This paper presents a novel class of systems assisting diagnosis and personalised assessment of diseases in healthcare. The targeted systems are end-to-end deep neural architectures that are designed (trained and tested) and subsequently used as whole systems, accepting raw input data and producing the desired outputs. Such architectures are state-of-the-art in image analysis and computer vision, speech recognition and language processing. Their application in healthcare for prediction and diagnosis purposes can produce high accuracy results and can be combined with medical knowledge to improve effectiveness, adaptation and transparency of decision making. The paper focuses on neurodegenerative diseases, particularly Parkinson's, as the development model, by creating a new database and using it for training, evaluating and validating the proposed systems. Experimental results are presented which illustrate the ability of the systems to detect and predict Parkinson's based on medical imaging information.

Neurodegenerative disorders, such as Alzheimer’s and Parkinson’s, constitute a major factor in long-term disability and are becoming more and more a serious concern in developed countries. As there are, at present, no effective therapies, early diagnosis along with avoidance of misdiagnosis seem to be critical in ensuring a good quality of life for patients. In this sense, the adoption of computer-aided-diagnosis tools can offer significant assistance to clinicians. In the present paper, we provide in the first place a comprehensive recording of medical examinations relevant to those disorders. Then, a review is conducted concerning the use of Machine Learning techniques in supporting diagnosis of neurodegenerative diseases, with reference to at times used medical datasets. Special attention has been given to the field of Deep Learning. In addition to that, we communicate the launch of a newly created dataset for Parkinson’s disease, containing epidemiological, clinical and imaging data, which will be publicly available to researchers for benchmarking purposes. To assess the potential of the new dataset, an experimental study in Parkinson’s diagnosis is carried out, based on state-of-the-art Deep Neural Network architectures and yielding very promising accuracy results.

No abstract

No abstract

No abstract

Figurative language (FL) seems ubiquitous in all social media discussion forums and chats, posing extra challenges to sentiment analysis endeavors. Identification of FL schemas in short texts remains largely an unresolved issue in the broader field of natural language processing, mainly due to their contradictory and metaphorical meaning content. The main FL expression forms are sarcasm, irony and metaphor. In the present paper, we employ advanced deep learning methodologies to tackle the problem of identifying the aforementioned FL forms. Significantly extending our previous work (Potamias et al., in: International conference on engineering applications of neural networks, Springer, Berlin, pp 164–175, 2019), we propose a neural network methodology that builds on a recently proposed pre-trained transformer-based network architecture which is further enhanced with the employment and devise of a recurrent convolutional neural network. With this setup, data preprocessing is kept in minimum. The performance of the devised hybrid neural architecture is tested on four benchmark datasets, and contrasted with other relevant state-of-the-art methodologies and systems. Results demonstrate that the proposed methodology achieves state-of-the-art performance under all benchmark datasets, outperforming, even by a large margin, all other methodologies and published studies.

Training in the random neural network (RNN) is generally speci®ed as the minimization of an appropriate error function with respect to the parameters of the network (weights corresponding to positive and negative connections). We propose here a technique for error minimization that is based on the use of quasi-Newton optimization techniques. Such techniques o er more sophisticated exploitation of the gradient information compared to simple gradient descent methods, but are computationally more expensive and di cult to implement. In this work we specify the necessary details for the application of quasi-Newton methods to the training of the RNN, and provide comparative experimental results from the use of these methods to some well-known test problems, which con®rm the superiority of the approach. Ó

No abstract