检索结果-南通市图书馆

Deep learning methods for noisy sperm image classification from convolutional neural network to visual transformer:a comprehensive comparative study

引用

Intelligent Medicine 2024年第2期4卷 114-127页

作者： Ao Chen Chen Li md mamunur rahaman Yudong Yao Haoyuan Chen Hechen Yang Peng Zhao Weiming Hu Wanli Liu Shuojia Zou Ning Xu Marcin Grzegorzek Microscopic Image and Medical Image Analysis Group College of Medicine and Biological Information EngineeringNortheastern UniversityShenyangLiaoning 110169China Department of Electrical and Computer Engineering Stevens Institute of TechnologyHobokenNJ 07030USA School of Arts and Design Liaoning Petrochemical UniversityFushunLiaoning 113001China Institute of Medical Informatics University of LübeckLüebeckGermany

Background With the gradual increase of infertility in the world,among which male sperm problems are the main factor for infertility,more and more couples are using computer-assisted sperm analysis(CASA)to assist in the analysis and treatment of ***,the rapid development of deep learning(DL)has led to strong results in image classification ***,the classification of sperm images has not been well studied in current deep learning methods,and the sperm images are often affected by noise in practical CASA *** purpose of this article is to investigate the anti-noise robustness of deep learning classification methods applied on sperm *** The SVIA dataset is a publicly available large-scale sperm dataset containing three *** this work,we used subset-C,which provides more than 125,000 independent images of sperms and impurities,including 121,401 sperm images and 4,479 impurity *** investigate the anti-noise robustness of deep learning classification methods applied on sperm images,we conducted a comprehensive comparative study of sperm images using many convolutional neural network(CNN)and visual transformer(VT)deep learning methods to find the deep learning model with the most stable anti-noise *** This study proved that VT had strong robustness for the classification of tiny object(sperm and impurity)image datasets under some types of conventional noise and some adversarial *** particular,under the influence of Poisson noise,accuracy changed from 91.45%to 91.08%,impurity precison changed from 92.7%to 91.3%,impurity recall changed from 88.8%to 89.5%,and impurity F1-score changed 90.7%to 90.4%.Meanwhile,sperm precision changed from 90.9%to 90.5%,sperm recall changed from 92.5%to 93.8%,and sperm F1-score changed from 92.1%to 90.4%.Conclusion Sperm image classification may be strongly affected by noise in current deep learning methods;the robustness with regard to noise of VT methods based

关键词： Computer-assisted sperm analysis Anti-noise Robustness Deep learning .Image classification Sperm image Conventional noise Adversarial attacks Convolutional neural network Visual transformer

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

Enhancing Telemarketing Success Using Ensemble-Based Online Machine Learning

引用

Big Data Mining and Analytics 2024年第2期7卷 294-314页

作者： Shahriar Kaisar md mamunur Rashid Abdullahi Chowdhury Sakib Shahriar Shafin Joarder Kamruzzaman Abebe Diro Department of Information Systems and Business Analytics RMIT UniversityMelbourne 3000Australia School of Engineering and Technology Central Queensland UniversityRockhampton 4700Australia Faculty of Engineering Computer and Mathematical ScienceUniversity of AdelaideAdelaide 5005Australia Centre for Smart Analytics Federation University AustraliaBallarat 3350Australia School of Accounting Information Systems and Supply ChainRMIT UniversityMelbourne 3000Australia

Telemarketing is a well-established marketing approach to offering products and services to prospective *** effectiveness of such an approach,however,is highly dependent on the selection of the appropriate consumer base,as reaching uninterested customers will induce annoyance and consume costly enterprise resources in vain while missing interested *** introduction of business intelligence and machine learning models can positively influence the decision-making process by predicting the potential customer base,and the existing literature in this direction shows promising ***,the selection of influential features and the construction of effective learning models for improved performance remain a ***,from the modelling perspective,the class imbalance nature of the training data,where samples with unsuccessful outcomes highly outnumber successful ones,further compounds the problem by creating biased and inaccurate ***,customer preferences are likely to change over time due to various reasons,and/or a fresh group of customers may be targeted for a new product or service,necessitating model retraining which is not addressed at all in existing works.A major challenge in model retraining is maintaining a balance between stability(retaining older knowledge)and plasticity(being receptive to new information).To address the above issues,this paper proposes an ensemble machine learning model with feature selection and oversampling techniques to identify potential customers more accurately.A novel online learning method is proposed for model retraining when new samples are available over *** newly introduced method equips the proposed approach to deal with dynamic data,leading to improved readiness of the proposed model for practical adoption,and is a highly useful addition to the *** experiments with real-world data show that the proposed approach achieves excellent results in all cases(e.g.,98.6

