Sentiment analysis of epidemiological surveillance reports on COVID-19 in Greece using machine learning models.

The present research deals with sentiment analysis performed with Microsoft Azure Machine Learning Studio to classify Facebook posts on the Greek National Public Health Organization (EODY) from November 2021 to January 2022 during the pandemic. Positive, negative and neutral sentiments were included after processing 300 reviews. This approach involved analyzing the words appearing in the comments and exploring the sentiments related to daily surveillance reports of COVID-19 published on the EODY Facebook page. Moreover, machine learning algorithms were implemented to predict the classification of sentiments. This research assesses the efficiency of a few popular machine learning models, which is one of the initial efforts in Greece in this domain. People have negative sentiments toward COVID surveillance reports. Words with the highest frequency of occurrence include government, vaccinated people, unvaccinated, telephone communication, health measures, virus, COVID-19 rapid/molecular tests, and of course, COVID-19. The experimental results disclose additionally that two classifiers, namely two class Neural Network and two class Bayes Point Machine, achieved high sentiment analysis accuracy and F1 score, particularly 87% and over 35%. A significant limitation of this study may be the need for more comparison with other research attempts that identified the sentiments of the EODY surveillance reports of COVID in Greece. Machine learning models can provide critical information combating public health hazards and enrich communication strategies and proactive actions in public health issues and opinion management during the COVID-19 pandemic.

Coastal Water Quality Modelling Using E. coli, Meteorological Parameters and Machine Learning Algorithms.

In this study, machine learning models were implemented to predict the classification of coastal waters in the region of Eastern Macedonia and Thrace (EMT) concerning Escherichia coli (E. coli) concentration and weather variables in the framework of the Directive 2006/7/EC. Six sampling stations of EMT, located on beaches of the regional units of Kavala, Xanthi, Rhodopi, Evros, Thasos and Samothraki, were selected. All 1039 samples were collected from May to September within a 14-year follow-up period (2009-2021). The weather parameters were acquired from nearby meteorological stations. The samples were analysed according to the ISO 9308-1 for the detection and the enumeration of E. coli. The vast majority of the samples fall into category 1 (Excellent), which is a mark of the high quality of the coastal waters of EMT. The experimental results disclose, additionally, that two-class classifiers, namely Decision Forest, Decision Jungle and Boosted Decision Tree, achieved high Accuracy scores over 99%. In addition, comparing our performance metrics with those of other researchers, diversity is observed in using algorithms for water quality prediction, with algorithms such as Decision Tree, Artificial Neural Networks and Bayesian Belief Networks demonstrating satisfactory results. Machine learning approaches can provide critical information about the dynamic of E. coli contamination and, concurrently, consider the meteorological parameters for coastal waters classification.

The influence of weather types over northern Greece on respiratory and cardio-vascular mortality.

Extreme ambient temperatures are well-known for their adverse impact on public health, in the form of increased mortality and morbidity due to respiratory and cardio-vascular diseases. However, to capture the total impact of weather on cause-specific mortality/morbidity, the synoptic atmospheric conditions over the region under study need to be taken into account. The objective of this work is to identify weather types over Thessaloniki, Greece, statistically associated with mortality from circulatory and respiratory diseases, in an attempt to holistically determine the impact of weather on cause-specific mortality in the region. For this purpose, we employed datasets from the NCEP/NCAR Reanalysis comprising intrinsic daily data, gridded at a resolution of 2.5°×2.5° and covering a 41-year period (1980-2020). The first set used contains data of 500 hPa and 1,000 hPa geopotential heights for the main geographical domain of the Mediterranean region (30°N-45°N, 10°Ε-35°E). The second set comprises meteorological variables (2 m temperature, specific humidity, 2 m zonal and 2 m meridional wind and total cloud cover) for a geographical domain of north Greece (40.95°Ν, 22.50°Ε-26.25°E). We applied a combination of principal components analysis (PCA) as a dimensionality reduction tool and k-means cluster analysis (CA) in order to group days with homogeneous synoptic meteorological parameters. The derived weather types were statistically correlated with respiratory and mortality data for the time-period 1999-2018. It was concluded that the most fatal conditions for public health in Thessaloniki were associated with weather types bringing low/extremely low ambient temperature over north Greece.

