Search

With the increasing requirement of high accuracy for particulate matter prediction, various attempts have been made to improve prediction accuracy by applying machine learning algorithms. However, the characteristics of particulate matter and the problem of the occurrence rate by concentration make it difficult to train prediction models, resulting in poor prediction. In order to solve this problem, in this paper, we proposed multiple classification models for predicting particulate matter concentrations required for prediction by dividing them into AQI-based classes. We designed multiple classification models using logistic regression, decision tree, SVM and ensemble among the various machine learning algorithms. The comparison results of the performance of the four classification models through error matrices confirmed the f-score of 0.82 or higher for all the models other than the logistic regression model. [ABSTRACT FROM AUTHOR]

This study was undertaken to characterize a lactic acid bacterium 4I1, isolated from the freshwater fish, Zacco koreanus. Morphological, biochemical, and molecular characterization of 4I1 revealed it to be Pediococcus pentosaceus 4I1. The cell free supernatant (CFS) of P. pentosaceus 4I1 exhibited significant (p < 0.05) antibacterial effects (inhibition zone diameters: 16.5-20.4 mm) against tested foodborne pathogenic bacteria with MIC and MBC values of 250-500 and 500-1,000 mg/mL, respectively. Further, antibacterial action of CFS of P. pentosaceus 4I1 against two selected bacteria Staphylococcus aureus KCTC-1621 and Escherichia coli O157:H7 was determined in subsequent assays. The CFS of P. pentosaceus 4I1 revealed its antibacterial action against S. aureus KCTC-1621 and E. coli O157:H7 on membrane integrity as confirmed by a reduction in cell viability, increased potassium ion release (900 and 800 mmol/L), reduced absorption at 260-nm (3.99 and 3.77 OD), and increased relative electrical conductivity (9.9 and 9.7%), respectively. Gas chromatography-mass spectrometry (GC-MS) analysis of the CFS of P. pentosaceus 4I1 resulted in the identification of seven major compounds, which included amino acids, fatty acids and organic acids. Scanning electron microscopic-based morphological analysis further confirmed the antibacterial effect of CFS of P. pentosaceus 4I1 against S. aureus KCTC-1621 and E. coli O157:H7. In addition, the CFS of P. Pentosaceus 4I1 displayed potent inhibitory effects on biofilms formation by S. aureus KCTC-1621 and E. coli O157:H7. The study indicates the CFS of P. pentosaceus 4I1 offers an alternative means of controlling foodborne pathogens. [ABSTRACT FROM AUTHOR]

The explosive growth of online education seems to slow down. Does this trend indicate that some courses are not appropriate for online education? We sought to find an answer to this question regarding graduate business statistics. We assumed that a course is well suited for online education if the students in the online and on-ground courses make overall grades that are not significantly different. We found that overall grades in the online graduate business statistics course were not significantly different from those in the on-ground course, though there was significant difference between the midterm grades of the two versions of courses. We assumed that it was due to the difference of learning speed. Comparison of letter grade distributions of the two modes of learning led us to the same conclusion. The results of this study led us to believe that graduate business statistics is appropriate for online education. We also recommend further research on students' perceptions on the two learning environments to find how to reduce or remove the difference in learning speed. [ABSTRACT FROM AUTHOR]

This paper presents an integrated decision-support framework that helps public agencies identify high-crash locations and develop cost-effective safety improvement projects. State-of-the-art safety concepts, such as safety performance functions, empirical Bayesian method, and potential for safety improvements, are incorporated to identify hazardous highway locations. Cost-effective safety projects are prioritized based on life-cycle safety benefit evaluation and optimal resource allocation models. An efficient solution algorithm to the optimization model is also proposed. The models are implemented in an internet-based, geographic information system (GIS) software tool that builds on state-of-the-art information technologies, graphical interfaces, and customized GIS algorithms such as spatial analysis with buffering operations. [ABSTRACT FROM AUTHOR]

In this paper, we propose predictive temperature-aware Dynamic Voltage and Frequency Scaling (DVFS) using the performance counters that are already embedded in commercial microprocessors. By using the performance counters and simple regression analysis, we can predict the localized temperature and efficiently scale the voltage/frequency. When localized thermal problems that were not detected by thermal sensors are found after layout (or fabrication), the thermal problems can be avoided by the proposed software solution without delaying time-to-market. The evaluation results show that in a Linux-based laptop with the Intel Core2 Duo processor, DVFS using the performance counters performs comparable to DVFS using the thermal sensor. [ABSTRACT FROM AUTHOR]

This paper analyzes the economic impact of an earthquake on transportation network that contains more detail for the Midwest states. Two aspects of cost are considered in the paper: final demand loss and transport cost increase. The 1812 New Madrid earthquake is used to develop a scenario for the analysis. The modeling system includes a transportation network loss function, a final demand loss function, and an integrated commodity flow model. After running the earthquake scenario, the analysis identifies the most significant link on the network in an economic sense as well as the link with the greatest physical disruption. The results reveal that the links with greater physical disruption are not always the ones exhibiting the greater economic damage. The resulting outputs can provide information to perform a cost-benefit analysis as well as to support a decision-making process on the optimal retrofit priority of bridges and links on the transportation network. [ABSTRACT FROM AUTHOR]