- 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
-
Biometric iris recognition using radial basis function neural network
摘要： The consistent and efficient method for the identification of biometrics is the iris recognition in view of the fact that it has richness in texture information. A good number of features performed in the past are built on handcrafted features. The proposed method is based on the feed-forward architecture and uses k-means clustering algorithm for the iris patterns classification. In this paper, segmentation of iris is performed using the circular Hough transform that realizes the iris boundaries in the eye and isolates the region of iris with no eyelashes and other constrictions. Moreover, Daugman's rubber sheet model is used to transform the resultant iris portion into polar coordinates in the process of normalization. A unique iris code is generated by log-Gabor filter to extract the features. The classification is achieved using neural network structures, the feed-forward neural network and the radial basis function neural network. The experiments have been conducted using the Chinese Academy of Sciences Institute of Automation (CASIA) iris database. The proposed system decreases computation time, size of the database and increases the recognition accuracy as compared to the existing algorithms.
关键词： Feed-forward neural network (FNN),Iris segmentation,Normalization,Biometrics,Radial basis function neural network (RBFNN),Iris recognition
更新于2025-09-23 15:23:52
-
[IEEE 2018 IEEE SmartWorld, Ubiquitous Intelligence & Computing, Advanced & Trusted Computing, Scalable Computing & Communications, Cloud & Big Data Computing, Internet of People and Smart City Innovation (SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI) - Guangzhou, China (2018.10.8-2018.10.12)] 2018 IEEE SmartWorld, Ubiquitous Intelligence & Computing, Advanced & Trusted Computing, Scalable Computing & Communications, Cloud & Big Data Computing, Internet of People and Smart City Innovation (SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI) - An Efficient Recognition Method for Incomplete Iris Image Based on CNN Model
摘要： The iris of the eye is a research hot spot in the field of biometric identification because of its uniqueness, non-contact and bioactivity. The incompleteness of the iris caused by the acquisition process has brought great uncertainty to the subsequent iris region segmentation and iris code matching, thereby reducing the efficiency of iris recognition. This paper describes a deep convolution neural network model with adaptive incomplete iris preprocessing mechanism. Based on the normalization of the iris image, the incomplete iris preprocessing mechanism adopts the method of making the inner circle or the outer circle. The iris region can be segmented by the line fitting and the circle fitting method for extracting as many iris features as possible. The deep convolution neural network then uses pixel coding of Irregular iris regions to complete the iris pattern classification. The model fully utilizes the characteristics of deep learning, local feature characterization and weight sharing, and realizes the problem of using large sample to compensate the incomplete feature of local feature. The experimental results show that this method has significant accuracy improvement compared with the traditional algorithms.
关键词： iris recognition,convolution neural network,iris image normalization,algorithm
更新于2025-09-23 15:23:52
-
[Lecture Notes in Networks and Systems] Renewable Energy for Smart and Sustainable Cities Volume 62 (Artificial Intelligence in Renewable Energetic Systems) || Prediction PV Power Based on Artificial Neural Networks
摘要： The goal of this contribution is to estimate the power delivered by a multicrystals solar photovoltaic module based on artificial neural networks. Two structures of ANNs were tested: multiple-layer perceptron and radial basic function. The results obtained gave good coefficients of correlation, the statistical R2-value obtained is about 0.96 to predict this important parameter.
