检索结果-南通市图书馆

Enhancing Septic Shock Detection through Interpretable Machine Learning

Computer Modeling in Engineering & Sciences 2024年第12期141卷 2501-2525页

作者： md Mahfuzur Rahman md solaiman chowdhury Mohammad Shorfuzzaman Lutful Karim md Shafiullah Farag Azzedin Department of Information and Computer Science King Fahd University of Petroleum and MineralsDhahran31261Saudi Arabia Department of Electrical and Computer Engineering North South UniversityDhaka1229Bangladesh Department of Computer Science Taif UniversityTaif21974Saudi Arabia College of Applied Arts and Technology Seneca PolytechnicTorontoM2J 2X5Canada Department of Control&Instrumentation Engineering King Fahd University of Petroleum and MineralsDhahran31261Saudi Arabia

This article presents an innovative approach that leverages interpretable machine learning models and cloud computing to accelerate the detection of septic shock by analyzing electronic health *** traditional methods,which often lack transparency in decision-making,our approach focuses on early detection,offering a proactive strategy to mitigate the risks of *** integrating advanced machine learning algorithms with interpretability techniques,our method not only provides accurate predictions but also offers clear insights into the factors influencing the model’s ***,we introduce a preference-based matching algorithm to evaluate disease severity,enabling timely interventions guided by the analysis *** innovative integration significantly enhances the effectiveness of our *** leverage a clinical health dataset comprising 1,552,210 Electronic Health Records(EHR)to train our interpretable machine learning models within a cloud computing *** techniques like feature importance analysis and model-agnostic interpretability tools,we aim to clarify the crucial indicators contributing to septic shock *** transparency not only assists healthcare professionals in comprehending the model’s predictions but also facilitates the integration of our system into existing clinical *** validate the effectiveness of our interpretable models using the same dataset,achieving an impressive accuracy rate exceeding 98%through the application of oversampling *** findings of this study hold significant implications for the advancement of more effective and transparent diagnostic tools in the critical domain of sepsis management.

关键词： Sepsis prediction machine learning cloud computing

来源：

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

Status and prospects for symmetric organic redox flow batteries

引用

Journal of Energy Chemistry 2025年第1期100卷 125-143页

作者： md Al Raihan C.Adam Dyker Department of Chemistry University of New BrunswickFrederictonNB E3B 5A3Canada

As environmental concerns from fossil fuel consumption intensify,large-scale energy storage becomes imperative for the integration of renewable sources like wind,hydro,and solar with the electrical *** flow batteries,particularly those employing organic molecules,are positioned as a key technology for this *** review explores the growing field of symmetric organic redox flow batteries(ORFBs)within this *** traditional asymmetric designs based on unique active materials for each electrode,symmetric ORFBs involve a single bipolar species for both *** review highlights the benefits of a symmetric design,and categorizes five distinct classes of organic bipolar molecules used in both aqueous and non-aqueous *** providing a comprehensive overview of their cell cycling and performance characteristics,the strengths and weaknesses of the diverse categories of bipolar molecules are highlighted for both solvent systems,as are opportunities for future *** should guide new research directions and advance the development of practical symmetric ORFBs.

关键词： Redox flow battery Symmetric battery Organic battery Aqueous electrolyte Non-aqueousel ectrolyte

来源：

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

Differences in Seedling and Sapling Densities and Species Composition between Canopy Gaps and Forest Understories in a Subtropical Forest in Bangladesh

引用

Journal of Resources and Ecology 2025年第1期16卷 105-114页

作者： Tarit Kumar BAUL Anwarul Islam chowdhury md Jamal UDDIN Mohammad Kamrul HASAN Tapan Kumar NATH Lars Holger SCHMIDT Institute of Forestry and Environmental Sciences University of ChittagongChittagong 4331Bangladesh Faculty of Science Forestry and TechnologySchool of Forest SciencesUniversity of Eastern FinlandJoensuu 80101Finland Department of Agricultural and Forest Sciences and Engineering University of LleidaLleida 25001Spain Natural Resources Institute Finland(Luke) Helsinki 00790Finland Faculty of Science and Engineering University of Nottingham MalaysiaJalan Broga 43500Malaysia Department of Geoscience and Natural Resource Management University of CopenhagenFrederiksberg C 1958Denmark

