This paper reports two newly recorded species, lsohypsibius lunulatus Iharos, 1966 and lsohypsibiusprosostomus Thulin, 1928, of the genus lsohypsibius （Tardigrada; Hypsibiidae） from China. The specimens of lsohysibi...This paper reports two newly recorded species, lsohypsibius lunulatus Iharos, 1966 and lsohypsibiusprosostomus Thulin, 1928, of the genus lsohypsibius （Tardigrada; Hypsibiidae） from China. The specimens of lsohysibius lunulatus were collected from Taibai Mt （34°18′N, 107°42′E） at 2,500 m a.s.1, and those oflsohypsibius prosostomus from Taibai Mt （34°10′N, 107°35′E） at 2,000 m above sea level. All specimens are deposited at the College of Life Sciences, Shaanxi Normal University, China. A key to the Chinese species of lsohypsibius was also given.展开更多
A machine-learning approach was developed for automated building of knowledgebases for soil resources mapping by using a classification tree to generate knowledge from trainingdata. With this method, building a knowle...A machine-learning approach was developed for automated building of knowledgebases for soil resources mapping by using a classification tree to generate knowledge from trainingdata. With this method, building a knowledge base for automated soil mapping was easier than usingthe conventional knowledge acquisition approach. The knowledge base built by classification tree wasused by the knowledge classifier to perform the soil type classification of Longyou County,Zhejiang Province, China using Landsat TM bi-temporal images and CIS data. To evaluate theperformance of the resultant knowledge bases, the classification results were compared to existingsoil map based on a field survey. The accuracy assessment and analysis of the resultant soil mapssuggested that the knowledge bases built by the machine-learning method was of good quality formapping distribution model of soil classes over the study area.展开更多
Machine Learning(ML) techniques have been widely applied in recent traffic classification.However, the problems of both discriminator bias and class imbalance decrease the accuracies of ML based traffic classifier. In...Machine Learning(ML) techniques have been widely applied in recent traffic classification.However, the problems of both discriminator bias and class imbalance decrease the accuracies of ML based traffic classifier. In this paper, we propose an accurate and extensible traffic classifier. Specifically, to address the discriminator bias issue, our classifier is built by making an optimal cascade of binary sub-classifiers, where each binary sub-classifier is trained independently with the discriminators used for identifying application specific traffic. Moreover, to balance a training dataset,we apply SMOTE algorithm in generating artificial training samples for minority classes.We evaluate our classifier on two datasets collected from different network border routers.Compared with the previous multi-class traffic classifiers built in one-time training process,our classifier achieves much higher F-Measure and AUC for each application.展开更多
Viviparidae are widely distributed around the globe, but there are considerable gaps in the taxonomic record. To date, 18 species of the viviparid genus Cipangopaludina have been recorded in China, but there is substa...Viviparidae are widely distributed around the globe, but there are considerable gaps in the taxonomic record. To date, 18 species of the viviparid genus Cipangopaludina have been recorded in China, but there is substantial disagreement on the validity of this taxonomy. In this study, we described the shell and internal traits of these species to better discuss the validity of related species. We found that C. ampulliformis is synonym of C. lecythis, and C. wingatei is synonym of C. chinensis, while C. ampullacea and C. fluminalis are subspecies of C. lecythis and C. chinensis, respectively. C. dianchiensis should be paled in the genus Margarya, while C. menglaensis and C. yunnanensis belong to genus Mekongia. Totally, this leaves 11 species and 2 subspecies recorded in China. Based on whether these specimens' spiral whorl depth was longer than aperture depth, these species or subspecies can be further divided into two groups, viz. chinensis group and cathayensis group, which can be determined from one another via the ratio of spiral depth and aperture depth, vas deferens and number of secondary branches of vas deferens. Additionally, Principal Component Analysis indicated that body whorl depth, shell width, aperture width and aperture length were main variables during species of Cipangopaludina. A key to all valid Chinese Cipangopaludina species were given.展开更多
