Particulate matter characterization by gray level co-occurrence matrix based support vector machines.

EECS Department, University of Toledo, Toledo, OH 43606, USA.
Journal of hazardous materials (Impact Factor: 4.14). 04/2012; 223-224:94-103. DOI: 10.1016/j.jhazmat.2012.04.056
Source: PubMed

ABSTRACT An efficient and highly reliable automatic selection of optimal segmentation algorithm for characterizing particulate matter is presented in this paper. Support vector machines (SVMs) are used as a new self-regulating classifier trained by gray level co-occurrence matrix (GLCM) of the image. This matrix is calculated at various angles and the texture features are evaluated for classifying the images. Results show that the performance of GLCM-based SVMs is drastically improved over the previous histogram-based SVMs. Our proposed GLCM-based approach of training SVM predicts a robust and more accurate segmentation algorithm than the standard histogram technique, as additional information based on the spatial relationship between pixels is incorporated for image classification. Further, the GLCM-based SVM classifiers were more accurate and required less training data when compared to the artificial neural network (ANN) classifiers.

  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Increasing demand for fossil fuels due to the luxurious lifestyle, significant growth of population, transportation and the basic industry sectors has caused serious environmental problems. Moreover, a rapid decline in the fossil fuels has led scientists and researchers to look for new alternatives. In this regard, alternative fuels such as biofuels are becoming important increasingly due to environmental and energy concerns. Biofuels are commonly referred to as first generations, which are produced primarily from food crops. However, the use of edible oil to produce biodiesel in many countries is not feasible in view of a big gap in the demand and supply of such oils for dietary consumption. This paper critically reviews the facts and prospects of biofuel utilization especially, three edible biodiesels namely soybean, rapeseed, palm and two non-edible viz. jatropha and cottonseed to reduce engine exhaust gas, noise emission and petro dependency. Based on various biofuel feedstocks, this paper generally found that biodiesel fuels are considered as offering many benefits, including sustainability, reduction of greenhouse gas emissions and many harmful pollutants along with noise emission, regional development, social structure and agriculture, and security of supply.
    Renewable and Sustainable Energy Reviews 01/2013; 18:552-567. · 5.63 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: In order to maintain cab comfort truck drivers have to idle their engine to obtain the required power for accessories, such as the air conditioner, heater, television, refrigerator, and lights. This idling of the engine has a major impact on its fuel consumption and exhaust emission. Idling emissions can be as high as 86.4 g/h, 16,500 g/h, 5130 g/h, 4 g/h, and 375 g/h for HC, CO2, CO, PM, and NOx, respectively. Idling fuel consumption rate can be as high as 1.85 gal/h. The accessory loading, truck model, fuel-injection system, ambient temperature, idling speed, etc., also affect significantly the emission levels and fuel consumption rate. An increase in accessory loading and ambient temperature increases the emissions and fuel consumption. During idling, electronic fuel-injection systems reduce HC, PM, and CO emission, but increase NOx emissions compared with a mechanical fuel-injection system. An increase of idling speed increases fuel consumption rate. There are many systems available on the market to reduce engine idling and improve air quality and fuel consumption rate, such as an auxiliary power unit (APU), truck stop electrification, thermal storage systems, fuel cells, and direct fire heaters. A direct fire heater reduces fuel consumption by 94–96% and an APU reduces consumption by 60–87%. Furthermore, these technologies increase air quality significantly by reducing idling emissions, which is the reason why they are considered as key alternatives to engine idling.
    Energy Conversion and Management 10/2013; 74:171-182. · 2.78 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Present energy situation of the world is unsustainable due to unequal geographical distribution of natural wealth as well as environmental, geopolitical and economical concerns. Ever increasing drift of energy consumption due to growth of population, transportation and luxurious lifestyle has motivated researchers to carry out research on biofuels as a sustainable alternative fuel for diesel engine. Renewability, cost effectiveness and reduction of pollutants in exhaust gas emission are promoting biofuels as a suitable substitute of diesel fuel in near future. This paper reviews the suitability of feedstock and comparative performance and emission of palm, mustard, waste cooking oil (WCO) and Calophyllum inophyllum biofuels with respect to diesel fuel from various recent publications. Probable analysis of performance and emission of biofuel is also included in further discussion. Palm oil has versatile qualities in terms of productivity, oil yield and land utilization. But tremendous demand of edible oil is motivating the use of non-edible vegetable oils as biofuel feedstock. Mustard oil is a promising new biofuel especially regarding NOx reduction. WCO is one of the most economic sources of biofuel which efficiently helps in liquid waste management and prevents recycling of used oil, injurious to human health. C. inophyllum is completely non-edible and trans-esterified oil shows similar engine performance and emission characteristics like other biofuels. Limited data were published regarding mustard and C. inophyllum as their use as biofuel is still in primary state compared to palm or WCO. Therefore, in depth research needs to be carried out on these two oils to use them effectively as alternative fuels.
    Renewable and Sustainable Energy Reviews 11/2013; 27:664-682. · 5.63 Impact Factor