Artificial intelligence for data collection and application of the probabilistic-logistic method in ship traffic control systems of seaports

An increase in the number of ships, their sizes, speeds and displacement increases the number of accidents, especially in places with intensive shipping. Control over the positions of vessels, their movement, identification of intentions is exercised by the vessel traffic control system (VTCS). A new generation VTCS that can predict optimal and safest traffic patterns in water areas requires artificial intelligence and forecasting elements. Currently, the fifth generation VTCSs are being implemented. They can plan optimal and safe traffic patterns in the water areas, depending on various external factors controlled by artificial intelligence. The VTCS is a traffic control body. Due to the intensive ship traffic, the control over water traffic is becoming more and more urgent. The “probabilistic” model and the target-object can stop moving when the signal is lost, and it is impossible to continue moving along the same route with the same speed. This must be taken into account when using software [4,5]. The knowledge base for developing a logistic-probabilistic method is available, but there is no real application, due to the lack of massive implementation of artificial intelligence in the software.

Compound Grey-Logistic Model and Its Application

Logistic regression model is widely used in ecology and in the analysis of social economic systems, because of its good adaptability. In order to improve the measurement accuracy of logistic model, this paper proposes a new method. A compound grey-logistic model is developed to carry out the grey transformation of the original data. Practice shows that the grey transformation data has better simulation accuracy; at the same time, grey transformation can reduce the observation noise of the original data. Mean absolute percentage error index has been used to evaluate the accuracy of prediction model, and information entropy can be used to evaluate the change of information entropy of forecasting data. In this paper, three cases are used to verify the applicability of grey-logistic model. From the perspective of the type of original data, the three cases represent three different data conditions: sufficient data, insufficient data, and fragmentary data. The cases represent different related fields: market share data, economic growth data, and R&D output data. The results show that the proposed grey-logistic method can effectively carry out the population growth analysis.

Development and Validation of Enzyme-Linked Immunosorbent Assay for Group B Streptococcal Polysaccharide Vaccine

Streptococcus agalactiae (group B Streptococcus, GBS) is a leading cause of neonatal sepsis and meningitis in infants. Limitations of prenatal GBS screening and intrapartum antibiotic prophylaxis render developing GBS vaccines a high priority. In this study, we developed an enzyme-linked immunosorbent assay (ELISA) for the practical and large-scale evaluation of GBS capsular polysaccharide (PS) vaccine immunogenicity against three main serotypes, Ia, III, and V. GBS-ELISA was developed and subsequently validated using a standardized curve-fitting four-parameter logistic method. Specificity was measured using adsorption of serum with homologous and heterologous PS. Homologous adsorption showed a ≥75% inhibition of all three serotypes, whereas with heterologous PS, IgG GBS-ELISA inhibited only ≤25% of serotypes III and V. However, with serotype Ia, IgG antibody levels decreased by >50%, even after adsorption with heterologous PS (III or V). In comparison, the inhibition opsonophagocytic killing assay (OPA) of serotypes Ia GBS exhibited a reduction in opsonophagocytic activity of only 20% and 1.1% for serotypes III and V GBS, respectively. The precision of the GBS-ELISA was assessed in five independent experiments using four serum samples. The coefficient of variation was <5% for all three serotypes. This standardized GBS-ELISA would be useful for GBS vaccine development and its evaluation.

Prediction of Effluent Arsenic Concentration of Wastewater Treatment Plants Using Machine Learning and Kriging-Based Models

We evaluate the potential of kriging-based (kriging and kriging-logistic) and machine learning models (MARS, GBRT, and ANN) in predicting the effluent arsenic concentration of a wastewater treatment plant. Two distinct input combination scenarios were established, using seven quantitative and qualitative independent influent variables. In the first scenario, all of the seven independent variables were taken into account for constructing the data-driven models. For the second input scenario, we used the forward selection k-fold cross-validation method to select effective explanatory influent parameters. The results obtained from both input scenarios show that the kriging-logistic and machine learning models are effective and robust. However, using the feature selection procedure in the second scenario, made not only the architecture of the model simpler and more effective, but also enhanced the performance of the developed models. Although the standard kriging method failed to provide fair predictive results, it was revealed that the kriging-logistic method gave the best performance among the applied models.

