期刊文献+
共找到1,597篇文章
< 1 2 80 >
每页显示 20 50 100
Prediction of Alzheimer’s Using Random Forest with Radiomic Features
1
作者 Anuj Singh Raman Kumar Arvind Kumar Tiwari 《Computer Systems Science & Engineering》 SCIE EI 2023年第4期513-530,共18页
Alzheimer’s disease is a non-reversible,non-curable,and progressive neurological disorder that induces the shrinkage and death of a specific neuronal population associated with memory formation and retention.It is a ... Alzheimer’s disease is a non-reversible,non-curable,and progressive neurological disorder that induces the shrinkage and death of a specific neuronal population associated with memory formation and retention.It is a frequently occurring mental illness that occurs in about 60%–80%of cases of dementia.It is usually observed between people in the age group of 60 years and above.Depending upon the severity of symptoms the patients can be categorized in Cognitive Normal(CN),Mild Cognitive Impairment(MCI)and Alzheimer’s Disease(AD).Alzheimer’s disease is the last phase of the disease where the brain is severely damaged,and the patients are not able to live on their own.Radiomics is an approach to extracting a huge number of features from medical images with the help of data characterization algorithms.Here,105 number of radiomic features are extracted and used to predict the alzhimer’s.This paper uses Support Vector Machine,K-Nearest Neighbour,Gaussian Naïve Bayes,eXtreme Gradient Boosting(XGBoost)and Random Forest to predict Alzheimer’s disease.The proposed random forest-based approach with the Radiomic features achieved an accuracy of 85%.This proposed approach also achieved 88%accuracy,88%recall,88%precision and 87%F1-score for AD vs.CN,it achieved 72%accuracy,73%recall,72%precisionand 71%F1-score for AD vs.MCI and it achieved 69%accuracy,69%recall,68%precision and 69%F1-score for MCI vs.CN.The comparative analysis shows that the proposed approach performs better than others approaches. 展开更多
关键词 Alzheimer’s disease radiomic features cognitive normal support vector machine mild cognitive impairment extreme gradient boosting random forest
下载PDF
Language Features in Katherine Mansfield's “The Garden-Party”
2
作者 周丽云 《海外英语》 2017年第8期180-183,共4页
This paper analyzes the features of language in"The Garden-Party"of Katherine Mansfield from three aspects of sentencestructure, word selection and characters' discourse. A large number of examples indic... This paper analyzes the features of language in"The Garden-Party"of Katherine Mansfield from three aspects of sentencestructure, word selection and characters' discourse. A large number of examples indicate Katherine Mansfield's language in the shortfiction creates a poetic imagery; moreover, the author's words depicting things and portraying figures have a great influence on the ex-pression of the theme and characterization of the short story. 展开更多
关键词 Katherine Mansfield The Garden party language features THEME
下载PDF
Stylistic Analysis on "Bill's Little Girl":Lexical Features
3
作者 曲雯 《海外英语》 2011年第12X期249-250,共2页
"Bill's Little Girl " is a prose. This article analysis's its stylistic features of language in the aspects of lexical. While analysis, we can further appreciate its plain and simple language, its na... "Bill's Little Girl " is a prose. This article analysis's its stylistic features of language in the aspects of lexical. While analysis, we can further appreciate its plain and simple language, its natural and fluent manner of writing and its complete discourse, meanwhile we can deeply understand that love is great, father's love is great. 展开更多
