Euclidean Distance Values Research Articles

Puncture Cube Patient-Mounted Navigation System versus Freehand Method for CT-Guided Needle Placement: Study on a Neoprene Covered Elliptical Cylinder Gelatin Phantom.

The study aims to show how the "Puncture Cube" (PC) (Medical Templates, Egg, Switzerland) compares to the freehand method (FHM) for CT-guided punctures. The PC is a patient-mounted disassemblable cube consisting of an upper and lower template with multiple holes each to predefine puncture trajectory. A total of 80 punctures (FHM in-plane, FHM off-plane, PC in-plane, PC off-plane) was performed by 4 radiologists on a target 9.1cm below surface level of a neoprene covered elliptical cylinder gelatin phantom. The PC was never disassembled. Evaluated parameters were procedure time, number of CT-scans, euclidean distance (ED) and normal distance (ND). Respective parameters of FHM and PC were compared using the Wilcoxon signed-rank test and Levene test with significance levels of 5%. PC achieved smaller ED and ND values after initial needle insertion without corrections for both in-plane and off-plane punctures (P > 0.05). Variance of initial NDs was off-plane significantly larger for FHM. Final ED after needle path corrections was smaller for FHM both in- and off-plane (P < 0.05). Final off-plane ND was significantly lower for FHM with no significant difference in final in-plane ND. FHM off-plane punctures were significantly faster. There was no significant difference in CT-scans between both methods. Utilizing the PC may improve initial needle positioning and safety especially off-plane. However, better final needle positioning after correction with the greater freedom of movement method may suggest need for disassembly of the cube.

Advancing fluoride (F–) detection: Exploring the potential of digital color analysis with a novel thiourea receptor

This study aimed to explore a novel colorimetric detection method for fluoride using spectroscopic and digital analysis techniques. Thiourea compound synthesized from p-phenylenediamine and 4-nitrophenyl isothiocyanate was used as a receptor, with the NH group playing the role of a binding site to enhance the colorimetric detection process. This method facilitated visual detection by the naked eye and offered selectivity for fluoride ions. The result showed that there was a significant color change response, shifting from colorless to orange when fluoride was detected using the thiourea receptor. In this context, the color change was characterized by a bathochromic shift observed with UV–Vis spectrophotometry and quantified through high Euclidean Distance (ΔE) value of RGB color characteristics in digital analysis. Furthermore, the thiourea-based fluoride detection method had a low detection limit of 1.4 µM for spectroscopic analysis and 1.7 µM for digital analysis, along with a high recovery rate. These results affirmed the significance of spectroscopic and digital analyses using the thiourea receptor as a promising alternative for the rapid on-site detection of fluoride in real environmental samples.

Comparative Chemical Study For Species of The Eryngium genus

Five species of Eryngium L. (Apiaceae) native to Iraq-Eryngium glomeratumLam, Eryngium creticum Lam, Eryngium thyrosoideum Boiss, Eryngium billardieri Lam., and L. Eryngium campestre—are the focus of this comparative chemical taxonomy. Chemical analysis revealed that the five species within the genus could be distinguished by their unique chemical signatures thanks to applying the GC Mass Spectrometer (GC-MS) technique to their secondary metabolic components. Species shared specific molecules but had distinct chemical make-ups in others. The chemical properties of the species in the genus were used to calculate Euclidean genetic distance values; the highest value was found to be 5.1962 between E.creticum and E.billardieri, and the pair with the smallest value of Euclidean distance (3.70) was E. campestre and E. billardieri. The clustering analysis was displayed in the phylogenetic tree. The species can be classified into three broad categories along a single Euclidean axis, as indicated by chemical evidence that corroborated the result of Principal Component Analysis (4.9). (PCA). The studies also demonstrated the ability to differentiate and identify evolutionary links across species by showing the independence of species in specific isolated chemicals. Keywords: Eryngium; genus; Chemical taxonomic; Lam Eryngium, (GC-MS) technique.

