Characteristics Of Image Data Research Articles

Hybrid soil strength prediction model for geotechnical ground investigation using convolutional neural network and ensemble learning

Abstract A hybrid model of soil strength prediction from the image data and feature data of soil was proposed, which is aimed at providing an efficient solution in geotechnical ground investigation by leveraging the power of AI. In this model, CNN purely with the encoder was used to establish the relationship between image data and strength parameters of soil, while ensemble learning stacked of three base learners, i.e., KNN, LASSO, and LSVM, was applied to the feature data. Then, the CNN part and the ensemble learning part were integrated into the loss function. Results show that the convergence of the hybrid model was slower than that of the ensemble learner. However, with the aid of soil image which has more features of soil in essence, the predicted soil strengths by the hybrid model better matched with the actual ones, compared with the ensemble learner and base learners. This hybrid model offers an effective framework of multi-modal data fusion for geotechnical engineering, by leveraging the synergy of the high-dimensional feature extraction capabilities of CNN and the generalization abilities of ensemble learning.

Discrete-Time Visual Servoing Control with Adaptive Image Feature Prediction Based on Manipulator Dynamics.

In this paper, a practical discrete-time control method with adaptive image feature prediction for the image-based visual servoing (IBVS) scheme is presented. In the discrete-time IBVS inner-loop/outer-loop control architecture, the time delay caused by image capture and computation is noticed. Considering the dynamic characteristics of a 6-DOF manipulator velocity input system, we propose a linear dynamic model to describe the motion of a robot end effector. Furthermore, for better estimation of image features and smoothing of the robot's velocity input, we propose an adaptive image feature prediction method that employs past image feature data and real robot velocity data to adopt the prediction parameters. The experimental results on a 6-DOF robotic arm demonstrate that the proposed method can ensure system stability and accelerate system convergence.

Image-Based Subtype Classification for Glioblastoma Using Deep Learning: Prognostic Significance and Biologic Relevance.

To apply deep learning algorithms to histopathology images, construct image-based subtypes independent of known clinical and molecular classifications for glioblastoma, and produce novel insights into molecular and immune characteristics of the glioblastoma tumor microenvironment. Using whole-slide hematoxylin and eosin images from 214 patients with glioblastoma in The Cancer Genome Atlas (TCGA), a fine-tuned convolutional neural network model extracted deep learning features. Biclustering was used to identify subtypes and image feature modules. Prognostic value of image subtypes was assessed via Cox regression on survival outcomes and validated with 189 samples from the Clinical Proteomic Tumor Analysis Consortium (CPTAC) data set. Morphological, molecular, and immune characteristics of glioblastoma image subtypes were analyzed. Four distinct subtypes and modules (imClust1-4) were identified for the TCGA patients with glioblastoma on the basis of the image feature data. The glioblastoma image subtypes were significantly associated with overall survival (OS; P = .028) and progression-free survival (P = .003). Apparent association was also observed for disease-specific survival (P = .096). imClust2 had the best prognosis for all three survival end points (eg, after 25 months, imClust2 had >7% surviving patients than the other subtypes). Examination of OS in the external validation using the unseen CPTAC data set showed consistent patterns. Multivariable Cox analyses confirmed that the image subtypes carry unique prognostic information independent of known clinical and molecular predictors. Molecular and immune profiling revealed distinct immune compositions of the tumor microenvironment in different image subtypes and may provide biologic explanations for the patterns in patients' outcomes. Our image-based subtype classification on the basis of deep learning models is a novel tool to refine risk stratification in cancers. The image subtypes detected for glioblastoma represent a promising prognostic biomarker with distinct molecular and immune characteristics and may facilitate developing novel, individualized immunotherapies for glioblastoma.