Canopy openings have a vital role in forest structure,regeneration,and plant *** this study,we investigated and compared the species composition and densities of seedlings and saplings between canopy gaps(openings)and forest understories(in dense canopies)in a sub-tropical forest of *** objectively identified 42 canopy openings between transect lines and 42 main plots in dense canopies,sampled for regeneration and young tree *** the regeneration study,we placed 2 m×2 m four subplots in each canopy opening and the main plot of dense canopy,thus making a total of 336 *** species diversity of seedlings,saplings,and trees were significantly(P≤0.05)higher in the dense canopy than in the canopy ***,most dominant and frequent regenerating species such as Diospyros pilosula,Garcinia cowa,Brownlowia elata,and Lithocarpus polystachya were common in both dense canopy and openings,the canopy openings had the highest Importance Value Index,suggesting the significance of gap dynamics in the dominance of native floral *** dense canopy played an important role in forest compositions because 12 regenerating species,including Stereospermum suaveolens and Diospyros montana,were not found in the canopy openings,implying that rain forests must maintain a high canopy cover for regeneration.

关键词： canopy opening disturbance forest dynamics native flora seedling sapling

来源：

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

Regeneration mechanisms and therapeutic strategies for neuromuscular junctions in aging and diseases

引用

Neural Regeneration Research 2025年第1期20卷 193-194页

作者： Masashi Fujitani Abu md Mamun Tarif Yoshinori Otani Department of Anatomy and Neuroscience Faculty of MedicineShimane UniversityShimaneJapan

The neuromuscular junction(NMJ)is an essential synaptic structure composed of motor neurons,skeletal muscles,and glial cells that orchestrate the critical process of muscle contraction(Li et al.,2018).The typical NMJ structure is classically described as having a“pretzel-like”shape in mice(Figure 1),whereas human NMJs have a smaller,fragmented structure throughout *** NMJs exhibit smaller or fragmented endplates,partial denervation,reduced numbers of synaptic vesicles,abnormal presynaptic mitochondria,and dysfunctional perisynaptic Schwann cells(Alhindi et al.,2022).

关键词： aging structure Figure

来源：

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

Steel Surface Defect Detection Using Learnable Memory Vision Transformer

引用

Computers, Materials & Continua 2025年第1期82卷 499-520页

作者： Syed Tasnimul Karim Ayon Farhan md.Siraj Jia Uddin Department of Computer Science and Engineering BRAC UniversityDhaka1212Bangladesh Department of AI and Big Data Endicott CollegeWoosong UniversityDaejeon34606Republic of Korea

This study investigates the application of Learnable Memory Vision Transformers(LMViT)for detecting metal surface flaws,comparing their performance with traditional CNNs,specifically ResNet18 and ResNet50,as well as other transformer-based models including Token to Token ViT,ViT withoutmemory,and Parallel *** awidely-used steel surface defect dataset,the research applies data augmentation and t-distributed stochastic neighbor embedding(t-SNE)to enhance feature extraction and *** techniques mitigated overfitting,stabilized training,and improved generalization *** LMViT model achieved a test accuracy of 97.22%,significantly outperforming ResNet18(88.89%)and ResNet50(88.90%),aswell as the Token to TokenViT(88.46%),ViT without memory(87.18),and Parallel ViT(91.03%).Furthermore,LMViT exhibited superior training and validation performance,attaining a validation accuracy of 98.2%compared to 91.0%for ResNet 18,96.0%for ResNet50,and 89.12%,87.51%,and 91.21%for Token to Token ViT,ViT without memory,and Parallel ViT,*** findings highlight the LMViT’s ability to capture long-range dependencies in images,an areawhere CNNs struggle due to their reliance on local receptive fields and hierarchical feature *** additional transformer-based models also demonstrate improved performance in capturing complex features over CNNs,with LMViT excelling particularly at detecting subtle and complex defects,which is critical for maintaining product quality and operational efficiency in industrial *** instance,the LMViT model successfully identified fine scratches and minor surface irregularities that CNNs often *** study not only demonstrates LMViT’s potential for real-world defect detection but also underscores the promise of other transformer-based architectures like Token to Token ViT,ViT without memory,and Parallel ViT in industrial scenarios where complex spatial relationships are *** research m

关键词： Learnable Memory Vision Transformer(LMViT) Convolutional Neural Networks(CNN) metal surface defect detection deep learning,computer vision image classification learnable memory gradient clipping label smoothing t-SNE visualization

来源：

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

Optimizing BERT for Bengali Emotion Classification: Evaluating Knowledge Distillation, Pruning, and Quantization