Lost item identification model development using similarity prediction method with CNN ResNet algorithm

&lt;p&gt;&lt;strong&gt;Background:&lt;/strong&gt; Incidents of personal belongings being lost often occur due to our negligence as human beings or criminal acts such as theft. The methods used to address such situations are still manual and ineffective. The manual process of reporting lost items requires significant time and effort. Additionally, matching the information of lost items with the found ones becomes increasingly difficult, and finding the original owners can be time-consuming. &lt;strong&gt;Objectives and Methods:&lt;/strong&gt; This research aims to develop an approach that aids the community in the management of lost items by incorporating a process of item identification. It proposes the creation of an iOS-based prototype model that implements image comparison and string matching. The ResNet-50 architecture extracts features from images, and the Euclidean Distance method measures similarity between these features. Natural language processing used for text pre-processing and employs the cosine similarity metric to assess textual similarity in item descriptions. &lt;strong&gt;Result and Conclusion:&lt;/strong&gt; By combining Euclidean distance and cosine similarity values, the model predicts similar lost item reports. Image comparison provides an accuracy result of 29.96% correctness, while string matching with 97.92% correctness. Thorough testing and validation confirm the model’s success across different reports.&lt;/p&gt;

Examining recording quality from two methods of remote data collection in a study of vowel reduction

Remote recording quality of speech data varies significantly by recording devices, formats, and platforms, and past work has asserted that fine-grained sociolinguistic work should not be conducted remotely, while broad questions, such as analyses of the relative position of phonemes in the vowel space, may be amendable to remote data collection. In this study, lossless offline remote recordings taken via smartphone and lossy web-based recording performed over Gorilla are compared to traditional laboratory recordings in order to determine how accurately the remote options replicate a study of English vowel reduction. Four measures of reduction are examined: Relative duration, Euclidean distance, Pillai scores, and normalized formant values of stressed and unstressed vowels. Temporal analyses and Pillai scores were unaffected by recording method, while Euclidean distance and formant values exhibited some statistically significant changes but remained largely in line with laboratory data. These findings indicate that remote offline recording via smartphone or Gorilla may hold promise for studying vowel reduction and other phenomena requiring a similar degree of precision in formant analysis, but researchers should be aware of the specific distortions likely to be incurred with each method, with smartphone recordings having a stronger impact than Gorilla on low and back vowels.

Cranial Affinity among Chronological Populations in Sardinia, Italy: Biometric Insights for Orthodontic Purposes

Since human skulls may be used as a benchmark of the evolutionary process, the aim of the present study is to assess the cranial affinity of Sardinian populations from different chronological periods, with a standard index to evaluate its benefits for orthodontic purposes. Craniometric variables from four throughout cephalograms (anterior and lateral) of 72 units from historical Sardinian populations, two prehistoric, one medieval, and one modern were compared to the Bolton standard. A one-way analysis of variance (ANOVA) was performed for means comparison. A hierarchical cluster analysis and the bootstrap technique for the reliability of the dendrogram were used. Length data revealed statistically significant results (p &lt; 0.01). Usually, the medieval population showed higher mean values compared to the other groups; the prehistoric population presented the highest value of Euclidean distance when compared to the medieval; the modern showed no affinity to prehistoric populations nor to the Bolton standard. The length and the breadth of the neurocranium, maxillary–alveolar length, orbital height, maximum cranial breadth, and external palate breadth contributed to the dissimilarity among populations. The dissimilarities in the craniometric measurements of Sardinian populations are remarkable. Therefore, the main outcome showed that the craniometric standards of the Bolton standard are not applicable across the Sardinian population.

Exploring European Eel Anguilla anguilla (L.) Habitat Differences Using Otolith Analysis in Central-Western Mediterranean Rivers and Coastal Lagoons from Sardinia

An otolith shape and morphometric analysis was performed on European eel (Anguilla anguilla) subpopulations from five rivers and three coastal lagoons of Sardinia (central-western Mediterranean) to assess the role of different habitats on otolith development. Sagittal otolith shape was described by 11 harmonics from elliptic Fourier descriptors. Comparisons among the harmonics were run through canonical discriminant analyses (CDAs). The CDA reclassification rate (75.7%) demonstrated a spatial environmental discrimination among local eel subpopulations of Sardinia. The Euclidean distance values demonstrated a dissimilarity between the river and lagoon groups. The form factor and roundness shape indices were significantly higher in the river group than in the lagoon group. The distances of the first three rings to the otolith core revealed site-specific otolith development. Moreover, the annual otolith growth rate was faster in the lagoon group than in the river group. The differences among the studied sites in terms of sagittal otolith shape could relate to changes in different local stocks potentially related to environmental peculiarities. Establishing a direct correlation between otolith morphology and environmental factors is challenging, and further studies are needed to investigate the relationship between habitat type/environmental variation and growth/body characteristics of eels. Nevertheless, the achieved results suggest that this method can be considered to be a valuable tool for studying the ontogeny of the European eel.

