NeroPRAI 2024 Abstracts

Area 1 - NeroPRAI
Full Papers

Area 1 - NeroPRAI

Full Papers
Paper Nr: 5
Title:

A Federated Learning System with Biometric Medical Image Authentication for Alzheimer's Diagnosis
Authors:

Francesco Castro, Donato Impedovo and Giuseppe Pirlo
Abstract: There are concerns within the medical/scientific community about the use of machine learning models for disease diagnosis from medical images. The causes are related not only to the high performance required in models for disease diagnosis but also to the sensitivity of the data processed and the protection of patient privacy. There are stringent policies on medical image dissemination to prevent image theft, image de-anonymization, data poisoning attacks, and other security issues. The proposed system for AD diagnosis from RGB MRI brain images implements the Federated Learning (FL) architecture and a strategy of medical image authentication through biometric recognition to protect the privacy and confidentiality of the medical image used for the training model and to mitigate the data poisoning attacks on the model. Experiments conducted on two datasets of RGB MRI images (OASIS and ADNI) demonstrate that the proposed system achieved performance comparable to a centralized ML system without a privacy-preserving strategy. The proposed system represents a solution to solve security and privacy issues in a healthcare application for AD diagnosis.
Download
Paper Nr: 6
Title:

Filtered Random Hybrid Strokes (Frhs): Filtering Time-Series Considerding Velocity Profile
Authors:

Stefania Bello, Alessia Monaco, Luca Musti, Giuseppe Pirlo and Gianfranco Semeraro
Abstract: This paper proposes an improvement to the data augmentation technique, Random Hybrid Stroke (RHS), widely used in handwriting analysis for the early detection of dementia. This improvement involves the appli- cation of a filtering method to handwriting time series, redefining the concept of a ’stroke’ based on insights derived from kinematic theory. Specifically, a trait is considered as the segment joining successive local mini- mum and local maximum points with respect to the lognormal velocity profile. Experimental evaluations were conducted using a dataset consisting of 23 different writing tasks (Mini-COG, MMSE, etc.) for the early de- tection of dementia using K-Fold cross-validation with K set to 10. The proposed improvement demonstrates promising results, showing an increase in performance over a wide range of writing tasks and representing a significant contribution, in particular, for the Mini-COG, MMSE and Trail Matrix Tests.
Download
Paper Nr: 7
Title:

Human Activity Recognition for Identifying Bullying and Cyberbullying: A Comparative Analysis Between Users Under and over 18 Years Old
Authors:

Vincenzo Gattulli and Lucia Sarcinella
Abstract: The smartphone is an excellent source of data. Sensor values can be extrapolated from the smartphone. This work exploits Human Activity Recognition (HAR) models and techniques to identify human activity performed while filling out a questionnaire that aims to classify users as Bullies, Cyberbullies, Victims of Bullying, and Victims of Cyberbullying. The paper aims to identify activities related to the questionnaire class other than just sitting. The paper starts with a state-of-the-art analysis of HAR to arrive at the design of a model that could recognize everyday life actions and discriminate them from actions resulting from alleged bullying activities (Questionnaire Personality Index). Five activities were considered for recognition: Walking, Jumping, Sitting, Running, and Falling. The best HAR activity identification model was applied to the dataset obtained from the "Smartphone Questionnaire Application" experiment to perform the analysis. The best model for HAR identification is CNN.
Download
Paper Nr: 8
Title:

Unveiling the Power of EEG Signals: Parkinson's Disease Identification via Yet Another Mobile Network (YAMNet)
Authors:

Ali A. Aldujaili, Rosa-Zurera Manuel and Ahmed Meri
Abstract: Parkinson’s disease is a neurodegenerative disorder with a progressively debilitating impact on patients’ movement in terms of cognitive and motor aspects. Early detection is crucial for effective disease management and better patient outcomes. There are many techniques to detect this disease, but one of the most interesting methods to achieve early detection of Parkinson’s disease is electroencephalography, which is a non-invasive and cost-effective diagnostic tool to measure brain activity. Recent studies have shown that deep learning networks can handle complex data to analyse it and extract features. One of these neural networks is called Yet Another Mobile Network (YAMNet), which was originally proposed to analyse speech signals using time-frequency information. In this research, a novel approach using YAMNet is presented for the detection of Parkinson’s disease patients using electroencephalogram brain signals, as the frequency information seems very relevant for Parkinson’s disease detection. The proposed approach was evaluated with an open access dataset available on the Internet, composed of electroencephalogram recordings from Parkinson’s disease patients and healthy control people, obtaining an accuracy rate of 98.9%. The results suggest that YAMNet could be an encouraging tool for the initial, non-invasive detection of Parkinson’s disease. This may improve patient treatments and stimulate future research in the field.
Download
Paper Nr: 13
Title:

Handwriting Detection Test (HWDT): Android Application for the Recognition of Neurodegenerative Diseases
Authors:

Giacomo P. Cuccovillo, Donato Impedovo, Alessia Monaco, Giuseppe Pirlo, Gianfranco Semeraro and Davide Veneto
Abstract: Nowadays there is an increase in the global incidence of dementia, with over 55 million reported cases worldwide. In Italy, the number is estimated to exceed 1 million individuals. According to evidence, a therapeutic approach in the pre-clinical stages involves conducting screening tests to identify changes in the handwriting process. This paper aims to propose an E-Health app named Handwriting Detection Test (HWDT). The proposed app is a smart-screening solution that reduces time and waiting periods in the interaction between experts and patients. We implemented screening tests derived from recent advances or ongoing research. The paper highlights the significant role of handwriting behavior and explains the design and development phases of the proposed system. This approach offers a more efficient and technologically advanced method for early detection and monitoring of cognitive changes associated with neurodegenerative impairments.
Download
Paper Nr: 14
Title:

Detecting Brain Tumors Through Multimodal Neural Networks
Authors:

Antonio Curci and Andrea Esposito
Abstract: Tumors can manifest in various forms and in different areas of the human body. Brain tumors are specifically hard to diagnose and treat because of the complexity of the organ in which they develop. Detecting them in time can lower the chances of death and facilitate the therapy process for patients. The use of Artificial Intelligence (AI) and, more specifically, deep learning, has the potential to significantly reduce costs in terms of time and resources for the discovery and identification of tumors from images obtained through imaging techniques. This research work aims to assess the performance of a multimodal model for the classification of Magnetic Resonance Imaging (MRI) scans processed as grayscale images. The results are promising, and in line with similar works, as the model reaches an accuracy of around 99%. We also highlight the need for explainability and transparency to ensure human control and safety.
Download