http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Animal Face Classification using Dual Deep Convolutional Neural Network
Rafiul Hasan Khan,Kyung-Won Kang,Seon-Ja Lim,윤성대,권오준,이석환,권기룡 한국멀티미디어학회 2020 멀티미디어학회논문지 Vol.23 No.4
A practical animal face classification system that classifies animals in image and video data is considered as a pivotal topic in machine learning. In this research, we are proposing a novel method of fully connected dual Deep Convolutional Neural Network (DCNN), which extracts and analyzes image features on a large scale. With the inclusion of the state of the art Batch Normalization layer and Exponential Linear Unit (ELU) layer, our proposed DCNN has gained the capability of analyzing a large amount of dataset as well as extracting more features than before. For this research, we have built our dataset containing ten thousand animal faces of ten animal classes and a dual DCNN. The significance of our network is that it has four sets of convolutional functions that work laterally with each other. We used a relatively small amount of batch size and a large number of iteration to mitigate overfitting during the training session. We have also used image augmentation to vary the shapes of the training images for the better learning process. The results demonstrate that, with an accuracy rate of 92.0%, the proposed DCNN outruns its counterparts while causing less computing costs.
Animal Face Classification using Dual Deep Convolutional Neural Network
Khan, Rafiul Hasan,Kang, Kyung-Won,Lim, Seon-Ja,Youn, Sung-Dae,Kwon, Oh-Jun,Lee, Suk-Hwan,Kwon, Ki-Ryong Korea Multimedia Society 2020 멀티미디어학회논문지 Vol.23 No.4
A practical animal face classification system that classifies animals in image and video data is considered as a pivotal topic in machine learning. In this research, we are proposing a novel method of fully connected dual Deep Convolutional Neural Network (DCNN), which extracts and analyzes image features on a large scale. With the inclusion of the state of the art Batch Normalization layer and Exponential Linear Unit (ELU) layer, our proposed DCNN has gained the capability of analyzing a large amount of dataset as well as extracting more features than before. For this research, we have built our dataset containing ten thousand animal faces of ten animal classes and a dual DCNN. The significance of our network is that it has four sets of convolutional functions that work laterally with each other. We used a relatively small amount of batch size and a large number of iteration to mitigate overfitting during the training session. We have also used image augmentation to vary the shapes of the training images for the better learning process. The results demonstrate that, with an accuracy rate of 92.0%, the proposed DCNN outruns its counterparts while causing less computing costs.
Khan, Rafiul Hasan,Lee, Youngsuk,Lee, Suk-Hwan,Kwon, Oh-Jun,Kwon, Ki-Ryong Korea Multimedia Society 2019 멀티미디어학회논문지 Vol.22 No.5
Anthropomorphism is the attribution of human traits, emotions, or intentions to non-human entities. Anthropomorphic animal face masking is the process by which human characteristics are plotted on the animal kind. In this research, we are proposing a compact system which finds the resemblance between a human face and animal face using Deep Convolutional Neural Network (DCNN) and later applies morphism between them. The whole process is done by firstly finding which animal most resembles the particular human face through a DCNN based animal face classification. And secondly, doing triangulation based morphing between the particular human face and the most resembled animal face. Compared to the conventional manual Control Point Selection system using an animator, we are proposing a Viola-Jones algorithm based Control Point selection process which detects facial features for the human face and takes the Control Points automatically. To initiate our approach, we built our own dataset containing ten thousand animal faces and a fourteen layer DCNN. The simulation results firstly demonstrate that the accuracy of our proposed DCNN architecture outperforms the related methods for the animal face classification. Secondly, the proposed morphing method manages to complete the morphing process with less deformation and without any human assistance.
