Displaying publications 1 - 20 of 28 in total

Abstract:
Sort:
  1. Chen W, Zhang J, Geng Z, Zhu D
    Yi Chuan Xue Bao, 1994;21(3):179-87.
    PMID: 7917431
    We report the fact that D. albomicans invaded into Shanghai suddenly in the autumn of 1991. Using 9 restriction enzymes, we analyse the RFLPs of mitochondrial DNA of 29 isofemale lines belonging to 4 populations of Shanghai, Jiading, Qinpu and Nanhui. We find that all 29 haplotypes are different from each other. Comparing with the populations of Canton, Kunming, Sanhutan (Taiwan), Sumoto (Japan), and Kuala Lumper (Malaysia), we come to the conclusion that D. albomicans caught in Shanghai and areas nearby is from a few of places in the south of China-mainland. This conclusion agrees with the viewpoint that this species is on the speciation stage of migration towards north. We also discuss the mtDNA polymorphism within the species.
  2. Chen WR, Tesh RB, Rico-Hesse R
    J. Gen. Virol., 1990 Dec;71 ( Pt 12):2915-22.
    PMID: 2273391
    Forty-six strains of Japanese encephalitis (JE) virus from a variety of geographic areas in Asia were examined by primer-extension sequencing of the RNA template. A 240 nucleotide sequence from the pre-M gene region was selected for study because it provided sufficient information for determining genetic relationships among the virus isolates. Using 12% divergence as a cutoff point for virus relationships, the 46 isolates fell into three distinct genotypic groups. One genotypic group consisted of JE virus isolates from northern Thailand and Cambodia. A second group was composed of isolates from southern Thailand, Malaysia, Sarawak and Indonesia. The remainder of the isolates, from Japan, China, Taiwan, the Philippines, Sri Lanka, India and Nepal, made up a third group. The implications of these findings in relation to the epidemiology of JE are discussed. Results of this study demonstrate that the comparison of short nucleotide sequences can provide insight into JE virus evolution, transmission and, possibly, pathogenesis.
  3. Chen WS, Tan JH, Mohamad Y, Imran R
    Injury, 2019 May;50(5):1118-1124.
    PMID: 30591225 DOI: 10.1016/j.injury.2018.12.031
    BACKGROUND: The establishment of an accurate prognostic model in major trauma patients is important mainly because this group of patients will benefit the most. Clinical prediction models must be validated internally and externally on a regular basis to ensure the prediction is accurate and current. This study aims to externally validate two prediction models, the Trauma and Injury Severity Score model developed using the Major Trauma Outcome Study in North America (MTOS-TRISS model), and the NTrD-TRISS model, which is a refined MTOS-TRISS model with coefficients derived from the Malaysian National Trauma Database (NTrD), by regarding mortality as the outcome measurement.

    METHOD: This retrospective study included patients with major trauma injuries reported to a trauma centre of Hospital Sultanah Aminah over a 6-year period from 2011 and 2017. Model validation was examined using the measures of discrimination and calibration. Discrimination was assessed using the area under the receiver operating characteristic curve (AUC) and 95% confidence interval (CI). The Hosmer-Lemeshow (H-L) goodness-of-fit test was used to examine calibration capabilities. The predictive validity of both MTOS-TRISS and NTrD-TRISS models were further evaluated by incorporating parameters such as the New Injury Severity Scale and the Injury Severity Score.

    RESULTS: Total patients of 3788 (3434 blunt and 354 penetrating injuries) with average age of 37 years (standard deviation of 16 years) were included in this study. All MTOS-TRISS and NTrD-TRISS models examined in this study showed adequate discriminative ability with AUCs ranged from 0.86 to 0.89 for patients with blunt trauma mechanism and 0.89 to 0.99 for patients with penetrating trauma mechanism. The H-L goodness-of-fit test indicated the NTrD-TRISS model calibrated as good as the MTOS-TRISS model for patients with blunt trauma mechanism.