Korean–English Bilingual Children's Productions of Korean and English /l/

Purpose: The aim of this study was to examine acoustic characteristics of Korean–English (KE) bilingual children's productions of Korean and English /l/ sounds. Specifically, individual variability in KE bilingual children's productions of Korean and English /l/ was examined in relation to each child's initial age and duration of exposure to their first and second languages. Method: A total of five KE bilingual children, ranging in age between 5 and 8 years, were included in this study. Each KE child produced word-initial (WI) and -final (WF) English /l/ and WF Korean /l/ embedded in monosyllabic words, using a picture naming task. English /l/ productions of monolingual American English (AE)–speaking children were also included. Productions of AE children were from an existing large data set that includes English WI and WF /l/ productions. The AE group was included as a control group for the productions of English /l/ of the same dialect. First (F1) and second formant frequency (F2) values extracted at the /l/ midpoint and Euclidean distance (ED) between English WI and WF /l/ were analyzed and compared across the productions. Results: KE children produced Korean WF /l/ with significantly higher F2–F1 values than their English counterparts and AE children's WF /l/. Acoustic patterns of KE English WI /l/ were similar to those of AE WI /l/, but variations were seen by the initial age and duration of their exposure to English. Mean ED values between English WI and WF /l/ also differed by KE children's initial age and duration of exposure to English. Conclusions: These results showed that KE children produce Korean and English WF /l/ with acoustic distinctions, but their patterns vary by the initial age and duration of their exposure to English and Korean. These findings suggest that a more detailed language background should be considered when working with bi-/multilingual children to accurately assess and examine their articulation skills.

KLASTERISASI SISWA PENYANDANG DISABILITAS BERDASARKAN TINGKAT TUNAGRAHITA MENGGUNAKAN ALGORITMA K-MEANS

ABSTRACT:SLB Negeri 1 Bengkulu City is one of the special schools in Bengkulu City that provides educational facilities for children with special needs with mental retardation so that they can get a proper education in teaching and learning process. In the class placement of students in schools, mental retardation is divided into 2 levels, namely mild and moderate by observing by looking at the IQ scores of students and the academic scores obtained. This is necessary, so that the teaching and learning process becomes more efficient and effective. However, sometimes the school has difficulty in determining class placement for students with special needs for mental retardation, because there is no application that can help grouping the student data. Application for clustering students with mental retardation at SLB Negeri 1 Bengkulu City by applying K-Means algorithm. This application is made using Visual Basic.Net programming language and SQL Server database. Based on the student clustering that has been carried out based on a data sample of 73 students using the application, the results obtained information that 47.9% of the Cluster 1 group (mild mental retardation level) and 37% of the Cluster 2 group (moderate mental retardation level) and 15.1% of the Cluster 3 group (severe mental retardation level) from the calculation of the Euclidean distance value by taking the closest distance&#x0D;

Application of color extraction methods and k-nearest neighbor to determine maturity avocado butter

Computerization requires system testing and further system development, namely color feature extraction with KNN. Avocado is one that has a high protein content in it. This research uses the KNN algorithm method and feature extraction in order to get more effective results, the purpose of this research is to make it easier for people to choose the ripeness level of butter avocados because people still don't know about the maturity level of butter avocados. In this study, testing was carried out by bringing the avocado fruit closer to the cellphone camera connected to the researcher's internet, after which the application will automatically match the color of the avocado. to the system, the system will produce output based on that color with output in the form of the ripeness level of the avocado, whether it is ripe, ripe, half ripe, rotten and also generates information on how much longer the avocado will ripen. All stages of system development are carried out by analyzing data first, then taking sample data, training and testing datasets, then the results of the system will become benchmarks. The test data in this study used several types of avocado objects, namely: Raw, Half Ripe, Ripe, Ripe, Rotten. It consisted of 55 data samples consisting of 11 raw avocado samples, 11 half-ripe avocado samples, 11 ripe avocado samples, 11 ripe avocado samples and 11 rotten avocado samples. Obtained euclidean distance values ​​for each type of avocado butter. After that, the sum is done to get the overall level of accuracy by adding up the total euclidean distance with the total euclidean distance for each type of avocado. After getting the added value multiply it by 100%. Then the overall accuracy results obtained are 98.38%.

