检索结果-南通市图书馆

Brain Tumor Auto-Segmentation on Multimodal Imaging Modalities Using Deep Neural Network

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2022年第9期72卷 4509-4523页

作者： Elias hossain md.Shazzad hossain md.Selim hossain Sabila Al Jannat Moontahina Huda Sameer Alsharif Osama S.Faragallah Mahmoud M.A.Eid Ahmed Nabih Zaki Rashed Department of Software Engineering Daffodil International UniversityDhaka 1207Bangladesh Department of Computing and Information System Daffodil International UniversityDhaka 1207Bangladesh Department of Computer Science&Engineering BRAC UniversityDhaka 1212Bangladesh Department of Information and Communication Engineering Bangladesh University of Professionals(BUP)Dhaka 1216Bangladesh Department of Computer Engineering College of Computers and Information TechnologyTaif UniversityP.O.Box 11099Taif 21944Saudi Arabia Department of Information Technology College of Computers and Information TechnologyTaif UniversityP.O.Box 11099Taif 21944Saudi Arabia Department of Electrical Engineering College of EngineeringTaif UniversityP.O.Box 11099Taif 21944Saudi Arabia Electronics and Electrical Communications Engineering Department Faculty of Electronic EngineeringMenouf 32951Egypt

Due to the difficulties of brain tumor segmentation, this paper proposes a strategy for extracting brain tumors from three-dimensional MagneticResonance Image (MRI) and Computed Tomography (CT) scans utilizing3D U-Net Design and ResNet50, taken after by conventional classificationstrategies. In this inquire, the ResNet50 picked up accuracy with 98.96%, andthe 3D U-Net scored 97.99% among the different methods of deep *** is to be mentioned that traditional Convolutional Neural Network (CNN)gives 97.90% accuracy on top of the 3D MRI. In expansion, the imagefusion approach combines the multimodal images and makes a fused image toextricate more highlights from the medical images. Other than that, we haveidentified the loss function by utilizing several dice measurements approachand received Dice Result on top of a specific test case. The average mean scoreof dice coefficient and soft dice loss for three test cases was 0.0980. At thesame time, for two test cases, the sensitivity and specification were recordedto be 0.0211 and 0.5867 using patch level predictions. On the other hand,a software integration pipeline was integrated to deploy the concentratedmodel into the webserver for accessing it from the software system using theRepresentational state transfer (REST) API. Eventually, the suggested modelswere validated through the Area Under the Curve–Receiver CharacteristicOperator (AUC–ROC) curve and Confusion Matrix and compared with theexisting research articles to understand the underlying problem. ThroughComparative Analysis, we have extracted meaningful insights regarding braintumour segmentation and figured out potential gaps. Nevertheless, the proposed model can be adjustable in daily life and the healthcare domain to identify the infected regions and cancer of the brain through various imagingmodalities.

关键词： Brain cancer segmentation 3D U-Net ResNet50 Dice measurement ROC-AUC

Nutrient dynamics associated with leaf litter decomposition of three agroforestry tree species (Azadirachta indica, Dalbergia sissoo, and Melia azedarach) of Bangladesh

维普期刊数据库评论

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 Forestry Research 2011年第4期22卷 577-582页

作者： Mahmood hossain Mohammad Raqibul Hasan Siddique md. Saidur Rahman md. Zaber hossain md. Mahedi Hasan Forestry and Wood Technology Discipline Khulna University Khulna - 9208 Bangladesh Soil Science Discipline Khulna University Khulna-9208 Forestry and Wood Technology Discipline Khulna University Khulna- 9208

Azadirachta indica A. Juss, Dalbergia, sissoo Roxb., and Melia azedarach L. are little studied species in nutrient return capabilities from leaf litter decomposition to maintenance of the soil fertility despite their importance in agroforestry practices of Bangladesh. A leaf litter decomposition experiment was conducted using a litterbag teeh7 nique to assess the nutrient reaun efficiency of these species. The de- composition rate of leaf litter was highest for M. azedarach and lowest for D. sissoo. Rainfall and temperature of study sites showed a significant （p〈0.05） positive relationship with the rate of leaf litter decomposition. The highest decay constant was observed for M. azedarach （6.67）. Nitrogen and Phosphorus concentration in leaf litter showed a decreased trend sharply at the end of the first month, whereas rapid decrease of Potassium concentration was reported within 10 days. Conversely, higher concentration of nutrient was observed at the later stages of decomposition. All three species showed a similar pattern of nutrient release （K 〉 N 〉 P） during the decomposition process of leaf litter. Among the studied species, D. sissoo was best in terms of N and P return and A. indica was best in terms of K return.