关键词 Bill’s LITTLE GIRL LEXICAL featurE
下载PDF
Parkinson’s Disease Classification Using Random Forest Kerb Feature Selection
4
作者 E.Bharath T.Rajagopalan 《Intelligent Automation & Soft Computing》 SCIE 2023年第5期1417-1433,共17页
Parkinson’s disease(PD)is a neurodegenerative disease cause by a deficiency of dopamine.Investigators have identified the voice as the underlying symptom of PD.Advanced vocal disorder studies provide adequate treatment... Parkinson’s disease(PD)is a neurodegenerative disease cause by a deficiency of dopamine.Investigators have identified the voice as the underlying symptom of PD.Advanced vocal disorder studies provide adequate treatment and support for accurate PD detection.Machine learning(ML)models have recently helped to solve problems in the classification of chronic diseases.This work aims to analyze the effect of selecting features on ML efficiency on a voice-based PD detection system.It includes PD classification models of Random forest,decision Tree,neural network,logistic regression and support vector machine.The feature selection is made by RF mean-decrease in accuracy and mean-decrease in Gini techniques.Random forest kerb feature selection(RFKFS)selects only 17 features from 754 attributes.The proposed technique uses validation metrics to assess the performance of ML models.The results of the RF model with feature selection performed well among all other models with high accuracy score of 96.56%and a precision of 88.02%,a sensitivity of 98.26%,a specificity of 96.06%.The respective validation score has an Non polynomial vector(NPV)of 99.47%,a Geometric Mean(GM)of 97.15%,a Youden’s index(YI)of 94.32%,and a Matthews’s correlation method(MCC)90.84%.The proposed model is also more robust than other models.It was also realised that using the RFKFS approach in the PD results in an effective and high-performing medical classifier. 展开更多
关键词 Parkinson’s disease machine learning healthcare random forest feature selection CLAssIFICATION
下载PDF
Diffuse large B-cell lymphoma arising from follicular lymphoma with warthin’s tumor of the parotid gland-immunophenotypic and genetic features: A case report 被引量:1
5
作者 Chang-Song Wang Xia Chu +5 位作者 Di Yang Lei Ren Nian-Long Meng Xue-Xia Lv Tian Yun Yan-Sha Cao 《World Journal of Clinical Cases》 SCIE 2019年第22期3895-3903,共9页
BACKGROUND Warthin’s tumor(WT)is composed of several cysts that are lined with tall,bilayered oncocytic columnar cells and lymphoid stroma.Within WT,the two components rarely transform into carcinoma or lymphoma,and ... BACKGROUND Warthin’s tumor(WT)is composed of several cysts that are lined with tall,bilayered oncocytic columnar cells and lymphoid stroma.Within WT,the two components rarely transform into carcinoma or lymphoma,and when it does,carcinoma is the most common type.Approximately 28 cases of lymphoma with WT have been reported,most of which were non-Hodgkin lymphomas,and only a few cases were Hodgkin lymphomas.In the present report,we studied a case of diffuse large B cell lymphoma(DLBCL)arising from follicular lymphoma(FL)with WT in the parotid gland and its immunophenotypic and genetic features.CASE SUMMARY A 67-year-old man presented with a slowly enlarging right cheek mass for 12 years,and the mass began to change in size over a 2-mo time period.Over time,the patient felt mild local pain and right cheek discomfort.His medical history included a hepatitis B virus infection for 20 years and 30 