The Impact of Ambient Temperature on Cardiorespiratory Mortality in Northern Greece.

It is well-established that exposure to non-optimum temperatures adversely affects public health, with the negative impact varying with latitude, as well as various climatic and population characteristics. This work aims to assess the relationship between ambient temperature and mortality from cardiorespiratory diseases in Eastern Macedonia and Thrace, in Northern Greece. For this, a standard time-series over-dispersed Poisson regression was fit, along with a distributed lag nonlinear model (DLNM), using a maximum lag of 21 days, to capture the non-linear and delayed temperature-related effects. A U-shaped relationship was found between temperature and cardiorespiratory mortality for the overall population and various subgroups and the minimum mortality temperature was observed around the 65th percentile of the temperature distribution. Exposure to extremely high temperatures was found to put the highest risk of cardiorespiratory mortality in all cases, except for females which were found to be more sensitive to extreme cold. It is remarkable that the highest burden of temperature-related mortality was attributed to moderate temperatures and primarily to moderate cold. The elderly were found to be particularly susceptible to both cold and hot thermal stress. These results provide new evidence on the health response of the population to low and high temperatures and could be useful to local authorities and policy-makers for developing interventions and prevention strategies for reducing the adverse impact of ambient temperature.

A call to incorporate systems theory and human factors into the existing investigation of harm in clinical research involving healthcare products.

This is a joint statement from individual pharmacology and pharmaceutical professionals acting in their own capacity, including members of the Alliance for Clinical Research Excellence and Safety (ACRES) and the International Society of Pharmacovigilance (ISoP). By building on the extensive pharmacological and regulatory investigations that already take place, we are calling for a fuller and more robust systems-based approach to the independent investigation of clinical research when serious incidents of harm occur, starting with first-in-human clinical trials. To complement existing activities and regulations, we propose an additional approach blending evidence derived from both pharmacological and organizational science, which addresses human factors and transparency, to enhance organizational learning and continuous improvement. As happens with investigations in other sectors of society, such as the chemical and aviation sector, this systems approach should be seen as an additional way to understand how problems occur and how they might be prevented in the future. We believe that repetition of potentially preventable and adverse outcomes during clinical research, by failing to identify and act upon all systematic vulnerabilities, is a situation that needs urgent change. As we will discuss further on, approaches based on applying systems theory and human factors are much more likely to improve objectivity and transparency, leading to better system design.

RiskSOAP: Introducing and applying a methodology of risk self-awareness in road tunnel safety.

Complex socio-technical systems, such as road tunnels, can be designed and developed with more or less elements that can either positively or negatively affect the capability of their agents to recognise imminent threats or vulnerabilities that possibly lead to accidents. This capability is called risk Situation Awareness (SA) provision. Having as a motive the introduction of better tools for designing and developing systems that are self-aware of their vulnerabilities and react to prevent accidents and losses, this paper introduces the Risk Situation Awareness Provision (RiskSOAP) methodology to the field of road tunnel safety, as a means to measure this capability in this kind of systems. The main objective is to test the soundness and the applicability of RiskSOAP to infrastructure, which is advanced in terms of technology, human integration, and minimum number of safety requirements imposed by international bodies. RiskSOAP is applied to a specific road tunnel in Greece and the accompanying indicator is calculated twice, once for the tunnel design as defined by updated European safety standards and once for the 'as-is' tunnel composition, which complies with the necessary safety requirements, but calls for enhancing safety according to what EU and PIARC further suggest. The derived values indicate the extent to which each tunnel version is capable of comprehending its threats and vulnerabilities based on its elements. The former tunnel version seems to be more enhanced both in terms of it risk awareness capability and safety as well. Another interesting finding is that despite the advanced tunnel safety specifications, there is still room for enriching the safe design and maintenance of the road tunnel.