Objective To explore the semi-supervised learning(SSL) algorithm for long-tail endoscopic image classification with limited annotations.Method We explored semi-supervised long-tail endoscopic image classification in H...Objective To explore the semi-supervised learning(SSL) algorithm for long-tail endoscopic image classification with limited annotations.Method We explored semi-supervised long-tail endoscopic image classification in HyperKvasir,the largest gastrointestinal public dataset with 23 diverse classes.Semi-supervised learning algorithm FixMatch was applied based on consistency regularization and pseudo-labeling.After splitting the training dataset and the test dataset at a ratio of 4:1,we sampled 20%,50%,and 100% labeled training data to test the classification with limited annotations.Results The classification performance was evaluated by micro-average and macro-average evaluation metrics,with the Mathews correlation coefficient(MCC) as the overall evaluation.SSL algorithm improved the classification performance,with MCC increasing from 0.8761 to 0.8850,from 0.8983 to 0.8994,and from 0.9075 to 0.9095 with 20%,50%,and 100% ratio of labeled training data,respectively.With a 20% ratio of labeled training data,SSL improved both the micro-average and macro-average classification performance;while for the ratio of 50% and 100%,SSL improved the micro-average performance but hurt macro-average performance.Through analyzing the confusion matrix and labeling bias in each class,we found that the pseudo-based SSL algorithm exacerbated the classifier’ s preference for the head class,resulting in improved performance in the head class and degenerated performance in the tail class.Conclusion SSL can improve the classification performance for semi-supervised long-tail endoscopic image classification,especially when the labeled data is extremely limited,which may benefit the building of assisted diagnosis systems for low-volume hospitals.However,the pseudo-labeling strategy may amplify the effect of class imbalance,which hurts the classification performance for the tail class.展开更多
Automatic image classification is the first step toward semantic understanding of an object in the computer vision area.The key challenge of problem for accurate object recognition is the ability to extract the robust...Automatic image classification is the first step toward semantic understanding of an object in the computer vision area.The key challenge of problem for accurate object recognition is the ability to extract the robust features from various viewpoint images and rapidly calculate similarity between features in the image database or video stream.In order to solve these problems,an effective and rapid image classification method was presented for the object recognition based on the video learning technique.The optical-flow and RANSAC algorithm were used to acquire scene images from each video sequence.After the selection of scene images,the local maximum points on comer of object around local area were found using the Harris comer detection algorithm and the several attributes from local block around each feature point were calculated by using scale invariant feature transform （SIFT） for extracting local descriptor.Finally,the extracted local descriptor was learned to the three-dimensional pyramid match kernel.Experimental results show that our method can extract features in various multi-viewpoint images from query video and calculate a similarity between a query image and images in the database.展开更多
Eight flavonoid derivatives： rutin, quercetin-3-glucoside, quercetin, luteolin-7-glucoside, isorhmnetin-3-sulphate, kaempferol-3,7-diglucoside,＇luteolin and kaempferol have been extracted and characterized from Nipa...Eight flavonoid derivatives： rutin, quercetin-3-glucoside, quercetin, luteolin-7-glucoside, isorhmnetin-3-sulphate, kaempferol-3,7-diglucoside,＇luteolin and kaempferol have been extracted and characterized from Nipa palm. Mild extraction technique involving the use of HPLC-DAD-MS was used. The structures of the flavonoids were determined on the basis of mass spectroscopy. Separation of the crude extract by paper chromatography （PC） on forestall as solvent system gave one major yellowish brown spot which had Rf value of 3.9. The Rf value and maximum absorption from UV spectroscopy were the same as those of quercetin standard. The most prominent compound was quercetin followed by three others： kaempferol-3,7-diglucoside, luteolin-7-glucoside, and isorhmnetin-3 -sulphate.展开更多
In this study the essential oil components aerial parts of Tanacetum heterotomum （Bornm.） Grierson, T. zahlbruckneri （Nab.） Griersson, T. densum （Lab.） Schultz Bip. subsp, amani Heywood and T. cadmeum （Boiss.）...In this study the essential oil components aerial parts of Tanacetum heterotomum （Bornm.） Grierson, T. zahlbruckneri （Nab.） Griersson, T. densum （Lab.） Schultz Bip. subsp, amani Heywood and T. cadmeum （Boiss.） Heywood subsp, orientale were examined by HS-SPME/GC-MS technique. Thirty six, thirty nine, forty and forty five constituents were determined representing 88.9%, 90.1%, 90.8% and 91.5% of the oil, respectively. The main compounds of studied Tanacetum L. taxa; borneol, α-pinene, 1,8-cineole, β-pinene, camphor, germacrene D, spathulenol are determined. Studied Tanacetum taxa showed congruency with the discription in Flora of Turkey as morphological properties; on the contrary essential oil composition were detected very quiet diverse infrageneric level. Chemotypes of Tanacetum L. taxa were reported as borneol, germacrene D, spathulenol, α-pinene, 1,8-cineole, β-pinene and camphor. The results obtained from this study were discussed in terms of chemotaxonomy and natural products.展开更多