Structural damage identification based on pattern matching using the flexibility change rate

AbstractIn this paper, a rapid identification method for postearthquake structural damage is proposed based on pattern matching using the flexibility change rate. In the first stage, a small number of dynamic signals are collected for extracting the modal information, which is used as a reference for model updating. Using the updated finite element model of the structure to be monitored, the characteristic vector of the flexibility change rate is calculated by modal analysis from the first two orders of modal information of various damage scenarios to establish a pattern database. For the real structure, the measured responses are used to identify the modal parameters to calculate the flexibility change rate characteristic vector, which is treated as the observed pattern. Then, the similarity between the observed pattern and the pattern in the pattern database is calculated using the Euclidean distance (ED). The damage location and severity of the measured structure are treated to be the same as the pattern corresponding to the minimum value of ED, so that the damage is identified. Numerical simulations and experiments of two types of concentrated mass structures, four floors, and six floors confirm that the proposed method can identify the damage well. In addition, the matching results based on different sensor combinations demonstrate that the method can quickly identify the damage location and severity of a structure even using a limited number of sensors. The proposed method can provide support for the government in rapid postearthquake emergency decision‐making.

Combined empirical mode decomposition and phase space reconstruction based psychologically stressed and non-stressed state classification from cardiac sound signals

The psychological stress and associated mental health conditions causes high socioeconomic impacts on society and the onset of pandemic worsened the situation making it imperative to timely detect psychological stress. This paper presents a novel framework for using a combination of empirical mode decomposition (EMD) and phase space reconstruction (PSR) analysis to capture non-linear, non-stationary dynamics of cardiac sound signals acquired from fifty-four healthy male adults for detecting psychological stress. The time interval among successive S1 peaks of acquired cardiac sound signals is extracted to obtain Interbeat Interval signal used for decomposition to Intrinsic Mode Functions (IMFs) using EMD technique. Thereafter, the feature vectors namely- largest singular value, smallest singular value from two-dimensional PSRs of IMFs and the mean value of Euclidean distance, standard deviation of Euclidean distance from three-dimensional PSRs are extracted to detect psychologically stressed state. The non-parametric Kruskal-Wallis statistical test is applied to select statistically significant features that are fed to Decision Tree, Naïve Bayes and Support Vector Machine classifiers for classifying stressed and non-stressed state with fivefold cross-validation to make it a reliable system. The average accuracy, sensitivity and specificity achieved is 97.14%, 99.8% and 94% respectively using SVM and Radial Basis Function kernel function. The proposed framework performed better on the dataset in comparison to ratio of low-frequency to high-frequency (LF/HF) power parameter of Electrocardiography signal. The use of easy to acquire, cost-effective cardiac sound signals for detecting psychological stress makes proposed framework feasible for rural healthcare centres of developing economies, homecare and telemedicine.

Low complexity symmetric-coded based sphere decoding for low-rate polar codes

The sphere decoding (SD) algorithm can provide (sub)optimal solutions with reduced computational complexity of maximum likelihood (ML) detection for multi-input multi-output (MIMO) communication systems. In this paper, we propose a novel low complexity symmetric-coded based SD algorithm for short polar codes with low rate. At the encoding stage, the first N/2 sub-channels transmit the frozen bits, while the information bits are selected from the latter N/2 sub-channels. Two symmetric codes are generated due to the mathematical structure of the generator matrix, which is well conditioned to the SD search. At the decoding stage, the presented SD algorithm computes the Euclidean distance value by the combined signals to estimate the latter N/2 input bits. Furthermore, the backtrack operation starts from the earlier (N/2+1)-th bit, which can significantly reduce the average visited nodes (AVN). Simulation results show that, compared to the original SD algorithm, the presented variant of the SD algorithm can reduce the AVN to 0.9% for the polar code P(64, 14) at SNR = 1 dB with a performance loss within 0.2 dB. The presented SD algorithm may find applications in MIMO systems where the complexity of the standar ML detection increases exponentially with the transmitting antennas.

