Object-based classification differentiates forest gaps from canopies at large regional scale by using remote sensing data. To study the segmentation and classification processes of object-based forest gaps classificat...Object-based classification differentiates forest gaps from canopies at large regional scale by using remote sensing data. To study the segmentation and classification processes of object-based forest gaps classification at a regional scale, we sampled a natural secondary forest in northeast China at Maoershan Experimental Forest Farm.Airborne light detection and ranging(LiDAR; 3.7 points/m2) data were collected as the original data source and the canopy height model(CHM) and topographic dataset were extracted from the LiDAR data. The accuracy of objectbased forest gaps classification depends on previous segmentation. Thus our first step was to define 10 different scale parameters in CHM image segmentation. After image segmentation, the machine learning classification method was used to classify three kinds of object classes, namely,forest gaps, tree canopies, and others. The common support vector machine(SVM) classifier with the radial basis function kernel(RBF) was first adopted to test the effect of classification features(vegetation height features and some typical topographic features) on forest gap classification.Then the different classifiers(KNN, Bayes, decision tree,and SVM with linear kernel) were further adopted to compare the effect of classifiers on machine learning forest gaps classification. Segmentation accuracy and classification accuracy were evaluated by using Mo¨ller's method and confusion metrics, respectively. The scale parameter had a significant effect on object-based forest gap segmentation and classification. Classification accuracies at different scales revealed that there were two optimal scales(10 and 20) that provided similar accuracy, with the scale of 10 yielding slightly greater accuracy than 20. The accuracy of the classification by using combination of height features and SVM classifier with linear kernel was91% at the optimal scale parameter of 10, and it was highest comparing with other classification classifiers, such as SVM RBF(90%), Decision Tree(90%), Bayes(90%),or KNN(87%). The classifiers had no significant effect on forest gap classification, but the fewer parameters in the classifier equation and higher speed of operation probably lead to a higher accuracy of final classifications. Our results confirm that object-based classification can extract forest gaps at a large regional scale with appropriate classification features and classifiers using LiDAR data. We note, however, that final satisfaction of forest gap classification depends on the determination of optimal scale(s) of segmentation.展开更多
A machine-learning approach was developed for automated building of knowledge bases for soil resourcesmapping by using a classification tree to generate knowledge from training data. With this method, buildinga knowle...A machine-learning approach was developed for automated building of knowledge bases for soil resourcesmapping by using a classification tree to generate knowledge from training data. With this method, buildinga knowledge base for automated soil mapping was easier than using the conventional knowledge acquisitionapproach. The knowledge base built by classification tree was used by the knowledge classifier to perform thesoil type classification of Longyou County, Zhejiang Province, China using Landsat TM bi-temporal imagesand GIS data. To evaluate the performance of the resultant knowledge bases, the classification results werecompared to existing soil map based on a field survey. The accuracy assessment and analysis of the resultantsoil maps suggested 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
Objective: To determine the in vitro and in vivo absorption properties of active ingredients of the Chinese medicine, baicalein, to enrich mechanistic understanding of oral drug absorption.Methods: The Biopharmaceutic...Objective: To determine the in vitro and in vivo absorption properties of active ingredients of the Chinese medicine, baicalein, to enrich mechanistic understanding of oral drug absorption.Methods: The Biopharmaceutic Classification System(BCS) category was determined using equilibrium solubility, intrinsic dissolution rate, and intestinal permeability to evaluate intestinal absorption mechanisms of baicalein in rats in vitro. Physiologically based pharmacokinetic(PBPK) model commercial software GastroPlus~(TM) was used to predict oral absorption of baicalein in vivo.Results: Based on equilibrium solubility, intrinsic dissolution rate, and permeability values of main absorptive segments in the duodenum, jejunum, and ileum, baicalein was classified as a drug with low solubility and high permeability. Intestinal perfusion with venous sampling(IPVS) revealed that baicalein was extensively metabolized in the body, which corresponded to the low bioavailability predicted by the PBPK model. Further, the PBPK model predicted the key indicators of BCS, leading to reclassification as BCS-II. Predicted values of peak plasma concentration of the drug(C_(max)) and area under the curve(AUC)fell within two times of the error of the measured results, highlighting the superior prediction of absorption of baicalein in rats, beagles, and humans. The PBPK model supported in vitro and in vivo evidence and provided excellent prediction for this BCS class II drug.Conclusion: BCS and PBPK are complementary methods that enable comprehensive research of BCS parameters, intestinal absorption rate, metabolism, prediction of human absorption fraction and bioavailability, simulation of PK, and drug absorption in various intestinal segments across species. This combined approach may facilitate a more comprehensive and accurate analysis of the absorption characteristics of active ingredients of Chinese medicine from in vitro and in vivo perspectives.展开更多
In this paper, a feature selection method combining the reliefF and SVM-RFE algorithm is proposed. This algorithm integrates the weight vector from the reliefF into SVM-RFE method. In this method, the reliefF filters ...In this paper, a feature selection method combining the reliefF and SVM-RFE algorithm is proposed. This algorithm integrates the weight vector from the reliefF into SVM-RFE method. In this method, the reliefF filters out many noisy features in the first stage. Then the new ranking criterion based on SVM-RFE method is applied to obtain the final feature subset. The SVM classifier is used to evaluate the final image classification accuracy. Experimental results show that our proposed relief- SVM-RFE algorithm can achieve significant improvements for feature selection in image classification.展开更多
BACKGROUND: Recent international multidisciplinary consultation proposed the use of local(sterile or infected pancreatic necrosis) and/or systemic determinants(organ failure) in the stratification of acute pancreatiti...BACKGROUND: Recent international multidisciplinary consultation proposed the use of local(sterile or infected pancreatic necrosis) and/or systemic determinants(organ failure) in the stratification of acute pancreatitis. The present study was to validate the moderate severity category by international multidisciplinary consultation definitions.METHODS: Ninety-two consecutive patients with severe acute pancreatitis(according to the 1992 Atlanta classification) were classified into(i) moderate acute pancreatitis group with the presence of sterile(peri-) pancreatic necrosis and/or transient organ failure; and(ii) severe/critical acute pancreatitis group with the presence of sterile or infected pancreatic necrosis and/or persistent organ failure. Demographic and clinical outcomes were compared between the two groups.RESULTS: Compared with the severe/critical group(n=59), the moderate group(n=33) had lower clinical and computerized tomographic scores(both P<0.05). They also had a lower incidence of pancreatic necrosis(45.5% vs 71.2%, P=0.015),infection(9.1% vs 37.3%, P=0.004), ICU admission(0% vs27.1%, P=0.001), and shorter hospital stay(15±5 vs 27±12days; P<0.001). A subgroup analysis showed that the moderate group also had significantly lower ICU admission rates, shorter hospital stay and lower rate of infection compared with the severe group(n=51). No patients died in the moderate group but7 patients died in the severe/critical group(4 for severe group).CONCLUSIONS: Our data suggest that the definition of moderate acute pancreatitis, as suggested by the international multidisciplinary consultation as sterile(peri-) pancreatic necrosis and/or transient organ failure, is an accurate category of acute pancreatitis.展开更多