Flood classification is an effective way to improve flood forecasting accuracy. According to the opposite unity mathematical theorem in Variable Sets theory, this paper proposes a Variable Sets principle and method fo...Flood classification is an effective way to improve flood forecasting accuracy. According to the opposite unity mathematical theorem in Variable Sets theory, this paper proposes a Variable Sets principle and method for flood classification, which is based on the mathematical theorem of dialectics basic laws. This newly proposed method explores a novel way to analyze and solve engineering problems by utilizing a dialectical thinking. In this paper, the Tuwei River basin, located in the Yellow River tributary, is taken as an example for flood classification. The results obtained in this study reveal the problems in a previous method—Set Pair Analysis classification method. The variable sets method is proven to be theoretically rigorous, computationally simple. The classification results are objective, accurate and consistent with the actual situations. This study demonstrates the significant importance of using a scientifically sound method in solving engineering problems.展开更多
Most biologists recognize the ＂species phenomenon＂ as a real pattern in nature： Biodiversity is characterized by dis- continuities between recognizable groups classified as species. Many conservation laws focus on ...Most biologists recognize the ＂species phenomenon＂ as a real pattern in nature： Biodiversity is characterized by dis- continuities between recognizable groups classified as species. Many conservation laws focus on preventing species extinction. However, species are not fixed. Discontinuities evolve gradually and sometimes disappear. Exactly how to define particular spe- cies is not always obvious. Hybridization between taxonomic species reminds us that species classification is not a perfect repre- sentation of nature. Classification is a model that is very useful, but not adequate in all cases. Conservationists often confront questions about how to apply species-based laws when hybridization confounds classification. Development of sophisticated techniques and nuanced interpretation of data in the basic study of species and speciation has exposed the need for deeper educa- tion in genetics and evolution for applied conservationists and decision makers. Here we offer a brief perspective on hybridiza- tion and the species problem in conservation. Our intended audience is conservation practitioners and decision-makers more than geneticists and evolutionary biologists. We wish to emphasize that the goals and premises of legislative classification are not identical to those of scientific classification. Sometimes legal classification is required when the best available science indicates that discrete classification is not an adequate model for the case. Establishing legal status and level of protection for hybrids and hybrid populations means choosing from a range of scientifically valid alternatives. Although we should not abandon species-based approaches to conservation, we must recognize their limitations and work to clarify the roles of science and values in ethical and legal decisions [Current Zoology 61 （1）： 206-216, 2015].展开更多
The rivers in Nepal are classified in terms of geographical regions but a more scientific classification such as on the ba-sis of morphology is clearly lacking. This study was done in 9 rivers namely Jhikhukhola of th...The rivers in Nepal are classified in terms of geographical regions but a more scientific classification such as on the ba-sis of morphology is clearly lacking. This study was done in 9 rivers namely Jhikhukhola of the Koshi system, Aandhikhola, Arungkhola, East Rapti, Karrakhola, Seti and main channel Narayani of the Gandaki system, and two independent systems within Nepal, Bagmati and Tinau. Among the morphologies, river bed or the substratum was taken as the main variable for the analysis which was categorized into 7 types as rocks, boulders, cobbles, pebbles, gravels, sand and silt. There were 23 sampling sites each with 2 stretches of around 100m in those rivers. The data were taken as a percentage, and to avoid biases it was observed visually by the same person for a complete year in every season. With 23 sites each with 2 stretches and 4 replicates corresponding to 4 seasons, there are altogether 184 observations, each termed as a case, that constitute this work. Canonical Discrimination Analysis (CDA) which is most suitable when the data pool is huge was applied to see if the rivers studied distinguish themselves in terms of its morphology. The result was remarkably successful and was close to the established regional classification of the rivers. This kind of river classification has great application in the utilization, conservation and restoration of the most important natural re-source of the country.展开更多
