检索结果-南通市图书馆

Transfer learning from T1-weighted to T2-weighted Magnetic resonance sequences for brain image segmentation

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

CAAI Transactions on Intelligence Technology 2024年第1期9卷 26-39页

作者： Imene Mecheter Maysam Abbod Habib Zaidi Abbes amira Brunel University LondonUK Geneva University Hospital GenevaSwitzerland Geneva University GenevaSwitzerland University of Groningen GroningenNetherlands University of Southern Denmark OdenseDenmark University of Sharjah SharjahUAE De Montfort University LeicesterUK

Magnetic resonance(MR)imaging is a widely employed medical imaging technique that produces detailed anatomical images of the human *** segmentation of MR im-ages plays a crucial role in medical image analysis,as it enables accurate diagnosis,treatment planning,and monitoring of various diseases and *** to the lack of sufficient medical images,it is challenging to achieve an accurate segmentation,especially with the application of deep learning *** aim of this work is to study transfer learning from T1-weighted(T1-w)to T2-weighted(T2-w)MR sequences to enhance bone segmentation with minimal required computation *** the use of an excitation-based convolutional neural networks,four transfer learning mechanisms are proposed:transfer learning without fine tuning,open fine tuning,conservative fine tuning,and hybrid transfer ***,a multi-parametric segmentation model is proposed using T2-w MR as an intensity-based augmentation *** novelty of this work emerges in the hybrid transfer learning approach that overcomes the overfitting issue and preserves the features of both modalities with minimal computation time and *** segmentation results are evaluated using 14 clinical 3D brain MR and CT *** results reveal that hybrid transfer learning is superior for bone segmentation in terms of performance and computation time with DSCs of 0.5393±*** T2-w-based augmentation has no significant impact on the performance of T1-w MR segmentation,it helps in improving T2-w MR segmentation and developing a multi-sequences segmentation model.

关键词： computer vision convolution image segmentation learning(artificial intelligence)

Exploring Sequential Feature Selection in Deep Bi-LSTM Models for Speech Emotion Recognition

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 2024年第2期78卷 2689-2719页

作者： Fatma Harby Mansor Alohali Adel Thaljaoui amira Samy Talaat Computer Science Department Future Academy-Higher Future Institute for Specialized Technological StudiesCairo12622Egypt Department of Computer Science and Information College of Science at Zulfi Majmaah UniversityP.O.Box 66Al-Majmaah11952Saudi Arabia Preparatory Institute for Engineering Studies of Gafsa ZarrougGafsa2112Tunisia Computers and Systems Department Electronics Research InstituteCairo12622Egypt

Machine Learning(ML)algorithms play a pivotal role in Speech Emotion Recognition(SER),although they encounter a formidable obstacle in accurately discerning a speaker’s emotional *** examination of the emotional states of speakers holds significant importance in a range of real-time applications,including but not limited to virtual reality,human-robot interaction,emergency centers,and human behavior *** identifying emotions in the SER process relies on extracting relevant information from audio *** studies on SER have predominantly utilized short-time characteristics such as Mel Frequency Cepstral Coefficients(MFCCs)due to their ability to capture the periodic nature of audio signals *** these traits may improve their ability to perceive and interpret emotional depictions appropriately,MFCCS has some *** this study aims to tackle the aforementioned issue by systematically picking multiple audio cues,enhancing the classifier model’s efficacy in accurately discerning human *** utilized dataset is taken from the EMO-DB database,preprocessing input speech is done using a 2D Convolution Neural Network(CNN)involves applying convolutional operations to spectrograms as they afford a visual representation of the way the audio signal frequency content changes over *** next step is the spectrogram data normalization which is crucial for Neural Network(NN)training as it aids in faster *** the five auditory features MFCCs,Chroma,Mel-Spectrogram,Contrast,and Tonnetz are extracted from the spectrogram *** attitude of feature selection is to retain only dominant features by excluding the irrelevant *** this paper,the Sequential Forward Selection(SFS)and Sequential Backward Selection(SBS)techniques were employed for multiple audio cues features ***,the feature sets composed from the hybrid feature extraction methods are fed into the deep Bidirectional Long Short

关键词： Artificial intelligence application multi features sequential selection speech emotion recognition deep Bi-LSTM

Computational Analysis of Novel Extended Lindley Progressively Censored Data

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computer Modeling in Engineering & Sciences 2024年第3期138卷 2571-2596页

作者： Refah Alotaibi Mazen nassar Ahmed Elshahhat Department of Mathematical Sciences College of SciencePrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Statistics Faculty of ScienceKing Abdulaziz UniversityJeddah21589Saudi Arabia Department of Statistics Faculty of CommerceZagazig UniversityZagazigEgypt Faculty of Technology and Development Zagazig UniversityZagazig44519Egypt