Proper quality planning of limestone raw materials is an essential job of maintaining desired feed in cement plant. Rock-type identification is an integrated part of quality planning for limestone mine. In this paper,...Proper quality planning of limestone raw materials is an essential job of maintaining desired feed in cement plant. Rock-type identification is an integrated part of quality planning for limestone mine. In this paper, a computer vision-based rock-type classification algorithm is proposed for fast and reliable identification without human intervention. A laboratory scale vision-based model was developed using probabilistic neural network(PNN) where color histogram features are used as input. The color image histogram-based features that include weighted mean, skewness and kurtosis features are extracted for all three color space red, green, and blue. A total nine features are used as input for the PNN classification model. The smoothing parameter for PNN model is selected judicially to develop an optimal or close to the optimum classification model. The developed PPN is validated using the test data set and results reveal that the proposed vision-based model can perform satisfactorily for classifying limestone rocktypes. Overall the error of mis-classification is below 6%. When compared with other three classification algorithms, it is observed that the proposed method performs substantially better than all three classification algorithms.展开更多
AIM:To support probe-based confocal laser endomi-croscopy (pCLE) diagnosis by designing software for the automated classification of colonic polyps. METHODS:Intravenous fluorescein pCLE imaging of colorectal lesions w...AIM:To support probe-based confocal laser endomi-croscopy (pCLE) diagnosis by designing software for the automated classification of colonic polyps. METHODS:Intravenous fluorescein pCLE imaging of colorectal lesions was performed on patients under-going screening and surveillance colonoscopies, followed by polypectomies. All resected specimens were reviewed by a reference gastrointestinal pathologist blinded to pCLE information. Histopathology was used as the criterion standard for the differentiation between neoplastic and non-neoplastic lesions. The pCLE video sequences, recorded for each polyp, were analyzed off-line by 2 expert endoscopists who were blinded to the endoscopic characteristics and histopathology. These pCLE videos, along with their histopathology diagnosis, were used to train the automated classification software which is a content-based image retrieval technique followed by k-nearest neighbor classification. The performance of the off-line diagnosis of pCLE videos established by the 2 expert endoscopists was compared with that of automated pCLE software classification. All evaluations were performed using leave-one-patient- out cross-validation to avoid bias. RESULTS:Colorectal lesions (135) were imaged in 71 patients. Based on histopathology, 93 of these 135 lesions were neoplastic and 42 were non-neoplastic. The study found no statistical significance for the difference between the performance of automated pCLE software classification (accuracy 89.6%, sensitivity 92.5%, specificity 83.3%, using leave-one-patient-out cross-validation) and the performance of the off-line diagnosis of pCLE videos established by the 2 expert endoscopists (accuracy 89.6%, sensitivity 91.4%, specificity 85.7%). There was very low power (< 6%) to detect the observed differences. The 95% confidence intervals for equivalence testing were:-0.073 to 0.073 for accuracy, -0.068 to 0.089 for sensitivity and -0.18 to 0.13 for specificity. The classification software proposed in this study is not a "black box" but an informative tool based on the query by example model that produces, as intermediate results, visually similar annotated videos that are directly interpretable by the endoscopist. CONCLUSION:The proposed software for automated classification of pCLE videos of colonic polyps achieves high performance, comparable to that of off-line diagnosis of pCLE videos established by expert endoscopists.展开更多
To explore fertilization methods for wine bamboo cultivation in southwestern semi-arid areas of China,this study analyzed annual changes in sap yield and nutrient composition from May 2013 to March 2015 by using bambo...To explore fertilization methods for wine bamboo cultivation in southwestern semi-arid areas of China,this study analyzed annual changes in sap yield and nutrient composition from May 2013 to March 2015 by using bamboo charcoal-based bio-fertilizer(ZT) and organic fertilizer treatments(CK).The study also provided basic data for functional beverage preparation and for application of ZT.The results of the two experimental cycles revealed that under the ZT treatment, sap was available for collection from May, the beginning of the rainy season, to November, the beginning of the dry season.The period of abundance was July to October with the highest yield of sap of 3.18 L stalk^(-1) in September, 2014,still lower than the moso bamboo sap, which was likely due to the scale of sap production of monopodial bamboos being different from that of sympodial bamboos.In January, trace amounts of sap were still detected, suggesting that the effect of the treatment was significant.Moreover,in the dry season, soil water content and soil temperatures at 10–15 cm depths indicated that the fertilizer had the ability to maintain soil temperatures and moisture.In both fertilizer treatments, the correlation between the collected sap and environmental parameters was significant.In the ZT treatment for the entire 2 years, the effectual environmental factors were soil water at 10–15 cm, air temperatures, and wind speeds.The same determining factors were observed for the rainy season.In the CK treatments, the effectual environmental factors for the entire year and the rainy season were soil water at 0–5 cm and air moisture.The bamboo charcoal-based bio-fertilizer elevated the potassium, calcium, iron, manganese, copper, and total phosphorus content, simultaneously increasing the sap yield, protein and reducing sugar contents, and with a relative increase in sap pH.The wine bamboo sap contained 18 amino acids.Glutamic acid, alanine and proline were the most abundant.Compared to the controls, the treatment showed higher levels of all amino acids.Thus,the ZT treatment could be more beneficial to the development of root systems because the function of heat preservation and moisture retention prolong the sap collection period, increase sap yields, and elevate mineral element, conventional nutrients, and amino acid contents with evident fertilization effects and broader application prospects.展开更多
This paper proposed to use double polarization synthetic aperture radar (SAR) image to classify surface feature, based on DEM. It takes fully use of the polarization information and external information. This pa-per u...This paper proposed to use double polarization synthetic aperture radar (SAR) image to classify surface feature, based on DEM. It takes fully use of the polarization information and external information. This pa-per utilizes ENVISAT ASAR APP double-polarization data of Poyang lake area in Jiangxi Province. Com-pared with traditional pixel-based classification, this paper fully uses object features (color, shape, hierarchy) and accessorial DEM information. The classification accuracy improves from the original 73.7% to 91.84%. The result shows that object-oriented classification technology is suitable for double polarization SAR’s high precision classification.展开更多