关键词： machine learning online learning oversampling telemarketing imbalanced dataset ensemble model

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

Effectiveness of hybrid ensemble machine learning models for landslide susceptibility analysis:Evidence from Shimla district of North-west Indian Himalayan region

引用

Journal of Mountain Science 2024年第7期21卷 2368-2393页

作者： SHARMA Aastha SAJJAD Haroon rahaman md Hibjur SAHA Tamal Kanti BHUYAN Nirsobha Department of Geography Faculty of SciencesJamia Millia IslamiaNew Delhi-110025India

The Indian Himalayan region is frequently experiencing climate change-induced ***,landslide susceptibility assessment assumes greater significance for lessening the impact of a landslide *** paper makes an attempt to assess landslide susceptibility in Shimla district of the northwest Indian Himalayan *** examined the effectiveness of random forest(RF),multilayer perceptron(MLP),sequential minimal optimization regression(SMOreg)and bagging ensemble(B-RF,BSMOreg,B-MLP)models.A landslide inventory map comprising 1052 locations of past landslide occurrences was classified into training(70%)and testing(30%)*** site-specific influencing factors were selected by employing a multicollinearity *** relationship between past landslide occurrences and influencing factors was established using the frequency ratio *** effectiveness of machine learning models was verified through performance *** landslide susceptibility maps were validated by the area under the receiver operating characteristic curves(ROC-AUC),accuracy,precision,recall and *** key performance metrics and map validation demonstrated that the BRF model(correlation coefficient:0.988,mean absolute error:0.010,root mean square error:0.058,relative absolute error:2.964,ROC-AUC:0.947,accuracy:0.778,precision:0.819,recall:0.917 and F-1 score:0.865)outperformed the single classifiers and other bagging ensemble models for landslide *** results show that the largest area was found under the very high susceptibility zone(33.87%),followed by the low(27.30%),high(20.68%)and moderate(18.16%)susceptibility *** factors,namely average annual rainfall,slope,lithology,soil texture and earthquake magnitude have been identified as the influencing factors for very high landslide *** texture,lineament density and elevation have been attributed to high and moderate ***,the study calls for devising suitable landslide mitig

关键词： Landslide susceptibility Site-specific factors Machine learning models Hybrid ensemble learning Geospatial techniques Himalayan region

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

Computer vision-based six layered ConvNeural network to recognize sign language for both numeral and alphabet signs

引用

Biomimetic Intelligence & Robotics 2024年第1期4卷 45-58页

作者： Muhammad Aminur rahaman Kabiratun Ummi Oyshe Prothoma Khan Chowdhury Tanoy Debnath Anichur Rahman md.Saikat Islam Khan Department of Computer Science and Engineering Green University of BangladeshDhakaBangladesh Department of Computer Science and Engineering National Institute of Textile Engineering and Research(NITER)Constituent Institute of Dhaka UniversityDhakaBangladesh Department of Computer Science and Engineering Mawlana Bhashani Science and Technology UniversityTangailBangladesh

People who have trouble communicating verbally are often dependent on sign language,which can be difficult for most people to understand,making interaction with them a difficult *** Sign Language Recognition(SLR)system takes an input expression from a hearing or speaking-impaired person and outputs it in the form of text or voice to a normal *** existing study related to the Sign Language Recognition system has some drawbacks,such as a lack of large datasets and datasets with a range of backgrounds,skin tones,and *** research efficiently focuses on Sign Language Recognition to overcome previous *** importantly,we use our proposed Convolutional Neural Network(CNN)model,“ConvNeural”,in order to train our ***,we develop our own datasets,“BdSL_OPSA22_STATIC1”and“BdSL_OPSA22_STATIC2”,both of which have ambiguous backgrounds.“BdSL_OPSA22_STATIC1”and“BdSL_OPSA22_STATIC2”both include images of Bangla characters and numerals,a total of 24,615 and 8437 images,***“ConvNeural”model outperforms the pre-trained models with accuracy of 98.38%for“BdSL_OPSA22_STATIC1”and 92.78%for“BdSL_OPSA22_STATIC2”.For“BdSL_OPSA22_STATIC1”dataset,we get precision,recall,F1-score,sensitivity and specificity of 96%,95%,95%,99.31%,and 95.78%***,in case of“BdSL_OPSA22_STATIC2”dataset,we achieve precision,recall,F1-score,sensitivity and specificity of 90%,88%,88%,100%,and 100%respectively.