KNEE REPLACEMENT RISK PREDICTION MODELING fOR KNEE OSTEOARTHRITIS USING CLINICAL AND MAGNETIC RESONANCE IMAGE FEATURES: DATA FROM THE OSTEOARTHRITIS INITIATIVE

This study aims to develop effective predictive models to assess knee replacement (KR) risk in knee osteoarthritis (KOA) patients, which is important in the personalized diagnosis, assessment, and treatment of KOA. A total of 269[Formula: see text]KOA patients were selected from the osteoarthritis initiative (OAI) public database and their clinical and knee cartilage image feature data were included in this study. First, the clinical risk factors were screened using univariate Cox regression and then used in the construction of the Clinical model. Next, their image features were selected using univariate and least absolute shrinkage and selection operator (LASSO) Cox methods step by step, and then used in the construction of the Image model. Finally, the Image+Clinical model was constructed by combining the Image model and clinical risk factors, which was then converted into a nomogram for better visualization and future clinical use. All models were validated and compared using the metric of C-index. In addition, Kaplan–Meier (KM) survival curve with log-rank test and calibration curve were also included in the assessment of the model risk stratification ability and prediction consistency. Age and three Western Ontario and McMaster Universities (WOMAC) scores were found significantly correlated with KR, and thus included in Clinical model construction. Fifty-eight features were selected from 92[Formula: see text]knee cartilage image features using univariate cox, and four image features were retained using the LASSO Cox method. Image+Clinical model and nomogram were finally constructed by combining clinical risk factors and the Image model. Among all models, the Image+Clinical model showed the best predictive performance, and the Image model was better than the Clinical model in the KR risk predictive consistency. By determining an optimal cutoff value, both Image and Image+Clinical models could effectively stratify the KOA patients into KR high-risk and low-risk groups (log-rank test: [Formula: see text]). In addition, the calibration curves also showed that model predictions were in excellent agreement with the actual observations for both 3-year and 6-year KR risk probabilities, both in training and test sets. The constructed model and nomogram showed excellent risk stratification and prediction ability, which can be used as a useful tool to evaluate the progress and prognosis of KOA patients individually, and guide the clinical decision-making of KOA treatment and prognosis.

Improved CNN-based CatBoost model for license plate remote sensing image classification

The rapid development of artificial intelligence technology has brought profound technical changes to many traditional industries, among which intelligent transportation has become a hot spot for development in the traditional transportation field. Remote sensing license plate image recognition technology is extensively emphasized in such domains as intelligent transportation and intelligent vehicle management. However, in the practical traffic environment, low visibility scenes caused by complex environmental factors such as rain, snow, haze and cloudy days influence the recognition and classification of license plates, while the distortion of license plate images that may be caused by irregular movements of vehicles bring challenges to license plate recognition classification. The CNN-CatBoost model proposed in this paper divides the license plate recognition classification into two stages. The first stage uses the excellent performance of convolutional neural network in processing image data to extract various license plate image features; the second stage uses the CatBoost module to further process the image feature data and finally obtain the remote sensing license plate information. The model achieves outstanding results in the experiments and has practical application value. Through comparison with other network models, the CNN-CatBoost model proposed in this paper has superior performance.

Automatic Classification Method for Oracle Images based on Deep Learning

There are some problems in oracle image classification, such as high image-feature extraction error and low classification accuracy, which leads to low efficiency. Therefore, we designed an automatic classification method for oracle images based on deep learning. The clustering center of an oracle image is determined using k-means algorithm. The obtained oracle image block is used as parallel input to extract a dictionary. The oracle image features are output through a feature mapping function for feature extraction. The CS algorithm is used to reduce the dimension of the oracle image, and the oracle feature compressed sensing signal is sparse under a certain basis for preprocessing of image features. The center of six feature points in the features is used to describe the center of the feature points of the whole oracle image, to determine the position change state of the feature points, and to characterize the key features of the image to achieve the target alignment of oracle image feature points. Based on this, the image feature data are learned using a transfer learning model. The automatic classifier was constructed through a convolution neural network. Experimental results show that the proposed method can effectively reduce the error of image feature extraction and improve the classification accuracy. At the application level, the research results of this paper have brought great improvement to the performance of oracle image classification technology. At the theoretical level, this research introduces k-means and CS algorithms to oracle image classification technology based on deep learning and makes an effective exploration in the direction of this technological progress.