years of smoking.Gross examination of the excised specimen showed a gray-red and gray-white appearance and a soft texture lobulated external surface neoplasm that measured 9 cm×8 cm×7 cm and was well circumscribed by relative normal parotid gland tissue.In cross section,the cut surfaces of the neoplasm were multicystic and had a homogeneous scaly appearance.A small fluid was discovered in the cyst.Bilateral oxyphilic,cuboidal or polygonal epithelium cells and lymphoid intraparenchymal components were observed.Many medium-to large-sized lymphoid cells were observed diffusely in part of the neoplasm,and a few secondary lymphoid follicles were observed at the center or edge of the neoplasm.Immunohistochemical staining showed that the columnar oncocytic cells were positive for AE1/AE3;neoplastic cells located in coarctate follicular were positive for CD20,Pax-5,bcl-2 and bcl-6;and the adjacent diffusely medium-to large-sized lymphoid cells were positive for Pax-5,bcl-6,CD20,MUM-1,bcl-2 and CD79a.The bcl-6(3q27)break-apart rearrangement was observed,and an Epstein Barr virus test was negative in the tumor cells.The patient survived 6 months after being diagnosed without any treatment.CONCLUSION WT-associated lymphoma is a very rare neoplasm in the parotid gland.Most cases are B cell non-Hodgkin lymphomas and involve middle-age and older males.This case highlights the extremely rare association of DLBCL arising from FL with WT and the importance of deliberate evaluation of the WT intraparenchymal stroma.Molecular detection techniques have potential advantages in the diagnosis of lymphoma with WT. 展开更多
关键词 DIFFUsE large B cell LYMPHOMA Warthin’s TUMOR PAROTID GLAND Follicularlymphoma Case report GENETIC feature
下载PDF
基于广义S变换和并联神经网络的结构损伤识别研究
6
作者 李行健 吕建达 +1 位作者 赵凌云 刁延松 《青岛理工大学学报》 CAS 2024年第1期26-35,共10页
目前在利用CNN网络提取特征的结构损伤识别研究中,仅仅利用1D-CNN和2D-CNN提取的特征进行损伤识别存在准确率低、识别效率不高等问题。提出了一种基于广义S变换和并联神经网络的结构损伤识别方法。为了丰富输入信号的特征维度,利用广义... 目前在利用CNN网络提取特征的结构损伤识别研究中,仅仅利用1D-CNN和2D-CNN提取的特征进行损伤识别存在准确率低、识别效率不高等问题。提出了一种基于广义S变换和并联神经网络的结构损伤识别方法。为了丰富输入信号的特征维度,利用广义S变换将滤波后的信号转化成时频图,并同时将一维加速度响应信号和二维时频图分别输入1D-CNN和2D-CNN中进行时域和时频域特征提取,并在汇聚层进行特征拼接,然后通过FC层和Softmax层对损伤识别结果进行分类。利用IASC-ASCE SHM Benchmark结构第二阶段试验数据对所提出的并联网络模型进行验证,结果表明,所提出的网络模型与其他同类方法相比具有更高的识别精度和识别效率。 展开更多
关键词 损伤识别 广义s变换 卷积神经网络 时频分析 特征融合
下载PDF
Clinical and pathological features of Devic’s neuromyelitis optica and multiple sclerosis in Chinese patients
7
作者 Liangyu Zou Xiaofan Chu Xuejun Fu Gang Li Yiguang Rao 《Neural Regeneration Research》 SCIE CAS CSCD 2010年第8期565-571,共7页
BACKGROUND:Devic's neuromyelitis optica (DNMO) and multiple sclerosis in Asian populations have been considered to be the same disease. However, there is an increasing number of studies suggesting that DNMO and mu... BACKGROUND:Devic's neuromyelitis optica (DNMO) and multiple sclerosis in Asian populations have been considered to be the same disease. However, there is an increasing number of studies suggesting that DNMO and multiple sclerosis are different diseases.OBJECTIVE:Little information is available regarding comparisons of DNMO patients between China and other countries, as well as clinical manifestations of Chinese patients with DNMO and multiple sclerosis. The present study performed a multi-center, pathological, retrospective analysis.DESIGN, TIME AND SETTING:A retrospective analysis of clinical data from seven patients with DNMO diagnosed between 1957 and 1998.PARTICIPANTS:Data from Chinese DNMO patients was provided by the Shanghai Second Medical University, Sun