    CONCLUSION: For patients with blunt trauma mechanism, both the MTOS-TRISS and NTrD-TRISS models showed good discrimination and calibration performances. Discrimination performance for the NTrD-TRISS model was revealed to be as good as the MTOS-TRISS model specifically for patients with penetrating trauma mechanism. Overall, this validation study has ascertained the discrimination and calibration performances of the NTrD-TRISS model to be as good as the MTOS-TRISS model particularly for patients with blunt trauma mechanism.

  4. Chen H, Lin H, Lin Z, Chen J, Chen W
    BMC Ophthalmol, 2016 May 01;16(1):47.
    PMID: 27138378 DOI: 10.1186/s12886-016-0221-5
    BACKGROUND: Ocular biometry is important for preoperative assessment in cataract and anterior segment surgery. The purpose of this study was to investigate normative ocular biometric parameters and their associations in an older Chinese population.

    METHODS: This was a cross-sectional observational study. From 2013 to 2014, we recruited inhabitants aged 50 years or older in Guangzhou, China. Among 1,117 participants in the study, data from 1,015 phakic right eyes were used for analyses. Ocular parameters including axial length (AL), anterior chamber depth (ACD), and corneal curvature (K) were measured using an IOL Master.

    RESULTS: The mean AL, ACD, and K were 23.48 mm [95 % confidence interval (CI), 23.40-23.55], 3.03 mm (CI, 3.01-3.05), and 44.20 mm (CI, 44.11-44.29), respectively. A mean reduction in ACD with age was observed (P = 0.002) in male subjects but not in female subjects (P = 0.558). Male subjects had significantly longer ALs (23.68 mm versus 23.23 mm, P 

  5. Zhang YT, Ghaffar MA, Li Z, Chen W, Chen SX, Hong WS
    Mitochondrial DNA, 2016;27(1):62-4.
    PMID: 24438254 DOI: 10.3109/19401736.2013.873901
    The Boddart's goggle-eyed mudskipper, Boleophthalmus boddarti (Perciformes, Gobiidae) is an amphibious fish, inhabiting brackish waters of estuaries and builds burrows in soft mud along the intertidal zone. In this paper, the complete mitochondrial genome sequence of B. boddarti was firstly determined. The circle genome (16,727 bp) comprises 13 protein-coding genes, 22 tRNA genes, 2 rRNA genes and 1 control region. The overall base composition of B. boddarti is 29.1% for C, 28.9% for A, 25.9% for T, and 16.0% for G, with a slight A + T bias of 54.8%. The termination-associated sequence, conserved sequence block domains, and a 131-bp tandem repeat were found in the control region. It has the typical vertebrate mitochondrial gene arrangement.
  6. Aljunid SM, Srithamrongsawat S, Chen W, Bae SJ, Pwu RF, Ikeda S, et al.
    Value Health, 2012 Jan-Feb;15(1 Suppl):S132-8.
    PMID: 22265060 DOI: 10.1016/j.jval.2011.11.004
    This article sought to describe the health-care data situation in six selected economies in the Asia-Pacific region. Authors from Thailand, China mainland, South Korea, Taiwan, Japan, and Malaysia present their analyses in three parts. The first part of the article describes the data-collection process and the sources of data. The second part of the article presents issues around policies of data sharing with the stakeholders. The third and final part of the article focuses on the extent of health-care data use for policy reform in these different economies. Even though these economies differ in their economic structure and population size, they share some similarities on issues related to health-care data. There are two main institutions that collect and manage the health-care data in these economies. In Thailand, China mainland, Taiwan, and Malaysia, the Ministry of Health is responsible through its various agencies for collecting and managing the health-care data. On the other hand, health insurance is the main institution that collects and stores health-care data in South Korea and Japan. In all economies, sharing of and access to data is an issue. The reasons for limited access to some data are privacy protection, fragmented health-care system, poor quality of routinely collected data, unclear policies and procedures to access the data, and control on the freedom on publication. The primary objective of collecting health-care data in these economies is to aid the policymakers and researchers in policy decision making as well as create an awareness on health-care issues for the general public. The usage of data in monitoring the performance of the heath system is still in the process of development. In conclusion, for the region under discussion, health-care data collection is under the responsibility of the Ministry of Health and health insurance agencies. Data are collected from health-care providers mainly from the public sector. Routinely collected data are supplemented by national surveys. Accessibility to the data is a major issue in most of the economies under discussion. Accurate health-care data are required mainly to support policy making and evidence-based decisions.
  7. Ang BH, Chen WS, Ngin CK, Oxley JA, Lee SWH
    Public Health, 2018 Feb;155:8-16.
    PMID: 29274898 DOI: 10.1016/j.puhe.2017.11.003
    OBJECTIVES: This study aimed to examine the reliability and validity of the English and Malay versions of the Driving and Riding Questionnaire.

