检索结果-内蒙古大学图书馆

Detection of external defects in tomatoes using deep learning

Journal of Ambient Intelligence and Humanized Computing 2023年第3期14卷 2709-2721页

作者： Chaturvedi, Akshat Sharma, Sanjeev Janghel, Rekh Ram Computer Science and Engineering Indian Institute of Information Technology Maharashtra Pune411041 India Information Technology National Institute of Technology CG Raipur492010 India

computer vision helps a computer to understand, classify and label images. Digital cameras can capture images and videos and then be analyzed with deep learning models for accurate identification and classification. Similarly, deep learning can be used for separating defective or unusable items for quality control. This paper presents a method to separate tomatoes that have some form of external defect from ones that do not. External defects may include bruises, aberrations, cuts, and rotten spots. The dataset selected to train our convolutional neural networks (CNN) contains 43,843 images, which is highly biased toward the healthy class. Ever since AlexNet won the ILSVRC 2012, CNN has been used extensively in Deep Learning models. For our paper, five Deep Learning models based on CNN were trained, namely VGG19, ResNet50, DenseNet201, EfficientNetB4, and Inceptionv3. The highest accuracy achieved was 97.97% by EfficientNetB4 while having an average precision of 97.00% and an average recall of 93.00%. These results achieved in our paper on the selected dataset are the highest to date anyone has achieved. This paper compares the different models based on the results, architecture, and effectiveness of the selected datasets. © 2023, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Pre-trained SAM as data augmentation for image segmentation

引用

CAAI Transactions on Intelligence technology 2025年第1期10卷 268-282页

作者： Junjun Wu Yunbo Rao Shaoning Zeng Bob Zhang Yangtze Delta Region Institute(Huzhou) University of Electronic Science and Technology of ChinaHuzhouChina School of Information and Software Engineering University of Electronic Science and Technology of ChinaChengduChina Pattern Analysis and Machine Intelligence Research Group Department of Computer and Information ScienceUniversity of MacaoMacaoChina

Data augmentation plays an important role in training deep neural model by expanding the size and diversity of the ***,data augmentation mainly involved some simple transformations of ***,in order to increase the diversity and complexity of data,more advanced methods appeared and evolved to sophisticated generative ***,these methods required a mass of computation of training or *** this paper,a novel training-free method that utilises the Pre-Trained Segment Anything Model(SAM)model as a data augmentation tool(PTSAM-DA)is proposed to generate the augmented annotations for *** the need for training,it obtains prompt boxes from the original annotations and then feeds the boxes to the pre-trained SAM to generate diverse and improved *** this way,annotations are augmented more ingenious than simple manipulations without incurring huge computation for training a data augmentation *** comparative experiments on three datasets are conducted,including an in-house dataset,ADE20K and *** this in-house dataset,namely Agricultural Plot Segmentation Dataset,maximum improvements of 3.77%and 8.92%are gained in two mainstream metrics,mIoU and mAcc,***,large vision models like SAM are proven to be promising not only in image segmentation but also in data augmentation.

关键词： data augmentation image segmentation large model segment anything model

来源：评论

学校读者我要写书评

暂无评论

Breaking demodulation limitations:AWG and Deep Learning in Dynamic Spectral Reconstruction for Differential FBG Accelerometers

引用

IEEE Sensors Journal 2025年第11期25卷 19210-19222页

作者： Yang, Qian Liu, Lei Niu, Ning Quan, ChenYi Ren, SuFen Chen, ShengChao Zhang, JiaLin Yan, YuMeng Xiang, LongTeng Wang, YiPing Liao, ChangRui He, Jun Wang, GuanJun School of Information and Communication Engineering Hainan University College of Electronic Science and Technology China Henan Mechanical and Electrical Vocational College School of Electrical Engineering Henan451100 China Hainan University College of Electronic Science and Technology School of Information and Communication Engineering Haikou570228 China University of Technology Sydney School of Computer Science Faculty of Engineering and Information Technology SydneyNSW Australia Hainan University College of Electronic Science and Technology Haikou570228 China Shenzhen University School of Physics and Optoelectronic Engineering Shenzhen518060 China

