Average Similarity Coefficient Research Articles

A numerical study on the siphonic effect of enhanced external counterpulsation at lower extremities with a coupled 0D-1D closed-loop personalized hemodynamics model

Enhanced external counterpulsation (EECP) is a treatment and rehabilitation approach for ischemic diseases, including coronary artery disease. Its therapeutic benefits are primarily attributed to the improved blood circulation achieved through sequential mechanical compression of the lower extremities. However, despite the crucial role that hemodynamic effects in the lower extremity arteries play in determining the effectiveness of EECP treatment, most studies have focused on the diastole phase and ignored the systolic phase. In the present study, a novel siphon model (SM) was developed to investigate the interdependence of several hemodynamic parameters, including pulse wave velocity, femoral flow rate, the operation pressure of cuffs, and the mean blood flow changes in the femoral artery throughout EECP therapy. To verify the accuracy of the SM, we coupled the predicted afterload in the lower extremity arteries during deflation using SM with the 0D-1D patient-specific model. Finally, the simulation results were compared with clinical measurements obtained during EECP therapy to verify the applicability and accuracy of the SM, as well as the coupling method. The precision and reliability of the previously developed personalized approach were further affirmed in this study. The average waveform similarity coefficient between the simulation results and the clinical measurements during the rest state exceeded 90%. This work has the potential to enhance our understanding of the hemodynamic mechanisms involved in EECP treatment and provide valuable insights for clinical decision-making.

A comparative analysis of colour-emotion associations in 16-88-year-old adults from 31 countries.

As people age, they tend to spend more time indoors, and the colours in their surroundings may significantly impact their mood and overall well-being. However, there is a lack of empirical evidence to provide informed guidance on colour choices, irrespective of age group. To work towards informed choices, we investigated whether the associations between colours and emotions observed in younger individuals also apply to older adults. We recruited 7393 participants, aged between 16 and 88 years and coming from 31 countries. Each participant associated 12 colour terms with 20 emotion concepts and rated the intensity of each associated emotion. Different age groups exhibited highly similar patterns of colour-emotion associations (average similarity coefficient of .97), with subtle yet meaningful age-related differences. Adolescents associated the greatest number but the least positively biased emotions with colours. Older participants associated a smaller number but more intense and more positive emotions with all colour terms, displaying a positivity effect. Age also predicted arousal and power biases, varying by colour. Findings suggest parallels in colour-emotion associations between younger and older adults, with subtle but significant age-related variations. Future studies should next assess whether colour-emotion associations reflect what people actually feel when exposed to colour.

Distribution Patterns and Determinants of Invasive Alien Plants in China.

In recent years, invasive alien plants (IAPs) have caused serious ecological disasters and economic losses in China. This study combined three IAP species richness-related indices (species richness of IAPs, first records of IAPs, and the relative species richness of IAPs), as well as indices reflecting distribution and dispersal patterns (average similarity coefficient of IAPs) and invasiveness (average risk score of IAPs), to conduct an integrated regional-invasion risk assessment based on the principal component analysis (PCA) method. Partial least-squares (PLS) regression was conducted to explore the explanatory power of 12 environmental and anthropogenic factors on different invasion indices. The results indicated that coastal provinces and Yunnan had high IAP introduction risk, as well as high synthetic-risk scores. The dispersal of IAPs in mid-latitude provinces should be particularly prevented. For species richness of IAPs, more environmental factors with variable importance for the project (VIP) values higher than 1 were retained in the optimal model, reflecting the importance of environmental filtering on IAPs. Visitors were the most important predictor for first records of IAPs. Compared to species richness (R2 = 79.5%), first records were difficult to predict (R2 = 60.4%) and were influenced by anthropogenic factors. There was spatial distribution congruence of various families of IAPs. Generally, the correlations of the residuals of species richness were still significant, with 0.421 (p < 0.05) as the lowest Pearson correlation coefficient, which indicated that external factors could not fully explain the spatial distribution congruence. These findings could enrich the relevant research on IAP invasion mechanisms and provide suggestions for regional IAP detection and response.