    STUDY DESIGN: An observational study with a mix-method approach by utilising both questionnaire and short debriefing interviews.

    METHODS: Forward and backward translations of the original questionnaire were performed. The translated questionnaire was assessed for clarity by a multidisciplinary research team, translators, and several Malay native speakers. A total of 24 subjects participated in the pilot study. Reliability (Cronbach's alpha) and validity (content validity) of the original and translated questionnaires were examined.

    RESULTS: The English and Malay versions of the Driving and Riding Questionnaire were found to be reliable tools in measuring driving behaviours amongst older drivers and riders, with Cronbach's alpha of 0.9158 and 0.8919, respectively. For content validity, the questionnaires were critically reviewed in terms of relevance, clarity, simplicity, and ambiguity. The feedback obtained from participants addressed various aspects of the questionnaire related to the improvement of wordings used and inclusion of visual guide to enhance the understanding of the items in the questionnaire. This feedback was incorporated into the final versions of the English and Malay questionnaires.

    CONCLUSION: The findings of this study demonstrated both the English and Malay versions of the Driving and Riding Questionnaire to be valid and reliable.
  8. Waqas MY, Lisi H, Yang P, Ullah S, Zhang L, Zhang Q, et al.
    J Exp Zool A Ecol Genet Physiol, 2015 Nov;323(9):655-65.
    PMID: 26350585 DOI: 10.1002/jez.1957
    The oviduct is the location of fertilization and sperm storage. We examined the ultrastructure of the oviduct epithelium and its glandular secretions in the isthmus, uterus and vagina of Chinese soft-shelled turtle Pelodiscus sinensis using light and transmission electron microscopy. The epithelium in these segments is lined with ciliated, secretory and other cells; the first two cell types span the entire epithelium, with secretory cells being predominant. The ciliated cells are characterized by the presence of a secretory vacuole that releases apocrine secretions into the lumen, whereas the secretory cells contain typical biphasic granules with both dark and light aspects. The third type of cells observed have wider proximal portion, abundant mitochondria, vacuoles, and narrow nuclei. The storage of spermatozoa is restricted to the isthmus, uterus, and vagina. In addition, the gland cells show prominent features, including the presence of granules of different shapes, sizes, and electron densities. The synthesis of these granules is described for the first time in this study. Mitochondria appear to play an important role in the formation of dense granules, the rough endoplasmic reticulum and microfilaments may also play a role in the maturation of these dense granules. After completing the maturation process, these granules are released into the lumen of the gland cells.
  9. Liu X, Lai X, Zhang S, Huang X, Lan Q, Li Y, et al.
    J. Agric. Food Chem., 2012 Dec 26;60(51):12477-81.
    PMID: 23214475 DOI: 10.1021/jf303533p
    Edible bird's nest (EBN) is made of the swiftlets' saliva, which has attracted rather more attention owing to its nutritious and medical properties. Although protein constitutes the main composition and plays an important role in EBN, few studies have focused on the proteomic profile of EBN. The purpose of this study was to produce a proteomic map and clarify common EBN proteins. Liquid-phase isoelectric focusing (LIEF) was combined with two-dimensional electrophoresis (2-DE) for comprehensive analysis of EBN proteins. From 20 to 100 protein spots were detected on 2-DE maps of EBN samples from 15 different sources. The proteins were mainly distributed in four taxa (A, B, C, and D) according to their molecular mass. Taxa A and D both contained common proteins and proteins that may be considered another characteristic of EBN. Taxon A was identified using MALDI-TOF-TOF/MS and found to be homologous to acidic mammalian chitinase-like ( Meleagris gallopavo ), which is in glycosyl hydrolase family 18.