关键词： agroforestry decay constant decomposition leaf litter andnutrient dynamics

Anterior Chamber Depth Changes in Narrow Iridocorneal Angles after Phacoemulsification

在线全文

学校读者我要写书评

暂无评论

Open Journal of Ophthalmology 2023年第2期13卷 187-198页

作者： md. Ariful Islam Abir Bin Sajj Tohura Sharmin md. sanwar hossain md. Shafiqul Islam Department of Ophthalmology Combined Military Hospital (CMH) Dhaka Bangladesh Vision Eye Hospital Dhaka Bangladesh Department of Community Medicine Ad-Din Women’s Medical College Dhaka Bangladesh Department of Ophthalmology Dr. Sirajul Islam Medical College & Hospital Dhaka Bangladesh Department of Ophthalmology Bangabandhu Sheikh Mujib Medical University (BSMMU) Dhaka Bangladesh

Background: The burden of cataract and glaucoma has been increasing. Primary angle closure occurs as a result of crowded anterior segment anatomy causing appositional contact between peripheral iris and trabecular meshwork. Lens extraction has been proposed as a method of deepening anterior chamber and managing intraocular pressure. Purpose: To assess changes in anterior chamber depth after phacoemulsification with intraocular lens implantation in narrow angle eyes. Design: Prospective controlled trial (before-after) study. Method: The study was conducted from March 2015 to August 2017 among the patients of department of Ophthalmology of BSMMU who were diagnosed as cataract with narrow angles. Anterior chamber angle grading of 2 or less (Shaffer grading) in 3 or more quadrants was considered narrow angle (NA). The purposive type sampling technique was applied to collect sample from the study population, as per inclusion and exclusion criteria. Complete clinical evaluation including history, physical examination, relevant ocular examinations and systemic examinations were performed. In this prospective study, subjects underwent phacoemulsification with foldable lens implantation. A scan ultrasonography was performed preoperatively and 10th and 30th postoperative days of surgery. Results: Thirty eyes of 29 patients included in the study, male: female ratio was 1:1, with an overall mean age of 62.03 ± 8.95 years. The mean preoperative central ACD was 2.95 ± 0.35 mm. At 10th and 30th POD mean central ACD were 3.94 ± 0.32, and 3.92 ± 0.28 mm respectively. Mean of increase in central ACD at final follow-up was 0.96 mm (p Conclusion: Phacoemulsification with posterior chamber in bag lens implantation can deepen the anterior chamber depth in patients with narrow angles. Based on these findings, it is concluded that phacoemulsification with foldable intraocular lens implantation is an effective tool in deepening the anterior chambe

关键词： Anterior Chamber Depth Phacoemulsification Iridocorneal Angles Open Angle Narrow Angle

Energy Fluctuation of Ideal Fermi Gas Trapped under Generic Power Law Potential U=Σ_(i=1)~d c_i|x_i/a_i|^(n_i) in d Dimensions

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Communications in Theoretical Physics 2016年第4期65卷 465-468页

作者： Mir Mehedi Faruk md.Muktadir Rahman Dwaipayan Debnath md.Sakhawat hossain Himel Theoretical Physics Blackett LaboratoryImperial College Department of Theoretical Physics University of Dhaka Department of Biomedical Physics and Technology University of Dhaka

Energy fluctuation of ideal Fermi gas trapped under generic power law potential U=Σ_(i=1)~d c_i|x_i/a_i|^(n_i) has been calculated in arbitrary *** fluctuation is scrutinized further in the degenerate limit μ>>K_B T with the help of Sommerfeld *** dependence of energy fluctuation on dimensionality and power law potential is studied in *** importantly our general result can not only exactly reproduce the recently published result regarding free and harmonically trapped ideal Fermi gas in d =3 but also can describe the outcome for any power law potential in arbitrary dimension.