Conventional fiber Bragg grating (FBG) accelerometer demodulation often suffers from high environmental sensitivity, complexity, and cost. To address these issues, this paper presents two arrayed waveguide grating (AWG)-based dynamic spectral reconstruction models. First, a novel differential FBG accelerometer with an equal-intensity triangular cantilever beam and a symmetric string-like design enhances sensitivity and mitigates temperature interference. A power ratio-nonlinear logarithmic regression (PR-NLR) model derived from static calibration then enables spectral reconstruction and wavelength demodulation across varying accelerations, achieving 4-82pm accuracy, slightly below that of high-speed demodulators (HSD). Next, by integrating convolutional neural networks (CNN), bidirectional long short-term memory (BiLSTM), attention mechanisms, and a generative adversarial network (GAN) for data augmentation, prediction errors drop to 1-26pm at 20Hz and 0.2-21pm at 40Hz-a reduction of at least 60% over PR-NLR. This outcome underscores the advantages of deep learning (DL) in managing complex spectral shifts. By overcoming frequency-only demodulation limits, the proposed AWG approach achieves precise wavelength demodulation through dynamic spectral reconstruction. Its compact design, low manufacturing cost, and robust performance facilitate scalable deployment in structural health monitoring, particularly for bridge vibration analysis and industrial machinery diagnostics. © 2001-2012 IEEE.

关键词： Arrayed waveguide gratings

来源：评论

学校读者我要写书评

暂无评论

Dual-Cloud Multi-Secret Sharing Architecture for Privacy Preserving Persistent Computation

引用

IEEE Transactions on information Forensics and Security 2024年 19卷 7523-7535页

作者： Chen, Yu-Chi Yang, Jhe-Kai Yen, Hsin-Chan Lin, Pei-Wen National Taipei University of Technology Department of Computer Science and Information Engineering Taipei10608 Taiwan Yuan Ze University Department of Computer Science and Engineering Taoyuan32003 Taiwan Genie Networks Taipei114064 Taiwan

With the prevalence of artificial intelligence, people collect data through numerous sensors and use machine learning to create models for intelligent services. However, data privacy and massive data issues are raised with the proliferation of devices. Although secret sharing can be the solution to providing privacy and performing efficient computations (than homomorphic encryption-based) in the privacy domain, sharing large amounts of data may impose a considerable storage burden on resource-restricted devices. Therefore, we aim to reduce the shares that participants need to hold and construct secure computation protocols that form privacy-preserving data utilization with multi-secret sharing. In this paper, we study the mechanism of persistent computation with multi-secret sharing for privacy protection, which avoids the requirements for participants to store extra information during secure computation. We present the mask techniques to convert secrets into protected data and upload them separately to non-colluding dual-cloud servers through multi-secret sharing. Then, we can locally evaluate the operation result shares by revealing a part of the protected data, where the true secret consistently remains secure as the other part stays in a shared state. Eventually, we outsource a dataset to the cloud, build a privacy-preserving multi-party kNN classification based on our scheme, and provide some experiments to demonstrate the feasibility and usability of storage size. © 2005-2012 IEEE.

关键词： computer architecture

来源：评论

学校读者我要写书评

暂无评论

Routability-driven Ordered Escape Routing Method based on Neural Network

Routability-driven Ordered Escape Routing Method based on Ne...

引用

2025 International Workshop on Advanced Imaging technology, IWAIT 2025

作者： Yeh, Hung Liang Cheng, Dun Wei Department of Computer Science and Information Engineering National Yunlin University of Science & Technology Yunlin Taiwan

ISBN: (数字)9781510688131

ISBN: (纸本)9781510688124

This study presents an innovative approach that utilizes neural network-based techniques to address the Ordered Escape Routing (OER) *** OER problem holds a crucial position in integrated circuit design, requiring multiple pins to be connected to the boundary of a chip in a specific order while ensuring that the routing paths do not ***, the total wire length must be minimized during the *** tackle this challenging problem, we propose a novel routability-driven method that leverages neural networks (NN) to predict feasible routing paths that satisfy the required *** approach not only ensures non-crossing paths but also strictly adheres to the specified pin connection order, while further minimizing the total wire length under these *** core of this technique lies in the efficient predictive capabilities of neural networks. © 2024 SPIE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Classifying Misinformation of User Credibility in Social Media Using Supervised Learning

引用

computers, Materials & Continua 2023年第5期75卷 2921-2938页

作者： Muhammad Asfand-e-Yar Qadeer Hashir Syed Hassan Tanvir Wajeeha Khalil Department of Computer Science Center of Excellence in Artificial Intelligence(CoE-AI)Bahria UniversityIslamabad44000Pakistan Department of Computer Science and Information Technology University of Engineering and TechnologyPeshawar25000Pakistan

