检索结果-南通市图书馆

Computer Modeling in Engineering & Sciences 2020年第11期125卷 579-596页

作者： Xing Deng Haijian Shao Liang Shi Xia Wang Tongling Xie School of Computer Science Jiangsu University of Science and TechnologyZhenjiang212003China School of Automation Key Laboratory of Measurement and Control for CSEMinistry of EducationSoutheast UniversityNanjing210096China School of Computer Science and Communication Engineering Jiangsu UniversityZhenjiang212003China School of Information Science and Technology Nantong UniversityNantong226019China Department of Electrical and Computer Engineering National University of Singapore117583Singapore The People’s Hospital of RUGAO Nantong226500China

The Coronavirus Disease 2019(COVID-19)is wreaking havoc around the world,bring out that the enormous pressure on national health and medical staff *** of the most effective and critical steps in the fight against COVID-19,is to examine the patient’s lungs based on the Chest X-ray and CT generated by radiation *** this paper,five keras-related deep learning models:ResNet50,InceptionResNetV2,Xception,transfer learning and pre-trained VGGNet16 is applied to formulate an classification-detection approaches of *** benchmark methods SVM(Support Vector Machine),CNN(Conventional Neural Networks)are provided to compare with the classification-detection approaches based on the performance indicators,i.e.,precision,recall,F1 scores,confusion matrix,classification accuracy and three types of AUC(Area Under Curve).The highest classification accuracy derived by classification-detection based on 5857 Chest X-rays and 767 Chest CTs are respectively 84%and 75%,which shows that the keras-related deep learning approaches facilitate accurate and effective COVID-19-assisted detection.

关键词： COVID-19 detection deep learning transfer learning pre-trained models

Survey on leveraging pre-trained generative adversarial networks for image editing and restoration

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2023年第5期66卷 28-55页

作者： Ming LIU Yuxiang WEI Xiaohe WU Wangmeng ZUO Lei ZHANG School of Computer Science and Technology Harbin Institute of Technology Department of Computing Hong Kong Polytechnic University

Generative adversarial networks(GANs) have drawn enormous attention due to their simple yet efective training mechanism and superior image generation quality. With the ability to generate photorealistic high-resolution(e.g., 1024 × 1024) images, recent GAN models have greatly narrowed the gaps between the generated images and the real ones. Therefore, many recent studies show emerging interest to take advantage of pre-trained GAN models by exploiting the well-disentangled latent space and the learned GAN priors. In this study, we briefly review recent progress on leveraging pre-trained large-scale GAN models from three aspects, i.e.,(1) the training of large-scale generative adversarial networks,(2) exploring and understanding the pre-trained GAN models, and(3) leveraging these models for subsequent tasks like image restoration and editing.

关键词： survey generative adversarial networks pre-trained models image editing image restoration

Multi-Modal Military Event Extraction Based on Knowledge Fusion

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2023年第10期77卷 97-114页

作者： Yuyuan Xiang Yangli Jia Xiangliang Zhang Zhenling Zhang School of Computer Science Liaocheng UniversityLiaocheng252059China

Event extraction stands as a significant endeavor within the realm of information extraction,aspiring to automatically extract structured event information from vast volumes of unstructured *** event elements from multi-modal data remains a challenging task due to the presence of a large number of images and overlapping event elements in the *** researchers have proposed various methods to accomplish this task,most existing event extraction models cannot address these challenges because they are only applicable to text *** solve the above issues,this paper proposes a multi-modal event extraction method based on knowledge ***,for event-type recognition,we use a meticulous pipeline approach that integrates multiple pre-trained *** approach enables a more comprehensive capture of the multidimensional event semantic features present in military texts,thereby enhancing the interconnectedness of information between trigger words and *** event element extraction,we propose a method for constructing a priori templates that combine event types with corresponding trigger *** approach facilitates the acquisition of fine-grained input samples containing event trigger words,thus enabling the model to understand the semantic relationships between elements in greater ***,a fusion method for spatial mapping of textual event elements and image elements is proposed to reduce the category number overload and effectively achieve multi-modal knowledge *** experimental results based on the CCKS 2022 dataset show that our method has achieved competitive results,with a comprehensive evaluation value F1-score of 53.4%for the *** results validate the effectiveness of our method in extracting event elements from multi-modal data.

