检索结果-南通市图书馆

3DGE-UNet磁共振成像的脑胶质瘤全自动分割算法:对不充分全局特征提取的改进

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

四川大学学报（医学版） 2024年第2期55卷 447-454页

作者：田恒屹王瑜计亚荣 rahman mdMostafizur 北京工商大学人工智能学院北京100048

目的脑胶质瘤及其子区域的全自动分割是计算机辅助肿瘤临床诊断的基础,卷积神经网络在脑部磁共振成像(magnetic resonance imaging, MRI)分割过程中,小卷积核只能提取局部特征而无法有效融合全局特征,缩小了对影像信息的感知范围,从而... 详细信息

目的脑胶质瘤及其子区域的全自动分割是计算机辅助肿瘤临床诊断的基础,卷积神经网络在脑部磁共振成像(magnetic resonance imaging, MRI)分割过程中,小卷积核只能提取局部特征而无法有效融合全局特征,缩小了对影像信息的感知范围,从而导致分割精度不足的问题。本研究旨在利用膨胀卷积,针对三维(three-dimensional, 3D)-UNet不能充分提取全局特征的问题进行改进。方法 (1)算法构建:本文提出一种带有三条全局上下文特征提取通路的3D-UNet模型,即3DGE-UNet模型。使用脑部肿瘤分割挑战赛(Brain Tumor Segmentation Challenge, BraTS)2019提供的公开数据集(335例患者),设计一种全局上下文特征提取(more global contextual feature extraction, GE)模块,并将该模块引入到3DUNet网络的第一、二、三条跳跃连接处,利用该模块充分提取图像的不同尺度全局特征,并与上采样得到的特征图叠加,扩大模型感受野,实现不同尺度特征的深层融合,从而完成端到端的脑肿瘤全自动分割。(2)算法验证:图像数据来源于BraTs2019数据集(335例患者术前MRI图像,包括T1、T1ce、T2和FLAIR四种模态图像和一张医生标注的肿瘤标签图像),将数据集分别按照8∶1∶1划分为训练集、验证集和测试集。以医生标注的肿瘤标签图像为金标准,使用Dice系数(综合评价有效性)、敏感度(病灶区域的查全率)和95%Hausdorff距离(肿瘤边界的分割精度)在测试集中评估算法对完整肿瘤区域(whole tumor, WT)、核心肿瘤区域(tumor core, TC)和增强肿瘤区域(enhancing tumor, ET)三种区域的分割性能,分别使用无GE模块的3D-UNet模型和有GE模块的3DGE-UNet模型进行检测,内部验证GE模块设置的有效性。使用3DGEUNet模型、ResUNet、UNet++、nnUNet、UNETR检测上述性能指标,并比较5种算法模型的收敛性,外部验证3DGEUNet模型的有效性。结果 (1)在内部验证中,改进的3DGE-UNet模型在测试集中分割WT、TC和ET区域的Dice均值分别为91.47%、87.14%和83.35%,与传统的3D-UNet模型相比(89.79%、85.13%和80.90%),综合评价达到了最优值,对于三个区域的分割精度都有提升(P<0.05)。3DGE-UNet模型与3D-UNet模型相比,ET区(86.46%vs. 80.77%)具有更高的敏感度(P<0.05),在查全率方面表现更为优越,在面对病灶区域时,3DGE-UNet模型更倾向于正确识别并捕获更全面的阳性区域,更为有效地避免漏诊发生。3DGE-UNet模型在肿瘤WT区域边缘分割的出色性能,其95%Hausdorff距离均值优于3DUNet模型(8.17 mm vs. 13.61 mm,P<0.05),但在TC区(8.73 mm vs. 7.47 mm)和ET区(6.21 mm vs. 5.45 mm)的性能表现与3DUNet模型相似。(2)在外部验证中,其余4种算法仅TC的Dice均值(87.25%)、WT的敏感度均值(94.59%)、TC的敏感度均值(86.98%)和ET的平均95%Hausdorff距离(5.37 mm)优于3DGE-UNet模型,但差异无统计学意义。3DGE-UNet模型可以在训练阶段快速收敛,速度优于其他外部模型。结论 3DGE-UNet模型可以有效地提取和融合不同尺度的特征信息,提高脑肿瘤分割的准确性。

关键词：脑胶质瘤核磁共振成像图像处理计算机辅助人工智能

A Critical Review of Community Resilience Building Framework: Contexts of Climate Change and Disasters in Bangladesh

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Journal of Geoscience and Environment Protection 2024年第9期12卷 315-334页