Yat-sen University of Medical Sciences and the First Affiliated Hospital of Harbin Medical University in China.METHODS:Clinical and pathological data from Chinese patients with DNMO were retrospectively analyzed. The clinical characteristics of DNMO were compared between Chinese and Caucasian patients. In addition, clinical and pathological differences between DNMO and multiple sclerosis Chinese patients were compared.MAIN OUTCOME MEASURES:Clinical and pathological features of Chinese patients with DNMO.RESULTS:All seven Chinese patients with DNMO exhibited abrupt onset of vision disturbance, with a disease course of 3 clays to 9 years. DNMO recurred in two of the patients. Demyelinating lesions were observed in all patients, with necrotic lesions and gitter cells in five patients, collagenous hyperplasia in one patient, and perivascular inflammatory cell infiltration in six patients. Comparison between Chinese and Caucasian DNMO patients revealed no significant differences in age at onset, clinical onset, duration, or interval between optic neuritis and myelitis. Compared with Chinese multiple sclerosis patients, Chinese DNMO patients presented with fewer recurrences, higher occurrence of necrosis, perivascular inflammatory cell infiltration and gitter cells, and a lower occurrence of collagenous hyperplasia.CONCLUSION:There was no difference in DNMO clinical features between Chinese and Caucasian patients. However, the clinical and pathological features of DNMO were different compared with multiple sclerosis in Chinese patients. Results suggested that the characteristics of DNMO in Chinese patients were significantly different than multiple sclerosis. 展开更多
关键词 Clinical features Devic's neuromyelitis optica multiple sclerosis pathological features China neural regeneration
下载PDF
Larval Instars and Division Features of Apriona germari
8
作者 Le Baothanh Ji Baozhong +3 位作者 Liu Shuwen Wang Guoxing Zhang Kai Wu Hua 《Plant Diseases and Pests》 CAS 2014年第4期1-5,共5页
Apriona germari larvae were obtained via sample collection in woodland and indoor rearing. In this study, larval instars were divided by Dyar's law, and the results showed that the larval stage of A. germari comprise... Apriona germari larvae were obtained via sample collection in woodland and indoor rearing. In this study, larval instars were divided by Dyar's law, and the results showed that the larval stage of A. germari comprised six instars, while the width of head capsule was the best instar-dividing structure. On the basis of instar division, tubercle numbers on the transverse furrow downside of first abdominal dorsal ambulatory ampullae, seta numbers of abdominal telson and lateral seta numbers of mandible were observed and statistically calculated. The accuracy of instar-dividing was verified by comparing with the Dyar's law. The coincidence rate of two instar-dividing results was 90. 47%. It is approved that the above morphological features could be used in instar division ofA. germari larvae. 展开更多
关键词 Apriona gerrnari Larval instars Dyar's law Morphological features
下载PDF
Gly-LysPred: Identification of Lysine Glycation Sites in Protein Using Position Relative Features and Statistical Moments via Chou’s 5 Step Rule
9
作者 Shaheena Khanum Muhammad Adeel Ashraf +5 位作者 Asim Karim Bilal Shoaib Muhammad Adnan Khan Rizwan Ali Naqvi Kamran Siddique Mohammed Alswaitti 《Computers, Materials & Continua》 SCIE EI 2021年第2期2165-2181,共17页