关键词： Event extraction multi-modal knowledge fusion pre-trained models

Embedding Extraction for Arabic Text Using the AraBERT Model

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7期72卷 1967-1994页

作者： Amira Hamed Abo-Elghit Taher Hamza Aya Al-Zoghby Faculty of Computers and Information Department of Computer SciencesMansoura UniversityMansoura35516Egypt Faculty of Computers and Artificial Intelligence Department of Computer SciencesDamietta UniversityDamietta34517Egypt

Nowadays,we can use the multi-task learning approach to train a machine-learning algorithm to learn multiple related tasks instead of training it to solve a single *** this work,we propose an algorithm for estimating textual similarity scores and then use these scores in multiple tasks such as text ranking,essay grading,and question answering *** used several vectorization schemes to represent the Arabic texts in the SemEval2017-task3-subtask-D *** used schemes include lexical-based similarity features,frequency-based features,and pre-trained model-based ***,we used contextual-based embedding models such as Arabic Bidirectional Encoder Representations from Transformers(AraBERT).We used the AraBERT model in two different ***,as a feature extractor in addition to the text vectorization schemes’*** fed those features to various regression models to make a prediction value that represents the relevancy score between Arabic text ***,AraBERT is adopted as a pre-trained model,and its parameters are fine-tuned to estimate the relevancy scores between Arabic textual *** evaluate the research results,we conducted several experiments to compare the use of the AraBERT model in its two *** terms of Mean Absolute Percentage Error(MAPE),the results showminor variance between AraBERT v0.2 as a feature extractor(21.7723)and the fine-tuned AraBERT v2(21.8211).On the other hand,AraBERT v0.2-Large as a feature extractor outperforms the finetuned AraBERT v2 model on the used data set in terms of the coefficient of determination(R2)values(0.014050,−0.032861),respectively.

关键词： Semantic textual similarity arabic language embeddings AraBERT pre-trained models regression contextual-based models concurrency concept

Intelligent Deep Convolutional Neural Network Based Object DetectionModel for Visually Challenged People

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 Systems Science & Engineering 2023年第9期46卷 3191-3207页

作者： S.Kiruthika Devi Amani Abdulrahman Albraikan Fahd N.Al-Wesabi Mohamed K.Nour Ahmed Ashour Anwer Mustafa Hilal Department of Computing Technology SRM Institute of Science and TechnologyIndia Department of Computer Sciences College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Computer Science College of Science&Art at MahayilKing Khalid UniversitySaudi Arabia Department of Computer Science College of Computing and Information SystemUmm Al-Qura UniversitySaudi Arabia Department of Engineering Mathematics and Physics Faculty of Engineering and TechnologyFuture University in EgyptNew Cairo11845Egypt Department of Computer and Self Development Preparatory Year DeanshipPrince Sattam bin Abdulaziz UniversityAlKharjSaudi Arabia

Artificial Intelligence(AI)and Computer Vision(CV)advancements have led to many useful methodologies in recent years,particularly to help visually-challenged *** detection includes a variety of challenges,for example,handlingmultiple class images,images that get augmented when captured by a camera and so *** test images include all these variants as *** detection models alert them about their surroundings when they want to walk *** study compares four CNN-based pre-trainedmodels:ResidualNetwork(ResNet-50),Inception v3,DenseConvolutional Network(DenseNet-121),and SqueezeNet,predominantly used in image recognition *** on the analysis performed on these test images,the study infers that Inception V3 outperformed other pre-trained models in terms of accuracy and *** further improve the performance of the Inception v3 model,the thermal exchange optimization(TEO)algorithm is applied to tune the hyperparameters(number of epochs,batch size,and learning rate)showing the novelty of the *** accuracy was achieved owing to the inclusion of an auxiliary classifier as a regularizer,hyperparameter optimizer,and factorization ***,Inception V3 can handle images of different *** makes Inception V3 the optimum model for assisting visually challenged people in real-world communication when integrated with Internet of Things(IoT)-based devices.