  10. Fuziah MZ, Hong JY, Zanariah H, Harun F, Chan SP, Rokiah P, et al.
    Med. J. Malaysia, 2008 Sep;63 Suppl C:37-40.
    PMID: 19230245
    In Malaysia, Diabetes in Children and Adolescents Registry (DiCARE) was launched nationwide in August 2006 to determine and monitor the number, the time trend of diabetes mellitus (DM) patients, their socio-demographic profiles, outcome of intervention and facilitate research using this registry. This is an on going real time register of diabetic patients < or = 20 years old via the e-DiCARE, an online registration system. To date were 240 patients notified from various states in Malaysia. The mean age was 12.51 years (1.08-19.75) and 46.4% were boys. The mean age at diagnosis was 8.31 +/- 4.13 years old with an estimated duration of diabetes of 4.32 +/- 3.55 years. A total of 166/240 (69.2%) have T1DM, 42/240 (17.5%) have T2DM and 18/240 (7.5%) have other types of DM. Basis of diagnosis was known in 162 patients with T1DM and 41 patients with T2DM. In T1DM patients, 6.0% of the girls and 19.1% boys were overweight or obese. As for T2DM, 64.3% had their BMI reported: 66.7% girls and 91.6% boys were overweight or obese. Most patients (80.4%) practiced home blood glucose monitoring. Patients were seen by dietitian (66.7%), diabetes educator (50.0%), and optometrist or ophthalmologist (45.0%). Only 10.8% attended diabetic camps. In the annual census of 117 patients, the mean HbAlc level was 10.0% + 2.2 (range 5.2 to 17.0%). The early results of DiCARE served as a starting point to improve the standard of care of DM among the young in the country.
  11. Jamaiyah H, Geeta A, Safiza MN, Khor GL, Wong NF, Kee CC, et al.
    Med. J. Malaysia, 2010 Jun;65 Suppl A:131-7.
    PMID: 21488474
    The National Health and Morbidity Survey III 2006 wanted to perform anthropometric measurements (length and weight) for children in their survey. However there is limited literature on the reliability, technical error of measurement (TEM) and validity of these two measurements. This study assessed the above properties of length (LT) and weight (WT) measurements in 130 children age below two years, from the Hospital Universiti Kebangsaan Malaysia (HUKM) paediatric outpatient clinics, during the period of December 2005 to January 2006. Two trained nurses measured WT using Tanita digital infant scale model 1583, Japan (0.01kg) and Seca beam scale, Germany (0.01 kg) and LT using Seca measuring mat, Germany (0.1cm) and Sensormedics stadiometer model 2130 (0.1cm). Findings showed high inter and intra-examiner reliability using 'change in the mean' and 'intraclass correlation' (ICC) for WT and LT. However, LT was found to be less reliable using the 'Bland and Altman plot'. This was also true using Relative TEMs, where the TEM value of LT was slightly more than the acceptable limit. The test instruments were highly valid for WT using 'change in the mean' and 'ICC' but was less valid for LT measurement. In spite of this we concluded that, WT and LT measurements in children below two years old using the test instruments were reliable and valid for a community survey such as NHMS III within the limits of their error. We recommend that LT measurements be given special attention to improve its reliability and validity.
    Study site: Paediatric clinic, Pusat Perubatan Universiti Kebangsaan Malaysia (PPUKM), Kuala Lumpur, Malaysia
  12. Abas FS, Shana'ah A, Christian B, Hasserjian R, Louissaint A, Pennell M, et al.
    Cytometry A, 2017 06;91(6):609-621.
    PMID: 28110507 DOI: 10.1002/cyto.a.23049