Recent days,Image retrieval has become a tedious process as the image database has grown very larger.The introduction of Machine Learning(ML)and Deep Learning(DL)made this process more comfortable.In these,the pair-wi...Recent days,Image retrieval has become a tedious process as the image database has grown very larger.The introduction of Machine Learning(ML)and Deep Learning(DL)made this process more comfortable.In these,the pair-wise label similarity is used tofind the matching images from the database.But this method lacks of limited propose code and weak execution of misclassified images.In order to get-rid of the above problem,a novel triplet based label that incorporates context-spatial similarity measure is proposed.A Point Attention Based Triplet Network(PABTN)is introduced to study propose code that gives maximum discriminative ability.To improve the performance of ranking,a corre-lating resolutions for the classification,triplet labels based onfindings,a spatial-attention mechanism and Region Of Interest(ROI)and small trial information loss containing a new triplet cross-entropy loss are used.From the experimental results,it is shown that the proposed technique exhibits better results in terms of mean Reciprocal Rank(mRR)and mean Average Precision(mAP)in the CIFAR-10 and NUS-WIPE datasets.展开更多
Many researches have been performed comparing object-based classification (OBC) and pixel-based classification (PBC), particularly in classifying high-resolution satellite images. VNREDSat-1 is the first optical remot...Many researches have been performed comparing object-based classification (OBC) and pixel-based classification (PBC), particularly in classifying high-resolution satellite images. VNREDSat-1 is the first optical remote sensing satellite of Vietnam with resolution of 2.5 m (Panchromatic) and 10 m (Multispectral). The objective of this research is to compare two classification approaches using VNREDSat-1 image for mapping mangrove forest in Vien An Dong commune, Ngoc Hien district, Ca Mau province. ISODATA algorithm (in PBC method) and membership function classifier (in OBC method) were chosen to classify the same image. The results show that the overall accuracies of OBC and PBC are 73% and 62.16% respectively, and OBC solved the “salt and pepper” which is the main issue of PBC as well. Therefore, OBC is supposed to be the better approach to classify VNREDSat-1 for mapping mangrove forest in Ngoc Hien commune.展开更多
This paper offers a symbiosis based hybrid modified DNA-ABC optimization algorithm which combines modified DNA concepts and artificial bee colony (ABC) algorithm to aid hierarchical fuzzy classification. According to ...This paper offers a symbiosis based hybrid modified DNA-ABC optimization algorithm which combines modified DNA concepts and artificial bee colony (ABC) algorithm to aid hierarchical fuzzy classification. According to literature, the ABC algorithm is traditionally applied to constrained and unconstrained problems, but is combined with modified DNA concepts and implemented for fuzzy classification in this present research. Moreover, from the best of our knowledge, previous research on the ABC algorithm has not combined it with DNA computing for hierarchical fuzzy classification to explore the merits of cooperative coevolution. Therefore, this paper is the first to apply the mechanism of symbiosis to create a hybrid modified DNA-ABC algorithm for hierarchical fuzzy classification applications. In this study, the partition number and the shape of the membership function are extracted by the symbiosis based hybrid modified DNA-ABC optimization algorithm, which provides both sufficient global exploration and also adequate local exploitation for hierarchical fuzzy classification. The proposed optimization algorithm is applied on five benchmark University of Irvine (UCI) data sets, and the results prove the efficiency of the algorithm.展开更多
Building detection in very high resolution (VHR) images is crucial for mapping and analysing urban environments. Since buildings are elevated objects, elevation data need to be integrated with images for reliable dete...Building detection in very high resolution (VHR) images is crucial for mapping and analysing urban environments. Since buildings are elevated objects, elevation data need to be integrated with images for reliable detection. This process requires two critical steps: optical-elevation data co-registration and aboveground elevation calculation. These two steps are still challenging to some extent. Therefore, this paper introduces optical-elevation data co-registration and normalization techniques for generating a dataset that facilitates elevation-based building detection. For achieving accurate co-registration, a dense set of stereo-based elevations is generated and co-registered to their relevant image based on their corresponding image locations. To normalize these co-registered elevations, the bare-earth elevations are detected based on classification information of some terrain-level features after achieving the image co-registration. The developed method was executed and validated. After implementation, 80% overall-quality of detection result was achieved with 94% correct detection. Together, the developed techniques successfully facilitate the incorporation of stereo-based elevations for detecting buildings in VHR remote sensing images.展开更多
The character variable discrete numeralization destroyed the disorder of character variables. As text classification problem contains more character variable, discrete numeralization approach affects the classificatio...The character variable discrete numeralization destroyed the disorder of character variables. As text classification problem contains more character variable, discrete numeralization approach affects the classification performance of classifiers. In this paper, we propose a character variable numeralization algorithm based on dimension expanding. Firstly, the algorithm computes the number of different values which the character variable takes. Then it replaces the original values with the natural bases in the m-dimensional Euclidean space. Though the algorithm causes a dimension expanding, it reserves the disorder of character variables because the natural bases are no difference in size, so this algorithm is a better character variable numerical processing algorithm. Experiments on text classification data sets show that though the proposed algorithm costs a little more running time, its classification performance is better.展开更多
Medical images are important for medical research and clinical diagnosis.The research of medical images includes image acquisition,processing,analysis and other related research fields.Crowdsourcing is attracting grow...Medical images are important for medical research and clinical diagnosis.The research of medical images includes image acquisition,processing,analysis and other related research fields.Crowdsourcing is attracting growing interests in recent years as an effective tool.It can harness human intelligence to solve problems that computers cannot perform well,such as sentiment analysis and image recognition.Crowdsourcing can achieve higher accuracies in medical image classification,but it cannot be widely used for its low efficiency and the monetary cost.We adopt a hybrid approach which combines computer’s algorithm and crowdsourcing system for image classification.Medical image classification algorithms have a high error rate near the threshold.And it is not significant by improving these classification algorithms to achieve a higher accuracy.To address the problem,we propose a hybrid framework,which can achieve a higher accuracy significantly than only use classification algorithms.At the same time,it only processes the images that classification algorithms perform not well,so it has a lower monetary cost.In the framework,we device an effective algorithm to generate a range-threshold that assign images to crowdsourcing or classification algorithm.Experimental results show that our method can improve the accuracy of medical images classification and reduce the crowdsourcing monetary cost.展开更多