Introducing RiskSOAP to communicate the distributed situation awareness of a system about safety issues: an application to a robotic system.

This paper introduces the RiskSOAP ('RiskSOAP' is the abbreviation for Risk SituatiOn Awareness Provision.) indicator to measure the capability of a complex socio-technical system to provide its agents with situation awareness (SA) about the presence of its threats and vulnerabilities and enables analysts to assess distributed SA. The RiskSOAP methodology adopts a comparative approach between two design versions of a system differing in the elements and characteristics that can enhance or cause the degradation of the awareness provision capability. The methodology uniquely combines three methods: (1) the STPA hazard analysis, (2) the EWaSAP early warning sign identification approach, and (3) a dissimilarity measure for calculating the distance between binary sets. In this paper, the RiskSOAP methodology was applied to a robotic system and the findings show that the indicator is an objective measure for the system's capability to provide its agents with SA about its threats and vulnerabilities. Practitioner Summary: This paper suggests a novel methodology for assessing distributed situation awareness (DSA) regarding safety issues. Given that systems consist of specifications and components possible to be mapped, the risk SA provision capability (RiskSOAP) methodology demonstrates the feasibility of measuring to what extent systems' elements contribute to the emergence of DSA.

A knowledge acquisition process to analyse operational problems in solid waste management facilities.

The available expertise on managing and operating solid waste management (SWM) facilities varies among countries and among types of facilities. Few experts are willing to record their experience, while few researchers systematically investigate the chains of events that could trigger operational failures in a facility; expertise acquisition and dissemination, in SWM, is neither popular nor easy, despite the great need for it. This paper presents a knowledge acquisition process aimed at capturing, codifying and expanding reliable expertise and propagating it to non-experts. The knowledge engineer (KE), the person performing the acquisition, must identify the events (or causes) that could trigger a failure, determine whether a specific event could trigger more than one failure, and establish how various events are related among themselves and how they are linked to specific operational problems. The proposed process, which utilizes logic diagrams (fault trees) widely used in system safety and reliability analyses, was used for the analysis of 24 common landfill operational problems. The acquired knowledge led to the development of a web-based expert system (Landfill Operation Management Advisor, http://loma.civil.duth.gr), which estimates the occurrence possibility of operational problems, provides advice and suggests solutions.

Functional relationships of landfill and landraise capacity with design and operation parameters.

Solid waste management presses for effective landfill design and operation. While planning and operating a landfill (LF) or a landraise (LR), choices need to be made regarding: (1) LF-LR morphology (base shape, side slopes, final cover thickness, LR/LF height/depth); (2) cell geometry (height, length, slopes); and (3) operation parameters (waste density, working face length, cover thicknesses). These parameters affect LF/LR capacity, operation lifespan and construction/ operation costs. In this paper, relationships are generated between capacity (C, space available for waste) and the above parameters. Incorporating real data into simulation kgamma A1.38, runs, two types of functions are developed: first, C = where A is the LF/LR base area size and kgamma a base shape-dependent coefficient; and second, C = alpha(p,gamma,A) + delta(p,gamma,A)Xp for every parameter p, where Xp is the value of p and alpha(p,gamma,A) and delta(p,gamma,A) are parameter- and base (shape/size)-specific coefficients. Moreover, the relationship between LF depth and LR height that balances excavation volume with cover material, is identified. Another result is that, for a symmetrical combination of LF/LR, with base surface area shape between square and 1:2 orthogonal, and final density between 500 and 800 kg m(-3), waste quantity placed ranges from 1.76A1.38 to 2.55A1.38 tons. The significance of such functions is obvious, as they allow the analyst to investigate alternative LF/LR schemes and make trade-off analyses.