    The advance of high resolution digital scans of pathology slides allowed development of computer based image analysis algorithms that may help pathologists in IHC stains quantification. While very promising, these methods require further refinement before they are implemented in routine clinical setting. Particularly critical is to evaluate algorithm performance in a setting similar to current clinical practice. In this article, we present a pilot study that evaluates the use of a computerized cell quantification method in the clinical estimation of CD3 positive (CD3+) T cells in follicular lymphoma (FL). Our goal is to demonstrate the degree to which computerized quantification is comparable to the practice of estimation by a panel of expert pathologists. The computerized quantification method uses entropy based histogram thresholding to separate brown (CD3+) and blue (CD3-) regions after a color space transformation. A panel of four board-certified hematopathologists evaluated a database of 20 FL images using two different reading methods: visual estimation and manual marking of each CD3+ cell in the images. These image data and the readings provided a reference standard and the range of variability among readers. Sensitivity and specificity measures of the computer's segmentation of CD3+ and CD- T cell are recorded. For all four pathologists, mean sensitivity and specificity measures are 90.97 and 88.38%, respectively. The computerized quantification method agrees more with the manual cell marking as compared to the visual estimations. Statistical comparison between the computerized quantification method and the pathologist readings demonstrated good agreement with correlation coefficient values of 0.81 and 0.96 in terms of Lin's concordance correlation and Spearman's correlation coefficient, respectively. These values are higher than most of those calculated among the pathologists. In the future, the computerized quantification method may be used to investigate the relationship between the overall architectural pattern (i.e., interfollicular vs. follicular) and outcome measures (e.g., overall survival, and time to treatment). © 2017 International Society for Advancement of Cytometry.
  13. Chen W, Liao X, Wu Y, Liang JB, Mi J, Huang J, et al.
    Waste Manag, 2017 Mar;61:506-515.
    PMID: 28117129 DOI: 10.1016/j.wasman.2017.01.014
    Biochar, because of its unique physiochemical properties and sorption capacity, may be an ideal amendment in reducing gaseous emissions during composting process but there has been little information on the potential effects of different types of biochar on undesired gaseous emissions. The objective of this study was to examine the ability and mechanism of different types of biochar, as co-substrate, in mitigating gaseous emission from composting of layer hen manure. The study was conducted in small-scale laboratory composters with the addition of 10% of one of the following biochars: cornstalk biochar, bamboo biochar, woody biochar, layer manure biochar and coir biochar. The results showed that the cumulative NH3 production was significantly reduced by 24.8±2.9, 9.2±1.3, 20.1±2.6, 14.2±1.6, 11.8±1.7% (corrected for initial total N) in the cornstalk biochar, bamboo biochar, woody biochar, layer manure biochar and coir biochar treatments, respectively, compared to the control. Total CH4 emissions was significantly reduced by 26.1±2.3, 15.5±2.1, 22.4±3.1, 17.1±2.1% (corrected for the initial total carbon) for cornstalk biochar, bamboo biochar, woody biochar and coir biochar treatments than the control. Moreover, addition of cornstalk biochar increased the temperature and NO3(-)-N concentration and decreased the pH, NH4(+)-N and organic matter content throughout the composting process. The results suggested that total volatilization of NH3 and CH4 in cornstalk biochar treatment was lower than the other treatments; which could be due to (i) decrease of pH and higher nitrification, (ii) high sorption capacity for gases and their precursors, such as ammonium nitrogen from composting mixtures, because of the higher surface area, pore volumes, total acidic functional groups and CEC of cornstalk biochar.
  14. Tien Bui D, Shahabi H, Shirzadi A, Chapi K, Pradhan B, Chen W, et al.
    Sensors (Basel), 2018 Jul 31;18(8).
    PMID: 30065216 DOI: 10.3390/s18082464