基金This study was supported by scientific research foundation project of Shaanxi Institute of Education (No. 07KJ37Q)
文摘This paper reports two newly recorded species, lsohypsibius lunulatus Iharos, 1966 and lsohypsibiusprosostomus Thulin, 1928, of the genus lsohypsibius （Tardigrada; Hypsibiidae） from China. The specimens of lsohysibius lunulatus were collected from Taibai Mt （34°18′N, 107°42′E） at 2,500 m a.s.1, and those oflsohypsibius prosostomus from Taibai Mt （34°10′N, 107°35′E） at 2,000 m above sea level. All specimens are deposited at the College of Life Sciences, Shaanxi Normal University, China. A key to the Chinese species of lsohypsibius was also given.
基金Project supported by the National Natural Science Foundation of China(Nos.40101014 and 40001008).
文摘A machine-learning approach was developed for automated building of knowledgebases for soil resources mapping by using a classification tree to generate knowledge from trainingdata. With this method, building a knowledge base for automated soil mapping was easier than usingthe conventional knowledge acquisition approach. The knowledge base built by classification tree wasused by the knowledge classifier to perform the soil type classification of Longyou County,Zhejiang Province, China using Landsat TM bi-temporal images and CIS data. To evaluate theperformance of the resultant knowledge bases, the classification results were compared to existingsoil map based on a field survey. The accuracy assessment and analysis of the resultant soil mapssuggested that the knowledge bases built by the machine-learning method was of good quality formapping distribution model of soil classes over the study area.
基金supported by the National Natural Science Foundation of China under Grant No.61402485National Natural Science Foundation of China under Grant No.61303061supported by the Open fund from HPCL No.201513-01
文摘Machine Learning(ML) techniques have been widely applied in recent traffic classification.However, the problems of both discriminator bias and class imbalance decrease the accuracies of ML based traffic classifier. In this paper, we propose an accurate and extensible traffic classifier. Specifically, to address the discriminator bias issue, our classifier is built by making an optimal cascade of binary sub-classifiers, where each binary sub-classifier is trained independently with the discriminators used for identifying application specific traffic. Moreover, to balance a training dataset,we apply SMOTE algorithm in generating artificial training samples for minority classes.We evaluate our classifier on two datasets collected from different network border routers.Compared with the previous multi-class traffic classifiers built in one-time training process,our classifier achieves much higher F-Measure and AUC for each application.
基金funded by the National Natural Science Foundation of China(31301865)the Natural Science Foundation of Zhejiang Province of China(LY12C19006)the Collection and Preparation of Display Specimens at Kunming Natural History Museum of Zoology(KSZD–EW–TZ–005)
文摘Viviparidae are widely distributed around the globe, but there are considerable gaps in the taxonomic record. To date, 18 species of the viviparid genus Cipangopaludina have been recorded in China, but there is substantial disagreement on the validity of this taxonomy. In this study, we described the shell and internal traits of these species to better discuss the validity of related species. We found that C. ampulliformis is synonym of C. lecythis, and C. wingatei is synonym of C. chinensis, while C. ampullacea and C. fluminalis are subspecies of C. lecythis and C. chinensis, respectively. C. dianchiensis should be paled in the genus Margarya, while C. menglaensis and C. yunnanensis belong to genus Mekongia. Totally, this leaves 11 species and 2 subspecies recorded in China. Based on whether these specimens' spiral whorl depth was longer than aperture depth, these species or subspecies can be further divided into two groups, viz. chinensis group and cathayensis group, which can be determined from one another via the ratio of spiral depth and aperture depth, vas deferens and number of secondary branches of vas deferens. Additionally, Principal Component Analysis indicated that body whorl depth, shell width, aperture width and aperture length were main variables during species of Cipangopaludina. A key to all valid Chinese Cipangopaludina species were given.