关键词： Conv NeuralSign language CNN Static Feature extraction Convolution2D Fully connected layer Dropout

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

Insights into Manipulation: Unveiling Tampered Images Using Modified ELA, Deep Learning, and Explainable AI

引用

Journal of Computer and Communications 2024年第6期12卷 135-151页

作者： md. Mehedi Hasan md. Masud Rana Abu Sayed md. Mostafizur rahaman Department of Information and Communication Technology Bangladesh University of Professionals Dhaka Bangladesh Department of Computer Science and Engineering Jahangirnagar University Dhaka Bangladesh

Digital image forgery (DIF) is a prevalent issue in the modern age, where malicious actors manipulate images for various purposes, including deception and misinformation. Detecting such forgeries is a critical task for maintaining the integrity of digital content. This thesis explores the use of Modified Error Level Analysis (ELA) in combination with a Convolutional Neural Network (CNN), as well as, Feedforward Neural Network (FNN) model to detect digital image forgeries. Additionally, incorporation of Explainable Artificial Intelligence (XAI) to this research provided insights into the process of decision-making by the models. The study trains and tests the models on the CASIA2 dataset, emphasizing both authentic and forged images. The CNN model is trained and evaluated, and Explainable AI (SHapley Additive exPlanation— SHAP) is incorporated to explain the model’s predictions. Similarly, the FNN model is trained and evaluated, and XAI (SHAP) is incorporated to explain the model’s predictions. The results obtained from the analysis reveals that the proposed approach using CNN model is most effective in detecting image forgeries and provides valuable explanations for decision interpretability.

关键词： IFD DIF ELA CNN FNN XAI SHAP CASIA2.0

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 link between intracellular calcium signaling and exosomal PD-L1 in cancer progression and immunotherapy

引用

Genes & Diseases 2024年第1期11卷 321-334页

作者： md Rakibul Alam md Mizanur Rahman Zhiguo Li Department of Toxicology and Cancer Biology College of MedicineUniversity of KentuckyLexingtonKY 40506USA Department of Medicine(Nephrology) Faculty of Medicine and DentistryUniversity of AlbertaEdmontonAlberta T6E2H7Canada

Exosomes are small membrane vesicles containing microRNA,RNA,DNA fragments,and proteins that are transferred from donor cells to recipient *** cells release exo-somes to reprogram the factors associated with the tumor microenvironment(TME)causing tu-mor metastasis and immune *** evidence revealed that cancer cell-derived exosomes carry immune inhibitory molecule program death ligand 1(PD-L1)that binds with re-ceptor program death protein 1(PD-1)and promote tumor progression by escaping immune ***,some FDA-approved monoclonal antibodies are clinicallyused for cancer treatment by blocking PD-1/PD-L1 *** notable treatment outcomes,some pa-tients show poor drug *** PD-L1 plays a vital role in lowering the treatment response,showing resistance to PD-1/PD-L1 blockage therapy through recapitulating the ef-fect of cell surface *** enhance therapeutic response,inhibition of exosomal PD-L1 is *** signaling is the central regulator of tumorigenesis and can regulate exosome biogenesis and secretion by modulating Rab GTPase family and membrane fusion ***-mune checkpoints are also connected with calcium signaling and calcium channel blockers like amlodipine,nifedipine,lercanidipine,diltiazem,and verapamil were also reported to suppress cellular PD-L1 ***,to enhance the PD-1/PD-L1 blockage therapy response,the reduction of exosomal PD-L1 secretion from cancer cells is in our therapeutic *** this review,we proposed a therapeutic strategy by targeting calcium signaling to inhibit the expression of PD-L1-containing exosome levels that could reduce the anti-PD-1/PD-L1 therapy resistance and increase the patient's drug response rate.