引用

Computer Modeling in Engineering & Sciences 2025年第2期142卷 1637-1666页

作者： md Hasibur Rahman Mohammed Arif Uddin Zinnat Fowzia Ria Rashedur M.Rahman Department of Electrical and Computer Engineering North South UniversityDhaka1229Bangladesh

The rapid growth of digital data necessitates advanced natural language processing(NLP)models like BERT(Bidi-rectional Encoder Representations from Transformers),known for its superior performance in text ***,BERT’s size and computational demands limit its practicality,especially in resource-constrained *** research compresses the BERT base model for Bengali emotion classification through knowledge distillation(KD),pruning,and quantization *** Bengali being the sixth most spoken language globally,NLP research in this area is *** approach addresses this gap by creating an efficient BERT-based model for Bengali *** have explored 20 combinations for KD,quantization,and pruning,resulting in improved speedup,fewer parameters,and reduced memory *** best results demonstrate significant improvements in both speed and *** instance,in the case of mBERT,we achieved a 3.87×speedup and 4×compression ratio with a combination of Distil+Prune+Quant that reduced parameters from 178 to 46 M,while the memory size decreased from 711 to 178 *** results offer scalable solutions for NLP tasks in various languages and advance the field of model compression,making these models suitable for real-world applications in resource-limited environments.

关键词： Bengali NLP black-box distillation emotion classification model compression post-training quantization unstructured pruning

来源：

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

Ternary Hybrid Nanofluid with First and Second Order Velocity Slips: Dual Solutions with Stability Analysis

引用

Computer Modeling in Engineering & Sciences 2025年第2期142卷 1865-1881页

作者： Nur Syahirah Wahid Nor Ain Azeany Mohd Nasir Norihan md Arifin Ioan Pop Department of Mathematics and Statistics Faculty of ScienceUniversiti Putra Malaysia(UPM)Serdang43400Malaysia Department of Mathematics Centre for Defence Foundation StudiesUniversiti Pertahanan Nasional MalaysiaKuala Lumpur57000Malaysia Institute for Mathematical Research Universiti Putra Malaysia(UPM)Serdang43400Malaysia Department of Mathematics Babes-Bolyai UniversityCluj-Napoca400084Romania Academy of Romanian Scientists Bucharest050044Romania

Modeling the boundary layer flow of ternary hybrid nanofluids is important for understanding and optimizing their thermal performance,particularly in applications where enhanced heat transfer and fluid dynamics are *** study numerically investigates the boundary layer flow of alumina-copper-silver/water nanofluid over a permeable stretching/shrinking sheet,incorporating both first and second-order velocity *** mathematical model is solved in MATLAB facilitated by the bvp4c function that employs the finite difference scheme and Lobatto IIIa *** solver successfully generates dual solutions for the model,and further analysis is conducted to assess their *** findings reported that only one of the solutions is *** the shrinking sheet case,increasing the first-order velocity slip delays boundary layer separation and enhances heat transfer,while,when the sheet is stretched,the second-order velocity slip accelerates separation and improves heat *** layer separation is most likely to occur when the sheet is shrinking;however,this can be controlled by adjusting the velocity slip with the inclusion of boundary layer suction.

关键词： Boundary layer ternary hybrid nanofluid stretching/shrinking velocity slip

来源：

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

The Electric Vehicle Surge:Effective Solutions for Charging Challenges with Advanced Converter Technologies

引用

Energy Engineering 2025年第2期122卷 431-469页

作者： Rajanand Patnaik Narasipuram md M.Pasha Saleha Tabassum Amit Singh Tandon Sustainability Group Cyient Ltd.Pune411057India Department of Electronics and Communication Engineering K.S.R.M.College of EngineeringKadapa516003India Department of Electrical and Electronics Engineering K.S.R.M.College of EngineeringKadapa516003India Mobility Group Eaton India Innovation Center LLPPune411028India

The global adoption of Electric Vehicles(EVs)is on the rise due to their advanced features,with projections indicating they will soon dominate the private vehicle ***,improper management of EV charging can lead to significant *** paper reviews the development of high-power,reliable charging solutions by examining the converter topologies used in rectifiers and converters that transfer electricity from the grid to EV *** covers technical details,ongoing developments,and challenges related to these topologies and control *** integration of rapid charging stations has introduced various Power Quality(PQ)issues,such as voltage fluctuations,harmonic distortion,and supra-harmonics,which are discussed in *** paper also highlights the benefits of controlled EV charging and discharging,including voltage and frequency regulation,reactive power compensation,and improved power *** energy management and control strategies are crucial for optimizing EV battery charging within microgrids to meet increasing *** stations must adhere to specific converter topologies,control strategies,and industry standards to function *** paper explores microgrid architectures and control strategies that integrate EVs,energy storage units(ESUs),and Renewable Energy Sources(RES)to enhance performance at charging *** emphasizes the importance of various RES-connected architectures and the latest power converter ***,the paper provides a comparative analysis of microgrid-based charging station architectures,focusing on energy management,control strategies,and charging converter *** goal is to offer insights into future research directions in EV charging systems,including architectural considerations,control factors,and their respective advantages and disadvantages.