Recently,developments of Internet and cloud technologies have resulted in a considerable rise in utilization of online media for day to day lives.It results in illegal access to users’private data and compromises it....Recently,developments of Internet and cloud technologies have resulted in a considerable rise in utilization of online media for day to day lives.It results in illegal access to users’private data and compromises it.Phishing is a popular attack which tricked the user into accessing malicious data and gaining the data.Proper identification of phishing emails can be treated as an essential process in the domain of cybersecurity.This article focuses on the design of bio-geography based optimization with deep learning for Phishing Email detection and classification(BBODL-PEDC)model.The major intention of the BBODL-PEDC model is to distinguish emails between legitimate and phishing.The BBODL-PEDC model initially performs data pre-processing in three levels namely email cleaning,tokenization,and stop word elimination.Besides,TF-IDF model is applied for the extraction of useful feature vectors.Moreover,optimal deep belief network(DBN)model is used for the email classification and its efficacy can be boosted by the BBO based hyperparameter tuning process.The performance validation of the BBODL-PEDC model can be performed using benchmark dataset and the results are assessed under several dimensions.Extensive comparative studies reported the superior outcomes of the BBODL-PEDC model over the recent approaches.展开更多
BACKGROUND The overuse and misuse of antimicrobials contribute significantly to antimicrobial resistance(AMR),which is a global public health concern.India has particularly high rates of AMR,posing a threat to effecti...BACKGROUND The overuse and misuse of antimicrobials contribute significantly to antimicrobial resistance(AMR),which is a global public health concern.India has particularly high rates of AMR,posing a threat to effective treatment.The World Health Or-ganization(WHO)Access,Watch,Reserve(AWaRe)classification system was introduced to address this issue and guide appropriate antibiotic prescribing.However,there is a lack of studies examining the prescribing patterns of antimi-crobials using the AWaRe classification,especially in North India.Therefore,this study aimed to assess the prescribing patterns of antimicrobials using the WHO AWaRe classification in a tertiary care centre in North India.Ophthalmology,Obstetrics and Gynecology).Metronidazole and ceftriaxone were the most prescribed antibiotics.According to the AWaRe classification,57.61%of antibiotics fell under the Access category,38.27%in Watch,and 4.11%in Reserve.Most Access antibiotics were prescribed within the Medicine department,and the same department also exhibited a higher frequency of Watch antibiotics prescriptions.The questionnaire survey showed that only a third of participants were aware of the AWaRe classification,and there was a lack of knowledge regarding AMR and the potential impact of AWaRe usage.RESULTS The research was carried out in accordance with the methodology presented in Figure 1.A total of n=123 patients were enrolled in this study,with each of them receiving antibiotic prescriptions.The majority of these prescriptions were issued to inpatients(75.4%),and both the Medicine and Surgical departments were equally represented,accounting for 49.6%and 50.4%,respectively.Among the healthcare providers responsible for prescribing antibiotics,72%were Junior Residents,18.7%were Senior Residents,and 9.3%were Consultants.These findings have been summarized in Table 1.The prescriptions included 27 different antibiotics,with metronidazole being the most prescribed(19%)followed by ceftriaxone(17%).The mean number of antibiotics used per patient was 1.84±0.83.The mean duration of antibiotics prescribed was 6.63±3.83 days.The maximum number of antibiotics prescribed per patient was five.According to the AWaRe classification,57.61%of antibiotics fell under the Access,38.27%in Watch,and 4.11%in Reserve categories,suggesting appropriate antibiotic selection according to these criteria.The distribution of antibiotics prescribed according to the WHO AWaRe categories is presented in Figure 2.The difference in prescribing frequencies amongst departments can be noted.Most of the antibiotics prescribed in the Access category were from the Medicine department(75.4%),followed by Surgery(24.6%).For Watch antibiotics,Medicine had a higher proportion(63.4%)compared to Surgery(36.6%).In terms of seniority,Junior Residents prescribed the highest number of antibiotics for both Access and Watch categories in Medicine and Surgery departments.Senior residents and Consultants prescribed a lower number of antibiotics in all categories and departments.Only a few antibiotics were prescribed in the Reserve category,with most prescriptions being from the Medicine department.The study also evaluated the Knowledge and Awareness of Healthcare professionals towards the WHO AWaRe classi-fication through a questionnaire survey.A total of 93 participants responded to the survey.Among them,most parti-cipants were Junior Residents(69.9%),followed by Senior Residents(25.8%)and Faculty(4.3%).When enquired if they knew about the WHO AWaRe classification only 33.3%of the participants responded positively.Of those who were aware of the AWaRe classification,the most common source of information was the internet(31.2%),followed by the antimicrobial policy of their institution(15.1%)as seen in Table 2.The survey results on the knowledge and awareness of AMR among healthcare professionals are also presented in Tables 3 and 4.Out of the 93 participants,68(73.1%)agreed that the emergence of AMR is inevitable,while only 13(14.0%)disagreed that AWaRe usage will result in the inability to treat serious infections.Additionally,58(62.4%)agreed that it will lead to lengthier hospital stays,43(46.2%)agreed that the success of chemotherapy and major surgery will be hampered,and the majority also agreed that its use will lead to increased cost of treatment and increased mortality rates.Regarding the utilization of AWaRe in the hospital summarized in Tables 4 and 5,35.5%of the participants agreed that it should be used,while only 2.2%disagreed.Additionally,34.4%agreed that AWaRe reduces adverse effects of inappro-priate prescription.However,37.6%of the participants considered that AWaRe threatens a clinician's autonomy and 30.1%thought that its use can delay treatment.Additionally,the DDD of each drug was also evaluated.The usage of various antimicrobial drugs in a hospital setting,along with their daily doses and DDD according to the WHO's Anatomical Therapeutic Chemical classification system was calculated.Some of the important findings include high usage rates of ceftriaxone and metronidazole,and relatively low usage rates of drugs like colistin and clindamycin.Additionally,some drugs had wider ranges than others.Comparison of WHO defined DDD with Daily Drug dose(Mean)in the studied prescriptions is represented in the Clustered Bar chart in Figure 3.Finally,the Mean Daily Drug Dose for prescribed drugs was compared with WHO defined DDD for each drug using a Student’s T test.The mean daily drug dose of amoxy/clav was significantly higher than the WHO DDD(1.8 vs 1.50,P=0.014),while the mean daily drug dose of metronidazole and doxycycline were significantly lower than the WHO DDD(P<0.001 and P=0.008,respectively).The mean daily drug dose of piperacillin/tazobactam,amikacin,clindamycin,and levofloxacin did not show significant differences compared to the WHO DDD(P>0.05).CONCLUSION This research indicates an appropriate proportion of prescriptions falling under the Access category(57.61%),suggesting appropriate antibiotic selection,a significant proportion also belongs to the Watch category(38.27%),emphasizing the need for greater caution to prevent the escalation of AMR.There is a moderate level of awareness among healthcare professionals about AMR and the steps being taken to tackle it,highlighting the gap in implementation of policies and need for more steps to be taken in spreading the knowledge about the subject.However,there is a significant difference between the WHO DDD and the prescribed daily dose in the analysed prescriptions suggesting overuse and underuse of antibiotics.展开更多
The probability-based covering algorithm(PBCA)is a new algorithm based on probability distribution.It decides,by voting,the class of the tested samples on the border of the coverage area,based on the probability of tr...The probability-based covering algorithm(PBCA)is a new algorithm based on probability distribution.It decides,by voting,the class of the tested samples on the border of the coverage area,based on the probability of training samples.When using the original covering algorithm(CA),many tested samples that are located on the border of the coverage cannot be classified by the spherical neighborhood gained.The network structure of PBCA is a mixed structure composed of both a feed-forward network and a feedback network.By using this method of adding some heterogeneous samples and enlarging the coverage radius,it is possible to decrease the number of rejected samples and improve the rate of recognition accuracy.Relevant computer experiments indicate that the algorithm improves the study precision and achieves reasonably good results in text classification.展开更多