文摘Objective To explore the semi-supervised learning(SSL) algorithm for long-tail endoscopic image classification with limited annotations.Method We explored semi-supervised long-tail endoscopic image classification in HyperKvasir,the largest gastrointestinal public dataset with 23 diverse classes.Semi-supervised learning algorithm FixMatch was applied based on consistency regularization and pseudo-labeling.After splitting the training dataset and the test dataset at a ratio of 4:1,we sampled 20%,50%,and 100% labeled training data to test the classification with limited annotations.Results The classification performance was evaluated by micro-average and macro-average evaluation metrics,with the Mathews correlation coefficient(MCC) as the overall evaluation.SSL algorithm improved the classification performance,with MCC increasing from 0.8761 to 0.8850,from 0.8983 to 0.8994,and from 0.9075 to 0.9095 with 20%,50%,and 100% ratio of labeled training data,respectively.With a 20% ratio of labeled training data,SSL improved both the micro-average and macro-average classification performance;while for the ratio of 50% and 100%,SSL improved the micro-average performance but hurt macro-average performance.Through analyzing the confusion matrix and labeling bias in each class,we found that the pseudo-based SSL algorithm exacerbated the classifier’ s preference for the head class,resulting in improved performance in the head class and degenerated performance in the tail class.Conclusion SSL can improve the classification performance for semi-supervised long-tail endoscopic image classification,especially when the labeled data is extremely limited,which may benefit the building of assisted diagnosis systems for low-volume hospitals.However,the pseudo-labeling strategy may amplify the effect of class imbalance,which hurts the classification performance for the tail class.
文摘Automatic image classification is the first step toward semantic understanding of an object in the computer vision area.The key challenge of problem for accurate object recognition is the ability to extract the robust features from various viewpoint images and rapidly calculate similarity between features in the image database or video stream.In order to solve these problems,an effective and rapid image classification method was presented for the object recognition based on the video learning technique.The optical-flow and RANSAC algorithm were used to acquire scene images from each video sequence.After the selection of scene images,the local maximum points on comer of object around local area were found using the Harris comer detection algorithm and the several attributes from local block around each feature point were calculated by using scale invariant feature transform （SIFT） for extracting local descriptor.Finally,the extracted local descriptor was learned to the three-dimensional pyramid match kernel.Experimental results show that our method can extract features in various multi-viewpoint images from query video and calculate a similarity between a query image and images in the database.
文摘Eight flavonoid derivatives： rutin, quercetin-3-glucoside, quercetin, luteolin-7-glucoside, isorhmnetin-3-sulphate, kaempferol-3,7-diglucoside,＇luteolin and kaempferol have been extracted and characterized from Nipa palm. Mild extraction technique involving the use of HPLC-DAD-MS was used. The structures of the flavonoids were determined on the basis of mass spectroscopy. Separation of the crude extract by paper chromatography （PC） on forestall as solvent system gave one major yellowish brown spot which had Rf value of 3.9. The Rf value and maximum absorption from UV spectroscopy were the same as those of quercetin standard. The most prominent compound was quercetin followed by three others： kaempferol-3,7-diglucoside, luteolin-7-glucoside, and isorhmnetin-3 -sulphate.