Structure of a semantic segmentation-based defect detection network for laser cladding infrared images

While selecting the most suitable infrared thermal imaging detection scheme for online inspection during laser cladding processing, this paper designs the RespathU-net semantic segmentation defect detection network for cladding coating defects in infrared images. The network is based on the U-net network framework. It is optimized and improved by redesigning the coding network structure, expanding the network perceptual field, and connecting the paths of residuals, thus enhancing the segmentation effect on the defective areas of the melt coating by addressing the problems that the original network cannot realize the end-to-end output and the poor segmentation effect on the complex objects. The generalization performance test and defect detection experiment of the RespathU-net network were conducted using the Kolektor SDD dataset and the infrared dataset constructed in this paper. The designed network is compared with fully convolutional networks, SegNet, U-net, and DeepLab_V3 in terms of average exchange ratio, similarity coefficient, and running time. The results show that the proposed RespathU-net achieves good multi-size feature recognition, and the effect is much better than other semantic segmentation networks. The via experimental results verify that the actual defect detection accuracy of the designed network is 87.01% .

Horizontal Geolocation Error Evaluation and Correction on Full-Waveform LiDAR Footprints via Waveform Matching

The geolocation accuracy of spaceborne LiDAR (Light Detection And Ranging) data is important for quantitative forest inventory. Geolocation errors in Global Ecosystem Dynamics Investigation (GEDI) footprints are almost unavoidable because of the instability of orbital parameter estimation and GNSS (Global Navigation Satellite Systems) positioning accuracy. This study calculates the horizontal geolocation error of multiple temporal GEDI footprints using a waveform matching method, which compares original GEDI waveforms with the corresponding simulated waveforms from airborne LiDAR point clouds. The results show that the GEDI footprint geolocation error varies from 3.04 m to 65.03 m. In particular, the footprints from good orbit data perform better than those from weak orbit data, while the nighttime and daytime footprints perform similarly. After removing the system error, the average waveform similarity coefficient of multi-temporal footprints increases obviously in low-waveform-similarity footprints, especially in weak orbit footprints. When the waveform matching effect is measured using the threshold of the waveform similarity coefficient, the waveform matching method can significantly improve up to 32% of the temporal GEDI footprint datasets from a poor matching effect to a good matching effect. In the improvement of the ratio of individual footprint waveform similarity, the mean value of the training set and test set is about two thirds, but the variance in the test set is large. Our study first quantifies the geolocation error of the newest version of GEDI footprints (Version 2). Future research should focus on the improvement of the detail of the waveform matching method and the combination of the terrain matching method with GEDI waveform LiDAR.

Computer-Aided Diagnosis System for Blood Diseases Using EfficientNet-B3 Based on a Dynamic Learning Algorithm.

The immune system's overproduction of white blood cells (WBCs) results in the most common blood cancer, leukemia. It accounts for about 25% of childhood cancers and is one of the primary causes of death worldwide. The most well-known type of leukemia found in the human bone marrow is acute lymphoblastic leukemia (ALL). It is a disease that affects the bone marrow and kills white blood cells. Better treatment and a higher likelihood of survival can be helped by early and precise cancer detection. As a result, doctors can use computer-aided diagnostic (CAD) models to detect early leukemia effectively. In this research, we proposed a classification model based on the EfficientNet-B3 convolutional neural network (CNN) model to distinguish ALL as an automated model that automatically changes the learning rate (LR). We set up a custom LR that compared the loss value and training accuracy at the beginning of each epoch. We evaluated the proposed model on the C-NMC_Leukemia dataset. The dataset was pre-processed with normalization and balancing. The proposed model was evaluated and compared with recent classifiers. The proposed model's average precision, recall, specificity, accuracy, and Disc similarity coefficient (DSC) were 98.29%, 97.83%, 97.82%, 98.31%, and 98.05%, respectively. Moreover, the proposed model was used to examine microscopic images of the blood to identify the malaria parasite. Our proposed model's average precision, recall, specificity, accuracy, and DSC were 97.69%, 97.68%, 97.67%, 97.68%, and 97.68%, respectively. Therefore, the evaluation of the proposed model showed that it is an unrivaled perceptive outcome with tuning as opposed to other ongoing existing models.