作者： Abdul Alim Shaikh Mousumi Halder Muhammad Ramzan Ali Ruhul Amin md Saifur rahman md. Kamruzzaman Khulna University Khulna Bangladesh Climate Change Program Christian Commission for Development in Bangladesh (CCDB) Dhaka Bangladesh International Rescue Committee-UK Coxs Bazar Bangladesh Tropical and International Forestry Technical University Dresden Cotta Bau Pienner Strae 7 01737 Tharandt Germany Forestry and Wood Technology Discipline Khulna University Khulna Bangladesh

The concept of community resilience in the contexts of climate change and disasters draws increasing attention and interest from practitioners and researchers in recent development discourse. This paper provides a critical review of six selected frameworks of community resilience building operationalized in Bangladesh over the span of years. In other words, this study aims to contribute to the understanding of resilience through a systematic analysis of the dimensions and indicators of community resilience frameworks. The analysis shows that comprehensive and effective community resilience frameworks should incorporate the missing components linked to fundamental elements of good governance, economic growth, environmental sustainability, social transformation, and capacity development. The paper concludes by highlighting a few other areas of grave concern that need more appropriate attention, considering the severe threats posed by climate change and natural disasters in line with sustainable development goals. Finally, this study recommends further research regarding the effectiveness of these frameworks in different climatic and disaster contexts that can lead the concept into a new dimension of community resilience and sustainability.

关键词： Community Resilience Resilience Building Framework Resilience Indicators Climate Change Disaster Bangladesh

Development of Framework for ACI-Powered Human Resource Recruitment Assistant

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Management Studies 2024年第3期12卷 182-187页

作者： md Jawadur rahman Gabriele M.Murry Stephanie Schmitt-Rüth OTH Amberg-Weiden AmbergGermany

The landscape of human resource management within large enterprises necessitates efficient and unbiased recruitment practices to ensure organisational effectiveness and foster diversity(Ayoko&Fujimoto,2023).Traditional hiring processes often create biases,which cause additional challenges in achieving proper objectives(Bogen,2021).According to Workable(***),the average time to fill a job requisition is 41 days(Howden,2023).This paper proposes a framework for the development and implementation of an Artificially Capable Intelligent(ACI)-powered Human Resource(HR)Assistant for large enterprises(possibly more than 300 employees)to eliminate these unnecessary challenges caused by biases in hiring practices,therefore directly addressing fair and just participation in society and the world of *** framework integrates ACI technologies,particularly candidate identification,to revolutionise HR *** leveraging ACI algorithms,the proposed hyper-realistic assistant aims to revolutionise the recruitment *** will significantly reduce the average time to fill job ***,the ACI-powered system is designed to mitigate biases inherent in traditional hiring practices,thus fostering a fair and inclusive environment for all candidates in the shortest possible time *** paper includes the key components and working processes of the ACI-powered HR Assistant *** a comprehensive theoretical analysis,the paper investigates the system’s working process and how the framework aligns with the goal of promoting a fair and participatory environment in the world of ***,the proposed framework represents a main step towards enhancing organisational effectiveness,fostering diversity,and advancing equitable recruitment practices in the futuristic workplace.

关键词： artificial capable intelligence human resource

Mechanical and Electrical Properties of Some Sn-Zn Based Lead-Free Quinary Alloys

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Materials Sciences and Applications 2024年第7期15卷 213-227页

作者： Shihab Uddin md. Abdul Gafur Suraya Sabrin Soshi Mohammad Obaidur rahman Department of Physics Jahangirnagar University Savar Dhaka Bangladesh Pilot Plant and Process Development Centre Dhaka Bangladesh Department of Mechanical Engineering Ahsanullah University of Science and Technology Tejgaon Dhaka Bangladesh

Although there are many lead-free soldering alloys on the market, none of them have ideal qualities. The researchers are combining binary alloys with a variety of additional materials to create the soldering alloys’ features. The eutectic Sn-9Zn alloy is among them. This paper investigated the mechanical and electrical properties of Sn-9Zn-x (Ag, Cu, Sb);{x = 0.2, 0.4, and 0.6} lead-free solder alloys. The mechanical properties such as elastic modulus, ultimate tensile strength (UTS), yield strength (YS), and ductility were examined at the strain rates in a range from 4.17 10−3 s−1 to 208.5 10−3 s−1 at room temperature. It is found that increasing the content of the alloying elements and strain rate increases the elastic modulus, ultimate tensile strength, and yield strength while the ductility decreases. The electrical conductivity of the alloys is found to be a little smaller than that of the Sn-9Zn eutectic alloy.