基金financially supported by grant from National Natural Science Foundation of China(No.31300533)
文摘Object-based classification differentiates forest gaps from canopies at large regional scale by using remote sensing data. To study the segmentation and classification processes of object-based forest gaps classification at a regional scale, we sampled a natural secondary forest in northeast China at Maoershan Experimental Forest Farm.Airborne light detection and ranging(LiDAR; 3.7 points/m2) data were collected as the original data source and the canopy height model(CHM) and topographic dataset were extracted from the LiDAR data. The accuracy of objectbased forest gaps classification depends on previous segmentation. Thus our first step was to define 10 different scale parameters in CHM image segmentation. After image segmentation, the machine learning classification method was used to classify three kinds of object classes, namely,forest gaps, tree canopies, and others. The common support vector machine(SVM) classifier with the radial basis function kernel(RBF) was first adopted to test the effect of classification features(vegetation height features and some typical topographic features) on forest gap classification.Then the different classifiers(KNN, Bayes, decision tree,and SVM with linear kernel) were further adopted to compare the effect of classifiers on machine learning forest gaps classification. Segmentation accuracy and classification accuracy were evaluated by using Mo¨ller's method and confusion metrics, respectively. The scale parameter had a significant effect on object-based forest gap segmentation and classification. Classification accuracies at different scales revealed that there were two optimal scales(10 and 20) that provided similar accuracy, with the scale of 10 yielding slightly greater accuracy than 20. The accuracy of the classification by using combination of height features and SVM classifier with linear kernel was91% at the optimal scale parameter of 10, and it was highest comparing with other classification classifiers, such as SVM RBF(90%), Decision Tree(90%), Bayes(90%),or KNN(87%). The classifiers had no significant effect on forest gap classification, but the fewer parameters in the classifier equation and higher speed of operation probably lead to a higher accuracy of final classifications. Our results confirm that object-based classification can extract forest gaps at a large regional scale with appropriate classification features and classifiers using LiDAR data. We note, however, that final satisfaction of forest gap classification depends on the determination of optimal scale(s) of segmentation.
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 knowledge bases for soil resourcesmapping by using a classification tree to generate knowledge from training data. With this method, buildinga knowledge base for automated soil mapping was easier than using the conventional knowledge acquisitionapproach. The knowledge base built by classification tree was used by the knowledge classifier to perform thesoil type classification of Longyou County, Zhejiang Province, China using Landsat TM bi-temporal imagesand GIS data. To evaluate the performance of the resultant knowledge bases, the classification results werecompared to existing soil map based on a field survey. The accuracy assessment and analysis of the resultantsoil maps suggested 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 (81473362)。
文摘Objective: To determine the in vitro and in vivo absorption properties of active ingredients of the Chinese medicine, baicalein, to enrich mechanistic understanding of oral drug absorption.Methods: The Biopharmaceutic Classification System(BCS) category was determined using equilibrium solubility, intrinsic dissolution rate, and intestinal permeability to evaluate intestinal absorption mechanisms of baicalein in rats in vitro. Physiologically based pharmacokinetic(PBPK) model commercial software GastroPlus~(TM) was used to predict oral absorption of baicalein in vivo.Results: Based on equilibrium solubility, intrinsic dissolution rate, and permeability values of main absorptive segments in the duodenum, jejunum, and ileum, baicalein was classified as a drug with low solubility and high permeability. Intestinal perfusion with venous sampling(IPVS) revealed that baicalein was extensively metabolized in the body, which corresponded to the low bioavailability predicted by the PBPK model. Further, the PBPK model predicted the key indicators of BCS, leading to reclassification as BCS-II. Predicted values of peak plasma concentration of the drug(C_(max)) and area under the curve(AUC)fell within two times of the error of the measured results, highlighting the superior prediction of absorption of baicalein in rats, beagles, and humans. The PBPK model supported in vitro and in vivo evidence and provided excellent prediction for this BCS class II drug.Conclusion: BCS and PBPK are complementary methods that enable comprehensive research of BCS parameters, intestinal absorption rate, metabolism, prediction of human absorption fraction and bioavailability, simulation of PK, and drug absorption in various intestinal segments across species. This combined approach may facilitate a more comprehensive and accurate analysis of the absorption characteristics of active ingredients of Chinese medicine from in vitro and in vivo perspectives.
文摘In this paper, a feature selection method combining the reliefF and SVM-RFE algorithm is proposed. This algorithm integrates the weight vector from the reliefF into SVM-RFE method. In this method, the reliefF filters out many noisy features in the first stage. Then the new ranking criterion based on SVM-RFE method is applied to obtain the final feature subset. The SVM classifier is used to evaluate the final image classification accuracy. Experimental results show that our proposed relief- SVM-RFE algorithm can achieve significant improvements for feature selection in image classification.
基金supported by grants from Science and Technology Support Program of Sichuan(2009SZ0201,2010SZ0068 and 2011SZ0291)National Institute for Health Research,UK
文摘BACKGROUND: Recent international multidisciplinary consultation proposed the use of local(sterile or infected pancreatic necrosis) and/or systemic determinants(organ failure) in the stratification of acute pancreatitis. The present study was to validate the moderate severity category by international multidisciplinary consultation definitions.METHODS: Ninety-two consecutive patients with severe acute pancreatitis(according to the 1992 Atlanta classification) were classified into(i) moderate acute pancreatitis group with the presence of sterile(peri-) pancreatic necrosis and/or transient organ failure; and(ii) severe/critical acute pancreatitis group with the presence of sterile or infected pancreatic necrosis and/or persistent organ failure. Demographic and clinical outcomes were compared between the two groups.RESULTS: Compared with the severe/critical group(n=59), the moderate group(n=33) had lower clinical and computerized tomographic scores(both P<0.05). They also had a lower incidence of pancreatic necrosis(45.5% vs 71.2%, P=0.015),infection(9.1% vs 37.3%, P=0.004), ICU admission(0% vs27.1%, P=0.001), and shorter hospital stay(15±5 vs 27±12days; P<0.001). A subgroup analysis showed that the moderate group also had significantly lower ICU admission rates, shorter hospital stay and lower rate of infection compared with the severe group(n=51). No patients died in the moderate group but7 patients died in the severe/critical group(4 for severe group).CONCLUSIONS: Our data suggest that the definition of moderate acute pancreatitis, as suggested by the international multidisciplinary consultation as sterile(peri-) pancreatic necrosis and/or transient organ failure, is an accurate category of acute pancreatitis.
