- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
Prediction of two-dimensional topography of laser cladding based on neural network
摘要： The two-dimensional morphology of the cladding layer has an important influence on the quality of the cladding layer and the crack tendency. Using the powerful nonlinear processing ability of the single hidden layer feedforward neural network, a prediction model between the cladding technological parameters and the two-dimensional morphology of the cladding layer is established. Taking the cladding parameters as the input and the two-dimensional morphology of the cladding as the output, the experimental data is used to train the network to achieve a high-level mapping of the input and output. On this basis, the algorithm of extreme learning machine is used to optimize the single hidden layer feedforward neural network to overcome the problems of slow convergence speed, more network training parameters and easy local convergence in back-propagation algorithm. The results show that the relationship between the cladding process parameters and the two-dimensional morphology of the cladding layer can be roughly reflected by the back-propagation algorithm. However, the prediction results are not stable and the error rate is between 10% and 40%. The neural network optimized by the extreme learning machine is utilized to get a better prediction result. The error rate is 10–20%.
关键词： extreme learning machine.,BP neural network,Layer cladding,morphology prediction
更新于2025-11-28 14:24:20
-
Deep learning enables cross-modality super-resolution in fluorescence microscopy
摘要： We present deep-learning-enabled super-resolution across different fluorescence microscopy modalities. This data-driven approach does not require numerical modeling of the imaging process or the estimation of a point-spread-function, and is based on training a generative adversarial network (GAN) to transform diffraction-limited input images into super-resolved ones. Using this framework, we improve the resolution of wide-field images acquired with low-numerical-aperture objectives, matching the resolution that is acquired using high-numerical-aperture objectives. We also demonstrate cross-modality super-resolution, transforming confocal microscopy images to match the resolution acquired with a stimulated emission depletion (STED) microscope. We further demonstrate that total internal reflection fluorescence (TIRF) microscopy images of subcellular structures within cells and tissues can be transformed to match the results obtained with a TIRF-based structured illumination microscope. The deep network rapidly outputs these super-resolved images, without any iterations or parameter search, and could serve to democratize super-resolution imaging.
关键词： GAN,cross-modality,super-resolution,fluorescence microscopy,deep learning
更新于2025-11-21 11:24:58
-
Using Deep Learning with Large Dataset of Microscope Images to Develop an Automated Embryo Grading System
摘要： The assessment of embryo viability for in vitro fertilization (IVF) is mainly based on subjective visual analysis, with the limitation of intra- and inter-observer variation and a time-consuming task. In this study, we used deep learning with large dataset of microscopic embryo images to develop an automated grading system for embryo assessment. This study included a total of 171,239 images from 16,201 embryos of 4,146 IVF cycles at Stork Fertility Center (https://www.e-stork.com.tw) from March 6, 2014 to April 13, 2018. The images were captured by inverted microscope (Zeiss Axio Observer Z1) at 112 to 116 hours (Day 5) or 136 to 140 hours (Day 6) after fertilization. Using a pre-trained network trained on the ImageNet dataset as convolution base, we applied Convolutional Neural Network (CNN) on embryo images, using ResNet50 architecture to fine-tune ImageNet parameters. The predicted grading results was compared with the grading results from trained embryologists to evaluate the model performance. The images were labeled by trained embryologists, based on Gardner’s grading system: blastocyst development ranking from 3–6, ICM quality as A, B, or C; and TE quality as a, b, or c. After pre-processing, the images were divided into training, validation, and test groups, in which 60% were allocated to the training group, 20% to the validation group, and 20% to the test group. The ResNet50 algorithm was trained on the 60% images allocated to the training group, and the algorithm’s performance was evaluated using the 20% images allocated to the test group. The results showed an average predictive accuracy of 75.36% for the all three grading categories: 96.24% for blastocyst development, 91.07% for ICM quality, and 84.42% for TE quality. To the best of our knowledge, this is the first study of an automatic embryo grading system using large dataset from Asian population. Combing the promising results obtained in this study with time-lapse microscope system integrated with IVF Electronic Medical Record platform, a fully automated and non-invasive pipeline for embryo assessment will be achieved.
