现有电力负荷预测方法面临诸多挑战,尤其是在考虑气象因素对负荷波动的影响时,传统方法往往忽视气象特征与负荷之间复杂的非线性关系,导致预测精度不足。对此文中提出一种基于气象相似日修正(meteorological similar day correction,MS...现有电力负荷预测方法面临诸多挑战,尤其是在考虑气象因素对负荷波动的影响时,传统方法往往忽视气象特征与负荷之间复杂的非线性关系,导致预测精度不足。对此文中提出一种基于气象相似日修正(meteorological similar day correction,MSDC)和改进鹦鹉优化(improved parrot optimizer,IPO)线性分解(decomposition-based linear,DLinear)的日前电力负荷预测模型。首先运用Logistic映射、自适应变异策略、螺旋波动搜索IPO对DLinear超参数进行优化,然后由DLinear提取数据的周期性和趋势性特征,最后通过比对气象特征欧氏距离修正负荷预测值,形成基于IPO-DLinear-MSDC的日前电力负荷预测模型。采用2024年6月至10月湖南株洲地区总电力负荷数据集进行仿真分析,IPO-DLinear-MSDC模型的输出平均绝对百分比误差(mean absolute percentage error,MAPE)、决定系数R2分别为4.67%、0.833,相较于IPO-DLinear与PO-DLinear模型,MAPE分别下降了0.83个百分点、1.43个百分点,R2分别提升了0.074、0.125。展开更多
Myocardial perfusion imaging(MPI),which uses single-photon emission computed tomography(SPECT),is a well-known estimating tool for medical diagnosis,employing the classification of images to show situations in coronar...Myocardial perfusion imaging(MPI),which uses single-photon emission computed tomography(SPECT),is a well-known estimating tool for medical diagnosis,employing the classification of images to show situations in coronary artery disease(CAD).The automatic classification of SPECT images for different techniques has achieved near-optimal accuracy when using convolutional neural networks(CNNs).This paper uses a SPECT classification framework with three steps:1)Image denoising,2)Attenuation correction,and 3)Image classification.Image denoising is done by a U-Net architecture that ensures effective image denoising.Attenuation correction is implemented by a convolution neural network model that can remove the attenuation that affects the feature extraction process of classification.Finally,a novel multi-scale diluted convolution(MSDC)network is proposed.It merges the features extracted in different scales and makes the model learn the features more efficiently.Three scales of filters with size 3×3 are used to extract features.All three steps are compared with state-of-the-art methods.The proposed denoising architecture ensures a high-quality image with the highest peak signal-to-noise ratio(PSNR)value of 39.7.The proposed classification method is compared with the five different CNN models,and the proposed method ensures better classification with an accuracy of 96%,precision of 87%,sensitivity of 87%,specificity of 89%,and F1-score of 87%.To demonstrate the importance of preprocessing,the classification model was analyzed without denoising and attenuation correction.展开更多
Background:Colorectal cancer(CRC)is the third-most-common malignancy and the second-leading cause of cancer-related deaths worldwide and current screening methods such as guaiac-based fecal occult blood test(gFOBT),fe...Background:Colorectal cancer(CRC)is the third-most-common malignancy and the second-leading cause of cancer-related deaths worldwide and current screening methods such as guaiac-based fecal occult blood test(gFOBT),fecal immunochemical test(FIT),and colonoscopy have their own pros and cons.This study aimed to assess the effectiveness of a fecal DNA methylation test by using methylated SDC2(mSDC2)as the epigenetic biomarker for detecting CRC in a screening-naïve population.Methods:Fecal mSDC2 test and FIT were simultaneously performed on eligible 40-to 74-year-old adults of a regional township in China.Subjects with positive results were recommended for colonoscopy.Data of positivity rates,positive predicted values(PPVs),and detection rates associated with clinical characteristics were analysed.Results:The positivity rate of mSDC2 was 7.6%for 10,578 participants with valid results from both fecal mSDC2 test and FIT.With an adherence rate of 63.8%to colonoscopy referral,25 CRCs,189 advanced adenomas(AAs),and 165 non-advanced adenomas(NAAs)and polyps were detected.The PPVs of mSDC2 were 4.93%,37.28%,and 32.54%for CRC,AA,and non-advanced lesions,respectively.When the CRCs and AAs were counted as positive findings,the fecal mSDC2 test showed a higher detective rate than FIT(relative risk[RR],1.313[1.129-1.528],P<0.001).When NAAs and polyps were also specified as treatable lesions,the mSDC2 test was more effective in detecting these benign growths(RR,1.872[1.419-2.410];P<0.001).A combination of mSDC2 and FIT detected 29 CRCs,298 AAs,and 234 NAAs and polyps.Overall,the fecal mSDC2 test had a higher detection rate for both advanced and non-advanced colonic lesions.The false-positive rate of the fecal mSDC2 test was comparable to that of FIT(RR,1.169[0.974-1.403];P=0.113).Conclusions:The single-target stool-based mSDC2 test can effectively and accurately detect CRC and precancerous lesions in a large-scale CRC-screening program.Trial registration number:NCT05374369.展开更多
文摘现有电力负荷预测方法面临诸多挑战,尤其是在考虑气象因素对负荷波动的影响时,传统方法往往忽视气象特征与负荷之间复杂的非线性关系,导致预测精度不足。对此文中提出一种基于气象相似日修正(meteorological similar day correction,MSDC)和改进鹦鹉优化(improved parrot optimizer,IPO)线性分解(decomposition-based linear,DLinear)的日前电力负荷预测模型。首先运用Logistic映射、自适应变异策略、螺旋波动搜索IPO对DLinear超参数进行优化,然后由DLinear提取数据的周期性和趋势性特征,最后通过比对气象特征欧氏距离修正负荷预测值,形成基于IPO-DLinear-MSDC的日前电力负荷预测模型。采用2024年6月至10月湖南株洲地区总电力负荷数据集进行仿真分析,IPO-DLinear-MSDC模型的输出平均绝对百分比误差(mean absolute percentage error,MAPE)、决定系数R2分别为4.67%、0.833,相较于IPO-DLinear与PO-DLinear模型,MAPE分别下降了0.83个百分点、1.43个百分点,R2分别提升了0.074、0.125。
基金the Research Grant of Kwangwoon University in 2024.