文摘Proper quality planning of limestone raw materials is an essential job of maintaining desired feed in cement plant. Rock-type identification is an integrated part of quality planning for limestone mine. In this paper, a computer vision-based rock-type classification algorithm is proposed for fast and reliable identification without human intervention. A laboratory scale vision-based model was developed using probabilistic neural network(PNN) where color histogram features are used as input. The color image histogram-based features that include weighted mean, skewness and kurtosis features are extracted for all three color space red, green, and blue. A total nine features are used as input for the PNN classification model. The smoothing parameter for PNN model is selected judicially to develop an optimal or close to the optimum classification model. The developed PPN is validated using the test data set and results reveal that the proposed vision-based model can perform satisfactorily for classifying limestone rocktypes. Overall the error of mis-classification is below 6%. When compared with other three classification algorithms, it is observed that the proposed method performs substantially better than all three classification algorithms.
文摘AIM:To support probe-based confocal laser endomi-croscopy (pCLE) diagnosis by designing software for the automated classification of colonic polyps. METHODS:Intravenous fluorescein pCLE imaging of colorectal lesions was performed on patients under-going screening and surveillance colonoscopies, followed by polypectomies. All resected specimens were reviewed by a reference gastrointestinal pathologist blinded to pCLE information. Histopathology was used as the criterion standard for the differentiation between neoplastic and non-neoplastic lesions. The pCLE video sequences, recorded for each polyp, were analyzed off-line by 2 expert endoscopists who were blinded to the endoscopic characteristics and histopathology. These pCLE videos, along with their histopathology diagnosis, were used to train the automated classification software which is a content-based image retrieval technique followed by k-nearest neighbor classification. The performance of the off-line diagnosis of pCLE videos established by the 2 expert endoscopists was compared with that of automated pCLE software classification. All evaluations were performed using leave-one-patient- out cross-validation to avoid bias. RESULTS:Colorectal lesions (135) were imaged in 71 patients. Based on histopathology, 93 of these 135 lesions were neoplastic and 42 were non-neoplastic. The study found no statistical significance for the difference between the performance of automated pCLE software classification (accuracy 89.6%, sensitivity 92.5%, specificity 83.3%, using leave-one-patient-out cross-validation) and the performance of the off-line diagnosis of pCLE videos established by the 2 expert endoscopists (accuracy 89.6%, sensitivity 91.4%, specificity 85.7%). There was very low power (< 6%) to detect the observed differences. The 95% confidence intervals for equivalence testing were:-0.073 to 0.073 for accuracy, -0.068 to 0.089 for sensitivity and -0.18 to 0.13 for specificity. The classification software proposed in this study is not a "black box" but an informative tool based on the query by example model that produces, as intermediate results, visually similar annotated videos that are directly interpretable by the endoscopist. CONCLUSION:The proposed software for automated classification of pCLE videos of colonic polyps achieves high performance, comparable to that of off-line diagnosis of pCLE videos established by expert endoscopists.
基金supported by Zhejiang Provincial Natural Science Foundation of China(LY14C030008)Forestry Industry Standard Project of China(2015LY-080)
文摘To explore fertilization methods for wine bamboo cultivation in southwestern semi-arid areas of China,this study analyzed annual changes in sap yield and nutrient composition from May 2013 to March 2015 by using bamboo charcoal-based bio-fertilizer(ZT) and organic fertilizer treatments(CK).The study also provided basic data for functional beverage preparation and for application of ZT.The results of the two experimental cycles revealed that under the ZT treatment, sap was available for collection from May, the beginning of the rainy season, to November, the beginning of the dry season.The period of abundance was July to October with the highest yield of sap of 3.18 L stalk^(-1) in September, 2014,still lower than the moso bamboo sap, which was likely due to the scale of sap production of monopodial bamboos being different from that of sympodial bamboos.In January, trace amounts of sap were still detected, suggesting that the effect of the treatment was significant.Moreover,in the dry season, soil water content and soil temperatures at 10–15 cm depths indicated that the fertilizer had the ability to maintain soil temperatures and moisture.In both fertilizer treatments, the correlation between the collected sap and environmental parameters was significant.In the ZT treatment for the entire 2 years, the effectual environmental factors were soil water at 10–15 cm, air temperatures, and wind speeds.The same determining factors were observed for the rainy season.In the CK treatments, the effectual environmental factors for the entire year and the rainy season were soil water at 0–5 cm and air moisture.The bamboo charcoal-based bio-fertilizer elevated the potassium, calcium, iron, manganese, copper, and total phosphorus content, simultaneously increasing the sap yield, protein and reducing sugar contents, and with a relative increase in sap pH.The wine bamboo sap contained 18 amino acids.Glutamic acid, alanine and proline were the most abundant.Compared to the controls, the treatment showed higher levels of all amino acids.Thus,the ZT treatment could be more beneficial to the development of root systems because the function of heat preservation and moisture retention prolong the sap collection period, increase sap yields, and elevate mineral element, conventional nutrients, and amino acid contents with evident fertilization effects and broader application prospects.
文摘This paper proposed to use double polarization synthetic aperture radar (SAR) image to classify surface feature, based on DEM. It takes fully use of the polarization information and external information. This pa-per utilizes ENVISAT ASAR APP double-polarization data of Poyang lake area in Jiangxi Province. Com-pared with traditional pixel-based classification, this paper fully uses object features (color, shape, hierarchy) and accessorial DEM information. The classification accuracy improves from the original 73.7% to 91.84%. The result shows that object-oriented classification technology is suitable for double polarization SAR’s high precision classification.
文摘Recent days,Image retrieval has become a tedious process as the image database has grown very larger.The introduction of Machine Learning(ML)and Deep Learning(DL)made this process more comfortable.In these,the pair-wise label similarity is used tofind the matching images from the database.But this method lacks of limited propose code and weak execution of misclassified images.In order to get-rid of the above problem,a novel triplet based label that incorporates context-spatial similarity measure is proposed.A Point Attention Based Triplet Network(PABTN)is introduced to study propose code that gives maximum discriminative ability.To improve the performance of ranking,a corre-lating resolutions for the classification,triplet labels based onfindings,a spatial-attention mechanism and Region Of Interest(ROI)and small trial information loss containing a new triplet cross-entropy loss are used.From the experimental results,it is shown that the proposed technique exhibits better results in terms of mean Reciprocal Rank(mRR)and mean Average Precision(mAP)in the CIFAR-10 and NUS-WIPE datasets.