Genetic relationship and diversity among some Moroccan and introduced rapeseed (Brassica napus L.) varieties as revealed by molecular markers

Rapeseed (Brassica napus L.) crop can be a lever for the development of oilseed sector in Morocco due to its adaptation to local conditions and its major economic and food importance. Genetic diversity and selection of valuable crossing parents are the key to successful breeding and improvement of this crop. In this regard, genetic variation within the existing germplasm must be explored and characterized. Therefore, the present study was carried out to investigate the genetic diversity among 22 varieties from Morocco as well as other origins, using twenty ISSR primers. The selected primers have generated a total of 319 markers. Polymorphic amplified bands varied from 8 to18, with an average of 13 per primer. The diversity index (PIC value) ranged from 0.295 to 0.509, with a mean value of 0.37 per primer, indicating a good genetic diversity level for the primers used. The average similarity coefficient was 0.31, fluctuating between 0.176 and 0.456, and the pairwise comparison of the studied varieties showed a great discriminating power of primers and a large genetic diversity among accessions. A total of eight ISSR primers could be identified as key to rapeseed varietal determination. Hierarchical classification allowed identifying three groups with some phylogeographic structuring. This is the first report of molecular characterization of rapeseed germplasm in Morocco and Africa. The obtained results have important implications for management of this germplasm to conserve the existing genetic diversity and use it properly in breeding programs in Morocco as well as in other Mediterranean and African countries.

Computer-Aided Diagnosis for Early Signs of Skin Diseases Using Multi Types Feature Fusion Based on a Hybrid Deep Learning Model

According to medical reports and statistics, skin diseases have millions of victims worldwide. These diseases might affect the health and life of patients and increase the costs of healthcare services. Delays in diagnosing such diseases make it difficult to overcome the consequences of these types of disease. Usually, diagnosis is performed using dermoscopic images, where specialists utilize certain measures to produce the results. This approach to diagnosis faces multiple disadvantages, such as overlapping infectious and inflammatory skin diseases and high levels of visual diversity, obstructing accurate diagnosis. Therefore, this article uses medical image analysis and artificial intelligence to present an automatic diagnosis system of different skin lesion categories using dermoscopic images. The addressed diseases are actinic keratoses (solar keratoses), benign keratosis (BKL), melanocytic nevi (NV), basal cell carcinoma (BCC), dermatofibroma (DF), melanoma (MEL), and vascular skin lesions (VASC). The proposed system consists of four main steps: (i) preprocessing the input raw image data and metadata; (ii) feature extraction using six pre-trained deep learning models (i.e., VGG19, InceptionV3, ResNet50, DenseNet201, and Xception); (iii) features concatenation; and (iv) classification/diagnosis using machine learning techniques. The evaluation results showed an average accuracy, sensitivity, specificity, precision, and disc similarity coefficient (DSC) of around 99.94%, 91.48%, 98.82%, 97.01%, and 94.00%, respectively.

Single channel blind source separation of complex signals based on spatial‐temporal fusion deep learning

Blind Source Separation (BSS) of complex signals composed of radar, communication and jamming signals is the first step in an integrated electronic system, which requires higher accuracy of separation. However, the traditional Single-Channel Blind Source Separation (SCBSS) method has low separation accuracy and poor robustness. Aiming at this problem, this paper proposes a SCBSS method based on spatial-temporal fusion deep learning model. This is a deep neural network model, which realizes spatial-temporal of mixed signals by integrating Convolutional Neural Network (CNN) and Bidirectional Long Short-Term Memory Network (BiLSTM). Convolutional Neural Network is used to extract spatial features from input sequences, and BiLSTM is used to mine timing rules of signals. A batch normalisation layer and a dropout layer are added to improve stability and prevent overfitting. The experiments show that the average similarity coefficient of the separated signals is above 0.99 and the Signal-Distortion Ratio (SDR) is up to 27 dB without noise. When the Signal-Noise Ratio is 0–20 dB and Jamming-Signal Ratio is 15 dB, the SDR is 5–30 dB higher than the traditional methods and the single network structure deep learning methods.

How to measure mental pain: a systematic review assessing measures of mental pain

QuestionAlthough mental pain is present in many mental disorders and is a predictor of suicide, it is rarely investigated in research or treated in care. A valid tool to measure...

Time-Frequency Mask-Aware Bidirectional LSTM: A Deep Learning Approach for Underwater Acoustic Signal Separation.

Underwater acoustic signal separation is a key technique for underwater communications. The existing methods are mostly model-based, and cannot accurately characterize the practical underwater acoustic communication environment. They are only suitable for binary signal separation and cannot handle multivariate signal separation. However, recurrent neural networks (RNNs) show a powerful ability to extract the features of temporal sequences. Inspired by this, in this paper, we present a data-driven approach for underwater acoustic signal separation using deep learning technology. We use a bidirectional long short-term memory (Bi-LSTM) approach to explore the features of a time–frequency (T-F) mask, and propose a T-F-mask-aware Bi-LSTM for signal separation. Taking advantage of the sparseness of the T-F image, the designed Bi-LSTM network is able to extract the discriminative features for separation, which further improves the separation performance. In particular, this method breaks through the limitations of the existing methods and not only achieves good results in multivariate separation but also effectively separates signals when they are mixed with 40 dB Gaussian noise signals. The experimental results show that this method can achieve a 97% guarantee ratio (PSR), and the average similarity coefficient of the multivariate signal separation is stable above 0.8 under high noise conditions. It should be noted that our model can only handle known signals such as test signals for calibration.