关键词： pre-trained models object detection visually challenged people deep learning Inception V3 DenseNet-121

Efficient Grad-Cam-Based Model for COVID-19 Classification and Detection

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 Systems Science & Engineering 2023年第3期44卷 2743-2757页

作者： Saleh Albahli Ghulam Nabi Ahmad Hassan Yar Department of Information Technology College of ComputerQassim UniversityBuraydahSaudi Arabia Department of Electrical and Computer Engineering Air UniversityIslamabadPakistan ZR-Tech 24CheadleStockportSK83EGGreater ManchesterUnited Kingdom

Corona Virus(COVID-19)is a novel virus that crossed an animal-human barrier and emerged in Wuhan,*** now it has affected more than 119 million *** of COVID-19 is a critical task and due to a large number of patients,a shortage of doctors has occurred for its *** this paper,a model has been suggested that not only detects the COVID-19 using X-ray and CT-Scan images but also shows the affected *** classes have been defined;COVID-19,normal,and Pneumonia for X-ray *** CT-Scan images,2 classes have been defined COVID-19 and *** classi-fication purposes,pretrained models like ResNet50,VGG-16,and VGG19 have been used with some *** detecting the affected areas Gradient-weighted Class Activation Mapping(GradCam)has been *** the X-rays and ct images are taken at different intensities,so the contrast limited adaptive histogram equalization(CLAHE)has been applied to see the effect on the training of the *** a result of these experiments,we achieved a maximum validation accuracy of 88.10%with a training accuracy of 88.48%for CT-Scan images using the ResNet50 *** for X-ray images we achieved a maximum validation accuracy of 97.31%with a training accuracy of 95.64%using the VGG16 model.

关键词： Convolutional neural networks(CNN) COVID-19 pre-trained models CLAHE Grad-Cam X-ray data augmentation

Health Monitoring of Dry Clutch System Using Deep Learning Approach

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Intelligent Automation & Soft Computing 2023年第8期37卷 1513-1530页

作者： Ganjikunta Chakrapani V.Sugumaran School of Mechanical Engineering VIT University Chennai CampusVandalur-Kelambakkam RoadKeelakottatiyurChennai600127India

Clutch is one of the most significant components in *** improve passenger safety,reliability and economy of automobiles,advanced supervision and fault diagnostics are *** Monitoring is one of the key divisions that can be used to track the reliability of clutch and allied *** state of the clutch elements can be monitored with the help of vibration signals which contain valuable information required for *** drawbacks of traditional fault diagnosis techniques like high reliability on human intelligence and the requirement of profes-sional expertise,have made researchers look for intelligent fault diagnosis *** this article,the classification performance of the deep learning technique(employing images plotted from vibration signals)is compared with the machine learning technique(using features extracted from vibration signals)to identify the most viable solution for condition monitoring of the clutch *** overall experimentation is carried out in two phases,namely the deep learning phase and the machine learning ***,the effectiveness of the pre-trained networks was assessed and compared with machine learning *** on the comparative study,the best-performing technique is recommended for real-time application.

关键词： Deep learning health monitoring pre-trained models transfer learning vibration analysis statistical features

SHEL:a semantically enhanced hardware-friendly entity linking method

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

High Technology Letters 2024年第1期30卷 13-22页

作者：亓东林 CHEN Shudong DU Rong TONG Da YU Yong Institute of Microelectronics of Chinese Academy of Sciences Beijing 100029P.R.China University of Chinese Academy of Sciences Beijing 100190P.R.China