关键词： Calcium signaling CD8^(+)T cells Exosomal PD-L1 Exosomes biogenesis Immunosuppression Immunotherapy

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

Dynamic Hand Gesture-Based Person Identification Using Leap Motion and Machine Learning Approaches

引用

Computers, Materials & Continua 2024年第4期79卷 1205-1222页

作者： Jungpil Shin md.AlMehedi Hasan md.Maniruzzaman Taiki Watanabe Issei Jozume School of Computer Science and Engineering The University of AizuAizuwakamatsuFukushima965-8580Japan Department of Computer Science&Engineering Rajshahi University of Engineering&TechnologyRajshahi6204Bangladesh

Person identification is one of the most vital tasks for network security. People are more concerned about theirsecurity due to traditional passwords becoming weaker or leaking in various attacks. In recent decades, fingerprintsand faces have been widely used for person identification, which has the risk of information leakage as a resultof reproducing fingers or faces by taking a snapshot. Recently, people have focused on creating an identifiablepattern, which will not be reproducible falsely by capturing psychological and behavioral information of a personusing vision and sensor-based techniques. In existing studies, most of the researchers used very complex patternsin this direction, which need special training and attention to remember the patterns and failed to capturethe psychological and behavioral information of a person properly. To overcome these problems, this researchdevised a novel dynamic hand gesture-based person identification system using a Leap Motion sensor. Thisstudy developed two hand gesture-based pattern datasets for performing the experiments, which contained morethan 500 samples, collected from 25 subjects. Various static and dynamic features were extracted from the handgeometry. Randomforest was used to measure feature importance using the Gini Index. Finally, the support vectormachinewas implemented for person identification and evaluate its performance using identification accuracy. Theexperimental results showed that the proposed system produced an identification accuracy of 99.8% for arbitraryhand gesture-based patterns and 99.6% for the same dynamic hand gesture-based patterns. This result indicatedthat the proposed system can be used for person identification in the field of security.

关键词： Person identification leap motion hand gesture random forest support vector machine

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

Synergistic enhancement of photocatalytic and antimicrobial efficacy of nitrogen and erbium co-doped ZnO nanoparticles

引用

Journal of Rare Earths 2024年第5期42卷 859-868,I0002页

作者： Sudipta Mondal Moniruzzaman Jamal Sikder Ashikuzzaman Ayon md Jannatul Ferdous Anik md Muktadir Billah Department of Materials and Metallurgical Engineering Bangladesh University of Engineering and TechnologyDhaka1000Bangladesh School of Materials Engineering Purdue UniversityWest LafayetteIN47907USA Department of Materials Science and Engineering University of CaliforniaBerkeleyCA94720USA Department of Materials Science and Engineering Northwestern UniversityEvanstonI28USA

Using the chemical co-precipitation approach,a series of nitrogen(N) and erbium(Er) co-doped ZnO nanoparticles(NPs) was effectively synthesized to enhance the photocatalytic and antibacterial *** characterization techniques,including X-ray diffraction(XRD),X-ray photoelectron spectro scopy(XPS),scanning electron microscopy(SEM),UV-vis,and photoluminescence(PL) spectroscopy,were carried out to validate the evaluated photocatalytic and antibacterial *** analysis confirms the pure wurtzite ZnO phase without the presence of any secondary *** analysis confirms the succe ssful incorporation of nitrogen and erbium into the ZnO *** optical bandgap of ZnO calculated from UV-vis spectroscopy shows a redshift after Er-N co-doping,with the lowest bandgap of 3.215 eV calculated for Zn_(0.97)Er_(0.03)N_(0.01)O_(0.99) *** images demonstrate the formation of nanorods after N-Er co-doping,followed by gradually increase d rod diameter and length after N-Er ***,the photocatalytic activities of ZnO samples we re measured by their ability to facilitate the photodegradation of Rhodamine B under UV *** with 1 mol% N doping exhibits 88% photodegradation of RhB under UV light within 360 min,and the photodegradation and antibacterial activity are greatly improved with Er *** fact,3 mol% Er-1 mol% N doped ZnO NPs demonstrate the highest photocatalytic activity,with approximately 96% degradation after 360 min,as well as superior antibacterial activity against Staphylococcus aureus(Gram-positive bacteria) and Pseudomonas aeruginosa(Gram-negative bacteria) with the highest zone of inhibition(ZOI) of 16 nm,due to nanorod formation,increased reactive oxygen species(ROS),and decreased electron-hole recombination,as validated by SEM,XPS,and PL spectroscopy.