A novel extended Lindley lifetime model that exhibits unimodal or decreasing density shapes as well as increasing,bathtub or unimodal-then-bathtub failure rates, named the Marshall-Olkin-Lindley (MOL) model is *** this research, using a progressive Type-II censored, various inferences of the MOL model parameters oflife are introduced. Utilizing the maximum likelihood method as a classical approach, the estimators of themodel parameters and various reliability measures are investigated. Against both symmetric and asymmetric lossfunctions, the Bayesian estimates are obtained using the Markov Chain Monte Carlo (MCMC) technique with theassumption of independent gamma priors. From the Fisher information data and the simulatedMarkovian chains,the approximate asymptotic interval and the highest posterior density interval, respectively, of each unknownparameter are calculated. Via an extensive simulated study, the usefulness of the various suggested strategies isassessedwith respect to some evaluationmetrics such as mean squared errors, mean relative absolute biases, averageconfidence lengths, and coverage percentages. Comparing the Bayesian estimations based on the asymmetric lossfunction to the traditional technique or the symmetric loss function-based Bayesian estimations, the analysisdemonstrates that asymmetric loss function-based Bayesian estimations are preferred. Finally, two data sets,representing vinyl chloride and repairable mechanical equipment items, have been investigated to support theapproaches proposed and show the superiority of the proposed model compared to the other fourteen lifetimemodels.

关键词： Marshall-Olkin-Lindleymodel reliability inference Bayesian and classical inference progressive Type-II censoring

A Weighted Multi-Layer Analytics Based Model for Emoji Recommendation

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 2024年第1期78卷 1115-1133页

作者： amira M.Idrees Abdul Lateef Marzouq Al-Solami Faculty of Computers and Information Technology Future University in EgyptCairo11835Egypt Alkamil College of Science and Arts University of JeddahJeddah21959Saudi Arabia

The developed system for eye and face detection using Convolutional Neural Networks(CNN)models,followed by eye classification and voice-based assistance,has shown promising potential in enhancing accessibility for individuals with visual *** modular approach implemented in this research allows for a seamless flow of information and assistance between the different components of the *** research significantly contributes to the field of accessibility technology by integrating computer vision,natural language processing,and voice *** leveraging these advancements,the developed system offers a practical and efficient solution for assisting blind *** modular design ensures flexibility,scalability,and ease of integration with existing assistive ***,it is important to acknowledge that further research and improvements are necessary to enhance the system’s accuracy and ***-tuning the CNN models and expanding the training dataset can improve eye and face detection as well as eye classification ***,incorporating real-time responses through sophisticated natural language understanding techniques and expanding the knowledge base of ChatGPT can enhance the system’s ability to provide comprehensive and accurate ***,this research paves the way for the development of more advanced and robust systems for assisting visually impaired *** leveraging cutting-edge technologies and integrating them into amodular framework,this research contributes to creating a more inclusive and accessible society for individuals with visual *** work can focus on refining the system,addressing its limitations,and conducting user studies to evaluate its effectiveness and impact in real-world scenarios.

关键词： Social networks text analytics emoji prediction features extraction information retrieval

A Proposed Feature Selection Particle Swarm Optimization Adaptation for Intelligent Logistics--A Supply Chain Backlog Elimination Framework

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 2024年第6期79卷 4081-4105页

作者： Yasser Hachaichi Ayman E.Khedr amira M.Idrees College of Computing and Information Technology at Khulais Department of Information SystemsUniversity of JeddahJeddah21959Saudi Arabia Faculty of Computers and Information Technology Future University in EgyptCairo11835Egypt

The diversity of data sources resulted in seeking effective manipulation and *** challenge that arises from the increasing dimensionality has a negative effect on the computation performance,efficiency,and stability of *** of the most successful optimization algorithms is Particle Swarm Optimization(PSO)which has proved its effectiveness in exploring the highest influencing features in the search space based on its fast convergence and the ability to utilize a small set of parameters in the search *** research proposes an effective enhancement of PSO that tackles the challenge of randomness search which directly enhances PSO *** the other hand,this research proposes a generic intelligent framework for early prediction of orders delay and eliminate orders backlogs which could be considered as an efficient potential solution for raising the supply chain *** proposed adapted algorithm has been applied to a supply chain dataset which minimized the features set from twenty-one features to ten significant *** confirm the proposed algorithm results,the updated data has been examined by eight of the well-known classification algorithms which reached a minimum accuracy percentage equal to 94.3%for random forest and a maximum of 99.0 for Naïve ***,the proposed algorithm adaptation has been compared with other proposed adaptations of PSO from the literature over different *** proposed PSO adaptation reached a higher accuracy compared with the literature ranging from 97.8 to 99.36 which also proved the advancement of the current research.

