Discovering anomalies in big data: a review focused on the application of metaheuristics and machine learning techniques.

With the increase in available data from computer systems and their security threats, interest in anomaly detection has increased as well in recent years. The need to diagnose faults and cyberattacks has also focused scientific research on the automated classification of outliers in big data, as manual labeling is difficult in practice due to their huge volumes. The results obtained from data analysis can be used to generate alarms that anticipate anomalies and thus prevent system failures and attacks. Therefore, anomaly detection has the purpose of reducing maintenance costs as well as making decisions based on reports. During the last decade, the approaches proposed in the literature to classify unknown anomalies in log analysis, process analysis, and time series have been mainly based on machine learning and deep learning techniques. In this study, we provide an overview of current state-of-the-art methodologies, highlighting their advantages and disadvantages and the new challenges. In particular, we will see that there is no absolute best method, i.e., for any given dataset a different method may achieve the best result. Finally, we describe how the use of metaheuristics within machine learning algorithms makes it possible to have more robust and efficient tools.

Participant perspectives of a home-based palliative approach for people with severe multiple sclerosis: A qualitative study.

BACKGROUND: We performed a qualitative study to investigate the experiences of participants in a multicentre randomized controlled trial on a home-based palliative approach (HPA) for adults with severe multiple sclerosis (MS) and their caregivers. Our aim was to explore the strengths and challenges of the intervention, and circumstances that may have influenced its efficacy. METHODS: Participants to the qualitative study were the patients, their caregivers, patient referring physicians, and the teams who delivered the HPA intervention. We performed semi-structured one-on-one interviews with 12 patients and 15 informal caregivers chosen using a maximum variation strategy, two focus group meetings with patient referring physicians (4 participants each), and one with the HPA teams (9 participants). RESULTS: From data analysis (framework method) 38 sub-categories emerged, which were grouped into 10 categories and 3 themes: 'expectations,' 'met and unmet needs', and 'barriers'. Intervention benefits were improved control of symptoms and reduced sense of isolation of the patient-caregiver dyads. Limitations were: factors related to experimental design (difficulty of dyads in identifying examiner and team roles, additional burden for caregivers); team issues (insufficient team building /supervision, competing priorities); limitations of the intervention itself (insufficient length, lack of rehabilitation input); and external factors (resource limitations, under-responsive services/professionals). The referring physician focus groups provided little experiential data. CONCLUSIONS: The HPA reduced patient symptoms and sense of isolation in patients and caregivers. The indirect role of the HPA teams, and insufficient length of the intervention were key limitations. The experimental design imposed additional burdens on the dyads. Key barriers were the paucity of available services, the demanding administrative procedures, and lack of networking facilities. These findings suggest that two major requirements are necessary for home palliative care to be effective in this patient population: HPA teams well-connected with MS rehabilitation services, and care delivered over the long-term, with variable intensity. TRIAL REGISTRATION: Current Controlled Trials ISRCTN73082124 (Registered 19/06/2014).