Data Mining Practical Machine Learning Tools and Techniques

Social Network Analysis

Image classification is a complex process that may be affected by many factors. This paper examines current practices, problems, and prospects of image classification. The emphasis is placed on the summarization of major advanced classification approaches and the techniques used for improving classification accuracy. In addition, some important issues affecting classification performance are discussed. This literature review suggests that designing a suitable image-processing procedure is a prerequisite for a successful classification of remotely sensed data into a thematic map. Effective use of multiple features of remotely sensed data and the selection of a suitable classification method are especially significant for improving classification accuracy. Non-parametric classifiers such as neural network, decision tree classifier, and knowledge-based classification have increasingly become important approaches for multisource data classification. Integration of remote sensing, geographical information systems (GIS), and expert system emerges as a new research frontier. More research, however, is needed to identify and reduce uncertainties in the image-processing chain to improve classification accuracy.

/pdf/a-survey-of-image-classification-methods-and-techniques-for-5bc5ltr9dq.pdf

A survey of image classification methods and techniques for improving classification performance

COVID-19 Dashboard

With the invention of the low-cost Microsoft Kinect sensor, high-resolution depth and visual (RGB) sensing has become available for widespread use. The complementary nature of the depth and visual information provided by the Kinect sensor opens up new opportunities to solve fundamental problems in computer vision. This paper presents a comprehensive review of recent Kinect-based computer vision algorithms and applications. The reviewed approaches are classified according to the type of vision problems that can be addressed or enhanced by means of the Kinect sensor. The covered topics include preprocessing, object tracking and recognition, human activity analysis, hand gesture analysis, and indoor 3-D mapping. For each category of methods, we outline their main algorithmic contributions and summarize their advantages/differences compared to their RGB counterparts. Finally, we give an overview of the challenges in this field and future research trends. This paper is expected to serve as a tutorial and source of references for Kinect-based computer vision researchers.

Enhanced Computer Vision With Microsoft Kinect Sensor: A Review

Developing a model curriculum for a university course in health impact assessment in the USA Keshia M. Pollack*, Andrew L. Dannenberg, Nisha D. Botchwey, Cynthia L. Stone and Edmund Seto Department of Health Policy and Management, Johns Hopkins Bloomberg School of Public Health, 624 N. Broadway, Room 557, Baltimore, MD 21215, USA; Department of Environmental and Occupational Health Sciences, University of Washington School of Public Health, 3940 NE Surber Drive, Seattle, WA 98105, USA; School of City and Regional Planning, Georgia Institute of Technology, 245 Fourth Street NW, Suite 204, Atlanta, GA 30332, USA; Department of Health Policy and Management, Richard M. Fairbanks School of Public Health, Indiana University, 714 N. Senate Ave, EF 204A, Indianapolis, IN 46202, USA; Department of Environmental and Occupational Health Sciences, University of Washington School of Public Health, 1959 NE Pacific Street, Campus Box 357234, Seattle, WA 98195, USA

/pdf/professional-practice-paper-developing-a-model-curriculum-3ec5lhzaje.pdf

PROFESSIONAL PRACTICE PAPER Developing a model curriculum for a university course in health impact assessment in the USA

The Healthy Air, Healthy Schools Study was established in January 2020 to better understand the impact of ultrafine particles (UFP) on indoor air quality in communities surrounding Seattle-Tacoma (Sea-Tac) International Airport. The study team took multipollutant measurements indoor and outdoor air pollution at five participating school locations to infiltration indoors. The schools participating in this project were located within a 7-mile radius of Sea-Tac Airport and within 0.5 miles of an active flight path. Based on experimental measures in an unoccupied classroom, infiltration rates of a) Ultrafine particles of aircraft origin b) Ultrafine particles of traffic origin and c) Wildfire smoke or other outdoor pollutants were characterized before and after the introduction of a classroom based portable HEPA filter intervention. The portable HEPA cleaners were an effective short-term intervention to improve the air quality in classroom environments, reducing the ultrafine particles to approximately 1/10th of that measured outside. Before the HEPA filter deployment, approximately one-half of all outdoor UFPs were measured indoors. This study is unique in focusing on UFP in school settings and demonstrating through multivariate methods that the UFP measured in the classroom space is primarily of outdoor origin. Although existing research suggests that improvements to indoor air quality in homes can significantly improve asthma outcomes, further research is necessary to establish the benefit to student health and academic performance of improved air quality in schools.

