Leveraging extreme scale analytics, AI and digital twins for maritime digitalization: the VesselAI architecture.

The modern maritime industry is producing data at an unprecedented rate. The capturing and processing of such data is integral to create added value for maritime companies and other maritime stakeholders, but their true potential can only be unlocked by innovative technologies such as extreme-scale analytics, AI, and digital twins, given that existing systems and traditional approaches are unable to effectively collect, store, and process big data. Such innovative systems are not only projected to effectively deal with maritime big data but to also create various tools that can assist maritime companies, in an evolving and complex environment that requires maritime vessels to increase their overall safety and performance and reduce their consumption and emissions. An integral challenge for developing these next-generation maritime applications lies in effectively combining and incorporating the aforementioned innovative technologies in an integrated system. Under this context, the current paper presents the architecture of VesselAI, an EU-funded project that aims to develop, validate, and demonstrate a novel holistic framework based on a combination of the state-of-the-art HPC, Big Data and AI technologies, capable of performing extreme-scale and distributed analytics for fuelling the next-generation digital twins in maritime applications and beyond.

Overview of methods and available tools used in complex brain disorders.

Complex brain disorders, including Alzheimer's dementia, sleep disorders, and epilepsy, are chronic conditions that have high prevalence individually and in combination, increasing mortality risk, and contributing to the socioeconomic burden of patients, their families and, their communities at large. Although some literature reviews have been conducted mentioning the available methods and tools used for supporting the diagnosis of complex brain disorders and processing different files, there are still limitations. Specifically, these research works have focused primarily on one single brain disorder, i.e., sleep disorders or dementia or epilepsy. Additionally, existing research initiatives mentioning some tools, focus mainly on one single type of data, i.e., electroencephalography (EEG) signals or actigraphies or Magnetic Resonance Imaging, and so on. To tackle the aforementioned limitations, this is the first study conducting a comprehensive literature review of the available methods used for supporting the diagnosis of multiple complex brain disorders, i.e., Alzheimer's dementia, sleep disorders, epilepsy. Also, to the best of our knowledge, we present the first study conducting a comprehensive literature review of all the available tools, which can be exploited for processing multiple types of data, including EEG, actigraphies, and MRIs, and receiving valuable forms of information which can be used for differentiating people in a healthy control group and patients suffering from complex brain disorders. Additionally, the present study highlights both the benefits and limitations of the existing available tools.

Explainable Identification of Dementia From Transcripts Using Transformer Networks.

Alzheimer's disease (AD) is the main cause of dementia which is accompanied by loss of memory and may lead to severe consequences in peoples' everyday life if not diagnosed on time. Very few works have exploited transformer-based networks and despite the high accuracy achieved, little work has been done in terms of model interpretability. In addition, although Mini-Mental State Exam (MMSE) scores are inextricably linked with the identification of dementia, research works face the task of dementia identification and the task of the prediction of MMSE scores as two separate tasks. In order to address these limitations, we employ several transformer-based models, with BERT achieving the highest accuracy accounting for 87.50%. Concurrently, we propose an interpretable method to detect AD patients based on siamese networks reaching accuracy up to 83.75%. Next, we introduce two multi-task learning models, where the main task refers to the identification of dementia (binary classification), while the auxiliary one corresponds to the identification of the severity of dementia (multiclass classification). Our model obtains accuracy equal to 86.25% on the detection of AD patients in the multi-task learning setting. Finally, we present some new methods to identify the linguistic patterns used by AD patients and non-AD ones, including text statistics, vocabulary uniqueness, word usage, correlations via a detailed linguistic analysis, and explainability techniques (LIME). Findings indicate significant differences in language between AD and non-AD patients.

Multimodal Deep Learning Models for Detecting Dementia From Speech and Transcripts.