Glycation is a non-enzymatic post-translational modification which assigns sugar molecule and residues to a peptide.It is a clinically important attribute to numerous age-related,metabolic,and chronic diseases such as... Glycation is a non-enzymatic post-translational modification which assigns sugar molecule and residues to a peptide.It is a clinically important attribute to numerous age-related,metabolic,and chronic diseases such as diabetes,Alzheimer’s,renal failure,etc.Identification of a non-enzymatic reaction are quite challenging in research.Manual identification in labs is a very costly and timeconsuming process.In this research,we developed an accurate,valid,and a robust model named as Gly-LysPred to differentiate the glycated sites from non-glycated sites.Comprehensive techniques using position relative features are used for feature extraction.An algorithm named as a random forest with some preprocessing techniques and feature engineering techniques was developed to train a computational model.Various types of testing techniques such as self-consistency testing,jackknife testing,and cross-validation testing are used to evaluate the model.The overall model’s accuracy was accomplished through self-consistency,jackknife,and cross-validation testing 100%,99.92%,and 99.88%with MCC 1.00,0.99,and 0.997 respectively.In this regard,a user-friendly webserver is also urbanized to accumulate the whole procedure.These features vectorization methods suggest that they can play a critical role in other web servers which are developed to classify lysine glycation. 展开更多
关键词 Gly-LysPred PseAAC post-translational modification lysine glycation Chou’s 5 step rule position relative features
下载PDF
Major Features of the New Situation and China's Foreign Policy
10
作者 Wang Jisi a Senior Research Fellow and Director of Institute for American Studies of China Academy of Social Sciences. 《Contemporary International Relations》 2003年第5期2-8,共7页
Speaking of "China’s foreign policy under new circumstances," there are five features of the new circumstances in my opinion. All these five features will not fundamentally change in accordance with major e... Speaking of "China’s foreign policy under new circumstances," there are five features of the new circumstances in my opinion. All these five features will not fundamentally change in accordance with major events such as the Iraq war, and to a certain extent, determine that China’s basic foreign policy need not and will not make major adjustments. 展开更多
关键词 of IT As WILL on Major features of the New situation and China’s Foreign Policy that in HAVE been
下载PDF
First and Second Order Statistics Features for Classification of Magnetic Resonance Brain Images
11
作者 Namita Aggarwal R. K. Agrawal 《Journal of Signal and Information Processing》 2012年第2期146-153,共8页
In literature, features based on First and Second Order Statistics that characterizes textures are used for classification of images. Features based on statistics of texture provide far less number of relevant and dis... In literature, features based on First and Second Order Statistics that characterizes textures are used for classification of images. Features based on statistics of texture provide far less number of relevant and distinguishable features in comparison to existing methods based on wavelet transformation. In this paper, we investigated performance of texture-based features in comparison to wavelet-based features with commonly used classifiers for the classification of Alzheimer’s disease based on T2-weighted MRI brain image. The performance is evaluated in terms of sensitivity, specificity, accuracy, training and testing time. Experiments are performed on publicly available medical brain images. Experimental results show that the performance with First and Second Order Statistics based features is significantly better in comparison to existing methods based on wavelet transformation in terms of all performance measures for all classifiers. 展开更多