关键词： Artificial neural network (ANNs),Multiple-layer perceptron (MLP),Radial basic function (RBF),Photovoltaic (PV) power
更新于2025-09-23 15:23:52
-
An enhanced diabetic retinopathy detection and classification approach using deep convolutional neural network
摘要： The objective of this study is to propose an alternative, hybrid solution method for diagnosing diabetic retinopathy from retinal fundus images. In detail, the hybrid method is based on using both image processing and deep learning for improved results. In medical image processing, reliable diabetic retinopathy detection from digital fundus images is known as an open problem and needs alternative solutions to be developed. In this context, manual interpretation of retinal fundus images requires the magnitude of work, expertise, and over-processing time. So, doctors need support from imaging and computer vision systems and the next step is widely associated with use of intelligent diagnosis systems. The solution method proposed in this study includes employment of image processing with histogram equalization, and the contrast limited adaptive histogram equalization techniques. Next, the diagnosis is performed by the classification of a convolutional neural network. The method was validated using 400 retinal fundus images within the MESSIDOR database, and average values for different performance evaluation parameters were obtained as accuracy 97%, sensitivity (recall) 94%, specificity 98%, precision 94%, FScore 94%, and GMean 95%. In addition to those results, a general comparison of with some previously carried out studies has also shown that the introduced method is efficient and successful enough at diagnosing diabetic retinopathy from retinal fundus images. By employing the related image processing techniques and deep learning for diagnosing diabetic retinopathy, the proposed method and the research results are valuable contributions to the associated literature.
关键词： Image processing,Deep learning,Convolutional neural network,Diabetic retinopathy
更新于2025-09-23 15:23:52
-
Computer-Assisted Diagnosis for Diabetic Retinopathy Based on Fundus Images Using Deep Convolutional Neural Network
摘要： Diabetic retinopathy (DR) is a complication of long-standing diabetes, which is hard to detect in its early stage because it only shows a few symptoms. Nowadays, the diagnosis of DR usually requires taking digital fundus images, as well as images using optical coherence tomography (OCT). Since OCT equipment is very expensive, it will benefit both the patients and the ophthalmologists if an accurate diagnosis can be made, based solely on reading digital fundus images. In the paper, we present a novel algorithm based on deep convolutional neural network (DCNN). Unlike the traditional DCNN approach, we replace the commonly used max-pooling layers with fractional max-pooling. Two of these DCNNs with a different number of layers are trained to derive more discriminative features for classification. After combining features from metadata of the image and DCNNs, we train a support vector machine (SVM) classifier to learn the underlying boundary of distributions of each class. For the experiments, we used the publicly available DR detection database provided by Kaggle. We used 34,124 training images and 1,000 validation images to build our model and tested with 53,572 testing images. The proposed DR classifier classifies the stages of DR into five categories, labeled with an integer ranging between zero and four. The experimental results show that the proposed method can achieve a recognition rate up to 86.17%, which is higher than previously reported in the literature. In addition to designing a machine learning algorithm, we also develop an app called 'Deep Retina.' Equipped with a handheld ophthalmoscope, the average person can take fundus images by themselves and obtain an immediate result, calculated by our algorithm. It is beneficial for home care, remote medical care, and self-examination.
关键词： deep convolutional neural network,mobile app,fractional max-pooling,support vector machine,diabetic retinopathy,fundus images,teaching-learning-based optimization
更新于2025-09-23 15:23:52
-
Deep structure tensor graph search framework for automated extraction and characterization of retinal layers and fluid pathology in retinal SD-OCT scans
摘要： Maculopathy is a group of retinal disorders that affect macula and cause severe visual impairment if not treated in time. Many computer-aided diagnostic methods have been proposed over the past that automatically detect macular diseases. However, to our best knowledge, no literature is available that provides an end-to-end solution for analyzing healthy and diseased macular pathology. This paper proposes a vendor-independent deep convolutional neural network and structure tensor graph search-based segmentation framework (CNN-STGS) for the extraction and characterization of retinal layers and fluid pathology, along with 3-D retinal profiling. CNN-STGS works by first extracting nine layers from an optical coherence tomography (OCT) scan. Afterward, the extracted layers, combined with a deep CNN model, are used to automatically segment cyst and serous pathology, followed by the autonomous 3-D retinal profiling. CNN-STGS has been validated on publicly available Duke datasets (containing a cumulative of 42,281 scans from 439 subjects) and Armed Forces Institute of Ophthalmology dataset (containing 4,260 OCT scans of 51 subjects), which are acquired through different OCT machinery. The performance of the CNN-STGS framework is validated through the marked annotations, and it significantly outperforms the existing solutions in various metrics. The proposed CNN-STGS framework achieved a mean Dice coefficient of 0.906 for segmenting retinal fluids, along with an accuracy of 98.75% for characterizing cyst and serous fluid from diseased retinal OCT scans.