The growth of the internet and technology has had a significant effect on social *** information has become an important research topic due to the massive amount of misinformed content on social *** is very easy for any user to spread misinformation through the ***,misinformation is a problem for professionals,organizers,and ***,it is essential to observe the credibility and validity of the News articles being shared on social *** core challenge is to distinguish the difference between accurate and false *** studies focus on News article content,such as News titles and descriptions,which has limited their ***,there are two ordinarily agreed-upon features of misinformation:first,the title and text of an article,and second,the user *** the case of the News context,we extracted different user engagements with articles,for example,tweets,i.e.,read-only,user retweets,likes,and *** calculate user credibility and combine it with article content with the user’s *** combining both features,we used three Natural language processing(NLP)feature extraction techniques,i.e.,Term Frequency-Inverse Document Frequency(TF-IDF),Count-Vectorizer(CV),and Hashing-Vectorizer(HV).Then,we applied different machine learning classifiers to classify misinformation as real or ***,we used a Support Vector Machine(SVM),Naive Byes(NB),Random Forest(RF),Decision Tree(DT),Gradient Boosting(GB),and K-Nearest Neighbors(KNN).The proposed method has been tested on a real-world dataset,i.e.,“fakenewsnet”.We refine the fakenewsnet dataset repository according to our required *** dataset contains 23000+articles with millions of user *** highest accuracy score is 93.4%.The proposed model achieves its highest accuracy using count vector features and a random forest *** discoveries confirmed that the proposed classifier would effectively classify misinformat

关键词： Misinformation user credibility fake news machine learning

来源：评论

学校读者我要写书评

暂无评论

Weed Classification Using Particle Swarm Optimization and Deep Learning Models

引用

computer Systems science & engineering 2023年第1期44卷 913-927页

作者： M.Manikandakumar P.Karthikeyan Department of Computer Science and Engineering Thiagarajar College of EngineeringTamil NaduIndia Department of Information Technology Thiagarajar College of EngineeringTamil NaduIndia

Weed is a plant that grows along with nearly allfield crops,including rice,wheat,cotton,millets and sugar cane,affecting crop yield and *** and accurate identification of all types of weeds is a challenging task for farmers in earlier stage of crop growth because of *** address this issue,an efficient weed classification model is proposed with the Deep Convolutional Neural Network(CNN)that implements automatic feature extraction and performs complex feature learning for image *** this work,weed images were trained using the proposed CNN model with evolutionary computing approach to classify the weeds based on the two publicly available weed *** Tamil Nadu Agricultural University(TNAU)dataset used as afirst dataset that consists of 40 classes of weed images and the other dataset is from Indian Council of Agriculture Research–Directorate of Weed Research(ICAR-DWR)which contains 50 classes of weed *** effective Particle Swarm Optimization(PSO)technique is applied in the proposed CNN to automa-tically evolve and improve its classification *** proposed model was evaluated and compared with pre-trained transfer learning models such as GoogLeNet,AlexNet,Residual neural Network(ResNet)and Visual Geometry Group Network(VGGNet)for weed *** work shows that the performance of the PSO assisted proposed CNN model is significantly improved the success rate by 98.58%for TNAU and 97.79%for ICAR-DWR weed datasets.

关键词： Deep learning convolutional neural network weed classification transfer learning particle swarm optimization evolutionary computing Algorithm 1:Metrics Evaluation

来源：评论

学校读者我要写书评

暂无评论

A deep learning-based early alzheimer’s disease detection using magnetic resonance images

引用

Multimedia Tools and Applications 2025年第16期84卷 16561-16582页

作者： Suchitra, S. Krishnasamy, Lalitha Poovaraghan, R.J. Department of Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R &D Institute of Science and Technology Avadi Tamil Nadu Chennai India Department of Information Technology Nandha Engineering College Tamil Nadu Erode India Department of Information Technology Jaya Engineering College Tamil Nadu Thiruninravur Chennai India

Alzheimer’s Disease (AD) is a degenerative, chronic condition of the brain for which there is now no effective treatment. However, there are medications that can slow its development. In order to stop and control the development of AD, earlier diagnosis of the disease is quintessential. Our proposed method’s primary objective is to establish a comprehensive model for the prior detection of Alzheimer’s disease and the categorization of distinct AD stages. This work employs a deep learning methodology, especially CNN. The proposed approach makes use of well-known models that have already been trained to classify medical images, like the EfficentNetB7 model, by applying the transfer learning principle. In order to achieve greater accuracy, convolutional neural networks (CNNs) are frequently scaled up as new resources become available at a fixed cost throughout the construction phase. A compound coefficient is used by the CNN architecture and scaling approach, which is the foundation of the pre-trained EfficientNetB7 model, to scale the dimensions equally. This proposed EfficientNetB7 model is quicker, easier, and more effective than other pre-trained models like VGG19 and InceptionV3. The proposed model includes simple structures that have memory requirements, provide manageable time, overfitting, and low computational complexity as well as training and inference speeds. The Alzheimer’s disease Neuroimaging Initiative (ADNI) dataset was employed for a comprehensive assessment of the method proposed, utilizing well-known performance metrics including sensitivity, specificity, and accuracy. The findings revealed that the improvised results achieved the accuracy metric when compared to existing methods. The EfficientNetB7 model has been enhanced, and this model achieves a sensitivity of 98.08%, specificity-98%, accuracy-98.2%, and F-score-98.95%, for multi-class AD stage classifications. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, par