With the help of pre-trained language models,the accuracy of the entity linking task has made great strides in recent ***,most models with excellent performance require fine-tuning on a large amount of training data using large pre-trained language models,which is a hardware threshold to accomplish this *** researchers have achieved competitive results with less training data through ingenious methods,such as utilizing information provided by the named entity recognition *** paper presents a novel semantic-enhancement-based entity linking approach,named semantically enhanced hardware-friendly entity linking(SHEL),which is designed to be hardware friendly and efficient while maintaining good ***,SHEL's semantic enhancement approach consists of three aspects:(1)semantic compression of entity descriptions using a text summarization model;(2)maximizing the capture of mention contexts using asymmetric heuristics;(3)calculating a fixed size mention representation through pooling *** series of semantic enhancement methods effectively improve the model's ability to capture semantic information while taking into account the hardware constraints,and significantly improve the model's convergence speed by more than 50%compared with the strong baseline model proposed in this *** terms of performance,SHEL is comparable to the previous method,with superior performance on six well-established datasets,even though SHEL is trained using a smaller pre-trained language model as the encoder.

关键词： entity linking(EL) pre-trained models knowledge graph text summarization semantic enhancement

Robust Deep Learning Model for Black Fungus Detection Based on Gabor Filter and Transfer Learning

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 Systems Science & Engineering 2023年第11期47卷 1507-1525页

作者： Esraa Hassan Fatma M.Talaat Samah Adel Samir Abdelrazek Ahsan Aziz Yunyoung Nam Nora El-Rashidy Machine Learning and Information Retrieval Department Faculty of Artificial IntelligenceKafrelsheikh UniversityKafrelsheikhEgypt Electronics and Communication Engineering Department Faculty of Engineering Horus UniversityDamiettaEgypt Information Systems Department Faculty of Computers and InformationMansoura UniversityMansoura35516Egypt Department of ICT Convergence Soonchunhyang UniversityAsanKorea

Black fungus is a rare and dangerous mycology that usually affects the brain and lungs and could be life-threatening in diabetic ***,some COVID-19 survivors,especially those with co-morbid diseases,have been susceptible to black ***,recovered COVID-19 patients should seek medical support when they notice mucormycosis *** paper proposes a novel ensemble deep-learning model that includes three pre-trained models:reset(50),VGG(19),and *** approach is medically intuitive and efficient compared to the traditional deep learning *** image dataset was aggregated from various resources and divided into two classes:a black fungus class and a skin infection *** the best of our knowledge,our study is the first that is concerned with building black fungus detection models based on deep learning *** proposed approach can significantly improve the performance of the classification task and increase the generalization ability of such a binary classification *** to the reported results,it has empirically achieved a sensitivity value of 0.9907,a specificity value of 0.9938,a precision value of 0.9938,and a negative predictive value of 0.9907.

关键词： Black fungus COVID-19 Transfer learning pre-trained models medical image

Stressed Coral Reef Identification Using Deep Learning CNN 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 Electronic & Information Systems 2023年第2期5卷 1-9页

作者： S.P.Aruna M.Thamarai Skilltroniks Technologies TadepalligudemAndhra Pradesh534101India ECE Department Sri Vasavi Engineering CollegeTadepalligudemAndhra Pradesh534102India

Deep learning is a machine learning technique that allows the computer to process things that occur naturally to ***,deep learning techniques are commonly used in computer vision to classify images and *** a result,for challenging computer vision problems,deep learning provides state of the art solutions to *** reefs are an essential resource of the earth.A new study finds the planet has lost half of its coral reefs since *** is necessary to restore and prevent damage to coral reefs as they play an important role in maintaining a balance in the marine *** proposed work helps to prevent the corals from bleaching and restore them to a healthy condition by identifying the root cause of the *** the proposed work,using deep learning CNN techniques,the images are classified into Healthy and Stressed coral *** coral reefs are an intermediate state of coral reef between healthy and bleached coral *** pre-trained models Resnet50 and Inception V3 are used in this study to classify the ***,a proposed CNN model is built and tested for the *** results of Inception V3 and Resnet50 are improved to 70%and 55%by tuning the hypermeters such as dropouts and batch ***,the proposed model is tuned as required and obtains a maximum of up to 90%*** large datasets,the optimum amount of neural networks and tuning it as required brings higher accuracy than other methods.

关键词： Stressed coral reef Deep learning Convolutional neural network pre-trained models