Alzheimer's dementia (AD) entails negative psychological, social, and economic consequences not only for the patients but also for their families, relatives, and society in general. Despite the significance of this phenomenon and the importance for an early diagnosis, there are still limitations. Specifically, the main limitation is pertinent to the way the modalities of speech and transcripts are combined in a single neural network. Existing research works add/concatenate the image and text representations, employ majority voting approaches or average the predictions after training many textual and speech models separately. To address these limitations, in this article we present some new methods to detect AD patients and predict the Mini-Mental State Examination (MMSE) scores in an end-to-end trainable manner consisting of a combination of BERT, Vision Transformer, Co-Attention, Multimodal Shifting Gate, and a variant of the self-attention mechanism. Specifically, we convert audio to Log-Mel spectrograms, their delta, and delta-delta (acceleration values). First, we pass each transcript and image through a BERT model and Vision Transformer, respectively, adding a co-attention layer at the top, which generates image and word attention simultaneously. Secondly, we propose an architecture, which integrates multimodal information to a BERT model via a Multimodal Shifting Gate. Finally, we introduce an approach to capture both the inter- and intra-modal interactions by concatenating the textual and visual representations and utilizing a self-attention mechanism, which includes a gate model. Experiments conducted on the ADReSS Challenge dataset indicate that our introduced models demonstrate valuable advantages over existing research initiatives achieving competitive results in both the AD classification and MMSE regression task. Specifically, our best performing model attains an accuracy of 90.00% and a Root Mean Squared Error (RMSE) of 3.61 in the AD classification task and MMSE regression task, respectively, achieving a new state-of-the-art performance in the MMSE regression task.

Hospitals' Cybersecurity Culture during the COVID-19 Crisis.

The coronavirus pandemic led to an unprecedented crisis affecting all aspects of the concurrent reality. Its consequences vary from political and societal to technical and economic. These side effects provided fertile ground for a noticeable cyber-crime increase targeting critical infrastructures and, more specifically, the health sector; the domain suffering the most during the pandemic. This paper aims to assess the cybersecurity culture readiness of hospitals' workforce during the COVID-19 crisis. Towards that end, a cybersecurity awareness webinar was held in December 2020 targeting Greek Healthcare Institutions. Concepts of cybersecurity policies, standards, best practices, and solutions were addressed. Its effectiveness was evaluated via a two-step procedure. Firstly, an anonymous questionnaire was distributed at the end of the webinar and voluntarily answered by attendees to assess the comprehension level of the presented cybersecurity aspects. Secondly, a post-evaluation phishing campaign was conducted approximately four months after the webinar, addressing non-medical employees. The main goal was to identify security awareness weaknesses and assist in drafting targeted assessment campaigns specifically tailored to the health domain needs. This paper analyses in detail the results of the aforementioned approaches while also outlining the lessons learned along with the future scientific routes deriving from this research.

Assessing MITRE ATT&CK Risk Using a Cyber-Security Culture Framework.

The MITRE ATT&CK (Adversarial Tactics, Techniques, and Common Knowledge) Framework provides a rich and actionable repository of adversarial tactics, techniques, and procedures. Its innovative approach has been broadly welcomed by both vendors and enterprise customers in the industry. Its usage extends from adversary emulation, red teaming, behavioral analytics development to a defensive gap and SOC (Security Operations Center) maturity assessment. While extensive research has been done on analyzing specific attacks or specific organizational culture and human behavior factors leading to such attacks, a holistic view on the association of both is currently missing. In this paper, we present our research results on associating a comprehensive set of organizational and individual culture factors (as described on our developed cyber-security culture framework) with security vulnerabilities mapped to specific adversary behavior and patterns utilizing the MITRE ATT&CK framework. Thus, exploiting MITRE ATT&CK's possibilities towards a scientific direction that has not yet been explored: security assessment and defensive design, a step prior to its current application domain. The suggested cyber-security culture framework was originally designed to aim at critical infrastructures and, more specifically, the energy sector. Organizations of these domains exhibit a co-existence and strong interaction of the IT (Information Technology) and OT (Operational Technology) networks. As a result, we emphasize our scientific effort on the hybrid MITRE ATT&CK for Enterprise and ICS (Industrial Control Systems) model as a broader and more holistic approach. The results of our research can be utilized in an extensive set of applications, including the efficient organization of security procedures as well as enhancing security readiness evaluation results by providing more insights into imminent threats and security risks.