    In this study, land subsidence susceptibility was assessed for a study area in South Korea by using four machine learning models including Bayesian Logistic Regression (BLR), Support Vector Machine (SVM), Logistic Model Tree (LMT) and Alternate Decision Tree (ADTree). Eight conditioning factors were distinguished as the most important affecting factors on land subsidence of Jeong-am area, including slope angle, distance to drift, drift density, geology, distance to lineament, lineament density, land use and rock-mass rating (RMR) were applied to modelling. About 24 previously occurred land subsidence were surveyed and used as training dataset (70% of data) and validation dataset (30% of data) in the modelling process. Each studied model generated a land subsidence susceptibility map (LSSM). The maps were verified using several appropriate tools including statistical indices, the area under the receiver operating characteristic (AUROC) and success rate (SR) and prediction rate (PR) curves. The results of this study indicated that the BLR model produced LSSM with higher acceptable accuracy and reliability compared to the other applied models, even though the other models also had reasonable results.
  15. Bui DT, Panahi M, Shahabi H, Singh VP, Shirzadi A, Chapi K, et al.
    Sci Rep, 2018 Oct 18;8(1):15364.
    PMID: 30337603 DOI: 10.1038/s41598-018-33755-7
    Adaptive neuro-fuzzy inference system (ANFIS) includes two novel GIS-based ensemble artificial intelligence approaches called imperialistic competitive algorithm (ICA) and firefly algorithm (FA). This combination could result in ANFIS-ICA and ANFIS-FA models, which were applied to flood spatial modelling and its mapping in the Haraz watershed in Northern Province of Mazandaran, Iran. Ten influential factors including slope angle, elevation, stream power index (SPI), curvature, topographic wetness index (TWI), lithology, rainfall, land use, stream density, and the distance to river were selected for flood modelling. The validity of the models was assessed using statistical error-indices (RMSE and MSE), statistical tests (Friedman and Wilcoxon signed-rank tests), and the area under the curve (AUC) of success. The prediction accuracy of the models was compared to some new state-of-the-art sophisticated machine learning techniques that had previously been successfully tested in the study area. The results confirmed the goodness of fit and appropriate prediction accuracy of the two ensemble models. However, the ANFIS-ICA model (AUC = 0.947) had a better performance in comparison to the Bagging-LMT (AUC = 0.940), BLR (AUC = 0.936), LMT (AUC = 0.934), ANFIS-FA (AUC = 0.917), LR (AUC = 0.885) and RF (AUC = 0.806) models. Therefore, the ANFIS-ICA model can be introduced as a promising method for the sustainable management of flood-prone areas.
  16. Jamaiyah H, Geeta A, Safiza MN, Wong NF, Kee CC, Ahmad AZ, et al.
    Malays J Nutr, 2008 Sep;14(2):137-50.
    PMID: 22691771 MyJurnal
    This study sought to examine the reliability of two measurements; Calf Circumference (CC) and Mid-half Arm Span (MHAS). A sample of 130 elderly persons aged 60 years and above seen consecutively in the Kuala Lumpur Hospital outpatient clinic during the period of December 2005 to January 2006, upon consent, were recruited to the study. There was a high degree of reliability for both inter- and intra-examiner (r close to 1). For inter-examiner, on average the CC measurements taken by the first examiner were 0.3 cm lower than that of the second examiner. The upper and lower limit of the differences were +0.4 to -0.9 cm respectively. Inter-examiner MHAS measurements on average by the first examiner were 0.2 cm lower than that of the second examiner. The limits were +1.7 to -2.1 cm. By comparison, the inter-examiner CC measurements were more reliable than the MHAS measurements. For intra-examiner, on average the CC measurements at Time 1 were consistent with Time 2 (mean difference=0) with limits of the difference at + 0.5 cm. MHAS measurements at Time 1 were on average 0.1 cm less than at Time 2 with limits at +1.7 and -1.8 cm. The technical error of measurement (TEM) and coefficient of variation of CC and MHAS for both interexaminer and intra-examiner measurements were within acceptable limits with the exception of MHAS TEM. This study suggests that CC and MHAS measured in elderly persons 60 years and above, using Seca Circumference Tape ® 206, Germany (0.05 cm) are reliable and can be used in a community survey.

