods are affected by the noise present in the electrooculograms, specially in subjects that suffer neurological diseases. This noise complicates the comparison of the differentiation methods using real saccadic signals because of the impossibility of establishing exact saccadic onset and offset points. In this work, we evaluate 16 differentiation methods by the design of an experiment that uses synthetic saccadic electrooculograms generated from parametric models of both healthy subjects and subjects suffering from Spinocerebellar Ataxia type 2 (SCA2). For these synthetic electrooculograms the exact velocity profile is known, hence we can use them as a reference for comparison and error computing for the tasks of saccade identification and saccade biomarker computing. Finally, we identify the best fitting method or methods for each evaluated task.

A hybrid unsupervised-Deep learning tandem for electrooculography time series analysis.

Medical data are often tricky to get mined for patterns even by the generally demonstrated successful modern methodologies of deep learning. This paper puts forward such a medical classification task, where patient registers of two of the categories are sometimes hard to be distinguished because of samples showing characteristics of both labels in turn in several repetitions of the screening procedure. To this end, the current research appoints a pre-processing clustering step (through self-organizing maps) to group the data based on shape similarity and relabel it accordingly. Subsequently, a deep learning approach (a tandem of convolutional and long short-term memory networks) performs the training classification phase on the 'cleaned' samples. The dual methodology was applied for the computational diagnosis of electrooculography tests within spino-cerebral ataxia of type 2. The accuracy obtained for the discrimination into three classes was of 78.24%. The improvement that this duo brings over the deep learner alone does not stem from significantly higher accuracy results when the performance is considered for all classes. The major finding of this combination is that half of the presymptomatic cases were correctly found, in opposition to the single deep model, where this category was sacrificed by the learner in favor of a good accuracy overall. A high accuracy in general is desirable for any medical task, however the correct identification of cases before the symptoms become evident is more important.