Use of SSR Markers for the Exploration of Genetic Diversity and DNA Finger-Printing in Early-Maturing Upland Cotton (Gossypium hirsutum L.) for Future Breeding Program

DNA fingerprinting and genetic diversity analysis of 79 early-maturing upland cotton (Gossypium hirsutum L.) cultivars were performed using Simple Sequence Repeat (SSR) molecular markers. Out of 126 pairs of SSR primers, we selected 71 pairs that gave good polymorphisms and clear bands, had good stability, and showed even distribution on the cotton chromosomes, and 142 polymorphic genotypes were amplified. The average number of alleles amplified with the SSR primers was 2.01. The polymorphism information content (PIC) of the markers ranged from 0.1841 to 0.9043, with an average of 0.6494. The results of fingerprint analysis showed that nine varieties had characteristic bands, and at least six primer pairs could be used to completely distinguish all 79 cotton accessions. Using NTSYS-pc 2.11 cluster analysis, the genetic similarity coefficients between the cotton genotypes ranged from 0.3310 to 0.8705, with an average of 0.5861. All cotton accessions were grouped into five categories at a similarity coefficient of 0.57, which was consistent with the pedigree sources. At the same time, the average genetic similarity coefficients of early-maturing upland cotton varieties in China showed a low-high-low pattern of variation over time, revealing the development history of early-maturing upland cotton varieties from the 1980s to the present. This also indirectly reflects that in recent years, China’s cotton breeders have focused on innovation and have continuously broadened the genetic resources for early-maturing upland cotton.

Macrozoobenthos Community Structure in Situ Cileunca, Pangalengan District, Bandung Regency, West Java

This research aims to determine the structure of the macrozoobenthos community which includes variety, diversity, uniformity, coefficient of similarity and the Family Biotic Index (FBI) macrozoobenthos as well as the physical and chemical parameters of the waters and to determine the pollution status of Situ Cileunca waters. The research was conducted in Situ Cileunca, Bandung Regency, West Java from January to February 2021. The research method used a survey method. The method used in data collection is purposive sampling by determining 5 stations and 4 times. Data analysis in this research uses descriptive analysis. The results showed that the lowest average Biochemical Oxygen Demand (BOD5) value was found at station 4 of 8.90 ±4.92 mg/L and the highest average BOD5 value was found at station 5 of 12.99 ± 6.60 mg/L. There are three species of macrozoobenthos that live in the waters of Situ Cileunca, namely Pomacea canaliculata, Filopaludina javanica and Anodonta woodiana. Macrozoobenthos abundance ranges from 400 - 704 ind/m2. The diversity index of macrozoobenthos is included in the low category, ranging from 0.17 to 0.28. The uniformity value ranged from 0.36 - 0.59 which was classified as moderate in all including except at station 4 which was classified as low. The lowest average similarity coefficient was found between stations 3 and 5 was 0.13 and the highest average similarity coefficient between stations 4 and 5 was 0.30. The index value of the FBI macrozoobenthos ranged from 6.05 to 6.18 with a rather poor category. The pollution status of Situ Cileunca is moderately polluted because the BOD5 value is categorized as moderately polluted, the diversity (H') is classified as heavily polluted and the FBI value is in the rather poor category.