Vision-based Inspection of PCB Soldering Defects

Vision-based inspection of printed circuit board (PCB) soldering defects was studied for preparing feature data and classifying the overall PCB soldering defects on a PCB prototype into different classes. The image data of overall PCB soldering defects on a PCB prototype was developed using an image sensor camera. Image data augmentation was conducted to enhance the dataset volume. Image pre-processing included image resizing, image colour conversion, and image denoising. Watershed-based image segmentation was performed in the image post-processing to segmented images; then, feature extraction was conducted using curvelet transform to prepare image feature data. The feature data as the statistical data include kurtosis, contrast, energy, homogeneity, and variance. These data were analysed, and the percentage difference of mean values of statistical data between image classes was calculated. Kurtosis had the highest percentage difference among the statistical data. In the comparison of the mean values, kurtosis obtained 4.97% difference for the class of good and medium condition; 17.02% difference for the good and bad condition; and 12.08% difference for the bad and medium condition. Through this analysis, kurtosis is considered more reliable data for the machine-learning based classification in this project. The extracted data can be applied in future studies to classify overall solder joint defects on a PCB prototype by artificial neural network in machine learning classification.

Application of GIS Technology-Supported Cross Media Fusion Method Based on Deep Learning in Landscape Performance Evaluation.

GIS technology can provide reasonable and sustainable data support for landscape planning and ecological development and make wetland landscape planning consider the spatial layout of landscape and the optimal allocation of resources more. The key technologies of cross media intelligence mainly focus on intelligent information retrieval, analysis and reasoning, knowledge map construction, and intelligent storage. Convolutional neural network (CNN), as one of the representative algorithms of deep learning, plays an important role in retrieving landscape data and extracting image and text features across media. Further retrieval of media data, in-depth text processing, and image feature data extraction are realized by using deep learning technology, and comprehensive in-depth analysis is carried out by combining landscape plane images, three-dimensional images, and vector information in GIS technology. Provide quantitative information for the evaluation system of human landscape, economy, history, and region, so as to formulate a scientific and reasonable performance evaluation system.

Detection storage time of mild bruise’s yellow peaches using the combined hyperspectral imaging and machine learning method

To deduce the process of bruise and reduce the number of bruised fruits from the source, the storage time of yellow peaches after bruise should be identified. In order to distinguish the different storage times of mild bruise’s yellow peaches more effectively than current detection methods, the combined hyperspectral imaging and machine learning method was proposed. Firstly, the sample bruise region spectrum was extracted as spectral features, and then, the hyperspectral images were processed by Principal Component Analysis (PCA), and eight single-wavelength images were selected according to the weight coefficient curve of PC1 images, and the gray values of the selected images were calculated as image features. Finally, in order to find the optimal discriminative model, random forest (RF), support vector machine (SVM), and extreme gradient boosting (XGBoost) models were built based on spectral features, image features, and spectral features combined with image features, respectively. The results show that the XGBoost models based on spectral features, image features, and spectral features combined with image features are the optimal models with the overall accuracy of 77.50%, 87.50% and 90.00%, respectively. To simplify the model, Competitive Adaptive Reweighted Sampling (CARS) algorithm was used to screen the wavelength of the normalized spectral data, and then they were fused with the image feature data again and the XGBoost model with an overall model accuracy of 95.00% was built. To sum up, the combined hyperspectral imaging and machine learning method can be used to distinguish the different storage times (2 h, 8 h, 24 h and 48 h) of mild bruise’s yellow peaches effectively. It provides a certain theoretical basis for hyperspectral imaging technology in fruit bruise detection.