关键词： Fermi gas power law potential energy fluctuation

Antioxidant Defense Mechanisms of Salinity Tolerance in Rice Genotypes

在线全文

学校读者我要写书评

暂无评论

Rice science 2017年第3期24卷 155-162页

作者： Mohammad Golam KIBRIA Mahmud hossain Yoshiyuki MURATA md.Anamul HOQUE Department of Soil Science Bangladesh Agricultural University Graduate School of Natural Science and Technology Okayama University

In order to elucidate the role of antioxidant responses in salinity tolerance in rice genotypes under salt stress, experiments were conducted using four rice varieties, including salt-sensitive BRRI dhan 28 and three salt-tolerant varieties BRRI dhan 47, BINA dhan 8 and BINA dhan 10. Thirty-day-old rice seedlings were transplanted into pots. At the active tillering stage(35 d after transplanting), plants were exposed to different salinity levels(0, 20, 40 and 60 mmol/L NaCl). Salt stress caused a significant reduction in growth for all the rice genotypes. Growth reduction was higher in the salt-sensitive genotype than in the salt-tolerant ones, and BINA dhan 10 showed higher salt tolerance in all measured physiological parameters. The reduction in shoot and root biomass was found to be minimal in BINA dhan 10. Chlorophyll content significantly decreased under salt stress except for BINA dhan 10. Proline content significantly increased in salt-tolerant rice genotypes with increased salt concentration, and the highest proline content was obtained from BINA dhan 10 under salt stress. Catalase and ascorbate peroxidase activities significantly decreased in salt-sensitive genotype whereas significantly increased in salt-tolerant ones with increasing salt concentration. However, salt stress significantly decreased guaiacol peroxidase activity in all the rice genotypes irrespective of salt tolerance. K^+/Na^+ ratio also significantly decreased in shoots and roots of all the rice genotypes. The salt-tolerant genotype BINA dhan 10 maintained higher levels of chlorophyll and proline contents as well as catalase and ascorbate peroxidase activities under salt stress, thus, this might be the underlying mechanism for salt tolerance.

关键词： antioxidant enzyme salinity chlorophyll content proline content K+/Na+ ratio rice

The effects of teak monoculture on forest soils: a case study in Bangladesh

在线全文

学校读者我要写书评

暂无评论

Journal of Forestry Research 2018年第4期29卷 1100-1109页

作者： md.Abdullah Al Mahmud Mohammad Mahfuzur Rahman Mohammed Kamal hossain Institute of Forestry and Environmental Sciences University of Chittagong

Teak plantations date back to 1871 in Bangladesh. This study was designed to assess how teak monoculture has impacted the soil properties in Bangladesh. Multiple linear regression and correlation matrices were estimated to evaluate these impacts. The means of soil physicochemical properties were compared across various attributes of the plantations. Older plantations accumulated more organic carbon in the soils than the younger plantations. Excessive removal of litter from the forest floor resulted in reduced levels of N, P, K, and other nutrients in the soils. Since bulk density was continuously decreasing deeper into the soil, the penetration of mineral nutrients into the soil was low. Furthermore, moisture content in the topsoil was significantly lower than that in the bottom layers due to the exposed and dry condition of the forest floor under teak plantations. For improving depleted teak plantation soils, teak could be planted with other tree species rather than just in monocultures. In addition, the forest floor could be enriched with leguminous herbs and shrubs to improve soil health in these plantations.

关键词： CHTs Monoculture. Organic carbon Soilnutrients Teak plantation

Impact of International Collaboration (Openness) on Bangladesh Textile Production Capacity,with the Moderating Role of Financial and Government Support

在线全文

学校读者我要写书评

暂无评论

Impact of International Collaboration (Openness) on Banglade...