文摘In this study the essential oil components aerial parts of Tanacetum heterotomum （Bornm.） Grierson, T. zahlbruckneri （Nab.） Griersson, T. densum （Lab.） Schultz Bip. subsp, amani Heywood and T. cadmeum （Boiss.） Heywood subsp, orientale were examined by HS-SPME/GC-MS technique. Thirty six, thirty nine, forty and forty five constituents were determined representing 88.9%, 90.1%, 90.8% and 91.5% of the oil, respectively. The main compounds of studied Tanacetum L. taxa; borneol, α-pinene, 1,8-cineole, β-pinene, camphor, germacrene D, spathulenol are determined. Studied Tanacetum taxa showed congruency with the discription in Flora of Turkey as morphological properties; on the contrary essential oil composition were detected very quiet diverse infrageneric level. Chemotypes of Tanacetum L. taxa were reported as borneol, germacrene D, spathulenol, α-pinene, 1,8-cineole, β-pinene and camphor. The results obtained from this study were discussed in terms of chemotaxonomy and natural products.
基金supported by the National Natural Science Foundation of China (Grant Nos. 51209032, 50779005)
文摘Flood classification is an effective way to improve flood forecasting accuracy. According to the opposite unity mathematical theorem in Variable Sets theory, this paper proposes a Variable Sets principle and method for flood classification, which is based on the mathematical theorem of dialectics basic laws. This newly proposed method explores a novel way to analyze and solve engineering problems by utilizing a dialectical thinking. In this paper, the Tuwei River basin, located in the Yellow River tributary, is taken as an example for flood classification. The results obtained in this study reveal the problems in a previous method—Set Pair Analysis classification method. The variable sets method is proven to be theoretically rigorous, computationally simple. The classification results are objective, accurate and consistent with the actual situations. This study demonstrates the significant importance of using a scientifically sound method in solving engineering problems.
文摘Most biologists recognize the ＂species phenomenon＂ as a real pattern in nature： Biodiversity is characterized by dis- continuities between recognizable groups classified as species. Many conservation laws focus on preventing species extinction. However, species are not fixed. Discontinuities evolve gradually and sometimes disappear. Exactly how to define particular spe- cies is not always obvious. Hybridization between taxonomic species reminds us that species classification is not a perfect repre- sentation of nature. Classification is a model that is very useful, but not adequate in all cases. Conservationists often confront questions about how to apply species-based laws when hybridization confounds classification. Development of sophisticated techniques and nuanced interpretation of data in the basic study of species and speciation has exposed the need for deeper educa- tion in genetics and evolution for applied conservationists and decision makers. Here we offer a brief perspective on hybridiza- tion and the species problem in conservation. Our intended audience is conservation practitioners and decision-makers more than geneticists and evolutionary biologists. We wish to emphasize that the goals and premises of legislative classification are not identical to those of scientific classification. Sometimes legal classification is required when the best available science indicates that discrete classification is not an adequate model for the case. Establishing legal status and level of protection for hybrids and hybrid populations means choosing from a range of scientifically valid alternatives. Although we should not abandon species-based approaches to conservation, we must recognize their limitations and work to clarify the roles of science and values in ethical and legal decisions [Current Zoology 61 （1）： 206-216, 2015].
文摘The rivers in Nepal are classified in terms of geographical regions but a more scientific classification such as on the ba-sis of morphology is clearly lacking. This study was done in 9 rivers namely Jhikhukhola of the Koshi system, Aandhikhola, Arungkhola, East Rapti, Karrakhola, Seti and main channel Narayani of the Gandaki system, and two independent systems within Nepal, Bagmati and Tinau. Among the morphologies, river bed or the substratum was taken as the main variable for the analysis which was categorized into 7 types as rocks, boulders, cobbles, pebbles, gravels, sand and silt. There were 23 sampling sites each with 2 stretches of around 100m in those rivers. The data were taken as a percentage, and to avoid biases it was observed visually by the same person for a complete year in every season. With 23 sites each with 2 stretches and 4 replicates corresponding to 4 seasons, there are altogether 184 observations, each termed as a case, that constitute this work. Canonical Discrimination Analysis (CDA) which is most suitable when the data pool is huge was applied to see if the rivers studied distinguish themselves in terms of its morphology. The result was remarkably successful and was close to the established regional classification of the rivers. This kind of river classification has great application in the utilization, conservation and restoration of the most important natural re-source of the country.