CHARACTERIZATION OF LEAF FEATURES IN SOME BLACKBERRY GENOTYPES COLLECTED FROM THE BLACK SEA REGION

In this study, morphological characterization studies regarding to leaf characteristics (leaf length, leaf width, leaf cross section shape, leaf edge waviness, swelling between leaf veins, leaf tooth depth, dominant leaflet number, leaf shape, green color intensity on the upper part of the leaf and brightness on the upper part of the leaf) were carried out in some blackberry genotypes collected from the Black Sea Region of Turkey, according to the definition lists of UPOV (International Association for the Protection of New Plant Varieties). The measurements and observations made were transformed into feature scores, and using these scores, dendrogram and principal component analysis (PCA) related to morphological features were obtained. In the dendrogram obtained according to the morphological characterization data, the similarity level between the materials was determined between 0.50-1.00 and the average similarity coefficient was found as 0.75. The dendrogram consists of 2 main clusters (A and B). According to the dendrogram, genotypes obtained from Samsun (Çarşamba 1), Samsun (Çarşamba 2) and Ordu (Gülyalı), Bartın (Center) and Rize (Küçükçayır) regions were found to be the closest genotypes with 1.00 similarity level. In addition, as a result of the principal component analysis (PCA), the similarities and differences within the blackberry genotypes were clearly revealed. It was determined that they consisted of three main groups and two outer groups in their distribution on the two-dimensional plot.As a result of the study, it was determined that there is a certain level of variation between blackberry genotypes. The data obtained from this study will help to protect the diversity and to evaluate it with different studies.

A Novel Coarse-to-Fine Sea-Land Segmentation Technique Based on Superpixel Fuzzy C-Means Clustering and Modified Chan-Vese Model

The sea-land segmentation for optical remote sensing images (RSIs) has a valuable role in water resources and coastal zones management. However, it is challenging because optical RSIs mainly suffer from low contrast, intensity inhomogeneity with mixed pixels, and large image size with redundant information. This paper introduces a novel coarse-to-fine sea-land segmentation method that incorporates Superpixel Fuzzy C-Means (SPFCM) and a Modified Chan-Vese active contour model (MCV). First, the image is over-segmented into superpixels to reduce the information redundancy and utilize spectral and spatial information. The SPFCM employs local relationships among neighboring superpixels to cluster the superpixels based on their color and texture features, deal with mixed pixels, and produce coarse segmentation results. The CV depends on the initial contour. If the contour is incorrectly initialized, the CV may trap in local minima and needs many iterations. The purpose of the SPFCM result is to provide an automatic initial contour for an MCV model instead of manual initialization to improve the CV model's performance. Finally, color and texture features are combined in vector-valued images to solve the traditional CV's problems to deal with complicated nature images with intensity inhomogeneity or rich texture features to produce fine segmentation results. The proposed method is evaluated and achieved an average accuracy of 98.9%, an average Jaccard Similarity Coefficient (JSC) equals 97.1%, an average Disc Similarity Coefficient (DSC) equals 98.5%, and an average recall equals 99.3%. The proposed method results are promising, and it outperformed the results of other state-of-the-art sea-land segmentation methods.

Universal Patterns in Color-Emotion Associations Are Further Shaped by Linguistic and Geographic Proximity

Many of us “see red,” “feel blue,” or “turn green with envy.” Are such color-emotion associations fundamental to our shared cognitive architecture, or are they cultural creations learned through our languages and traditions? To answer these questions, we tested emotional associations of colors in 4,598 participants from 30 nations speaking 22 native languages. Participants associated 20 emotion concepts with 12 color terms. Pattern-similarity analyses revealed universal color-emotion associations (average similarity coefficient r = .88). However, local differences were also apparent. A machine-learning algorithm revealed that nation predicted color-emotion associations above and beyond those observed universally. Similarity was greater when nations were linguistically or geographically close. This study highlights robust universal color-emotion associations, further modulated by linguistic and geographic factors. These results pose further theoretical and empirical questions about the affective properties of color and may inform practice in applied domains, such as well-being and design.

Staging Melanocytic Skin Neoplasms Using High-Level Pixel-Based Features

The formation of malignant neoplasm can be seen as deterioration of a pre-malignant skin neoplasm in its functionality and structure. Distinguishing melanocytic skin neoplasms is a challenging task due to their high visual similarity with different types of lesions and the intra-structural variants of melanocytic neoplasms. Besides, there is a high visual likeliness level between different lesion types with inhomogeneous features and fuzzy boundaries. The abnormal growth of melanocytic neoplasms takes various forms from uniform typical pigment network to irregular atypical shape, which can be described by border irregularity of melanocyte lesion image. This work proposes analytical reasoning for the human-observable phenomenon as a high-level feature to determine the neoplasm growth phase using a novel pixel-based feature space. The pixel-based feature space, which is comprised of high-level features and other color and texture features, are fed into the classifier to classify different melanocyte neoplasm phases. The proposed system was evaluated on the PH2 dermoscopic images benchmark dataset. It achieved an average accuracy of 95.1% using a support vector machine (SVM) classifier with the radial basis function (RBF) kernel. Furthermore, it reached an average Disc similarity coefficient (DSC) of 95.1%, an area under the curve (AUC) of 96.9%, and a sensitivity of 99%. The results of the proposed system outperform the results of other state-of-the-art multiclass techniques.