关键词： Magnetic resonance

来源：评论

学校读者我要写书评

暂无评论

Hyperspectral Image Classification Based on A Multi-Scale Weighted Kernel Network

引用

Chinese Journal of Electronics 2022年第5期31卷 832-843页

作者： SUN Le XU Bin LU Zhenyu School of Computer Science Nanjing University of Information Science and Technology Engineering Research Center of Digital Forensics Ministry of Education Nanjing University of Information Science and Technology School of Artificial Intelligence Nanjing University of Information Science and Technology

Recently, many deep learning models have shown excellent performance in hyperspectral image(HSI) classification. Among them, networks with multiple convolution kernels of different sizes have been proved to achieve richer receptive fields and extract more representative features than those with a single convolution kernel. However, in most networks, different-sized convolution kernels are usually used directly on multibranch structures, and the image features extracted from them are fused directly and simply. In this paper, to fully and adaptively explore the multiscale information in both spectral and spatial domains of HSI, a novel multi-scale weighted kernel network(MSWKNet) based on an adaptive receptive field is proposed. First, the original HSI cubic patches are transformed to the input features by combining the principal component analysis and one-dimensional spectral convolution. Then, a three-branch network with different convolution kernels is designed to convolve the input features, and adaptively adjust the size of the receptive field through the attention mechanism of each branch. Finally, the features extracted from each branch are fused together for the task of *** on three well-known hyperspectral data sets show that MSWKNet outperforms many deep learning networks in HSI classification.

关键词： multibranch structures image features convolution kernels multiple convolution kernels adaptive receptive field image classification feature extraction HSI classification single convolution kernel convolutional neural nets hyperspectral image classification representative features hyperspectral imaging geophysical image processing deep learning (artificial intelligence) multiscale weighted kernel network deep learning networks hyperspectral data sets three-branch network HSI cubic patches principal component analysis 1D spectral convolution different-sized convolution kernels

来源：评论

学校读者我要写书评

暂无评论

Enhanced Neutrosophic Set and Machine Learning Approach for Kidney Disease Prediction

引用

Neutrosophic Sets and Systems 2025年 80卷 465-477页

作者： Al-Doori, Humam M. Alkellezli, Tareef S. Abdelhafeez, Ahmed Eassaa, Mohamed Sawah, Mohamed S. El-Douh, Ahmed A. Cybersecurity Sciences Department College of Science Ashur University Baghdad Iraq Cybersecurity Engineering Department College of Engineering Ashur University Baghdad Iraq Computer Science Department Faculty of Information System and Computer Science October 6 University Giza12585 Egypt Applied Science Research Center Applied Science Private University Amman Jordan Department of Computer Science Faculty of Information Technology Ajloun National University P.O.43 Ajloun26810 Jordan Cybersecurity Technology Engineering Department College of Engineering Technology Ashur University Baghdad Iraq

Kidney disease (KD) is a gradually increasing global health concern. It is a chronic illness linked to higher rates of morbidity and mortality, a higher risk of cardiovascular disease and numerous other illnesses, and expensive medical expenses. The machine learning (ML) models are applied for KD prediction with higher accuracy and precision. The KD dataset has uncertainty and vague information, so, we used the neutrosophic set (NS) to deal with vague and uncertainty information in the KD dataset. The KD dataset is converted into the N-KD dataset with three membership functions: truth, indeterminacy, and falsity. Three ML models are used in this study such as logistic regression (LR), support vector machine (SVM), and k-nearest neighbor (KNN). These ML models are applied to the N-KD dataset. The results show the LR has higher accuracy and precision on the N-KD dataset than the original KD dataset. © 2025, University of New Mexico. All rights reserved.

关键词： Logistic regression

来源：评论

学校读者我要写书评

暂无评论

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

请选择保存的检索档案：

请选择收藏分类：

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

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

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：