关键词 Alzheimer’s Disease Magnetic REsONANCE Imaging feature Extraction Discrete WAVELET TRANsFORM FIRsT and second Order statistical features
下载PDF
改进YOLOX-S的偏光片表面缺陷检测算法
12
作者 陈乐 周永霞 祖佳贞 《计算机工程与应用》 CSCD 北大核心 2024年第2期295-303,共9页
偏光片是液晶显示器的重要组成部分,其表面缺陷不仅会降低液晶显示器的显示质量,甚至可能造成整个液晶面板的报废。针对偏光片表面缺陷存在尺度差异大、形状变化多样的问题,提出一种改进YOLOX-S的偏光片表面缺陷检测算法。提出自适应平... 偏光片是液晶显示器的重要组成部分,其表面缺陷不仅会降低液晶显示器的显示质量,甚至可能造成整个液晶面板的报废。针对偏光片表面缺陷存在尺度差异大、形状变化多样的问题,提出一种改进YOLOX-S的偏光片表面缺陷检测算法。提出自适应平衡特征金字塔(ABFP)模块充分融合主干网提取的多级特征,并通过单个卷积增加检测分支,进一步增强模型的多尺度检测能力。在ABFP中引入注意力模块CBAM关注重要特征。采用CIo U损失函数的同时使用Mish激活函数替代Si LU激活函数。实验结果表明,改进的算法在偏光片表面缺陷数据集上的m AP_(50)和m AP_(50:95)分别达到92.97%和55.16%,相比YOLOX-S(FPN)提升了1.86和1.34个百分点,每秒检测帧数(FPS)达到50,基本满足工业实时检测的需求。 展开更多
关键词 偏光片表面 缺陷检测 YOLOX-s 自适应平衡特征金字塔 CIoU Mish
下载PDF
New Features of Beijing's Use of Foreign Investment
13
作者 Jing Mao 《China's Foreign Trade》 1997年第10期18-18,共1页
The Beijing Foreign Economic and Trade Commission has announced that,in 1997, Beijing’s use of foreign investment has had the following new features:
关键词 Us New features of Beijing’s Use of Foreign Investment
下载PDF
TEN FEATURES OF CHINA'S LAW ON INSURANCE
14
作者 Wu Jun,Legal Division of the Insurance Instituteof the China People’sInsurance Corporation 《China's Foreign Trade》 1996年第2期38-39,共2页
The Law on Insurance is becomingeffective as the monopoly position ofChina’s insurance and insurance marketis being shifted to an opening one.The lawassimilates the experience and legal contentof advanced internation... The Law on Insurance is becomingeffective as the monopoly position ofChina’s insurance and insurance marketis being shifted to an opening one.The lawassimilates the experience and legal contentof advanced international legislation,but itcan also meet the needs of China’s insurancesystem reform and provide legal protectionfor insurance supervision and sound 展开更多
关键词 TEN features OF CHINA’s LAW ON INsURANCE
下载PDF
A SPECIAL ISSUE OF THE US WEEKLY "SCIENCE" FEATURES A PANORAMIC DEPICTION OF TODAY'S CHINESE SCIENCE IN A DETAILED WAY
15
《Bulletin of the Chinese Academy of Sciences》 1996年第1期3-3,共1页
For the first time in history, the current state and latest developments of China’s S&T endeavors become the keynote of one of the world-renowned scientific journals,"Science," published by the American... For the first time in history, the current state and latest developments of China’s S&T endeavors become the keynote of one of the world-renowned scientific journals,"Science," published by the American Association for Advancement of Science. The prestigious journal "Science,"is one of most influential scientific periodicals in the world today.Under the banner headline of "Science in Asia: China" at a special issue coming out recently, it recounts the increas- 展开更多
关键词 CAs features A PANORAMIC DEPICTION OF TODAY’s CHINEsE sCIENCE IN A DETAILED WAY Us
下载PDF
Relationship between biological features and the SMVS's inhibitory effect on mating behavior of Nilaparvata lugens (Stal)
16
作者 FU Qiang and ZHANG Zhitao, CNRRI, Hangzhou 310006, China 《Chinese Rice Research Newsletter》 1997年第3期3-4,共2页