文摘Many researches have been performed comparing object-based classification (OBC) and pixel-based classification (PBC), particularly in classifying high-resolution satellite images. VNREDSat-1 is the first optical remote sensing satellite of Vietnam with resolution of 2.5 m (Panchromatic) and 10 m (Multispectral). The objective of this research is to compare two classification approaches using VNREDSat-1 image for mapping mangrove forest in Vien An Dong commune, Ngoc Hien district, Ca Mau province. ISODATA algorithm (in PBC method) and membership function classifier (in OBC method) were chosen to classify the same image. The results show that the overall accuracies of OBC and PBC are 73% and 62.16% respectively, and OBC solved the “salt and pepper” which is the main issue of PBC as well. Therefore, OBC is supposed to be the better approach to classify VNREDSat-1 for mapping mangrove forest in Ngoc Hien commune.
文摘This paper offers a symbiosis based hybrid modified DNA-ABC optimization algorithm which combines modified DNA concepts and artificial bee colony (ABC) algorithm to aid hierarchical fuzzy classification. According to literature, the ABC algorithm is traditionally applied to constrained and unconstrained problems, but is combined with modified DNA concepts and implemented for fuzzy classification in this present research. Moreover, from the best of our knowledge, previous research on the ABC algorithm has not combined it with DNA computing for hierarchical fuzzy classification to explore the merits of cooperative coevolution. Therefore, this paper is the first to apply the mechanism of symbiosis to create a hybrid modified DNA-ABC algorithm for hierarchical fuzzy classification applications. In this study, the partition number and the shape of the membership function are extracted by the symbiosis based hybrid modified DNA-ABC optimization algorithm, which provides both sufficient global exploration and also adequate local exploitation for hierarchical fuzzy classification. The proposed optimization algorithm is applied on five benchmark University of Irvine (UCI) data sets, and the results prove the efficiency of the algorithm.
文摘Building detection in very high resolution (VHR) images is crucial for mapping and analysing urban environments. Since buildings are elevated objects, elevation data need to be integrated with images for reliable detection. This process requires two critical steps: optical-elevation data co-registration and aboveground elevation calculation. These two steps are still challenging to some extent. Therefore, this paper introduces optical-elevation data co-registration and normalization techniques for generating a dataset that facilitates elevation-based building detection. For achieving accurate co-registration, a dense set of stereo-based elevations is generated and co-registered to their relevant image based on their corresponding image locations. To normalize these co-registered elevations, the bare-earth elevations are detected based on classification information of some terrain-level features after achieving the image co-registration. The developed method was executed and validated. After implementation, 80% overall-quality of detection result was achieved with 94% correct detection. Together, the developed techniques successfully facilitate the incorporation of stereo-based elevations for detecting buildings in VHR remote sensing images.
基金This work is sponsored by the National Natural Science Foundation of China (Nos. 61402246, 61402126, 61370083, 61370086, 61303193, and 61572268), a Project of Shandong Province Higher Educational Science and Technology Program (No. J15LN38), Qingdao indigenous innovation program (No. 15-9-1-47-jch), the National Research Foundation for the Doctoral Program of Higher Education of China (No. 20122304110012), the Natural Science Foundation of Heilongjiang Province of China (No. F201101), the Science and Technology Research Project Foundation of Heilongjiang Province Education Department (No. 12531105), Heilongjiang Province Postdoctoral Research Start Foundation (No. LBH-Q13092), and the National Key Technology R&D Program of the Ministry of Science and Technology under Grant No. 2012BAH81F02.
文摘The character variable discrete numeralization destroyed the disorder of character variables. As text classification problem contains more character variable, discrete numeralization approach affects the classification performance of classifiers. In this paper, we propose a character variable numeralization algorithm based on dimension expanding. Firstly, the algorithm computes the number of different values which the character variable takes. Then it replaces the original values with the natural bases in the m-dimensional Euclidean space. Though the algorithm causes a dimension expanding, it reserves the disorder of character variables because the natural bases are no difference in size, so this algorithm is a better character variable numerical processing algorithm. Experiments on text classification data sets show that though the proposed algorithm costs a little more running time, its classification performance is better.
文摘Medical images are important for medical research and clinical diagnosis.The research of medical images includes image acquisition,processing,analysis and other related research fields.Crowdsourcing is attracting growing interests in recent years as an effective tool.It can harness human intelligence to solve problems that computers cannot perform well,such as sentiment analysis and image recognition.Crowdsourcing can achieve higher accuracies in medical image classification,but it cannot be widely used for its low efficiency and the monetary cost.We adopt a hybrid approach which combines computer’s algorithm and crowdsourcing system for image classification.Medical image classification algorithms have a high error rate near the threshold.And it is not significant by improving these classification algorithms to achieve a higher accuracy.To address the problem,we propose a hybrid framework,which can achieve a higher accuracy significantly than only use classification algorithms.At the same time,it only processes the images that classification algorithms perform not well,so it has a lower monetary cost.In the framework,we device an effective algorithm to generate a range-threshold that assign images to crowdsourcing or classification algorithm.Experimental results show that our method can improve the accuracy of medical images classification and reduce the crowdsourcing monetary cost.
基金This research was supported by the Researchers Supporting Program(TUMA-Project2021–27)Almaarefa University,Riyadh,Saudi Arabia.
文摘Recently,developments of Internet and cloud technologies have resulted in a considerable rise in utilization of online media for day to day lives.It results in illegal access to users’private data and compromises it.Phishing is a popular attack which tricked the user into accessing malicious data and gaining the data.Proper identification of phishing emails can be treated as an essential process in the domain of cybersecurity.This article focuses on the design of bio-geography based optimization with deep learning for Phishing Email detection and classification(BBODL-PEDC)model.The major intention of the BBODL-PEDC model is to distinguish emails between legitimate and phishing.The BBODL-PEDC model initially performs data pre-processing in three levels namely email cleaning,tokenization,and stop word elimination.Besides,TF-IDF model is applied for the extraction of useful feature vectors.Moreover,optimal deep belief network(DBN)model is used for the email classification and its efficacy can be boosted by the BBO based hyperparameter tuning process.The performance validation of the BBODL-PEDC model can be performed using benchmark dataset and the results are assessed under several dimensions.Extensive comparative studies reported the superior outcomes of the BBODL-PEDC model over the recent approaches.