作者： md Motaher hossain 中原工学院

学位级别：硕士

基于资源基础观和国际组织关系理论,本研究旨在探讨开放对孟加拉国纺织生产能力的影响。本研究的次要目的是分析政府支持和财政支持对开放度与产能关系的调节作用。使用来自153家孟加拉国公司的调查数据和一位关键信息提供者,我们发现... 详细信息

基于资源基础观和国际组织关系理论,本研究旨在探讨开放对孟加拉国纺织生产能力的影响。本研究的次要目的是分析政府支持和财政支持对开放度与产能关系的调节作用。使用来自153家孟加拉国公司的调查数据和一位关键信息提供者,我们发现开放性是提高纺织生产能力的关键驱动力。政府和金融支持在塑造纺织产能方面发挥着调节作用。为了分析这些影响,作者采用了SPSS软件,并采用了回归分析技术。结果表明,纺织部门要提高产能,需要国际合作,回归分析还表明,政府支持和财政支持加强了开放对产能的影响。这项研究具有理论意义,因为它提供了来自欠发达国家孟加拉国的实证证据,进一步将影响从业者更加关注国际合作,提高从业者的生产能力将专注于与国际品牌建立战略联盟。这项研究也将为未来的研究提供基础,更侧重于提取能够提高纺织部门生产能力的因素。

关键词：开放国际合作政府支持、资金支持纺织生产能力

On the QoS for ATM Networks Using a New Buffer Utilization Technique

同方学位论文库评论

在线全文

同方学位论文库

学校读者我要写书评

暂无评论

光学学报 2003年第S1期23卷 705-706页

作者： md. Julius hossain md. Nurul Huda Department of Computer Science University of Dhaka Dhaka BangladeshDepartment of Computer Science University of Dhaka Dhaka Bangladesh

A buffer sharing scheme need to meet many competing objectives like robustness to changes in traffic conditions, fairness, efficiency, implementation simplicity, etc. Of the existing techniques, Push Out (PO) is optimum in terms of overall cell loss performance, but its delay performance is worse than that of all other methods for the multiple space priority. Another scheme named Dynamic Threshold (DT) is robust and adaptive which has good delay performance. A hybrid technique named Dynamic Threshold wi...

关键词： ATM in on for On the QoS for ATM Networks Using a New Buffer Utilization Technique

A hybrid deep neural network based prediction of 300 MW coalfired boiler combustion operation condition

在线全文

学校读者我要写书评

暂无评论

Science China(Technological Sciences) 2021年第10期64卷 2300-2311页

作者： HAN ZheZhe HUANG YiZhi LI Jian ZHANG Biao hossain md.Moinul XU ChuanLong Key Laboratory of Energy Thermal Conversion and Control of Ministry of Education School of Energy and EnvironmentSoutheast UniversityNanjing 210096China School of Engineering and Digital Arts University of KentCanterburyKent CT27NTUK Lomon Billions Group Co. Ltd.Jiaozuo 454191China

In power generation industries,boilers are required to be operated under a range of different conditions to accommodate demands for fuel randomness and energy *** prediction of the combustion operation condition is crucial for an in-depth understanding of boiler performance and maintaining high combustion ***,it is difficult to establish an accurate prediction model based on traditional data-driven methods,which requires prior expert knowledge and a large number of labeled *** overcome these limitations,a novel prediction method for the combustion operation condition based on flame imaging and a hybrid deep neural network is *** proposed hybrid model is a combination of convolutional sparse autoencoder(CSAE)and least support vector machine(LSSVM),i.e.,CSAE-LSSVM,where the convolutional sparse autoencoder with deep architectures is utilized to extract the essential features of flame image,and then essential features are input into the least support vector machine for operation condition prediction.A comprehensive investigation of optimal hyper-parameter and dropout technique is carried out to improve the performance of the *** effectiveness of the proposed model is evaluated by 300 MW tangential coal-fired boiler flame *** prediction accuracy of the proposed hybrid model reaches 98.06%,and its prediction time is 3.06 ms/*** is observed that the proposed model could present a superior performance in comparison to other existing neural network models.

关键词： coal-fired power plant combustion operation condition prediction flame image convolutional sparse autoencoder least support vector machine