Comparative Study of Classification Algorithms to Detect Interlayer Debondings within Pavement Structures from Step-Frequency Radar Data

Author(s):  
Shreedhar Savant Todkar ◽  
Cedric Le Bastard ◽  
Vincent Baltazart ◽  
Amine Ihamouten ◽  
Xavier Derobort
Author(s):  
Anish Mebal. P ◽  
Hema. S ◽  
Jothika. S.J ◽  
Manochitra M

Now-a-days the more accurate prediction of the demand for fast-moving consumer goods (FMCG) is a competitive factor for both the manufacturers and retailers, especially in the super markets, wholesale manufacturers and fresh food sectors and other consumable industries. This proposed system presents the benefits of Machine Learning in sales forecasting for short shelf-life and highly-perishable products, as it predict the statistical information as a result, improves inventory balancing throughout the chain, improving availability to consumers and increasing profitability. This performance is done with various classification algorithms and comparative study is done with some metrics like accuracy, precision, recall and f-score. So that it helps in finding customer need and to increase the profit of the manufacturers


2017 ◽  
Vol 9 (3) ◽  
pp. 58-72 ◽  
Author(s):  
Guangyu Wang ◽  
Xiaotian Wu ◽  
WeiQi Yan

The security issue of currency has attracted awareness from the public. De-spite the development of applying various anti-counterfeit methods on currency notes, cheaters are able to produce illegal copies and circulate them in market without being detected. By reviewing related work in currency security, the focus of this paper is on conducting a comparative study of feature extraction and classification algorithms of currency notes authentication. We extract various computational features from the dataset consisting of US dollar (USD), Chinese Yuan (CNY) and New Zealand Dollar (NZD) and apply the classification algorithms to currency identification. Our contributions are to find and implement various algorithms from the existing literatures and choose the best approaches for use.


2006 ◽  
Vol 23 (7) ◽  
pp. 952-963 ◽  
Author(s):  
Sergey Y. Matrosov ◽  
Robert Cifelli ◽  
Patrick C. Kennedy ◽  
Steven W. Nesbitt ◽  
Steven A. Rutledge ◽  
...  

Abstract A comparative study of the use of X- and S-band polarimetric radars for rainfall parameter retrievals is presented. The main advantage of X-band polarimetric measurements is the availability of reliable specific differential phase shift estimates, KDP, for lighter rainfalls when phase measurements at the S band are too noisy to produce usable KDP. Theoretical modeling with experimental raindrop size distributions indicates that due to some non-Rayleigh resonant effects, KDP values at a 3.2-cm wavelength (X band) are on average a factor of 3.7 greater than at 11 cm (S band), which is a somewhat larger difference than simple frequency scaling predicts. The non-Rayleigh effects also cause X-band horizontal polarization reflectivity, Zeh, and differential reflectivity, ZDR, to be larger than those at the S band. The differences between X- and S-band reflectivities can exceed measurement uncertainties for Zeh starting approximately at Zeh > 40 dBZ, and for ZDR when the mass-weighted drop diameter, Dm, exceeds about 2 mm. Simultaneous X- and S-band radar measurements of rainfall showed that consistent KDP estimates exceeding about 0.1° km−1 began to be possible at reflectivities greater than ∼26–30 dBZ while at the S band such estimates can generally be made if Zeh > ∼35–39 dBZ. Experimental radar data taken in light-to-moderate stratiform rainfalls with rain rates R in an interval from 2.5 to 15 mm h−1 showed availability of the KDP-based estimates of R for most of the data points at the X band while at the S band such estimates were available only for R greater than about 8–10 mm h−1. After correcting X-band differential reflectivity measurements for differential attenuation, ZDR measurements at both radar frequency bands were in good agreement with each other for Dm < 2 mm, which approximately corresponds to ZDR ≈ 1.6 dB. The ZDR-based retrievals of characteristic raindrop sizes also agreed well with in situ disdrometer measurements.


2018 ◽  
pp. 252-269
Author(s):  
Guangyu Wang ◽  
Xiaotian Wu ◽  
WeiQi Yan

The security issue of currency has attracted awareness from the public. De-spite the development of applying various anti-counterfeit methods on currency notes, cheaters are able to produce illegal copies and circulate them in market without being detected. By reviewing related work in currency security, the focus of this paper is on conducting a comparative study of feature extraction and classification algorithms of currency notes authentication. We extract various computational features from the dataset consisting of US dollar (USD), Chinese Yuan (CNY) and New Zealand Dollar (NZD) and apply the classification algorithms to currency identification. Our contributions are to find and implement various algorithms from the existing literatures and choose the best approaches for use.


Sign in / Sign up

Export Citation Format

Share Document