关键词： Embryo Grading,Machine Learning,Embryo Image,Artificial Intelligence
更新于2025-11-21 11:24:58
-
Introducing Manganese-Doped Lead Halide Perovskite Quantum Dots: A Simple Synthesis Illustrating Optoelectronic Properties of Semiconductors
摘要： Quantum dots (QDs) are considered useful for demonstrating quantum phenomena in undergraduate laboratories due to their monodisperse size and excellent optical properties. Although doping has an increasingly important role in QD fabrication in the semiconductor field, it has rarely been discussed in the context of the undergraduate laboratory. In this work, a simple synthesis and characterization method for Mn-doped CsPbCl3 QDs for an upper-level undergraduate inorganic chemistry laboratory is reported. The Mn-doped CsPbCl3 system benefits from a simplified synthesis and straightforward characterization. This experiment introduces QD research to students and offers opportunities for instructors to discuss many important concepts in inorganic chemistry, such as energy band theory, particle-in-a-box model, electron paramagnetic resonance, ligand field theory, and nanochemistry.
关键词： Inorganic Chemistry,Crystal Field/Ligand Field Theory,EPR/ESR Spectroscopy,Upper-Division Undergraduate,Hands-On Learning/Manipulatives,Laboratory Instruction,Nanotechnology
更新于2025-11-20 15:33:11
-
Dictionaries of deep features for land-use scene classification of very high spatial resolution images
摘要： Land-use classification in very high spatial resolution images is critical in the remote sensing field. Consequently, remarkable efforts have been conducted towards developing increasingly accurate approaches for this task. In recent years, deep learning has emerged as a dominant paradigm for machine learning, and methodologies based on deep convolutional neural networks have received particular attention from the remote sensing community. These methods typically utilize transfer learning and/or data augmentation to accommodate a small number of labeled images in the publicly available datasets in this field. However, they typically require powerful computers and/or a long time for training. In this work, we propose a simple and novel method for land-use classification in very high spatial resolution images, which efficiently combines transfer learning with a sparse representation. Specifically, the proposed method performs the classification of land-use scenes using a modified version of the well-known sparse representation-based classification method. While this method directly uses the training images to form dictionaries, which are employed to classify test images, our method utilizes a pre-trained deep convolutional neural network and the Gaussian mixture model to generate more robust and compact 'dictionaries of deep features.' The effectiveness of the proposed method was evaluated on two publicly available datasets: UC Merced and Brazilian Cerrado–Savana. The experimental results suggest that our method can potentially outperform state-of-the-art techniques for land-use classification in very high spatial resolution images.
关键词： Dictionary learning,Land-use classification,Sparse representation,Feature learning,Deep learning
更新于2025-09-23 15:23:52
-
Superpixel-Based Semisupervised Active Learning for Hyperspectral Image Classification
摘要： In this work, we propose a new semisupervised active learning approach for hyperspectral image classification. The proposed method aims at improving machine generalization by using pseudolabeled samples, both confident and informative, which are automatically and actively selected, via semisupervised learning. The learning is performed under two assumptions: a local one for the labeling via a superpixel-based constraint dedicated to the spatial homogeneity and adaptivity into the pseudolabels, and a global one modeling the data density by a multinomial logistic regressor with a Markov random field regularizer. Furthermore, we propose a density-peak-based augmentation strategy for pseudolabels, due to the fact that the samples without manual labels in their superpixel neighborhoods are out of reach for the automatic sampling. Three real hyperspectral datasets were used in our experiments to evaluate the effectiveness of the proposed superpixel-based semisupervised learning approach. The obtained results indicate that the proposed approach can greatly improve the potential for semisupervised learning in hyperspectral image classification.
