Dataset Information

Selective Detection of Target Volatile Organic Compounds in Contaminated Air Using Sensor Array with Machine Learning: Aging Notes and Mold Smells in Simulated Automobile Interior Contaminant Gases.

ABSTRACT: We investigated the selective detection of target volatile organic compounds (VOCs) which are age-related body odors (namely, 2-nonenal, pelargonic acid, and diacetyl) and a fungal odor (namely, acetic acid) in the presence of interference VOCs from car interiors (namely, n-decane, and butyl acetate). We used eight semiconductive gas sensors as a sensor array; analyzing their signals using machine learning; principal-component analysis (PCA), and linear-discriminant analysis (LDA) as dimensionality-reduction methods; k-nearest-neighbor (kNN) classification to evaluate the accuracy of target-gas determination; and random forest and ReliefF feature selections to choose appropriate sensors from our sensor array. PCA and LDA scores from the sensor responses to each target gas with contaminant gases were generally within the area of each target gas; hence; discrimination between each target gas was nearly achieved. Random forest and ReliefF efficiently reduced the required number of sensors, and kNN verified the quality of target-gas discrimination by each sensor set.

SUBMITTER: Itoh T

PROVIDER: S-EPMC7248965 | biostudies-literature | 2020 May

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Selective Detection of Target Volatile Organic Compounds in Contaminated Air Using Sensor Array with Machine Learning: Aging Notes and Mold Smells in Simulated Automobile Interior Contaminant Gases.

Itoh Toshio T Koyama Yutaro Y Shin Woosuck W Akamatsu Takafumi T Tsuruta Akihiro A Masuda Yoshitake Y Uchiyama Kazuhisa K

Sensors (Basel, Switzerland) 20200508 9

We investigated the selective detection of target volatile organic compounds (VOCs) which are age-related body odors (namely, 2-nonenal, pelargonic acid, and diacetyl) and a fungal odor (namely, acetic acid) in the presence of interference VOCs from car interiors (namely, <i>n</i>-decane, and butyl acetate). We used eight semiconductive gas sensors as a sensor array; analyzing their signals using machine learning; principal-component analysis (PCA), and linear-discriminant analysis (LDA) as dime ...[more]

PMID: 32397213

Similar Datasets

Project description:BACKGROUND:Low ridership of public transit buses among wheeled mobility device users suggests the need to identify vehicle design conditions that are either particularly accommodating or challenging. The objective of this study was to determine the effects of low-floor bus interior seating configuration and passenger load on wheeled mobility device user-reported difficulty, overall acceptability and design preference. METHODS:Forty-eight wheeled mobility users evaluated three interior design layouts at two levels of passenger load (high vs. low) after simulating boarding and disembarking tasks on a static full-scale low-floor bus mockup. RESULTS:User self-reports of task difficulty, acceptability and design preference were analyzed across the different test conditions. Ramp ascent was the most difficult task for manual wheelchair users relative to other tasks. The most difficult tasks for users of power wheelchairs and scooters were related to interior circulation, including moving to the securement area, entry and positioning in the securement area and exiting the securement area. Boarding and disembarking at the rear doorway was significantly more acceptable and preferred compared to the layouts with front doorways. CONCLUSION:Understanding transit usability barriers, perceptions and preferences among wheeled mobility users is an important consideration for clinicians who recommend mobility-related device interventions to those who use public transportation. Implications for Rehabilitation In order to maximize community participation opportunities for wheeled mobility users, clinicians should consider potential public transit barriers during the processes of wheelchair device selection and skills training. Usability barriers experienced by wheeled mobility device users on transit vehicles differ by mobility device type and vehicle configurations. Full-scale environment simulations are an effective means of identifying usability barriers and design needs in people with mobility impairments and may provide an alternative model for determining readiness for using fixed route buses or eligibility for paratransit.

Dataset Information

Selective Detection of Target Volatile Organic Compounds in Contaminated Air Using Sensor Array with Machine Learning: Aging Notes and Mold Smells in Simulated Automobile Interior Contaminant Gases.

Publications

Selective Detection of Target Volatile Organic Compounds in Contaminated Air Using Sensor Array with Machine Learning: Aging Notes and Mold Smells in Simulated Automobile Interior Contaminant Gases.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure