The optical character recognition for the right to left and cursive languages such as Arabic is challenging and received little attention from researchers in the past compared to the other Latin languages.Moreover,the...The optical character recognition for the right to left and cursive languages such as Arabic is challenging and received little attention from researchers in the past compared to the other Latin languages.Moreover,the absence of a standard publicly available dataset for several low-resource lan-guages,including the Pashto language remained a hurdle in the advancement of language processing.Realizing that,a clean dataset is the fundamental and core requirement of character recognition,this research begins with dataset generation and aims at a system capable of complete language understanding.Keeping in view the complete and full autonomous recognition of the cursive Pashto script.The first achievement of this research is a clean and standard dataset for the isolated characters of the Pashto script.In this paper,a database of isolated Pashto characters for forty four alphabets using various font styles has been introduced.In order to overcome the font style shortage,the graphical software Inkscape has been used to generate sufficient image data samples for each character.The dataset has been pre-processed and reduced in dimensions to 32×32 pixels,and further converted into the binary format with a black background and white text so that it resembles the Modified National Institute of Standards and Technology(MNIST)database.The benchmark database is publicly available for further research on the standard GitHub and Kaggle database servers both in pixel and Comma Separated Values(CSV)formats.展开更多
This paper presented chemical characteristics of wetland inflow diffuse dust and dirt. Single land use impervious areas (parking and roads) were observed and analyzed in commercial and residential areas for organic ma...This paper presented chemical characteristics of wetland inflow diffuse dust and dirt. Single land use impervious areas (parking and roads) were observed and analyzed in commercial and residential areas for organic matters, phosphorus and heavy metals. The buildup data were collected for approximately six months from December to June. The frequency of monitoring was observed daily for the first two months, twice a week for the next two months and once a week for the last two months. The results indicated significant variations in the organic matters and heavy metals strength and total accumulation among the observed areas. High pollutants strength was associated with smaller dust and dirt (DD) particles. Concentrations of phosphorus varied between 5.1 μg/g and 8.3 μg/g in DD particle less than 75 μm and account for 35%-60% of the total phosphorus. The organic matter accumulation rate associated with particles less than 600 μm and greater than 600 μm was 0.1-1 g·(curb-m) -1 ·d -1 and 0.1- 1.5 g·(curb-m) -1 ·d -1 , respectively. DD particles greater than 600 μm consist of 70%-90% of leaves and other plant residues. The strength of heavy metals was more at road compared to parking areas both in commercial and residential areas. Percentage of Zn, Cu and Pb attached with particles less than 200 μm were in the range of 50%-70% in parking, 45%-90% on smooth roads and 30%-80% on rough roads. All the dust and dirt exhibited rising trend with time. Dust and dirt buildup data follow a non-linear accumulation function and can be presented better either by an exponential or power function.展开更多
文摘The optical character recognition for the right to left and cursive languages such as Arabic is challenging and received little attention from researchers in the past compared to the other Latin languages.Moreover,the absence of a standard publicly available dataset for several low-resource lan-guages,including the Pashto language remained a hurdle in the advancement of language processing.Realizing that,a clean dataset is the fundamental and core requirement of character recognition,this research begins with dataset generation and aims at a system capable of complete language understanding.Keeping in view the complete and full autonomous recognition of the cursive Pashto script.The first achievement of this research is a clean and standard dataset for the isolated characters of the Pashto script.In this paper,a database of isolated Pashto characters for forty four alphabets using various font styles has been introduced.In order to overcome the font style shortage,the graphical software Inkscape has been used to generate sufficient image data samples for each character.The dataset has been pre-processed and reduced in dimensions to 32×32 pixels,and further converted into the binary format with a black background and white text so that it resembles the Modified National Institute of Standards and Technology(MNIST)database.The benchmark database is publicly available for further research on the standard GitHub and Kaggle database servers both in pixel and Comma Separated Values(CSV)formats.
文摘This paper presented chemical characteristics of wetland inflow diffuse dust and dirt. Single land use impervious areas (parking and roads) were observed and analyzed in commercial and residential areas for organic matters, phosphorus and heavy metals. The buildup data were collected for approximately six months from December to June. The frequency of monitoring was observed daily for the first two months, twice a week for the next two months and once a week for the last two months. The results indicated significant variations in the organic matters and heavy metals strength and total accumulation among the observed areas. High pollutants strength was associated with smaller dust and dirt (DD) particles. Concentrations of phosphorus varied between 5.1 μg/g and 8.3 μg/g in DD particle less than 75 μm and account for 35%-60% of the total phosphorus. The organic matter accumulation rate associated with particles less than 600 μm and greater than 600 μm was 0.1-1 g·(curb-m) -1 ·d -1 and 0.1- 1.5 g·(curb-m) -1 ·d -1 , respectively. DD particles greater than 600 μm consist of 70%-90% of leaves and other plant residues. The strength of heavy metals was more at road compared to parking areas both in commercial and residential areas. Percentage of Zn, Cu and Pb attached with particles less than 200 μm were in the range of 50%-70% in parking, 45%-90% on smooth roads and 30%-80% on rough roads. All the dust and dirt exhibited rising trend with time. Dust and dirt buildup data follow a non-linear accumulation function and can be presented better either by an exponential or power function.