关键词： semisupervised learning,hyperspectral image classification,superpixel,clustering,Active learning
更新于2025-09-23 15:23:52
-
Image classification with quantum pre-training and auto-encoders
摘要： Computer vision has a wide range of applications from medical image analysis to robotics. Over the past few years, the field has been transformed by machine learning and stands to benefit from potential advances in quantum computing. The main challenge for processing images on current and near-term quantum devices is the size of the data such devices can process. Images can be large, multidimensional and have multiple color channels. Current machine learning approaches to computer vision that exploit quantum resources require a significant amount of manual pre-processing of the images in order to be able to fit them onto the device. This paper proposes a framework to address the problem of processing large scale data on small quantum devices. This framework does not require any dataset-specific processing or information and works on large, grayscale and RGB images. Furthermore, it is capable of scaling to larger quantum hardware architectures as they become available. In the proposed approach, a classical autoencoder is trained to compress the image data to a size that can be loaded onto a quantum device. Then, a Restricted Boltzmann Machine (RBM) is trained on the D-Wave device using the compressed data, and the weights from the RBM are then used to initialize a neural network for image classification. Results are demonstrated on two MNIST datasets and two medical imaging datasets.
关键词： quantum machine learning,medical imaging,Quantum computing,machine learning
更新于2025-09-23 15:23:52
-
A review on graph-based semi-supervised learning methods for hyperspectral image classification
摘要： In this article, a comprehensive review of the state-of-art graph-based learning methods for classification of the hyperspectral images (HSI) is provided, including a spectral information based graph semi-supervised classification and a spectral-spatial information based graph semi-supervised classification. In addition, related techniques are categorized into the following sub-types: (1) Manifold representation based Graph Semi-supervised Learning for HSI Classification (2) Sparse representation based Graph Semi-supervised Learning for HSI Classification. For each technique, methodologies, training and testing samples, various technical difficulties, as well as performances, are discussed. Additionally, future research challenges imposed by the graph-based model are indicated.
关键词： Image classification,Hyperspectral images,Semi-supervised learning,Graph-based learning
更新于2025-09-23 15:23:52
-
Unsupervised Learning Based Fast Beamforming Design for Downlink MIMO
摘要： In the downlink transmission scenario, power allocation and beamforming design at the transmitter are essential when using multiple antenna arrays. This paper considers a multiple input-multiple output broadcast channel to maximize the weighted sum-rate under the total power constraint. The classical weighted minimum mean-square error (WMMSE) algorithm can obtain suboptimal solutions but involves high computational complexity. To reduce this complexity, we propose a fast beamforming design method using unsupervised learning, which trains the deep neural network (DNN) offline and provides real-time service online only with simple neural network operations. The training process is based on an end-to-end method without labeled samples avoiding the complicated process of obtaining labels. Moreover, we use the 'APoZ'-based pruning algorithm to compress the network volume, which further reduces the computational complexity and volume of the DNN, making it more suitable for low computation-capacity devices. Finally, experimental results demonstrate that the proposed method improves computational speed significantly with performance close to the WMMSE algorithm.
关键词： beamforming,unsupervised learning,deep learning,network pruning,MIMO
更新于2025-09-23 15:23:52
-
Two-Dimensional Angle Estimation of Two-Parallel Nested Arrays Based on Sparse Bayesian Estimation
摘要： To increase the number of estimable signal sources, two-parallel nested arrays are proposed, which consist of two subarrays with M sensors, and can estimate the two-dimensional (2-D) direction of arrival (DOA) of M2 signal sources. To solve the problem of direction finding with two-parallel nested arrays, a 2-D DOA estimation algorithm based on sparse Bayesian estimation is proposed. Through a vectorization matrix, smoothing reconstruction matrix and singular value decomposition (SVD), the algorithm reduces the size of the sparse dictionary and data noise. A sparse Bayesian learning algorithm is used to estimate one dimension angle. By a joint covariance matrix, another dimension angle is estimated, and the estimated angles from two dimensions can be automatically paired. The simulation results show that the number of DOA signals that can be estimated by the proposed two-parallel nested arrays is much larger than the number of sensors. The proposed two-dimensional DOA estimation algorithm has excellent estimation performance.
关键词： decoupled estimation,direction of arrival estimation,degrees of freedom,sparse Bayesian learning,sparse arrays
更新于2025-09-23 15:23:52