Indoor Air Quality Intervention in Schools; Effectiveness of a Portable HEPA Filter Deployment in Five Schools Impacted by Roadway and Aircraft Pollution Sources

Commercially available low-cost particulate matter (PM) sensors provide output as total or size-specific particle counts and mass concentrations. These quantities are not measured directly but are estimated by the original equipment manufacturers' (OEM) proprietary algorithms and have inherent limitations since particle scattering depends on their composition, size, shape, and complex index of refraction (CRI). Hence, there is a need to characterize and calibrate their performance under a controlled environment. We present calibration algorithms for Plantower PMS A003 sensor as a function of particle size and concentration. A standardized experimental protocol was used to control the PM level, environmental conditions and to evaluate sensor-to-sensor reproducibility. The calibration was based on tests when PMS A003 were exposed to different polydisperse standardized testing aerosols. The results suggested particle size distribution from PMS A003 was shifted compared to reference instrument measures. For calibration of number concentration, linear model without adjusting aerosol properties corrects the raw PMS A003 measurement for specific size bins with normalized mean absolute error within 4.0% of the reference instrument. Although the Bayesian Information Criterion suggests that models adjusting for particle optical properties and relative humidity are technically superior, they should be used with caution as the particle properties used in fitting were within a narrow range for challenge aerosols. The calibration models adjusted for particle CRI and density account for non-linearity in the OEM's mass concentrations estimates and demonstrated lower error. These results have significant implications for using PMS A003 in high concentration environments, including indoor air quality and occupational/industrial exposure assessments, wildfire smoke, or near-source monitoring scenarios.

Assessing the Value of Complex Refractive Index and Particle Density for Calibration of Low-Cost Particle Matter Sensor for Size-Resolved Particle Count and PM2.5 Measurements

Abstract:Background: This article describes the process and educational materials developed and implemented for high school students through a partnership between an urban public university and a rural, non-profit university. This specific partnership was novel but originated within a long-standing community-academic partnership. This project took place in a rural community impacted by air pollution and a higher asthma hospitalization rate compared with the rest of the state.Objectives: The objectives of this article are to describe the development and implementation of a high school program where students conducted their own research on local air quality using low-cost monitors with the guidance of undergraduate student mentors.Methods: University faculty, researchers, and students collaborated to develop an air quality curriculum relevant to local issues. This curriculum was delivered to high school students through an existing after school program, and guided students in conducting their own research on community air pollution. The students used university-provided low-cost monitors for their research, and presented their research to community members. Student learning was supported through hands-on activities and conducting research projects. Student projects examined air quality variation indoors within their school, outdoors in their community, and at home.Conclusions: This curriculum can be adapted for use with students in many different communities. It will likely be most successful and engaging if adapted to local air pollution sources and issues, and implemented through an existing programmatic structure with a high mentor to student ratio.

Partnership to Develop and Deliver Curriculum Supporting Student-led Air Quality Research in Rural Washington State

Characterization of time- and size-dependent particle emissions and decay from cooking oil fumes in residence: Impacts of various intervention measures

Edmund Seto

Papers

PROFESSIONAL PRACTICE PAPER Developing a model curriculum for a university course in health impact assessment in the USA

Indoor Air Quality Intervention in Schools; Effectiveness of a Portable HEPA Filter Deployment in Five Schools Impacted by Roadway and Aircraft Pollution Sources

Assessing the Value of Complex Refractive Index and Particle Density for Calibration of Low-Cost Particle Matter Sensor for Size-Resolved Particle Count and PM2.5 Measurements

Partnership to Develop and Deliver Curriculum Supporting Student-led Air Quality Research in Rural Washington State

Characterization of time- and size-dependent particle emissions and decay from cooking oil fumes in residence: Impacts of various intervention measures