VULNERABILIDADE AMBIENTAL NO ENTORNO DO MONUMENTO NATURAL DO ITABIRA, ES, BRASIL

ABSTRACT The institution of biological value areas through the creation of Natural Protected Areas is an essential tool for protecting the country’s environmental resources to face advanced anthropic development in natural areas, either to increase agriculture production or for economic growth. Environmental vulnerability studies combined with geotechnological tools have been vital to identifying the most vulnerable areas and consequently help Conservation Units protection. This study aimed to analyze environmental vulnerability at the buffer zone of Itabira Natural Monument (MONAI) in Cachoeiro de Itapemirim, Brazil. The necessary methodological steps for this study were as follows: a) Photointerpretation of land use; b) Anthropic variables selection; c) Application of Euclidean distance function in variables vector images; d) Application of fuzzy membership function in variables raster images; e) Application of Analytical Hierarchical Process (AHP); and f) Spatial classification of environmental vulnerability around MONAI. Land use conflicts reveal a relevant presence of pasture areas, representing 49.80% of the buffer zone. This fact corroborates with its Euclidean distance value, which showed the lowest linear value, 836 meters. Eight anthropic variables have been incorporated, highlighting crops, urban areas, exposed soil and pasture. Jenks natural breaks defined five vulnerability classes. According to the results, 57.14% of the entire MONAI buffer zone is represented by the high and very high classes. The outdated law creation of MONAI and the need for a management plan result in a vulnerable buffer zone. The present study can support management plan formulation and assist MONAI’s buffer zone delimitation.

A Reference Point-Based Evolutionary Algorithm Solves Multi and Many-Objective Optimization Problems: Method and Validation.

The integration of a decision maker's preferences in evolutionary multi-objective optimization (EMO) has been a common research scope over the last decade. In the published literature, several preference-based evolutionary approaches have been proposed. The reference point-based non-dominated sorting genetic (R-NSGA-II) algorithm represents one of the well-known preference-based evolutionary approaches. This method mainly aims to find a set of the Pareto-optimal solutions in the region of interest (ROI) rather than obtaining the entire Pareto-optimal set. This approach uses Euclidean distance as a metric to calculate the distance between each candidate solution and the reference point. However, this metric may not produce desired solutions because the final minimal Euclidean distance value is unknown. Thus, determining whether the true Pareto-optimal solution is achieved at the end of optimization run becomes difficult. In this study, R-NSGA-II method is modified using the recently proposed simplified Karush-Kuhn-Tucker proximity measure (S-KKTPM) metric instead of the Euclidean distance metric, where S-KKTPM-based distance measure can predict the convergence behavior of a point from the Pareto-optimal front without prior knowledge of the optimum solution. Experimental results show that the algorithm proposed herein is highly competitive compared with several state-of-the-art preference-based EMO methods. Extensive experiments were conducted with 2 to 10 objectives on various standard problems. Results show the effectiveness of our algorithm in obtaining the preferred solutions in the ROI and its ability to control the size of each preferred region separately at the same time.

BSA-Seq Approach Identified Candidate Region and Diagnostic Marker for Chilling Tolerance of High Oleic Acid Peanut at Germination Stage

High oleic acid peanut (HOAP) is extensively embraced in China because of its high nutritional value and enhanced oxidative stability. However, its dissemination has been severely constrained in high altitude and high latitude areas due to chilling stress during sowing, resulting in significant yield loss in these regions. Despite the lack of understanding of the molecular mechanisms underlying low temperature germination (LTG) in HOAP, discovering the quantitative trait loci (QTL) that confer this trait will undoubtedly benefit breeding efforts. In the present study, we identified putative genomic regions and single nucleotide polymorphisms (SNPs) that govern LTG tolerance of HOAP in an F2 population derived from the cross of chilling-tolerant YH65 and chilling-sensitive FL14 using bulk segregant analysis (BSA). Analysis of ΔSNP-index and Euclidean distance (ED) value association pinpointed the overlapped region to a 2.29 Mb interval on chromosome A05. The candidate interval showed that 122 genes were significantly related to response to abiotic stress and plant–pathogen interaction. Furthermore, an SNP site associated with LTG tolerance was discovered. The SNP site was employed as a Kompetitive Allele Specific PCR (KASP) marker and validated in a universal peanut panel. These findings may provide valuable insight into the molecular mechanism underpinning LTG tolerance and facilitate marker-assisted selective breeding in HOAP.