关键词： Electric vehicles converters rectifiers power and voltage levels efficiency supra-harmonics

来源：

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

Logarithmic sensitivity ratio elucidates thermal transport physics in multivariate thermoreflectance experiments

引用

Fundamental Research 2025年第1期5卷 288-295页

作者： Tu, Jing Haque, md Azimul Baran, Derya Ong, Wee-Liat ZJU-UIUC Institute College of Energy Engineering Zhejiang University Jiaxing Haining 314400 China KAUST Solar Center Physical Science and Engineering Division King Abdullah University of Science and Technology Thuwal 23955-6900 Saudi Arabia State Key Laboratory of Clean Energy Utilization Zhejiang University Hangzhou 310027 China

We mathematically derived a sensitivity-based method that identifies the thermal transport physics and parameters suitable for multivariate nonlinear fits in a frequency-domain thermoreflectance (FDTR) experiment. Modern electronic devices often consist of heterogeneous nanolayers with multiple unknown thermal transport properties. However, simultaneous fitting in a single experiment for these unknown parameters will produce unreliable results if they are correlated. Current methods to identify such correlations are unreliable. This unreliability has impeded the accuracy and speed of characterizing the unknown thermal properties of such multilayer stacks. Our proposed logarithmic sensitivity ratio (LSR) analysis can evaluate the feasibility of fitting a pair of unknown parameters and clarify the governing thermal transport physics. The effectiveness and convenience of this analysis were studied using Monte Carlo simulations and actual FDTR experiments for fitting up to three unknown parameters. The principle behind this method can be extended to other techniques where multivariate fits are needed. © 2023

关键词： Correlation Frequency-domain thermoreflectance Monte Carlo Multivariables Sensitivity Thermal conductivity Thermal properties Thermoreflectance

来源：

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

Ru/NiMnB spherical cluster pillar for highly proficient green hydrogen electrocatalyst at high current density

引用

Journal of Energy Chemistry 2025年第1期100卷 397-408页

作者： md Ahasan Habib Shusen Lin Mehedi Hasan Joni Sumiya Akter Dristy Rutuja Mandavkar Jae-Hun Jeong Jihoon Lee Department of Electronic Engineering College of Electronics and InformationKwangwoon UniversityNowon-guSeoul 01897Republic of Korea

Advanced OER/HER electrocatalytic alternatives are crucial for the wide adaptation of green hydrogen ***,Ru/NiMnB spherical cluster pillar(SCP),denoted as Ru/NiMnB,is synthesized using a combination of electro-deposition and hydrothermal *** investigation of Ru doping in the NiMnB matrix revealed significant improvements in electrocatalytic *** Ru/NiMnB SCPs demonstrate superior OER/HER activity with low overpotentials of 150 and 103 mV at 50mA/cm^(2)in 1 M KOH,making them highly competitive with state-of-the-art ***,the Ru/NiMnB SCPs exhibit a low 2-E cell voltage of 2.80 V at ultra-high current density of 2,000 m A/cm^(2)in 1 M KOH,outperforming the standard benchmark electrodes of RuO_(2)||Pt/C,thereby positioning Ru/NiMnB as one of the best bifunctional *** SCPs exhibit exceptional high-current characteristics,stability and corrosion resistance,as evidenced by continuous operation at 1,000 mA/cm^(2)high-current density for over 150 h in 6 M KOH at elevated temperatures under harsh industrial *** a small amount of Ru incorporation significantly enhances the electrocatalytic performances of NiMnB,attributed to increased active sites and improved intrinsic properties such as conductivity,adsorption/desorption capability and reaction ***,Ru/NiMnB SCPs present a promising bi-functional electrode concept for efficient green H_(2)production.

关键词： Advanced electrocatalyst High current Corrosion resistance Industrial requirement

来源：

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

欢迎您,

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：