关键词： Chemical co-precipitation Co-doping Bandgap Photocatalysis Rare earths Antimicrobial

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

Random fractal-based computational design of an ice-ray (IR) lattice shell structure

引用

Frontiers of Architectural Research 2024年第2期13卷 406-424页

作者： Iasef md Rian Department of Architecture Xi'an Jiaotong-Liverpool UniversitySuzhou 215123China

Chinese ice-ray (IR) lattices, known for their intricate and visually fascinating random patterns as decorative elements in traditional 18th-century Chinese window design, exhibit underlying stiffness as latticed window fences. Such unique patterns represent a new morphology within the family of stochastic lattices. However, the latent structural potential within the random patterns of ice-ray lattices remains largely unexplored, particularly in the context of lattice shell design. This study systematically studies the geometric qualities of ice-ray lattice patterns and develops an algorithm to model these patterns for ice-ray lattice shell design. Subsequently, it assesses the structural feasibility and effectiveness of these lattice shells in comparison to conventional gridshells. The practicality of constructing random lattice shells using digital fabrication tools is also explored. Employing fractal geometry as a foundational framework, this research not only offers insights into the potential of ice-ray lattices for innovative lattice shell design but also introduces a new structural morphology to the field, expanding the possibilities of incorporating stochastic patterns in lattice shell design. Ultimately, it opens up new opportunities for innovative lattice shell designs, emphasizing the potential of stochastic patterns in structural applications.

关键词： Ice-ray pattern Fractals Random Lattice shells Computational design Digital fabrication

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

Seasonal influence of freshwater discharge on spatio-temporal variations in primary productivity, sea surface temperature, and euphotic zone depth in the northern Bay of Bengal

引用

Acta Oceanologica Sinica 2024年第6期43卷 1-14页

作者： Hafez Ahmad Felix Jose md.Simul Bhuyan md.Nazrul Islam Padmanava Dash Geosystems Research Institute/Department of Geosciences Mississippi State UniversityStarkville 39759USA Department of Oceanography University of ChittagongChittagong 4331Bangladesh Department of Marine&Earth Sciences Florida Gulf Coast UniversityFort Myers 33965USA Bangladesh Oceanographic Research Institute Cox’s Bazar 4730Bangladesh Faculty of Marine Sciences&Fisheries Institute of Marine SciencesUniversity of ChittagongChittagong 4331Bangladesh Department of Geography and Environment Jahangirnagar UniversityDhaka 1342Bangladesh Department of Geosciences Mississippi State UniversityStarkville 39759USA

Ocean productivity is the foundation of marine food web,which continuously removes atmospheric carbon dioxide and supports life at sea and on ***-temporal variability of net primary productivity(NPP),sea surface temperature(SST),sea surface salinity(SSS),mixed layer depth(MLD),and euphotic zone depth(EZD) in the northern B ay of Bengal(BoB) during three monsoon seasons were examined in this study based on remote sensing data for the period 2005 to *** compare the NPP distribution between the coastal zones and open BoB,the study area was divided into five zones(Z1-Z5).Results suggest that most productive zones Z2 and Zl are located at the head bay area and are directly influenced by freshwater discharge together with riverine sediment and nutrient *** Z1-Z5,the NPP ranges from 5 315.38 mg/(m~2·d) to 346.7 mg/(m~2·d)(carbon,since then the same).The highest monthly average NPP of 5 315.38 mg/(m~2·d) in February and 5 039.36 mg/(m~2·d) in June were observed from Z2,while the lowest monthly average of 346.72 mg/(m~2·d) was observed in March from Z4,which is an oceanic *** values vary from 6-154 m for the study area,and it has an inverse correlation with NPP *** is deeper during the summer season and shallower during the wintertime,with a corresponding increase in *** the year,monthly SST shows slight fluctuation for the entire study area,and statistical analysis shows a significant correlation among NPP,and EZD,overall positive between NPP and MLD,whereas no significant correlation among SSS,and SST for the northern ***-term trends in SST and productivity were significantly po sitive in head bay zones but negatively productive in the open *** findings in this study on the distribution of NPP,SST,SSS,MLD,and EZD and their seasonal variability in five different zones of BoB can be used to further improve the management of marine resources and overall environmental condition in response to climate change

关键词： chlorophyll a sea surface temperature euphotic zone depth primary productivity Ganges-Brahmaputra ocean color Bay of Bengal monsoon

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：