MyMedR

Displaying all 4 publications

Abstract:

Sort:

Fulltext An improved accurate classification method for online education resources based on support vector machine (SVM): Algorithm and experiment

Quan Z, Pu L

Educ Inf Technol (Dordr), 2022 Dec 15.
PMID: 36536868 DOI: 10.1007/s10639-022-11514-6

In the face of surging online education around the globe, it seems quite necessary and helpful for learners and teachers to have the plethora of online resources well sorted out beforehand. To some extent, the efficiency and accuracy of resource search and retrieval may determine the quality and influence of online education. In this research, based on the methodological framework of design science, the support vector machine (SVM) algorithm is chosen to optimise the design of an accurate resource classifier. The aim is to improve the unsatisfactory classification effect of traditional classification methods for online education resources, so that online learners can enjoy more accurate and convenient access to education resources they are seeking out of many more. For the purpose of performance evaluation, the proposed SVM-based classifier was compared with two other classification methods based on multiple neutral networks and deep learning respectively. Upon collection and pre-processing of online materials, the features of educational resources were extracted and output in the form of feature vectors. By calculating the similarity between the extracted feature vectors and the standard vectors of the set type, we obtained the classification results of online education resources for each of the three classifiers. It was found that, compared with those of the two traditional classification methods, the precision ratio and the recall ratio of the proposed classifier improved by 3.26% and 2.01% respectively. In the meantime, the proposed SVM-based classifier seems to more advantageous in performance balance with better F measurement.
Comparison of fertilizer use efficiency in grain production between developing countries and developed countries

Liu Q, Wu TY, Pu L, Sun J

J Sci Food Agric, 2021 Oct 09.
PMID: 34626124 DOI: 10.1002/jsfa.11579

BACKGROUND: Study of chemical fertilization intensity (FI) and efficiency can provide basal data for the decision-making of food production and environmental impact assessment of fertilization. This research aimed to compare trends of the FI and efficiency during 1961-2018 in developed and developing countries with a simple method.
RESULTS: The FI in China increased rapidly from about 5 kg ha-1 in 1961 to the highest value of 282 kg ha-1 in 2014, then decreased to about 231 kg ha-1 in 2018. Although the fertilizer allocation efficiency (FAE) showed a slight downward trend, slight upward trend was observed for the fertilizer integrated efficiency (FIE). FIs in India, Iran and Turkey continuously rose from5 kg ha-1 in 1961to 116, 49(148 in 2006),120kg ha-1 in 2018, respectively, while FAEs showed a significant fluctuation around horizontal direction or downward trends and their FIEs showed a slight fluctuation downward. FIs of Britain, Germany and France except USA, increased rapidly from about 200-400 kg ha-1 in 1960s to peaks of 430-530 kg ha-1 in 1980s, then dropped to 150-340 kg ha-1 around 2010, and then up to current level of 200-350 kg ha-1 , while FAEs and FIEs increased rapidly.
CONCLUSION: France and Germany were found to have moderate chemical fertilizer input and the highest FIE. Thus, their experiences of ecological agricultures in both countries could provide good examples for the developing countries to follow. In short, models of FAE and FIE were easier way to reflect the fertilizer efficiencies in developed and developing countries. This article is protected by copyright. All rights reserved.
Analysis on the changes of fertilization intensity and efficiency in China's grain production from 1980 to 2019

Liu Q, Wu TY, Tu W, Pu L

J Sci Food Agric, 2023 Jan 30;103(2):908-916.
PMID: 36067269 DOI: 10.1002/jsfa.12202

BACKGROUND: Relieving serious non-point source pollution of nitrogen (N), phosphorus (P), and potassium (K) is an urgent task in China. It is necessary to explore the changing characteristics of chemical fertilization intensity (FI) and efficiency to provide references. A new method of 'relative productivity proportion weight', which was simpler than data envelope analysis, was proposed to construct models of fertilizer allocation efficiency (FAE) and chemical fertilizer integrated efficiency (FIE) by considering NPK multi-inputs and the grain output scale, respectively.
RESULTS: During 1980-2014, the FIs of NPK chemical fertilizers in China showed a significant growing trend. After reaching the highest value of 339 kg ha-1 in 2014, FIs were reduced to 303 kg ha-1 in 2019, higher than the 225 kg ha-1 maximum safe usage internationally recognized. Meanwhile, the pattern of change of FAE was one of 'decreasing to increasing', with values of 1 in 1980, 0.66 in 2003, and 0.80 in 2019. FIE basically showed an increasing trend, which could be divided into three stages: the first stage of low efficiency during 1980-2009, the second stage of medium efficiency after 2010, and the third stage of high efficiency after 2018.
CONCLUSION: From 1980 until 2019, a reduction of FAE from 1 to 0.80 with an average of 0.75 was observed in China. FIE was found between 0.65 and 0.85 and had the potential of upgrading by 15-35%. Therefore, China needs to improve the fertilizer use efficiency in order to strive for negative growth of chemical fertilizer intensity and ecological agriculture construction. © 2022 Society of Chemical Industry.
Narrow-band imaging for scar (NBI-SCAR) classification: from conception to multicenter validation

Zorron Cheng Tao Pu L, Chiam KH, Yamamura T, Nakamura M, Berzin TM, Mir FF, et al.

Gastrointest Endosc, 2020 May;91(5):1146-1154.e5.
PMID: 31494134 DOI: 10.1016/j.gie.2019.08.036

BACKGROUND AND AIMS: Surveillance post-endoscopic resection (ER) currently warrants biopsy samples from the resection site scar in most cases, although clinical practice is variable. A classification with standard criteria for scars has not yet been established. We aimed to create and validate a novel classification for post-ER scars by using specific criteria based on advanced imaging.
METHODS: Key endoscopic features for scars with and without recurrence were (1) dark brown color, elongated/branched pit pattern, and dense capillary pattern and (2) whitish, pale appearance, round/slightly large pits, and irregular sparse vessels. Scars were first assessed with high-definition white-light endoscopy (HD-WLE) followed by interrogation with narrow-band imaging (NBI). Scars with at least 2 concordant characteristics were diagnosed with "high confidence" for NBI for scar (NBI-SCAR) classification. The final endoscopic predictions were correlated with histopathology. The primary outcome was the difference in sensitivity between NBI-SCAR and HD-WLE predictions. Secondary outcomes included the validation of our findings in 6 different endoscopy settings (Australia, United States, Japan, Brazil, Singapore, and Malaysia). The validation took place in 2 sessions separated by 2 to 3 weeks, each with 10 one-minute videos of post-ER scars on underwater NBI with dual focus. Inter-rater and intrarater reliability were calculated with Fleiss' free-marginal kappa and Bennett et al. S score, respectively.
RESULTS: One hundred scars from 82 patients were included. Ninety-five scars were accurately predicted with high confidence by NBI-SCAR in the exploratory phase. NBI-SCAR sensitivity was significantly higher compared with HD-WLE (100% vs 73.7%, P < .05). In the validation phase, similar results were found for endoscopists who routinely perform colonoscopies and use NBI (sensitivity of 96.4%). The inter-rater and intrarater reliability throughout all centers were, respectively, substantial (κ = .61) and moderate (average S = .52) for this subset.
CONCLUSIONS: NBI-SCAR has a high sensitivity and negative predictive value for excluding recurrence for endoscopists experienced in colonoscopy and NBI. In this setting, this approach may help to accurately evaluate or resect scars and potentially mitigate the burden of unnecessary biopsy samples.