文摘Myocardial perfusion imaging(MPI),which uses single-photon emission computed tomography(SPECT),is a well-known estimating tool for medical diagnosis,employing the classification of images to show situations in coronary artery disease(CAD).The automatic classification of SPECT images for different techniques has achieved near-optimal accuracy when using convolutional neural networks(CNNs).This paper uses a SPECT classification framework with three steps:1)Image denoising,2)Attenuation correction,and 3)Image classification.Image denoising is done by a U-Net architecture that ensures effective image denoising.Attenuation correction is implemented by a convolution neural network model that can remove the attenuation that affects the feature extraction process of classification.Finally,a novel multi-scale diluted convolution(MSDC)network is proposed.It merges the features extracted in different scales and makes the model learn the features more efficiently.Three scales of filters with size 3×3 are used to extract features.All three steps are compared with state-of-the-art methods.The proposed denoising architecture ensures a high-quality image with the highest peak signal-to-noise ratio(PSNR)value of 39.7.The proposed classification method is compared with the five different CNN models,and the proposed method ensures better classification with an accuracy of 96%,precision of 87%,sensitivity of 87%,specificity of 89%,and F1-score of 87%.To demonstrate the importance of preprocessing,the classification model was analyzed without denoising and attenuation correction.
基金supported by the National Key Research and Development Program of China[2017YFC1308800 to H.Z.]and the Talent Project of Innovation and Entrepreneurship in Developmental Zone of Guangzhou[Grant No.2017-L1772022-L025 to H.Z.].
文摘Background:Colorectal cancer(CRC)is the third-most-common malignancy and the second-leading cause of cancer-related deaths worldwide and current screening methods such as guaiac-based fecal occult blood test(gFOBT),fecal immunochemical test(FIT),and colonoscopy have their own pros and cons.This study aimed to assess the effectiveness of a fecal DNA methylation test by using methylated SDC2(mSDC2)as the epigenetic biomarker for detecting CRC in a screening-naïve population.Methods:Fecal mSDC2 test and FIT were simultaneously performed on eligible 40-to 74-year-old adults of a regional township in China.Subjects with positive results were recommended for colonoscopy.Data of positivity rates,positive predicted values(PPVs),and detection rates associated with clinical characteristics were analysed.Results:The positivity rate of mSDC2 was 7.6%for 10,578 participants with valid results from both fecal mSDC2 test and FIT.With an adherence rate of 63.8%to colonoscopy referral,25 CRCs,189 advanced adenomas(AAs),and 165 non-advanced adenomas(NAAs)and polyps were detected.The PPVs of mSDC2 were 4.93%,37.28%,and 32.54%for CRC,AA,and non-advanced lesions,respectively.When the CRCs and AAs were counted as positive findings,the fecal mSDC2 test showed a higher detective rate than FIT(relative risk[RR],1.313[1.129-1.528],P<0.001).When NAAs and polyps were also specified as treatable lesions,the mSDC2 test was more effective in detecting these benign growths(RR,1.872[1.419-2.410];P<0.001).A combination of mSDC2 and FIT detected 29 CRCs,298 AAs,and 234 NAAs and polyps.Overall,the fecal mSDC2 test had a higher detection rate for both advanced and non-advanced colonic lesions.The false-positive rate of the fecal mSDC2 test was comparable to that of FIT(RR,1.169[0.974-1.403];P=0.113).Conclusions:The single-target stool-based mSDC2 test can effectively and accurately detect CRC and precancerous lesions in a large-scale CRC-screening program.Trial registration number:NCT05374369.
