Search Results

Now showing 1 - 6 of 6

Some of the metrics are blocked by your
consent settings
ConvXGB: A new deep learning model for classification problems based on CNN and XGBoost
(2021-02-01)
Thongsuwan, Setthanun
;
Jaiyen, Saichon
;
Padcharoen, Anantachai
;
Agarwal, Praveen
We describe a new deep learning model - Convolutional eXtreme Gradient Boosting (ConvXGB) for classification problems based on convolutional neural nets and Chen et al.’s XGBoost. As well as image data, ConvXGB also supports the general classification problems, with a data preprocessing module. ConvXGB consists of several stacked convolutional layers to learn the features of the input and is able to learn features automatically, followed by XGBoost in the last layer for predicting the class labels. The ConvXGB model is simplified by reducing the number of parameters under appropriate conditions, since it is not necessary re-adjust the weight values in a back propagation cycle. Experiments on several data sets from UCL Repository, including images and general data sets, showed that our model handled the classification problems, for all the tested data sets, slightly better than CNN and XGBoost alone and was sometimes significantly better.
Some of the metrics are blocked by your
consent settings
Relationship between overall difference decision and electronic tongue: Discrimination of civet coffee
(2016-07-01)
Lopetcharat, Kannapon
;
Kulapichitr, Fareeya
;
Suppavorasatit, Inthawoot
;
Chodjarusawad, Thanawee
;
Phatthara-Aneksin, Anat
This paper demonstrates a new approach to relate electronic tongue (E-tongue) to human perception for fine quality of beverage. Six civet, one weasel and one non-civet coffees were chosen as the testing platform. The sensory test based on the overall difference method by pair comparison followed by sureness-rating tasks was divided into three experiments. In each, 12-14 consumers were asked to express differences in six pairs of hot brew coffee samples on a four-point scale. The results were analyzed by the Multi-Dimensional Scaling (MDS) analysis. An in-house electronic tongue based on cyclic voltammetry and the Principal Component Analysis (PCA) was applied to measure the coffee samples, alongside the panel test. The relationship between PCA and MDS solutions was obtained by Generalized Procrustes Analysis (GPA), which reveals a strong correlation between E-tongue and human perception. Both were able to identify differences between all coffee samples from different sources.
Some of the metrics are blocked by your
consent settings
Fringe patterns generated by micro-optical sensors for pattern recognition
(2015-01-01)
Tamee, Kreangsak
;
Chaiwong, Khomyuth
;
Yothapakdee, Kriengsak
;
Yupapin, Preecha P.
We present a new result of pattern recognition generation scheme using a small-scale optical muscle sensing system, which consisted of an optical add-drop filter incorporating two nonlinear optical side ring resonators. When light from laser source enters into the system, the device is stimulated by an external physical parameter that introduces a change in the phase of light propagation within the sensing device, which can be formed by the interference fringe patterns. Results obtained have shown that the fringe patterns can be used to form the relationship between signal patterns and fringe pattern recognitions.
Some of the metrics are blocked by your
consent settings
Polymer-coated single-walled carbon nanotubes for ethanol and dichloromethane discrimination
(2013-10-29)
Muangrat, Worawut
;
Maolanon, Rungroj
;
Pratontep, Sirapat
;
Porntheeraphat, Supanit
;
Wongwiriyapan, Winadda
Sensor response and pattern recognition of polymer-coated single-walled carbon nanotubes (SWNTs) were investigated. Printed circuit board (PCB) with Cu/Au interdigitated electrode was used as sensor platform. SWNTs network was firstly formed on PCB by drop-casting. For polymer-coated SWNTs preparation, poly(methyl methacrylate) (PMMA) and thiophene were employed as polymers to coat on SWNTs by spin coating; PMMA/SWNTs and thiophene/SWNTs. Raman spectra showed no obvious structure changes of SWNTs after polymer coating. Next, gas sensing test was conducted. Pristine SWNTs, PMMA/SWNTs and thiophene/SWNTs were exposed to vapors of ethanol and dichloromethane at room temperature. From normalized sensor response results, it was found that pristine SWNTs and PMMA/SWNTs showed the highest response to ethanol and dichloromethane vapors, respectively. In order to discriminate vapors between ethanol and dichloromethane, pattern recognition technique was utilized. Principal component analysis (PCA) results showed that pattern recognition of ethanol and dichloromethane vapors can be discriminated by using pristine SWNTs and polymer-coated SWNTs sensors. © (2013) Trans Tech Publications, Switzerland.
1
Some of the metrics are blocked by your
consent settings
Pattern recognition technique for PAD inspection using chain-code-discrete fourier transform and signal correlation
(2011-07-26)
Saenthon, Anakkapon
;
Kaitwanidvilai, Somyot
This paper presents a new technique to recognize pattern for inspecting PAD, which is an important part in Hard Disk Drive (HDD) component and IC circuit. The proposed technique uses chain-code and discrete Fourier's transform for feature extraction, and uses signal correlation technique for classifying the pattern. The extraction of object's edge is performed to determine the position and alignment of PAD. The accuracy and inspection time of the proposed algorithm are investigated and compared with the other pattern recognition techniques, such as full template matching, coarse to fine method, etc. Experimental results show the effectiveness of the proposed technique.
1
Some of the metrics are blocked by your
consent settings
Thai vehicle license plate recognition using the hierarchical cross-correlation ARTMAP
(2006-12-01)
Duangphasuk, Pruegsa
;
Thammano, Arit
This paper proposes a Thai vehicle license plate recognition system, called the hierarchical cross-correlation ARTMAP. An ability to separately train each segment of the network gives the hierarchical cross-correlation ARTMAP an advantage over the other approaches. The experimental results show that the hierarchical cross-correlation ARTMAP outperforms the other approaches by a wide margin. © 2006 IEEE.

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results