Species Diversity Characteristics of a Natural Pinus taiwanensis Community with Different Diameter Classes and Forest Densities

Pinus taiwanensis is a species endemic to China. This study selected four typical plots of Pinus taiwanensis in the natural secondary forest around Macheng City, in order to reveal the characteristics of and the relationships between different diameter classes (determined based on the diameter at breast height or DBH), forest densities and species diversity, as well as the similarities of species diversity of different plots within the community. The result showed that Pinus taiwanensis was the dominant species in the community. The ratio of Pinus taiwanensis trees of diameter class IV reached a peak of 19.46% of the total followed by diameter class VII at 18.92%. The study recorded 156 species of vascular plants from 130 genera of 71 families; Pinus taiwanensis was the dominant species in the community. When the forest density was 1200 trees ha–1 with the largest average diameter of DBH=36.779±4.444 cm, the diversity (Shannon index H'=1.6716) and the evenness (Pielou index E=0.6727) of the tree layer was the highest. When the forest density reached 1525 trees ha–1 with the lowest average diameter of DBH=18.957±5.141 cm, the richness (Dma=5.4308), the diversity (H'=2.9612) and the evenness (E=0.8985) of all shrub layers climbed to the maximum. When the forest density was 1325 trees ha–1, the richness (Dma=5.8132), the diversity (H'=3.0697) and the evenness (E=0.9025) of all herb layers peaked. In terms of vertical structure, the average diversity indexes were herb layer>shrub layer>tree layer. High canopy density weakened light intensity in the community, causing a reduction in the species diversities of herbs and shrubs. The average similarity coefficient between the sample plots was 0.3356, which was at the medium dissimilarity level. External disturbances and improper management were major contributors to the low species diversity of the community. The implementation of scientific management measures is urgently needed to optimize the forest structures of Pinus taiwanensis, create a benign community environment, and promote species diversities and establish a stable forest community structure.

Study on quantification method for aggregate gradation of discrete Cemented Sand Gravel and Rock

As a new damming technique, Cemented sand gravel and rock damming technique could fill the gap between the earth-rock dam and the concrete dam in material and improve the construction system. The largest characteristic of this material is that it directly adopts the aggregates in the engineering field and only aggregates with a particle size above 150 mm are screened. The aggregate gradation is discrete and fluctuating, so it is significant to study the methods of quantization and characterization of aggregate grading. Based on Fuller curve, this paper quantified the variation and dispersion of aggregate gradation via using similarity coefficient of aggregate gradation, average similarity coefficient, mean average similarity coefficient and standard deviation of similarity coefficient, which has provided significant guidance for the real practice. Relevant quantization methods not only assist to differentiate the grading boundary including the thinnest and roughest graded aggregate, but also master the grading changes and predict the dispersion degree of strength of Cemented sand gravel and rock from the dispersion degree of aggregate, which could provide a scientific reference for the mixing design of Cemented sand gravel and rock

OPD analysis and prediction in aero-optics based on dictionary learning

When aircraft flying at a high speed, the density and reflective index of atmosphere around it become uneven. Thus images or videos observed from the observation window on the aircraft are usually blur or quivering, which is called the aero-optical effect. To recover the images from poor quality, it is necessary to learn about the wavefront distortion of the light, described as optical path difference (OPD). Among the existing methods, the method of computational fluid dynamics (CFD) simulation followed by ray tracing is very time consuming, and the method of real-time OPD measurement with OPD sensor has a certain lag for OPD with high frequency. In this paper, a reconstructible dimension reduction method based on dictionary learning is employed to map the high-dimensional OPD data into a low-dimensional space, and the OPD data are calculated when rays travel across the supersonic shear layer. All the parameters of training and test datasets remain the same except the convective Mach numbers (Mc number). According to the dimension reduction results of training sets, we find that OPD is obviously periodic and its distribution characteristics have a strong correlation with Mc number. By fitting the OPD data in the low-dimensional space, every point on the fitting curve can be reconstructed to the original high-dimensional space, which works as prediction. Compared with the truthful data, the average similarity coefficient of the prediction for the test datasets is up to 83%, which means that the prediction result is credible.