关键词： Lead-Free Solder Strain Rate Ultimate Tensile Strength Ductility Electrical Conductivity

Credit Card Fraud Detection Using Machine Learning Techniques

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Computer and Communications 2024年第6期12卷 1-11页

作者： Ananya Sarker Must. Asma Yasmin md. Atikur rahman md. Harun Or Rashid Bristi Rani Roy Department of Computer Science and Engineering Bangladesh Army University of Engineering & Technology (BAUET) Natore Bangladesh

Credit card companies must be able to identify fraudulent credit card transactions so that clients are not charged for items they did not purchase. Previously, many machine learning approaches and classifiers were used to detect fraudulent transactions. However, because fraud patterns are always changing, it is becoming increasingly vital to investigate new frauds and develop the model based on the new patterns. The purpose of this research is to create a machine learning classifier that not only detects fraud but also detects legitimate transactions. As a result, the model should have excellent accuracy, precision, recall, and f1-score. As a result, we began with a large dataset in this study and used four machine learning classifiers: Support Vector Machine (SVM), Decision Tree, Naïve Bayes, and Random Forest. The random forest classifier scored 99.96% overall accuracy with the best precision, recall, f1-score, and Matthews correlation coefficient in the experiments.

关键词： Support Vector Machine Decision Tree Nave Bayes Random Forest Matthews Correlation

Assessment of Physico-Chemical and Microbial Quality of Sugarcane Juice Sold by Street Vendors in Three Regions of Bangladesh

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Food and Nutrition Sciences 2024年第4期15卷 263-276页

作者： Nargis Akter Khan md. Murtaja Reza Linkon Munni Akter md. Alamgir Hossain md. Mahbubur rahman Tayeba Khan md. Abdul Alim md. Esrafil Department of Food Technology and Nutritional Science Mawlana Bhashani Science and Technology University Tangail Bangladesh Department of Biotechnology and Genetic Engineering Mawlana Bhashani Science and Technology University Tangail Bangladesh

Sugar cane juice is a popular refreshing drink in most part of Bangladesh. It has great taste and health benefits;also it is available most of the public places at reasonable prices which consumed by road side customers including general public, shopping personals, tourists, students. In our country, street vendors crushing sugarcane between roller crusher and sold without any heat treatment or preservative, also served with or without added ice and lemon juice. The study aimed to identify and compare the physico-chemical and microbial quality of sugarcane juice. The chemical qualities of juices including moisture, PH, ash, total soluble solid, total sugar, reducing sugar and titrable acidity were found slightly different in Mymensingh, Gazipur and Narayangonj areas. The highest and lowest value of moisture, ash, PH, total soluble solids, total sugar, reducing sugar and titrable acidity were found in 84.33% - 79.26% (Gazipur-Mymensingh), 0.57% - 0.04% (Mymensingh-Gazipur), 5.9 - 2.9 (Gazipur-Narayangonj), 17.48% - 4.98% (Mymensingh-Narayangonj), 21.9% - 6.56% (Mymensingh-Gazipur), 3.7 - 2.1 (Gazipur-Mymensingh) and 0.523% - 0.007% (Narayangonj-Gazipur) respectively. For microbiological analysis, the total viable count of sugar cane juice in Mymensingh, Gazipur and Narayangonj were ranged from 0.6 × 105 - 43.6 × 105 cfu/ml, 4.6 × 105 - 21.6 × 105 cfu/ml and 3.6 × 105 - 36.6 × 105 cfu/ml respectively, where the permitted value is 1.0 × 104 cfu/ml, whereas the total coliform count was ranged from 0.4 × 105 - 6.4 × 105 cfu/ml, 0.6 × 105 - 8.4 × 105 cfu/ml and 0.00 - 8.4 × 105 cfu/ml, where the permitted value is 100 cfu/ml and total fungal count was ranged from 5.5 × 105 - 56.5 × 105 cfu/ml, 21.5 × 105 - 54.5 × 105 cfu/ml and 32.5 × 105 - 68.5 × 105 cfu/

关键词： Sugarcane Street Vendors Microbial Quality Reducing Sugar

Predicting the Stitch Density of Finished Fabrics Using Weft Blended Grey Knit Fabrics

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Textile Science and Technology 2024年第3期10卷 51-63页

作者： Kazi md. Elias Mohammad Obaidur rahman H. M. Zakir Hossain Department of Physics Jahangirnagar University Savar Bangladesh Jute Textile Wing Bangladesh Jute Research Institute Dhaka Bangladesh

Stitch density is one of the critical quality parameters of knit fabrics. This parameter is closely related to other physical quality parameters like fabric weight, fabric tightness factor, fiber types, blend ratio, yarn diameter and linear density, and fabric structure. Selecting stitch density (wales per inch, course per inch) is essential to getting the appropriate fabric weight and desired quality. Usually, no rules or assumptions exist to get the desired stitch density in the finished fabric stage. Fifteen types of blended knit fabrics were prepared to conduct the study. The varying percentages of cotton, polyester, and elastane are incorporated in the blends. Regression analysis and regression ANOVA tests were done to predict the stitch density of finished fabrics. A suitable regression equation is established to get the desired results. The study also found that the stitch density value in the finished stage fabric decreases by approximately 15% compared to the stitch density in the grey fabric stage. This study will help the fabric manufacturers get the finished fabric stitch density in advance by utilizing the grey fabric stitch density data set. The author expects this research to benefit the knitting and dyeing industry, new researchers, and advanced researchers.