关键词： Optimization particle swarm optimization algorithm feature selection logistics supply chain management backlogs

Solute transport and geochemical modeling of the coastal quaternary aquifer, Delta Dahab Basin, South Sinai, Egypt

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Acta Geochimica 2024年第1期43卷 16-39页

作者： amira Samy Mustafa Eissa Seham Shahen Moustafa M.Said Rabab M.Abou-shahaba Division of Water Resources and Arid Land Department of HydrogeochemistryDesert Research CenterCairoEgypt Egypt Desalination Research Center of Excellence Desert Research CenterCairoEgypt Center for Water Supply Studies S&E-Physical&Environmental SciencesTexas A&M University Corpus ChristiCorpus ChristiUSA Department of Chemistry Faculty of Science(Girls)Al-Azhar UniversityYousef Abbas StrNasr CityP.O.Box:11754CairoEgypt

The wadi dahab delta is in a dry, arid coastal zone within Egypt’s south Sinai Peninsula’s eastern portion. The primary water source is the Quaternary coastal alluvial aquifer. The groundwater salinity varies from 890to 8213 mg/L, with a mean value of 3417 mg/L. The dissolved major ions have been used to calculate the seawater mixing index(SWMI) using a linear equation that discriminates the groundwater mostly affected by water–rock interaction(SWMI 1>) and other samples mixed with Seawater(SWMI < 1). The isotopic composition of groundwater for specifically chosen groundwater samples ranges from-0.645‰ to +5.212‰ for δ^(18)O and from-9.582‰ to + 22.778‰ for δ^(2)H, where the seawater represented by a Red Sea water sample(δ^(18)O + 1.64‰-δ^(2)H + 9.80‰) and reject brine water are considerably enriched the isotopic groundwater values. The geochemical NETPATH model constrained by the dissolved significant ions, isotopes, and the rock aquifer forming minerals as phases indicate the mixing percent with the seawater ranges from 9% to 97% of seawater from 91% to 3% of original recharge water. According to the SEAWAT 3-D flow models, seawater has penetrated the Northeastern Dahab delta aquifer, with the intrusion zone extending1500 m inland. The salt dissolution, upwelling of saline water, recharge from the upstream mountain block, and seawater encroachment are the primary aspects contributing to the deterioration of groundwater quality. These findings may have significance for effective groundwater withdrawal management in arid locations worldwide with similar hydrogeological systems.

关键词： Groundwater geochemistry Seawater intrusion Solute transport SEAWAT

Natural Convection of a Power-Law Nanofluid in a Square Cavity with a Vertical Fin

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

Fluid Dynamics & Materials Processing 2024年第9期20卷 2091-2108页

作者： amira M’hadbi Mohammed El Ganaoui Haïkel Ben Hamed Amenallah Guizani Khalid Chtaibi LERMAB Department of Transition and Energy Efficiency ProfessionsIUT H Poincaréde LongwyUniversity of LorraineLongwy54400France LPT Center for Energy Research and Technologies(Borj Cedria2084)University of Tunis El ManarTunis1068Tunisia LTI Department of Mechanical Engineering and ProductionIUTUniversity of Picardie Jules-VerneAmiens80025France

The behavior of non-Newtonian power-law nanofluids under free convection heat transfer conditions in a cooled square enclosure equipped with a heated fin is investigated *** particular,the impact of nanofluids,composed of water and Al_(2)O_(3),TiO_(2),and Cu nanoparticles,on heat transfer enhancement is *** aim of this research is also to analyze the influence of different parameters,including the Rayleigh number(Ra=10^(4)-10^(6)),nanoparticle volume fraction(φ=0%-20%),non-Newtonian power-law indexes(n=0.6-1.4),and fin dimensions(Ar=0.3,0.5,and 0.7).Streamlines and isotherms are used to depict flow and related heat transfer *** indicate that thermal performance improves with increasing Rayleigh number,regardless of the nanoparticle type or nanofluid rheological *** suggests that the buoyancy force has a significant impact on heat transfer,particularly near the heat *** Nusselt number is more sensitive to variations in Cu nanoparticle volume fractions compared to Al₂O₃and TiO₂.Moreover,the average Nusselt numbers for power-law nanofluids with n1)are greater(smaller)than for Newtonian fluids due to the decrease(increase)in viscosity with increasing(decreasing)shear rate,at the same values of Rayleigh number Ra owing to the amplification(attenuation)of the convective ***,the most substantial enhancement is observed with Cu-water shear-thinning nanofluid,where the Nusselt number increases by 136%when changing from Newtonian to shear thinning behavior and by 154.9%when adding 16%nanoparticle volume ***,an even larger increase of 57%in the average Nusselt number is obtained on increasing the fin length from 0.3 to 0.7.

