Search

In this paper an algorithm for detection of nonstandard situations in smart water metering based on machine learning is designed. The main categories for nonstandard situation or anomaly detection and two common methods for anomaly detection are analyzed. The proposed solution needs to fit the requirements for correct, efficient and real-time detection of non-standard situations in actual water consumption with minimal required consumer intervention to its operation. Moreover, a proposal to extend the original hardware solution is described and implemented to accommodate the needs of the detection algorithm. The final implemented and tested solution evaluates anomalies in water consumption for a given time in specific day and month using machine learning with a semi-supervised approach.

OBJECTIVE: To gain insight into the different protective mechanisms of approved vaccines, this study focuses on the comparison of humoral and cellular immune responses of five widely used vaccines including ChAdOx1 (AZD1222, AstraZeneca), BNT162b2 (Pfizer), mRNA-1273 (Moderna), BBIBP-CorV (Sinopharm), and Gam-COVID-Vac (Sputnik V). MATERIALS AND METHODS: Isolated plasma from 95 volunteers' blood samples was used to measure anti-SARS-CoV-2 humoral and cellular immune responses. Positive controls were recovered patients from COVID-19 (unvaccinated). Specific quantification kits for anti-nucleocapsid IgG, anti-Spike protein IgG, neutralizing antibodies as well as specific SARS-CoV-2 antigens for T-cell activation were used and Spearman correlation and matrix analyses were performed to compare overall immune responses. RESULTS: Nucleocapsid antibodies were significantly higher for the BBIBP-CorV and convalescent group when compared to other vaccines. In contrast, subjects vaccinated with BNT162b2 and mRNA-1273 presented significantly higher anti-spike IgG. In fact, 9.1% of convalescent, 4.5% of Gam-COVID-Vac, 28.6% of ChAdOx1, and 12.5% of BBIBP-CorV volunteers did not generate anti-spike IgG. Similarly, a positive correlation was observed after the neutralization assay. T-cell activation studies showed that mRNA-based vaccines induced a T-cell driven immune response in all cases, while 55% of convalescents, 8% of BNT162b1, 12,5% of mRNA-1273, 9% of Gam-COVID-Vac, 57% of ChAdOx1, and 56% of BBIBP-CorV subjects presented no cellular response. Further correlation matrix analyses indicated that anti-spike IgG and neutralizing antibodies production, and T-cell activation follow the same trend after immunization. CONCLUSIONS: RNA-based vaccines induced the most robust adaptive immune activation against SARS-CoV-2 by promoting a significantly higher T-cell response, anti-spike IgG and neutralization levels. Vector-based vaccines protected against the virus at a comparable level to convalescent patients. [ABSTRACT FROM AUTHOR]

In this paper an algorithm for detection of nonstandard situations in smart water metering based on machine learning is designed. The main categories for nonstandard situation or anomaly detection and two common methods for anomaly detection are analyzed. The proposed solution needs to fit the requirements for correct, efficient and real-time detection of non-standard situations in actual water consumption with minimal required consumer intervention to its operation. Moreover, a proposal to extend the original hardware solution is described and implemented to accommodate the needs of the detection algorithm. The final implemented and tested solution evaluates anomalies in water consumption for a given time in specific day and month using machine learning with a semi-supervised approach. [ABSTRACT FROM AUTHOR]