Histological Observation of Developmental Somatic Embryos of Eleutherococcus sessiliflorus
Abdullah Mohammad Shohael,Rafiul Islam,Eun-Joo Hahn,Kee-Yoeup Paek 한국원예학회 2006 Horticulture, Environment, and Biotechnology Vol.47 No.1
Calli were initiated from leaf explants of Eleutherococcus sessiliflorus cultured on Murashige and Skoog (MS) medium supplemented with 1.0 ㎎ㆍL?¹ 2,4-dichlorophenoxyacetic acid. Somatic embryos were induced in MS medium without plant growth regulators. The cells from friable embryogenic calli were converted to proembryogenic masses and started divisions, which resulted in the formation of the meristemic cells. The meristemic cells continued division to develop into globular, then heart, torpedo, and finally cotyledonary structures. These embryos contained well-defined root and shoot meristemetic zones and developed into plantlets. Embryogenic calli, non-embryogenic calli and their different developmental stages were histologically observed and described. Histological studies confirmed that developed embryos from leaf explants were somatic embryos, which passed through all the stages of normal embryo development.
Nilofer Sheikh,Himangshu Patowary,Rafiul Amin Laskar 대한독성 유전단백체 학회 2020 Molecular & cellular toxicology Vol.16 No.3
Background Malathion (organophosphate) and cypermethrin (pyrethroid) are widely in use to facilitate protection of major food crops in agriculture, due to which it is important to understand their toxic potential. Allium cepa L. has been considered as a reliable genetic model to detect the toxicity of all sorts of pollutants. Objective The objective of the present work is to determine the cytotoxic and genotoxic effects of two widely used pesticides (malathion and cypermethrin) using A. cepa assay. Allium root growth inhibition test showed 0.5% concentration as the EC50 value in both the pesticides. In the toxicity experiment, 1/10 × EC50; 1/5 × EC50; EC50; 2 × EC50 and 3 × EC50 concentrations of both the pesticides along with a control were employed in Allium assay. Results Cytotoxic study showed mitotic index decreased with increasing the pesticides concentrations and exposure time. A series of mitotoxicity was observed under the influence of malathon and cypermethrin. Most types of chromosome aberrations observed in high percentage were stickiness, disturbance, c-metaphase, chromosome bridges in anaphase, lagging chromosome, and binucleate lesions. It was observed that malathion and cypermethrin are highly genotoxic to the onion, causing aberration at different phases of mitosis which can arrest cellular growth and may lead to senescence. Conclusion In conclusion, the present results showed that malathion and cypermethrin can get absorbed in the exposed plant parts or other non-target organisms in the vicinity, and may adversely affect their genomes, thus cause significant harm to crop plants and the environment as well.
Hasan Nazarul,Choudhary Sana,Laskar Rafiul Amin,Naaz Neha,Sharma Nidhi 한국원예학회 2022 Horticulture, Environment, and Biotechnology Vol.63 No.5
This study was conducted to understand the toxic effects of cadmium nitrate and lead nitrate [Cd(NO3)2 and Pb(NO3)2] and their mitigating role on the Capsicum annuum L. cultivar. The biological effects of Cd and Pb were investigated using stress response indicators such as stomata, gas exchange parameters, proline, and defensive enzyme systems. Fresh seeds were treated with different concentrations (100, 200, 300, 400, and 500 ppm) of both Cd and Pb for 6 h. Cytological effects were observed under a microscope by crushing acetocarmine-stained anthers on glass slides. Stomata size was determined with a scanning electron microscope. Photosynthetic and transpiration rates were measured using an infrared gas analyzer. Chlorophyll and carotenoid pigments were determined analytically with a spectrophotometer. An expected decrease in chlorophyll and carotenoid content was observed with increasing concentrations. Cytotoxic effects of Cd and Pb resulted in various changes in chromosomes including laggard, stickiness, multi-nucleate, and disturbed polarity. The size of stomata decreased at higher concentration and measured to 2.20and 4.6 μM with low stomata conductance at 500 ppm of Cd and Pb. Photosynthetic and transpiration rates showed a moderate trend with increasing concentrations, where high photosynthetic and transpiration rates were measured to 20.20 and 23.40 m−2 s−1 at 200 ppm concentration. Maximum SOD and CAT activ- ity was 2.82 and 6.34 unit mg−1 at 300 ppm of Cd. These results are valuable for understanding how crop plants respond to heavy metals, especially when using them as inducing agents during cyto-physiological experiments.