Short-Term Stock Price Prediction Based on CAE-LSTM Method

Artificial intelligence methods are important tools for mining information for forecasting in the stock market. Most of the literature related to short-term stock price prediction focuses on the technical data, but in the real market, many individual investors make investment decisions more from stock price shape characteristics rather than specific stock price values. Compared with traditional measurement methods, deep neural networks perform better in processing high-dimensional complex data such as images. This paper proposes a model that combines CAE (convolutional autoencoder) and LSTM (long short-term memory) neural network, uses CAE to extract stock price image feature data, and combines technical data to predict short-term stock prices. The results show that the CAE-LSTM model, based on stock price image morphological feature data and technical data, performs well in short-term stock price prediction and has good generalization ability. The root mean square error of the CAE-LSTM model decreased by about 4% from that of LSTM. CAE-LSTM models have better predictive power than LSTM models that only use technical indicator data as valid inputs.

Key Technology of the Medical Image Wise Mining Method Based on the Meanshift Algorithm.

Mean-shift originally refers to the mean vector of the offset. The algorithm idea is to assume that the data sets of different clusters conform to different probability density distributions, and the area with high sample density corresponds to the center of the cluster. With the wide application of hospital information system, especially the popularity of the meanshift algorithm in the outpatient system, it has greatly improved the efficiency of medical staff. Medical imaging refers to the technology and process of obtaining internal tissue images of the human body or a certain part of the human body in a noninvasive manner for medical treatment or medical research. It contains the following two relatively independent research directions: medical imaging system and medical image processing. In this paper, we expect to improve the mining ability of medical image information with the help of the meanshift algorithm based on the key technology of the medical image intelligent mining algorithm. This paper proposes a method to enhance image feature extraction and data mining and how to apply relevant analysis rules for mining. Applying this integrated algorithm to extract simplified rules is more beneficial to people's understanding than the raw data and helps doctors quickly understand the patient's condition.

The Stereo Communication Method of Artistic Visual Image Based on CAD Platform

Due to the large amount of noise in the image background, the traditional methods have the problems of poor image communication effect, slow image communication efficiency, and poor noise processing effect. A three-dimensional communication method of art visual image based on CAD platform is proposed. Wavelet transform is used to extract artistic visual image features, and the fuzzy clustering method is used to standardize the obtained image feature data. Based on the data processing results, the CAD platform is constructed, the software program is designed, and the image chain coding is realized at the same time. The particle swarm optimization algorithm is used to convey the image of the obtained CAD general vectorization file, so as to complete the three-dimensional transmission of artistic visual image. The experimental results show that the image communication effect of this method is better, the image communication efficiency is higher, the noise suppression effect is better, the visual communication effect of the image is improved, and the performance of the designed method is superior.

Data Security Protection Mechanism of Video and Image Feature Modeling Based on Domestic Crypto Algorithm

Video and image monitoring is increasingly appearing in our home, travel and other aspects. Through video and image analysis and comparison of video and image monitoring data, it can provide strong analysis support capabilities for social security prevention and control, traffic command, safety production and so on. Video and image feature modeling is a necessary prerequisite for video and image analysis and comparison. Video and image feature modeling forms video and image feature data. Video and image feature data reflects the most essential information of various elements such as people, vehicles and objects. However, video and image data is easy to be damaged, changed and leaked in the process of collection, aggregation, analysis, modeling and storage, Facing data security risks. This paper proposes a set of video and image feature modeling data security protection mechanism based on domestic algorithm to realize the whole process encryption protection of data acquisition, transmission and storage.

Gesture Recognition of Somatosensory Interactive Acupoint Massage Based on Image Feature Deep Learning Model

During rehabilitation, many postoperative patients need to perform autonomous massage on time and on demand. Thus, this paper develops an individualized, intelligent, and independent rehabilitation training system for based on image feature deep learning model acupoint massage that excludes human factors. The system, which innovatively integrates massage gesture recognition with human pose recognition. It relies on the binocular depth camera Kinect DK and Google MediaPipe Holistic pipeline to collect the real-time image feature data on joints and gestures of the patient in autonomous massage. Then the system calculates the coordinates of each finger joint, and computes the human poses with VGG-16, a convolutional neural network (CNN); the calculated results are translated, and presented in a virtual reality (VR) model based on Unity 3D, aiming to guide the patient actions in autonomous massage. This is because the image feature of the gesture recognition and pose recognition is hindered, when the hand or the human is occluded by the body or other things, owing to the limited recognition range of the hardware. The experimental results show that, the proposed system could correctly recognize up to 84% of non-occluded gestures, and up to 93% of non-occluded poses; the system also exhibited a good real-time performance, a high operability, and a low cost. Facing the lack of medical staff, our system can effectively improve the life quality of patients.