关键词： Wales per Inch Course per Inch Stitch Density Blended Knit Fabric

Effect of Exchange-Correlation Functional on the Structural, Mechanical, and Optoelectronic Properties of Orthorhombic RbSrBr3 Perovskite

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Materials Sciences and Applications 2024年第6期15卷 137-154页

作者： Fatema Najrin Rabeya Bakar Sarna md. Alamin Sarker Budrun Neher md. Mahbubur rahman Bhuiyan Farid Ahmed Department of Physics Jahangirnagar University Dhaka Bangladesh Department of Electrical and Electronics Engineering Green University of Bangladesh Purbachal American City Kanchan Rupganj Narayanganj-1461 Dhaka Bangladesh

In the present study, the effect of the exchange-correlation functional on the structural, mechanical, and optoelectronic properties of orthorhombic RbSrBr3 perovskite has been investigated using various functionals in Density Functional Theory (DFT) with the CASTEP code. The optimized lattice parameters are quite similar for all the functionals. The electronic properties have shown that RbSrBr3 perovskite is a wide direct band gap compound with a band gap energy ranging from 4.296 eV to 4.494 eV for all the functionals. The mechanical parameters like elastic constants, Young’s modulus, Shear modulus, Poisson’s ratio, Pugh’s ratio, and an anisotropic factor reveal that the RbSrBr3 perovskite has ductile behavior and an anisotropic nature which signifies the mechanical stability of the compound. The Debye temperature might withstand lattice vibration heat. High absorption coefficient (>104 cm−1), high optical conductivity, and very low reflectivity have been found in the RbSrBr3 perovskite for all functions. The computed findings on the RbSrBr3 perovskite suggested that the presented studied material is potentially applicable for photodetector and optoelectronic devices.

关键词： Density Functional Theory Mechanical Properties Photodetector Ductility Anisotropic Factor

Phytochemical Screening and Evaluation of Pharmacological Potential of Baliospermum solanifolium Leaf Extract

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Clinical Complementary Medicine and Pharmacology 2024年第1期4卷 69-75页

作者： Amit Mazumder Rabindra Nath Acharyya Milton Kumar Kundu Pritam Kundu md.Amirul Islam md.Mustafizur rahman Pharmacy Discipline Khulna UniversityKhulna-9208Bangladesh

Background:Baliospermum solanifolium is a traditional medicinal plant,locally known as“dantigaacha”from Eu-phorbiaceae family,and has been used in different diseases treatments likes helminthiasis,skin diseases,diabetes,snake-bite,and ***:Depending on the traditional uses of *** and the lack of scientific works,we aimed to conduct some pharmacological tests on its ***:Active constituents of *** were assessed by qualitative ***(2,2-diphenyl-1-picrylhydrazyl)was used for free radical scavenging *** change and mortality rate were used as indicators to assess the toxicity of *** antidiabetic potential was evaluated by oral glucose toler-ance test(OGTT)and alpha-glucosidase enzyme inhibitory *** antidiarrheal activity,castor oil-induced mice were *** test was carried out by disk diffusion assay and MIC ***,analgesic activity was done by acetic acid-induced writhing ***:*** contains alkaloids,carbohydrates,glycosides,flavonoids,tannis,phenolics *** toxicity test ensured the safety of the *** DPPH,the extract showed antioxidant activity with an IC50(con-centration needed to scavenge 50%DPPH)value of 61.65μg/*** phenolic,flavonoid and tannin contents were determined as 124 mg GAE/g,440 mg QE/g and 344 mg GAE/g dried extract,*** OGTT,the ex-tract reduced the blood glucose level *** the alpha-glucosidase inhibitory activity,the plant showed a concentration-dependent reduction of the enzyme at IC50 of 8.53 mg/*** the antidiarrheal test,*** inhibit defecation 30.69%and 53.41%at dose 250 mg/kg and 500 mg/kg,*** extract also showed antibacterial activity against four bacterial strains in the disk diffusion method and minimum inhibitory concen-tration(MIC)values were 62.5μg/mL,62.5μg/mL,125μg/mL and 62.5μg/mL against four bacterial strains,*** an

关键词： Baliospermum solanifolium Antioxidant Antidiabetic Antidiarrheal Antibacterial Analgesic