关键词： convolutional neural network (CNN),Optical coherence tomography (OCT),maculopathy,ophthalmology,graph search
更新于2025-09-23 15:23:52
-
Remote sensing images super-resolution with deep convolution networks
摘要： Remote sensing image data have been widely applied in many applications, such as agriculture, military, and land use. It is difficult to obtain remote sensing images in both high spatial and spectral resolutions due to the limitation of implements in image acquisition and the law of energy conservation. Super-resolution (SR) is a technique to improve the resolution from a low-resolution (LR) to a high-resolution (HR). In this paper, a novel deep convolution network (DCN) SR method (SRDCN) is proposed. Based on hierarchical architectures, the proposed SRDCN learns an end-to-end mapping function to reconstruct an HR image from its LR version; furthermore, extensions of SRDCN based on residual learning and multi scale version are investigated for further improvement, namely Developed SRDCN(DSRDCN) and Extensive SRDCN(ESRDCN). Experimental results using different types of remote sensing data (e.g., multispectral and hyperspectral) demonstrate that the proposed methods outperform the traditional sparse representation based methods.
关键词： Convolution neural network,Remote sensing imagery,Super-resolution
更新于2025-09-23 15:23:52
-
Disparate effects of DOM extracted from coastal seawaters and freshwaters on photodegradation of 2,4-Dihydroxybenzophenone
摘要： As the rapid development of deep learning techniques, extensive interest has been taken into the applications of deep learning methods on challenging problems of different domains. In view of the recent success of convolutional neural network (CNN) in various tasks of audio analysis, a comparative performance study of different the-state-of-the-art CNN architectures on a large-scale whale-call classification task is investigated in this paper. On the basis of deep neural network models, distinctive features of whale sub-populations are extracted to obtain higher level abstract representations for the accurate classification, which is significantly superior to the traditional classification approaches using manual features based on expert knowledge. In particular, a large open-source acoustic dataset recorded by audio sensors carried by whales in different locations is employed for performance comparison. Based on the experiments, it is found that the advancement of popular CNN architectures significantly improve the accuracy on the whale-call classification task. The accuracy and computational efficiency varies with the change of the CNN architectures. Xception provides the best performance among all four CNN architectures while an ensemble of CNN models can produce even better results.
关键词： deep learning,whale call classification,convolutional neural network
更新于2025-09-23 15:23:52
-
DeepSpectra: An end-to-end deep learning approach for quantitative spectral analysis
摘要： Learning patterns from spectra is critical for the development of chemometric analysis of spectroscopic data. Conventional two-stage calibration approaches consist of data preprocessing and modeling analysis. Misuse of preprocessing may introduce artifacts or remove useful patterns and result in worse model performance. An end-to-end deep learning approach incorporated Inception module, named DeepSpectra, is presented to learn patterns from raw data to improve the model performance. DeepSpectra model is compared to three CNN models on the raw data, and 16 preprocessing approaches are included to evaluate the preprocessing impact by testing four open accessed visible and near infrared spectroscopic datasets (corn, tablets, wheat, and soil). DeepSpectra model outperforms the other three convolutional neural network models on four datasets and obtains better results on raw data than in preprocessed data for most scenarios. The model is compared with linear partial least square (PLS) and nonlinear artificial neural network (ANN) methods and support vector machine (SVR) on raw and preprocessed data. The results show that DeepSpectra approach provides improved results than conventional linear and nonlinear calibration approaches in most scenarios. The increased training samples can improve the model repeatability and accuracy.
关键词： model accuracy,Inception,convolutional neural network,chemometrics,repeatability
更新于2025-09-23 15:23:52