Classification and Recognition of Crops Based on GIS Image

Today, due to the rapid development of science and technology, new science and technology constantly change the status of agriculture, precision agriculture is developing rapidly. Precision agriculture is the combination of three new technologies: Global Positioning System (GPS), Remote Sensing Technology (RS) and Geographic Information System (GIS). In the 3S technology, GIS technology is the basis of realizing the other two technologies. It is a platform to achieve precision agriculture, supporting the input, analysis and output of agricultural resources data and other functions of precision agriculture. Classification and recognition of crop types is one of the most basic applications of precision agriculture. It can extract information from remote sensing images, accurately identify crop types and determine crop growth. In this paper, 7200 remote sensing image samples are divided into two groups: learning group and testing group. Combined with GIS image and RS technology, the characteristics of these four crops were summarized and counted through feature image extraction and feature data analysis of 5200 study group samples in GIS system. 2000 samples in the test group were used to calculate the recognition rate. Through experiments, we can know the recognition rate of peanut, spring maize, sweet potato and summer maize. The highest recognition rate is 98.60%, the lowest recognition rate is 90.20%, and the total recognition rate is 94.10%. It shows that in this experiment, the crop recognition rate of remote sensing image is very high in the application of classification and recognition based on GIS crop images. During the period when the spectral characteristics are very obvious, the recognition rate of crops in remote sensing images is higher, and the total recognition rate is increased by 3.98%. The NDVI values of crops in remote sensing images were analyzed and calculated, and the NDVI values of four crops in each growing period were obtained. By studying the NDVI value, we can determine the types of four crops and their growth period, and the accuracy of determining the types of crops is higher than that of determining the growth period of crops. Through the classification and identification of crop species and crop growth period, two experiments verify that the combination of GIS image and remote sensing image can improve the recognition accuracy of crop classification and identification, and the use of geospatial data in GIS can identify the differences between crops. By combining GIS images with remote sensing images, the development of precision agriculture can be promoted, and the reference for agricultural production and agricultural structure adjustment in designated areas can be provided.

Ground-Level Mapping and Navigating for Agriculture Based on IoT and Computer Vision

Autonomous agricultural systems are a promising solution to bridge the gap between labor shortage for agriculture tasks and the continuing needs for increasing productivity in agriculture. Automated mapping and navigation system will be a cornerstone of most autonomous agricultural system. Accordingly, we propose a ground-level mapping and navigating system based on computer vision technology (Mesh Simultaneous Localization and Mapping algorithm, Mesh-SLAM) and Internet of Things (IoT), to generate a 3D farm map on both the edge side and cloud. The innovation of this system includes three layers as sub-systems that are 1) ground-level robot vehicles’ layer for conducting frames collection only with a monocular camera, 2) edge node layer for image feature data edge computing and communication, and 3) cloud layer for general management and deep computing. High efficiency and speed of mapping stage are enabled by making the robot vehicles directly stream continuous frames to their corresponding edge node. Then each edge node, that coordinate a certain range of robots, applies a new Mesh-SLAM frame by frame, whose core is reconstructing the features map by a mesh-based algorithm with scalable units and reduce the feature data size by a filtering algorithm. Additionally, the cloud-computing allows comprehensive arrangement and heavily deep computing. The system is scalable to larger-scale fields and more complex environment by taking advantage of dynamically distributing the computation power to edges. Our evaluation indicates that: 1) this Mesh-SLAM algorithm outperforms in mapping and localization precision, accuracy, and yield prediction error (resolution at centimeter); and 2) The scalability and flexibility of the IoT architecture make the system modularized, easy adding/removing new functional modules or IoT sensors. We conclude the trade-off between cost and performance widely augments the feasibility and practical implementation of this system in real farms.

