Search

The increasing age of our society is connected to a rising number of people suffering from disorders. One such disorder is Parkinson’s disease (PD). Predictions indicate that the number of individuals affected by PD will more, than double in the future. Neurologists and data scientists consider handwriting as one of the motor symptoms of PD and recognize it as a valuable resource for detecting this disorder. Within this framework, we introduce an innovative system for Parkinson’s disease detection, which encompasses several key stages. The process commences with data augmentation and preprocessing, subsequently leading to the segmentation of online handwriting into Beta strokes. Following that, feature extraction is carried out utilizing the Beta-elliptical approach and the fuzzy perceptual detector. Finally, we employ bidirectional long short-term memory (BLSTM) for the classification task. To assess the performance of our system, we created a new online Arabic handwriting dataset designed for detecting Parkinson’s disease. The results we obtained affirm the efficacy of our proposed system. Through comprehensive evaluations conducted on the PaHaW dataset, we achieved good accuracy, thereby highlighting that our system surpasses the performance of existing systems.

Building upon the recent advances and successes in the application of deep learning to the medical field, we propose in this work a new approach to detect and classify early-stage Alzheimer patients using online handwriting (HW) loop patterns. To cope with the lack of training data prevalent in the tasks of classification of neuro-degenerative diseases from behavioral data, we investigate several data augmentation techniques. In this respect, compared to the traditional data augmentation techniques proposed for HW-based Parkinson detection, we investigate a variant of Generative Adversarial Networks (GANs), DoppelGANger, especially tailored for times series and hence suitable for synthesizing realistic online handwriting sequences. Based on a 1D-Convolutional Neural Network (1D-CNN) to perform Alzheimer classification, we show, on a real dataset related to HW and Alzheimer, that our DoppelGANger-based augmentation model allow the CNN to significantly outperform both the current state of the art and the other data augmentation techniques.

In this paper, we present a pressure characterization and normalization procedure for online handwritten acquisition. Normalization process has been tested in biometric recognition experiments (identification and verification) using online signature database MCYT, which consists of the signatures from 330 users. The goal is to analyze the real mismatch scenarios where users are enrolled with one stylus and then, later on, they produce some testing samples using a different stylus model with different pressure response. Experimental results show: 1) a saturation behavior in pressure signal 2) different dynamic ranges in the different stylus studied 3) improved biometric recognition accuracy by means of pressure signal normalization as well as a performance degradation in mismatched conditions 4) interoperability between different stylus can be obtained by means of pressure normalization. Normalization produces an improvement in signature identification rates higher than 7% (absolute value) when compared with mismatched scenarios.

Parkinson’s disease (PD) is the second most frequent neurodegenerative disease associated with several motor symptoms, including alterations in handwriting, also known as PD dysgraphia. Several computerized decision support systems for PD dysgraphia have been proposed, however, the associated challenges require new approaches for more accurate diagnosis. Therefore, this work adds spectral and cepstral handwriting features to the already-used temporal, kinematic and statistics handwriting features. First, we calculate temporal and kinematic features using displacement; statistic features $\left ({SF }\right)$ using displacement, and horizontal and vertical displacement; spectral $\left ({SDF }\right)$ and cepstral $\left ({CDF }\right)$ using displacement, horizontal and vertical displacement and pressure. Since the employed dataset (PaHaW) contains only 37 PD patients and 38 healthy control subjects (HC), then as the second step, we augment the percentage of the smaller training set to equal the larger. Next, we augment both classes to increase the training patient’s data and added random Gaussian noise in all augmentations. Third, the most relevant features were selected using the modified fast correlation-based filtering method (mFCBF). Finally, autoML is employed to train and test more than ten plain and ensembled classifiers. Experimental results show that adding spectral and cepstral features to temporal, kinematics and statistics features highly improved classification accuracy to 98.57%. Our proposed model, with lower computational complexities, outperforms conventional state-of-the-art models for all tasks, which is 97.62%.

Graphomotor disabilities (GD) are present in up to 30% of school-aged children and are associated with several symptoms in the field of kinematics. Although the basic kinematic features such as velocity, acceleration, and jerk were proved to effectively quantify these symptoms, a recent body of research identified that the theory of fractional calculus can be used to even improve the objective GD assessment. The goal of this study is to extend the current knowledge in this field and explore the abilities of several fractional order derivatives (FD) approximations to estimate the severity of GD in the children population. We enrolled 85 children attending the 3rd and 4th grade of primary school, who performed a combined loop task on a digitizing tablet. Their performance was rated by psychologists and the online handwriting signals were parametrised by kinematic features utilising three FD approximations: Grünwald-Letnikov's, Riemann-Liouville's, and Caputo's. In this study, we showed the differences across the employed FD approaches for the same kinematic handwriting features and their potential in GD analysis. The results suggest that the Riemann-Liouville's approximation in the field of quantitative GD analysis outperforms the other ones. Using this approach, we were able to estimate the overall score with a low error of 0.65 points, while the scale range is 4. In fact, the psychologists tend to make the error even higher.

School-aged children spend 31–60% of their time at school performing handwriting, which is a complex perceptual-motor skill composed of a coordinated combination of fine graphomotor movements. As up to 30% of them experience graphomotor difficulties (GD), timely diagnosis of these difficulties and therapeutic intervention are of great importance. At present, an objective, computerized decision support system for the identification and assessment of GD in school-aged children is still missing. In this study, we propose three novel advanced handwriting parametrization techniques based on modulation spectra, fractional order derivatives, and tunable Q-factor wavelet transform to improve the identification of GD using online handwriting. For this purpose, we analyzed signals acquired from 7 basic graphomotor tasks performed by 53 children attending 3rd and 4th grade at several primary schools around the Czech Republic. Combining the newly proposed features with the conventionally used ones, we were able to identify GD with 84% accuracy. In this study, we showed that using advanced parametrization of basic graphomotor movements can be potentially used to improve our capabilities of quantifying problems with the development of legible, fast-paced handwriting, and help with the early diagnosis of handwriting difficulties frequently manifested in developmental dysgraphia.