In this research work,an efficient sign language recognition tool for e-learning has been proposed with a new type of feature set based on angle and lines.This feature set has the ability to increase the overall perfo...In this research work,an efficient sign language recognition tool for e-learning has been proposed with a new type of feature set based on angle and lines.This feature set has the ability to increase the overall performance of machine learning algorithms in an efficient way.The hand gesture recognition based on these features has been implemented for usage in real-time.The feature set used hand landmarks,which were generated using media-pipe(MediaPipe)and open computer vision(openCV)on each frame of the incoming video.The overall algorithm has been tested on two well-known ASLalphabet(American Sign Language)and ISL-HS(Irish Sign Language)sign language datasets.Different machine learning classifiers including random forest,decision tree,and naïve Bayesian have been used to classify hand gestures using this unique feature set and their respective results have been compared.Since the random forest classifier performed better,it has been selected as the base classifier for the proposed system.It showed 96.7%accuracy with ISL-HS and 93.7%accuracy with ASL-alphabet dataset using the extracted features.展开更多
The red palm weevil（RPW; Rhynchophorus ferrugineus） is spreading worldwide and severely harming many palm species. However, most studies on RPW focused on insect biology, and little information is available about th...The red palm weevil（RPW; Rhynchophorus ferrugineus） is spreading worldwide and severely harming many palm species. However, most studies on RPW focused on insect biology, and little information is available about the plant response to the attack. In the present experiment, we used metabolomics to study the alteration of the leaf metabolome of Phoenix canariensis at initial（1^（st） stage） or advanced（2^（nd） stage）attack by RPW compared with healthy（unattacked） plants.The leaf metabolome significantly varied among treatments. At the 1^（st） stage of attack, plants showed a reprogramming of carbohydrate and organic acid metabolism; in contrast, peptides and lipid metabolic pathways underwent more changes during the 2^（nd） than 1^（st） stage of attack. Enrichment metabolomics analysis indicated that RPW attack mostly affected a particular group of compounds rather than rearranging plant metabolic pathways. Some compounds selectively affected during the 1^（st） rather than 2^（nd） stage（e.g. phenylalanine; tryptophan; cellobiose;xylose; quinate; xylonite; idonate; and iso-threonate; cellobiotol and arbutine） are upstream events in the phenylpropanoid,terpenoid and alkaloid biosynthesis. These compounds could be designated as potential markers of initial RPW attack. However,further investigation is needed to determine efficient early screening methods of RPW attack based on the concentrations of these molecules.展开更多
基金This research was supported by a Grant(2021R1F1A1063634)of the Basic Science Research Program through the National Research Foundation(NRF)funded by the Ministry of Education,Republic of Korea.
文摘In this research work,an efficient sign language recognition tool for e-learning has been proposed with a new type of feature set based on angle and lines.This feature set has the ability to increase the overall performance of machine learning algorithms in an efficient way.The hand gesture recognition based on these features has been implemented for usage in real-time.The feature set used hand landmarks,which were generated using media-pipe(MediaPipe)and open computer vision(openCV)on each frame of the incoming video.The overall algorithm has been tested on two well-known ASLalphabet(American Sign Language)and ISL-HS(Irish Sign Language)sign language datasets.Different machine learning classifiers including random forest,decision tree,and naïve Bayesian have been used to classify hand gestures using this unique feature set and their respective results have been compared.Since the random forest classifier performed better,it has been selected as the base classifier for the proposed system.It showed 96.7%accuracy with ISL-HS and 93.7%accuracy with ASL-alphabet dataset using the extracted features.
基金funded by the Project PROPALMA(D.M.25618/7301/11)by the Italian Ministry of Agricultural,Food and Forestry Policies(Mi PAAF)
文摘The red palm weevil（RPW; Rhynchophorus ferrugineus） is spreading worldwide and severely harming many palm species. However, most studies on RPW focused on insect biology, and little information is available about the plant response to the attack. In the present experiment, we used metabolomics to study the alteration of the leaf metabolome of Phoenix canariensis at initial（1^（st） stage） or advanced（2^（nd） stage）attack by RPW compared with healthy（unattacked） plants.The leaf metabolome significantly varied among treatments. At the 1^（st） stage of attack, plants showed a reprogramming of carbohydrate and organic acid metabolism; in contrast, peptides and lipid metabolic pathways underwent more changes during the 2^（nd） than 1^（st） stage of attack. Enrichment metabolomics analysis indicated that RPW attack mostly affected a particular group of compounds rather than rearranging plant metabolic pathways. Some compounds selectively affected during the 1^（st） rather than 2^（nd） stage（e.g. phenylalanine; tryptophan; cellobiose;xylose; quinate; xylonite; idonate; and iso-threonate; cellobiotol and arbutine） are upstream events in the phenylpropanoid,terpenoid and alkaloid biosynthesis. These compounds could be designated as potential markers of initial RPW attack. However,further investigation is needed to determine efficient early screening methods of RPW attack based on the concentrations of these molecules.