Logistics model for selecting road sections of a mining enterprise for equipping them with automated traffic control tools

The proposed model allows us to determine the sections and objects on the roads of mining enterprises that operate in the most intensive mode, in order to equip them with automated traffic control tools. The model is based on the logistic method of ABC and XYZ analysis, which allows determining such objects and areas with sufficient accuracy. In addition, the scientific novelty of this model is the choice of technical means not by two parameters, as in the classical logistics model, but by three. In addition, this model offers to determine the optimal number of technical means of traffic control, taking into account their cost and the required reliability. When optimizing the number of technical means of traffic control on the roads of mining enterprises, a linear programming model was used that minimizes the target function of total costs, taking into account the required reliability of technical means, while limiting their number used in performing traffic control tasks. The original distribution of technical means for the tasks of traffic control on the roads of mining enterprises is proposed.

An Analysis on the Factors Affecting Credit Selection In BPR to Increase Competitiveness (BPR Case Study in Surabaya)

Bank Perkreditan Rakyat (BPR) is part of the banking financial institutions apart from the commercial banking. .One of the activities of the BPR is to distribute the credits as done by the commercial banks. Problems. BPR as micro financial institutions, in doing their business to distribute the credit up to certain amount, are faced with the commercial banks which have more competitive advantages, both in the price and facilities provided. Objective of this research is to identify the factors influencing the customers in making decisions to take the credit at BPR. By identifying the determinant factors in choosing the banks, BPR can use it to improve their services to the customers and at the same time BPR can use it as a strategy in giving credit to the customers or debtors. The metode employed in this study was regressive logistic method, which was used to identify what factors determine the customers to choose credit at BPR. The conclusion is that the procedures and personality of staff are the main factors making the customers choose credit at BPR

Development Of A Logistic Method In The Placement Of Urban Passenger Transport Routes

Problems in the development of logistic methods in the placement of urban passenger transport routes and the effective placement of urban passenger transport, buses, taxis, cabs, routes, the development of urban transport and ensuring their operation in a competitive environment. In this regard, proposals have been developed to fully meet the needs of the population in passenger transport through the use of logistic methods and reduce congestion.

Family factors predicting self-rated health during early adolescence

Background: Health impairments in adolescents associated with divorce and loss of parental contact are frequently reported. However, other family factors more likely to promote health are less researched. We examined the impact of several family factors on self-rated health (SRH). Methods: A longitudinal cohort study of 1225 students in high school aged 11 and 13 years in 2011. The students were surveyed at onset and after 2 years with SRH as the outcome measure. We adjusted for sex, age and self-rated socioeconomic status in temporal causal analyses, and adjusted for SRH at onset in residual change analyses, applying an ordinal logistic method. Adjusted analyses with each factor and multivariable models with backward exclusion were performed. We reported the predictive associations with odds ratios and 95% confidence limits. Results: The most decisive factors predicting future positive SRH were linked to confidence in communicating with both parents about bothersome issues, and the experience of parental support with school work. Furthermore, the experience of opinions being taken seriously in the family and the absence of excessive parental expectations predicted SRH positively after 2 years. Divorce had a modest impact on SRH and was mediated by the other factors. Only the absence of contact with fathers moderated the effect that divorce experience had on SRH. We ascertained the causal relationships through residual change analyses. Conclusions: As SRH in adolescence has an impact on later health and is amendable, it is important, from a public health perspective, to preserve and improve relationships and confidence between children and both parents.

Population Aspects of Graceful Mojarra Eucinostomus gracilis (Perciformes: Gerreidae) in a Coastal Lagoon in the Tropical Eastern Pacific

Graceful mojarra (Eucinostomus gracilis) is an important component of the ichthyic fauna of lagoon systems but knowledge of its population aspects is scarce. Monthly samples in the Magdalena-Almejas Lagoon system (March-August, 2014-2017) were obtained with a trawling net. Abundance was estimated using the swept area method and its spatial variation; and the maturity size was determined using the logistic method. The sex ratio for mature and immature populations, and their length-weight relationship were estimated; FISAT was used to estimate the growth and recruitment parameters. Abundance ranged from 0.6 to 203 ind-Ha-1 with changes for each lagoon system areas and among years. Size at maturity (L50) was 132 mm in total length (TL) for the population, 129 mm TL females, and 135 mm TL males. Considering the population of the total organisms, L50 indicated that 18% were adults and 82% were juveniles. Juvenile dominance indicated that this lagoon system is used for grow-out. The smaller ratio of adult organisms does not allow asserting assertion that the priority of the area is for reproduction. E. gracilis showed moderate growth (K = 0.56 year-1) with longevity of 5.4 years and asymptotic length of L∞ = 195 mm.