关键词： Heat transfer nanofluid non-Newtonian fluid natural convection

A modular microfluidic platform to study how fluid shear stress alters estrogen receptor phenotype in ER+breast cancer cells

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Microsystems & Nanoengineering 2024年第1期10卷 287-299页

作者： Braulio Andrés Ortega Quesada Jonathan Cuccia Rachael Coates Blake nassar Ethan Littlefield Elizabeth C.Martin Adam T.Melvin Cain Department of Chemical Engineering Louisiana State UniversityBaton RougeLA 70803USA Department of Chemical and Biological Engineering Clemson UniversityClemsonSC 29634USA Biological and Agricultural Engineering Louisiana State UniversityBaton RougeLA 70803USA Department Medicine Section Hematology and Medical OncologyTulane UniversityNew OrleansLA 70118USA

Metastatic breast cancer leads to poor prognoses and worse outcomes in patients due to its invasive behavior and poor response to *** is still unclear what biophysical and biochemical factors drive this more aggressive phenotype in metastatic cancer;however recent studies have suggested that exposure to fluid shear stress in the vasculature could cause *** this study a modular microfluidic platform capable of mimicking the magnitude of fluid shear stress(FSS)found in human vasculature was designed and *** device provides a platform to evaluate the effects of FSS on MCF-7 cell line,an estrogen receptor positive(ER+)breast cancer cell line,during circulation in the *** of the effects of FSS on MCF-7 cells was carried out utilizing two approaches:single cell analysis and bulk *** single cell analysis,cells were trapped in a microarray after exiting the serpentine channel and followed by immunostaining on the device(on-chip).Bulk analysis was performed after cells were collected in a microtube at the outlet of the microfluidic serpentine channel for western blotting(off-chip).It was found that cells exposed to an FSS magnitude of 10 dyn/cm^(2) with a residence time of 60 s enhanced expression of the proliferation marker Ki67 in the MCF-7 cell line at a single cell *** understand possible mechanisms for enhanced Ki67 expression,on-chip and off-chip analyses were performed for pro-growth and survival pathways ERK,AKT,and JAK/*** demonstrated that after shearing the cells phosphorylation of p-AKT,p-mTOR,and p-STAT3 were ***,there was no change in p-ERK1/*** is a mediator of ER rapid signaling,analysis of phosphorylated ERαwas carried out and no significant differences between sheared and non-sheared populations were *** together these results demonstrate that FSS can increase phosphorylation of proteins associated with a more aggressive phenotype in circulating cancer *** findin

关键词： fluid breast estrogen

Sepsis Prediction Using CNNBDLSTM and Temporal Derivatives Feature Extraction in the IoT Medical Environment

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 2024年第4期79卷 1157-1185页

作者： Sapiah Sakri Shakila Basheer Zuhaira Muhammad Zain Nurul Halimatul Asmak Ismail Dua’Abdellatef nassar Manal Abdullah Alohali Mais Ayman Alharaki Department of Information Systems College of Computer and Information SciencesPrincess Nourah Bint Abdulrahman UniversityRiyadh11671Kingdom of Saudi Arabia Department of Computer Science and Information Technology Applied CollegePrincess Nourah Bint Abdulrahman UniversityRiyadh11671Kingdom of Saudi Arabia

Background:Sepsis,a potentially fatal inflammatory disease triggered by infection,carries significant healthimplications *** detection is crucial as sepsis can rapidly escalate if left *** in deep learning(DL)offer powerful tools to address this ***:Thus,this study proposeda hybrid CNNBDLSTM,a combination of a convolutional neural network(CNN)with a bi-directional long shorttermmemory(BDLSTM)model to predict sepsis *** the proposed model provides a robustframework that capitalizes on the complementary strengths of both architectures,resulting in more accurate andtimelier ***:The sepsis prediction method proposed here utilizes temporal feature extraction todelineate six distinct time frames before the onset of *** time frames adhere to the sepsis-3 standardrequirement,which incorporates 12-h observation windows preceding sepsis *** models were trained usingthe Medical Information Mart for Intensive Care III(MIMIC-III)dataset,which sourced 61,522 patients with 40clinical variables obtained from the IoT medical *** confusion matrix,the area under the receiveroperating characteristic curve(AUCROC)curve,the accuracy,the precision,the F1-score,and the recall weredeployed to evaluate ***:The CNNBDLSTMmodel demonstrated superior performance comparedto the benchmark and other models,achieving an AUCROC of 99.74%and an accuracy of 99.15%one hour beforesepsis *** results indicate that the CNNBDLSTM model is highly effective in predicting sepsis onset,particularly within a close proximity of one ***:The results could assist practitioners in increasingthe potential survival of the patient one hour before sepsis onset.

关键词： Temporal derivatives hybrid deep learning predicting sepsis onset MIMIC III machine learning(ML) deep learning