Dynamic monitoring of landscape vegetation coverage based on EM-MAP-NDVI fusion algorithm

Due to the complexity of the detection types of urban landscape vegetation, the existing methods have the problem of unclear image feature classification, which leads to the low accuracy of dynamic monitoring of landscape vegetation coverage. A dynamic monitoring method of urban landscape vegetation coverage based on EM-MAP-NDVI fusion algorithm is proposed. The multi-source remote sensing image feature data and vegetation dynamic characteristics of landscape vegetation are obtained. The expectation maximisation (EM) algorithm is used to estimate the vegetation coverage parameters. The problem of vegetation image feature classification is transformed into the problem of maximum posterior probability (MAP), and the dynamic monitoring results of vegetation coverage are calculated. The experimental results show that the proposed method can effectively improve the accuracy of urban landscape vegetation feature extraction and achieve high-precision dynamic monitoring of urban landscape vegetation coverage, which has good application value.

Dynamic monitoring of landscape vegetation coverage based on EM-MAP-NDVI fusion algorithm

Due to the complexity of the detection types of urban landscape vegetation, the existing methods have the problem of unclear image feature classification, which leads to the low accuracy of dynamic monitoring of landscape vegetation coverage. A dynamic monitoring method of urban landscape vegetation coverage based on EM-MAP-NDVI fusion algorithm is proposed. The multi-source remote sensing image feature data and vegetation dynamic characteristics of landscape vegetation are obtained. The expectation maximisation (EM) algorithm is used to estimate the vegetation coverage parameters. The problem of vegetation image feature classification is transformed into the problem of maximum posterior probability (MAP), and the dynamic monitoring results of vegetation coverage are calculated. The experimental results show that the proposed method can effectively improve the accuracy of urban landscape vegetation feature extraction and achieve high-precision dynamic monitoring of urban landscape vegetation coverage, which has good application value.

Quantitative analysis of wheat maltose by combined terahertz spectroscopy and imaging based on Boosting ensemble learning

To improve the prediction accuracy of existing data modeling that is based on either spectral data or image data alone, we herein propose a method for the quantitative analysis of wheat maltose contents based on the fusion of terahertz spectroscopy and terahertz imaging, which allows features and balance fusion information to be extracted from the data, and fusion modeling of the feature information to be conducted. Moreover, a Boosting-based, novel multivariate data fusion method and a Boosting iteration termination index based on the structural risk minimization theory are proposed to achieve automatic optimization of the basic model parameters of least squares support vector machines (LS-SVMs). The best results were obtained with data fusion combining spectroscopy and image feature data, with classification performances better than those obtained on single analytical sources, thereby indicating that the multivariate data fusion method proposed is an effective method for the quantitative detection of maltose content in wheat. Furthermore, four unknown maltose concentration wheat samples are analyzed quantitatively using proposed model.

A Deep Learning Fusion Recognition Method Based On SAR Image Data

In view of the research status and existing problems of synthetic aperture radar (SAR) target recognition, a new method of deep learning fusion recognition is proposed. Firstly, the 1-D features extracted with principle component analysis(PCA) are used as the input of the stacked autoencoder(SAE) network to extract deep features, which achieves target recognition based on 1-D PCA feature data. Then, the SAR target images are used as the input of convolutional neural network(CNN) to extract deep features, which achieves target recognition based on 2-D SAR image feature data. Finally, a deep learning recognition algorithm of decision-level and feature-level fusion is proposed for the diferent kinds of SAR image feature data. The experiment analysis shows that the proposed method of deep learning fusion recognition in this paper is adaptive and robust to the attitude angle, background and noise.