Giovanni Paragliola

A Safe Kitchen for Cognitive Impaired People

Cognitive diseases such as Alzheimer, Parkinson, Autism, etc. affect millions of people around the world and they reduce the quality of life for the patient and their relatives. An impaired patient may show irrationally behaviors which could led him to perform abnormal and/or dangerous actions for his safety. This paper presents an approach for modeling and detecting of anomalous and dangerous situations. The proposed method adopts the Situation-awareness paradigm for the detection of anomalous situations in a kitchen environment. Test performed in laboratory and theoretic results show the validity of the approach. Future work will develop a smart kitchen able to detect risks for the patient.

Addressing Security Issues of Electronic Health Record Systems through Enhanced SIEM Technology

Electronic Health Records (EHR) are digital documents containing citizen medical information that can be used for advanced eHealth services, like emergency patient summary retrieving, historical data and events analysis, remote medical report access, e-Prescription. In this work we present the case study of an EHR management infrastructure, namely the InFSE, which implements a federated network of regional autonomous districts deployed on national scale. Despite the adoption of access control mechanisms based on authenticated transactions and assertions, the InFSE can be illegitimately used to retrieve patient health data and violate the citizens privacy. We propose an enhanced Security Information and Event Management (SIEM) system, namely MASSIF, which is able to discover business logic anomalies and protect the identities of involved parties. In particular we focus on the software modules that perform sophisticated data aggregation and analysis, and provide fault and intrusion tolerant storage facilities, namely the Generic Event Translator, the Security Probes and the Trustworthy Event Storage. The components have been integrated on the widely used open source OSSIM SIEM and validated on a realistic test bed based on elements of the InFSE infrastructure.

Intelligent Monitoring of Stereotyped Motion Disorders in Case of Children with Autism

Autism is a complex developmental disability, which is the result of a neurological disorder that has an effect on normal brain function, affecting persons communication and social interaction skills. Main symptoms include motion conditions and stereotypical behaviors. This paper focuses on the detection and monitoring of stereotypical motion conditions of patients with autism. Artificial Intelligence techniques are used to identify stereotypical motion conditions, whereas the Situation-Awareness paradigm allows clinicians to obtain further medical information and the reduction of misclassifications. Results are under validation at the Department of Child Psychiatry at Childrens Hospital Santobono-Pausilipon in Naples.

An Approach for the Evaluation of Sleeping Behaviors Disorders in Patients with Cognitive Diseases: A Case Study

Cognitive disorders such as Alzheimers disease concern a persons ability to perform daily activities. With the worsening of the disease, the decline of the brains ability tends to disrupt also the sleep/waking cycle, which may cause sleep problems, night-time wandering, and agitation. It has been proved that there is a connection between sleeping disorders and the onset of cognitive disorders like Alzheimer. In this work we propose an approach for the analysis of the sleep of patients with Alzheimer(AD) in order to detect anomalous movements. In order to prove our approach we monitor two patients: a patient with very early AD and one with multiple sclerosis(MD), both have been monitored for a week. During the monitoring phase, a set of parameters has been acquired such as movements, electrodermal activity (EDA), heart rate (HR) and skin temperature. The results highlight some interesting findings in terms of the number of anomalous movements and the heart rate variation during these movements.

An Hybrid Architecture to Enhance Attacks Detection on IT infrastructure

Nowadays, IT systems are widely used to support the services offered from any infrastructure. This allows the improvement of business processes but on the other hand it exposes the infrastructure to cyber-attacks. Misuse and anomaly detection are two widely adopted approaches to discover known and unknown cyberattacks. In this paper we provide an overviewof the techniques currently adopted for misuse and anomaly detection and we discuss a conceptual architecture that exploits the advantages of both misuse and anomaly detection to improve cyber-security. Also we provide a conceptual description of an expert system that solves conflicts due to detection mismatches between misuse and anomaly detection techniques.

A Deep Learning-Based Approach for the Recognition of Sleep Disorders in Patients with Cognitive Diseases: A Case Study

Alzheimer’s disease is the most common type of dementia. Patients suffer from of this kind of disease could show symptoms such as sleep disturbances, muscle rigidity or other typical Alzheimer’s movement irregularities. In our work, we have focused on those types of disturbances related to sleep disorders. Due to their not well-known nature, it is difficult to develop software able to identify sleep disorders. In this work, we have addressed the problem of the automatic recognition of sleep disorders in patients with Alzheimer’s disease by using deep learning algorithms.

ALPHA: an eAsy inteLligent service Platform for Healthy Ageing

Dementia is one of the biggest global public health challenges facing our generation. Alzheimer’s disease (AD) is the most frequent cause of dementia in elderly people over 65 years of age. The typical characteristic of AD is impairment of memory. As the disease progresses, other cognitive domains such as language, praxis, visuo-spatial and executive functions become involved, eventually resulting in global cognitive decline. Behavioral Psychological Symptoms of Dementia (BPSD) problems are constant in AD and have a highly negative impact on the quality of life of patients and their families. ALPHA project aims at developing an intelligent situation-aware system to collect and process information about Alzheimer Disease patients’ life style. Starting from various data provided by caregivers and a set of non-invasive sensors and devices, ALPHA will provide clinicians with new quantitative and qualitative information about patients’ abnormal behavior which, along with medical data, will enhance the accuracy and reliability of monitoring and assessing the patient’s health status. Clinicians will be supported by a suite of specifically designed tools and interfaces to analyze the metadata captured, improve management of personalized care plans and interactions with both patients and caregivers. Furthermore studies of antique records of a former psychiatric hospital will give the chance to widen the knowledge of behavioral disorders thus allowing to compare the ancient and the recently ones and to probabilistically determine relation between type of dementia and behavioral disorders.

An Intelligent Monitoring System for Cognitive Impaired People

Cognitive impairment diseases show symptoms on difficulties in remembering, learning new things, concentrating, or making decisions that affect their everyday life. Age is a major risk factor for cognitive impairments and the number of people living with cognitive impairment is expected to grow dramatically. This paper presents a method and an infrastructure for i) monitoring behaviors of cognitive impaired people ii) detecting dangerous situations that involve patients iii) recovering the current situation whereas an anomaly is detected. The method adopts the Situation-Awareness paradigm to model monitoring infrastructure, an Artificial Intelligence techniques for the identification of patients behaviors. Test performed in laboratory and theoretic results show the validity of the approach. The research activity aims to develop a safe environments for cognitive impaired people.