文摘BACKGROUND The overuse and misuse of antimicrobials contribute significantly to antimicrobial resistance(AMR),which is a global public health concern.India has particularly high rates of AMR,posing a threat to effective treatment.The World Health Or-ganization(WHO)Access,Watch,Reserve(AWaRe)classification system was introduced to address this issue and guide appropriate antibiotic prescribing.However,there is a lack of studies examining the prescribing patterns of antimi-crobials using the AWaRe classification,especially in North India.Therefore,this study aimed to assess the prescribing patterns of antimicrobials using the WHO AWaRe classification in a tertiary care centre in North India.Ophthalmology,Obstetrics and Gynecology).Metronidazole and ceftriaxone were the most prescribed antibiotics.According to the AWaRe classification,57.61%of antibiotics fell under the Access category,38.27%in Watch,and 4.11%in Reserve.Most Access antibiotics were prescribed within the Medicine department,and the same department also exhibited a higher frequency of Watch antibiotics prescriptions.The questionnaire survey showed that only a third of participants were aware of the AWaRe classification,and there was a lack of knowledge regarding AMR and the potential impact of AWaRe usage.RESULTS The research was carried out in accordance with the methodology presented in Figure 1.A total of n=123 patients were enrolled in this study,with each of them receiving antibiotic prescriptions.The majority of these prescriptions were issued to inpatients(75.4%),and both the Medicine and Surgical departments were equally represented,accounting for 49.6%and 50.4%,respectively.Among the healthcare providers responsible for prescribing antibiotics,72%were Junior Residents,18.7%were Senior Residents,and 9.3%were Consultants.These findings have been summarized in Table 1.The prescriptions included 27 different antibiotics,with metronidazole being the most prescribed(19%)followed by ceftriaxone(17%).The mean number of antibiotics used per patient was 1.84±0.83.The mean duration of antibiotics prescribed was 6.63±3.83 days.The maximum number of antibiotics prescribed per patient was five.According to the AWaRe classification,57.61%of antibiotics fell under the Access,38.27%in Watch,and 4.11%in Reserve categories,suggesting appropriate antibiotic selection according to these criteria.The distribution of antibiotics prescribed according to the WHO AWaRe categories is presented in Figure 2.The difference in prescribing frequencies amongst departments can be noted.Most of the antibiotics prescribed in the Access category were from the Medicine department(75.4%),followed by Surgery(24.6%).For Watch antibiotics,Medicine had a higher proportion(63.4%)compared to Surgery(36.6%).In terms of seniority,Junior Residents prescribed the highest number of antibiotics for both Access and Watch categories in Medicine and Surgery departments.Senior residents and Consultants prescribed a lower number of antibiotics in all categories and departments.Only a few antibiotics were prescribed in the Reserve category,with most prescriptions being from the Medicine department.The study also evaluated the Knowledge and Awareness of Healthcare professionals towards the WHO AWaRe classi-fication through a questionnaire survey.A total of 93 participants responded to the survey.Among them,most parti-cipants were Junior Residents(69.9%),followed by Senior Residents(25.8%)and Faculty(4.3%).When enquired if they knew about the WHO AWaRe classification only 33.3%of the participants responded positively.Of those who were aware of the AWaRe classification,the most common source of information was the internet(31.2%),followed by the antimicrobial policy of their institution(15.1%)as seen in Table 2.The survey results on the knowledge and awareness of AMR among healthcare professionals are also presented in Tables 3 and 4.Out of the 93 participants,68(73.1%)agreed that the emergence of AMR is inevitable,while only 13(14.0%)disagreed that AWaRe usage will result in the inability to treat serious infections.Additionally,58(62.4%)agreed that it will lead to lengthier hospital stays,43(46.2%)agreed that the success of chemotherapy and major surgery will be hampered,and the majority also agreed that its use will lead to increased cost of treatment and increased mortality rates.Regarding the utilization of AWaRe in the hospital summarized in Tables 4 and 5,35.5%of the participants agreed that it should be used,while only 2.2%disagreed.Additionally,34.4%agreed that AWaRe reduces adverse effects of inappro-priate prescription.However,37.6%of the participants considered that AWaRe threatens a clinician's autonomy and 30.1%thought that its use can delay treatment.Additionally,the DDD of each drug was also evaluated.The usage of various antimicrobial drugs in a hospital setting,along with their daily doses and DDD according to the WHO's Anatomical Therapeutic Chemical classification system was calculated.Some of the important findings include high usage rates of ceftriaxone and metronidazole,and relatively low usage rates of drugs like colistin and clindamycin.Additionally,some drugs had wider ranges than others.Comparison of WHO defined DDD with Daily Drug dose(Mean)in the studied prescriptions is represented in the Clustered Bar chart in Figure 3.Finally,the Mean Daily Drug Dose for prescribed drugs was compared with WHO defined DDD for each drug using a Student’s T test.The mean daily drug dose of amoxy/clav was significantly higher than the WHO DDD(1.8 vs 1.50,P=0.014),while the mean daily drug dose of metronidazole and doxycycline were significantly lower than the WHO DDD(P<0.001 and P=0.008,respectively).The mean daily drug dose of piperacillin/tazobactam,amikacin,clindamycin,and levofloxacin did not show significant differences compared to the WHO DDD(P>0.05).CONCLUSION This research indicates an appropriate proportion of prescriptions falling under the Access category(57.61%),suggesting appropriate antibiotic selection,a significant proportion also belongs to the Watch category(38.27%),emphasizing the need for greater caution to prevent the escalation of AMR.There is a moderate level of awareness among healthcare professionals about AMR and the steps being taken to tackle it,highlighting the gap in implementation of policies and need for more steps to be taken in spreading the knowledge about the subject.However,there is a significant difference between the WHO DDD and the prescribed daily dose in the analysed prescriptions suggesting overuse and underuse of antibiotics.
基金supported by the Fund for Philosophy and Social Science of Anhui Provincethe Fund for Human and Art Social Science of the Education Department of Anhui Province(Grant Nos.AHSKF0708D13 and 2009sk038)
文摘The probability-based covering algorithm(PBCA)is a new algorithm based on probability distribution.It decides,by voting,the class of the tested samples on the border of the coverage area,based on the probability of training samples.When using the original covering algorithm(CA),many tested samples that are located on the border of the coverage cannot be classified by the spherical neighborhood gained.The network structure of PBCA is a mixed structure composed of both a feed-forward network and a feedback network.By using this method of adding some heterogeneous samples and enlarging the coverage radius,it is possible to decrease the number of rejected samples and improve the rate of recognition accuracy.Relevant computer experiments indicate that the algorithm improves the study precision and achieves reasonably good results in text classification.