Our previous studies revealed that second malevibration signal (SMVS) restrained the matingbehavior of N. lugens, the influences of threebiological features (density, age, and wingform) on SMVS’s inhibitory effect we... Our previous studies revealed that second malevibration signal (SMVS) restrained the matingbehavior of N. lugens, the influences of threebiological features (density, age, and wingform) on SMVS’s inhibitory effect were hereinstudied by playing back its record. The dura-tion of playback was 4 h. Except otherwisestatement, N. lugens tested were virginmacropterous males and females aged 4-6 d af-ter emergence, and the density was 5 pairs (5females and 5 males) of N. lugens per cage (4cm in diameter and 8 cm in height). The in-hibitory effect of SMVS was evaluated usingmating rate (i. e. the rate of females withspermatophore). The results were as follows: 展开更多
关键词 stal Relationship between biological features and the sMVs’s inhibitory effect on mating behavior of Nilaparvata lugens
下载PDF
Castleman病患者的临床特征及预后分析 被引量:2
17
作者 黄秀娟 张新莲 +6 位作者 魏小芳 梁小芹 伏媛 赵阳阳 李青芬 张启科 冯友繁 《中国实验血液学杂志》 CAS CSCD 北大核心 2023年第1期135-140,共6页
目的:分析Castleman病的临床特征及预后,以提高Castleman病的诊治水平。方法:回顾性分析甘肃省人民医院自2009年1月至2020年11月经病理活检诊断为Castleman病的29例患者的临床资料。根据临床分型分为两组:单中心型组(UCD,n=20)和多中心... 目的:分析Castleman病的临床特征及预后,以提高Castleman病的诊治水平。方法:回顾性分析甘肃省人民医院自2009年1月至2020年11月经病理活检诊断为Castleman病的29例患者的临床资料。根据临床分型分为两组:单中心型组(UCD,n=20)和多中心型组(MCD,n=9),对其临床表现、实验室检查、治疗方案、病理学检查和随访资料进行统计学分析。结果:UCD组和MCD组平均年龄、男女比例的差异无统计学意义。UCD患者中透明血管型占比80.0%,浆细胞型占比20.0%;MCD患者中透明血管型占比33.3%;浆细胞型占比55.6%,混合型占比11.1%,两组病理分型差异有统计学意义(P=0.039)。UCD患者常表现为无症状的单个淋巴结肿大,临床症状轻微;MCD患者表现为全身多发浅表及深部淋巴结肿大。MCD组乏力、脾大、浆膜腔积液发生率均高于UCD组(P<0.05),同时,贫血、低蛋白血症、血沉升高、血清球蛋白升高、β2-微球蛋白升高发生率均明显高于UCD组(P<0.05)。而两组白细胞计数和血小板计数异常、乳酸脱氢酶升高发生率相比较,差异均没有统计学意义(P>0.05)。20例UCD患者中,13例达CR,1例PR。9例MCD患者中,3例获得CR,4例获得PR。结论:Castleman病需病理检查确诊,UCD患者临床症状轻微,手术治疗效果良好且预后较好;MCD患者临床表现多样化,预后相对较差,需综合治疗。 展开更多
关键词 CAsTLEMAN病 临床特征 预后
下载PDF
2022年6月24日新疆鄯善M_(S)5.1地震序列特征及震前异常分析 被引量:1
18
作者 高荣 聂晓红 +3 位作者 梁卉 钱才 刘萍 高歌 《内陆地震》 2023年第1期23-31,共9页
介绍2022年6月24日鄯善M_(S)5.1地震基本参数、地震构造背景、震源机制解、地震序列特征和震前地震活动性异常和地球物理观测异常。结果:①本次地震发生在天山地震带的东段,发震构造为博罗科努-阿奇克库都克断裂,震源错动方式为逆冲型... 介绍2022年6月24日鄯善M_(S)5.1地震基本参数、地震构造背景、震源机制解、地震序列特征和震前地震活动性异常和地球物理观测异常。结果:①本次地震发生在天山地震带的东段,发震构造为博罗科努-阿奇克库都克断裂,震源错动方式为逆冲型。②此次地震序列类型为孤立型,序列余震不丰富,频度和强度衰减较快。③震前存在地震活动性异常5项,分别为天山中段M_(S)≥4.0地震平静、天山中段M_(S)≥4.0地震增强、天山中段M_(S)3.0-4.9地震增强区、天山中段M_(S)≥3.0增强、M_(S)≥3.0地震条带。④震前存在地球物理场异常2项,为新41井水位和库米什钻孔倾斜EW分量的速率变化异常。 展开更多
关键词 鄯善M_(s)5.1地震 序列特征 地震活动性异常
下载PDF
基于Faster R-CNN的密集人群检测算法 被引量:4
19
作者 邹斌 张聪 《计算机应用》 CSCD 北大核心 2023年第1期61-66,共6页
为提高拥挤场景下的人群检测准确率,提出一种基于改进Faster R-CNN的密集人群检测算法。首先,在特征提取阶段添加空间与通道注意力机制,使用加强的双向特征金字塔网络(S-BiFPN)替代原网络中的多尺度特征金字塔(FPN),使网络对重要特征进... 为提高拥挤场景下的人群检测准确率,提出一种基于改进Faster R-CNN的密集人群检测算法。首先,在特征提取阶段添加空间与通道注意力机制,使用加强的双向特征金字塔网络(S-BiFPN)替代原网络中的多尺度特征金字塔(FPN),使网络对重要特征进行自主学习并加强对图像深层特征的提取;其次,引入多实例预测(MIP)算法对实例进行预测,以避免模型对拥挤场景下的目标造成漏检;最后,对模型中的非极大值抑制(NMS)进行优化,并额外增设一个交并比(IoU)阈值,以对检测结果的干扰项进行精确抑制。在开源的密集人群检测数据集上进行测试的结果显示,相较于原Faster R-CNN算法,所提算法的平均精度(AP)提升5.6%,Jaccard指数值提升3.2%。所提算法具有较高检测精度和稳定性,可以满足密集场景人群检测的需求。 展开更多
关键词 密集人群检测 Faster R-CNN 注意力机制 多实例预测 加强的双向特征金字塔网络
下载PDF
基于ASP.NET的高校党建工作绩效评价管理系统设计 被引量:2
20
作者 张常泉 《计算机时代》 2023年第1期137-140,共4页
通过对高校党建工作调研,开发了一个采用MVC开发模式、B/S架构,以SQL作为数据存储技术,基于Asp.net技术的高校党建工作绩效评价管理系统,实现了自我评价、他人评价、评价分析、系统设计等常用功能。通过测试表明,系统设计合理,运行稳定... 通过对高校党建工作调研,开发了一个采用MVC开发模式、B/S架构,以SQL作为数据存储技术,基于Asp.net技术的高校党建工作绩效评价管理系统,实现了自我评价、他人评价、评价分析、系统设计等常用功能。通过测试表明,系统设计合理,运行稳定,指标设置灵活,保证了党员工作绩效评价的科学、公正,提高了考评管理的效率。 展开更多
关键词 高校党建 工作绩效 评价管理 MVC B/s Asp.net
下载PDF
上一页 1 2 80 下一页 到第
使用帮助 返回顶部