    Study site: Outpatient clinic, Hospital Kuala Lumpur
  17. Niazi MKK, Abas FS, Senaras C, Pennell M, Sahiner B, Chen W, et al.
    PLoS ONE, 2018;13(5):e0196547.
    PMID: 29746503 DOI: 10.1371/journal.pone.0196547
    Automatic and accurate detection of positive and negative nuclei from images of immunostained tissue biopsies is critical to the success of digital pathology. The evaluation of most nuclei detection algorithms relies on manually generated ground truth prepared by pathologists, which is unfortunately time-consuming and suffers from inter-pathologist variability. In this work, we developed a digital immunohistochemistry (IHC) phantom that can be used for evaluating computer algorithms for enumeration of IHC positive cells. Our phantom development consists of two main steps, 1) extraction of the individual as well as nuclei clumps of both positive and negative nuclei from real WSI images, and 2) systematic placement of the extracted nuclei clumps on an image canvas. The resulting images are visually similar to the original tissue images. We created a set of 42 images with different concentrations of positive and negative nuclei. These images were evaluated by four board certified pathologists in the task of estimating the ratio of positive to total number of nuclei. The resulting concordance correlation coefficients (CCC) between the pathologist and the true ratio range from 0.86 to 0.95 (point estimates). The same ratio was also computed by an automated computer algorithm, which yielded a CCC value of 0.99. Reading the phantom data with known ground truth, the human readers show substantial variability and lower average performance than the computer algorithm in terms of CCC. This shows the limitation of using a human reader panel to establish a reference standard for the evaluation of computer algorithms, thereby highlighting the usefulness of the phantom developed in this work. Using our phantom images, we further developed a function that can approximate the true ratio from the area of the positive and negative nuclei, hence avoiding the need to detect individual nuclei. The predicted ratios of 10 held-out images using the function (trained on 32 images) are within ±2.68% of the true ratio. Moreover, we also report the evaluation of a computerized image analysis method on the synthetic tissue dataset.
  18. Chen W, Li H, Hou E, Wang S, Wang G, Panahi M, et al.
    Sci. Total Environ., 2018 Sep 01;634:853-867.
    PMID: 29653429 DOI: 10.1016/j.scitotenv.2018.04.055
    The aim of the current study was to produce groundwater spring potential maps using novel ensemble weights-of-evidence (WoE) with logistic regression (LR) and functional tree (FT) models. First, a total of 66 springs were identified by field surveys, out of which 70% of the spring locations were used for training the models and 30% of the spring locations were employed for the validation process. Second, a total of 14 affecting factors including aspect, altitude, slope, plan curvature, profile curvature, stream power index (SPI), topographic wetness index (TWI), sediment transport index (STI), lithology, normalized difference vegetation index (NDVI), land use, soil, distance to roads, and distance to streams was used to analyze the spatial relationship between these affecting factors and spring occurrences. Multicollinearity analysis and feature selection of the correlation attribute evaluation (CAE) method were employed to optimize the affecting factors. Subsequently, the novel ensembles of the WoE, LR, and FT models were constructed using the training dataset. Finally, the receiver operating characteristic (ROC) curves, standard error, confidence interval (CI) at 95%, and significance level P were employed to validate and compare the performance of three models. Overall, all three models performed well for groundwater spring potential evaluation. The prediction capability of the FT model, with the highest AUC values, the smallest standard errors, the narrowest CIs, and the smallest P values for the training and validation datasets, is better compared to those of other models. The groundwater spring potential maps can be adopted for the management of water resources and land use by planners and engineers.
Related Terms
Filters
Contact Us

Please provide feedback to Administrator (tengcl@gmail.com)

External Links