Euclidean distance-based Raman spectroscopy (EDRS) for the prognosis analysis of gastric cancer: A solution to tumor heterogeneity

The prognosis analysis of gastric cancer is critical for selection of treatments and development of advanced therapeutic methods. A prognosis approach that is accurate, fast, convenient, and of low cost for gastric cancers is in high demand. Raman spectroscopy is a label-free and non-destructive technique to provide molecular fingerprints of biological samples, holding promises for cancer prognosis. However, the major challenge of gastric cancer prognosis lies in the widely existing tumor heterogeneity, which leads to unexpected spectral variations within one type of samples. In this work, we have developed the Euclidean distance (ED)-based Raman spectroscopy (EDRS) method for the prognosis analysis of gastric cancer to eliminate the influence of tumor heterogeneity. Raman spectra were first collected on the slices of paraffin-preserved tumor tissues from gastric cancer patients. A standard spectrum to represent the ‘worst prognostic tumor cells’ was then established. The similarity between each spectrum of tissues and the standard spectrum was assessed by ED, to provide a direct assessment on the prognosis status. We have successfully classified the patients into poor and favorable prognosis groups, either based on the averaged regional ED values (sensitivity of 75 %, specificity of 96.8 %), or based on the minimal ED values at the patient level (sensitivity of 90 %, specificity of 100 %). EDRS was also investigated for survival analysis (AUC = 0.955), much better than the commonly applied post-neoadjuvant therapy (ypTNM) category (AUC = 0.718). Our work highlights EDRS as a rapid, accurate, low-cost and robust tool for heterogeneous cancer-related prognosis assessment and survival prediction, providing new insights for spectroscopic tumor analysis.

An Image Retrieval Framework Design Analysis Using Saliency Structure and Color Difference Histogram

This paper focuses on retrieving plant leaf images based on different features that can be useful in the plant industry. Various images and their features can be used to identify the type of leaf and its disease. For this purpose, a well-organized computer-assisted plant image retrieval approach is required that can use a hybrid combination of the color and shape attributes of leaf images for plant disease identification and botanical gardening in the agriculture sector. In this research work, an innovative framework is proposed for the retrieval of leaf images that uses a hybrid combination of color and shape features to improve retrieval accuracy. For the color features, the Color Difference Histograms (CDH) descriptor is used while shape features are determined using the Saliency Structure Histogram (SSH) descriptor. To extract the various properties of leaves, Hue and Saturation Value (HSV) color space features and First Order Statistical Features (FOSF) features are computed in CDH and SSH descriptors, respectively. After that, the HSV and FOSF features of leaf images are concatenated. The concatenated features of database images are compared with the query image in terms of the Euclidean distance and a threshold value of Euclidean distance is taken for retrieval of images. The best results are obtained at the threshold value of 80% of the maximum Euclidean distance. The system’s effectiveness is also evaluated with different performance metrics like precision, recall, and F-measure, and their values come out to be respectively 1.00, 0.96, and 0.97, which is better than individual feature descriptors.

Web-Based Face Recognition using Line Edge Detection and Euclidean Distance Method

A face recognition system is to perform a match face image using the face extraction method. There are many applications used in various algorithms and implemented in many programming languages, but still difficult to implement on web-based applications using the PHP programming language. The purpose of this research is to produce a website-based application focused on the face recognition section. The author will limit the system only to detect the front view of the face, the main goal is to get a fairly high level of accuracy. There will be a feature to find where the face is located. The research method used is a laboratory experiment where the search system scheme based on face recognition will produce the appearance of several faces that have the closest Euclidean distance values from grades 1st to 5th. The results from the comparison of the test image with the training image based on Line Edge Detection and Euclidean Distance calculation concluded that the system can be implemented in searching of similarity and recognizing the face.

Robust fault diagnosis of rolling bearing via phase space reconstruction of intrinsic mode functions and neural network under various operating conditions

Rolling bearings are important components in mechanical, civil, and aerospace engineering. The practical working conditions of rolling bearings are complex; hence, fault diagnosis of rolling bearings under various operating conditions is very challenging. This paper proposes a novel approach to fault diagnosis of rotary machinery using phase space reconstruction (PSR) of intrinsic mode functions (IMFs) and neural network under various operating conditions. Complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) is employed to decompose vibration signal of rotary component into IMFs denoting high-to-low instantaneous frequencies adaptively. PSR constructs one-dimensional IMFs to high-dimensional IMFs, which helps reveal the underlying nonlinear geometric topology via the reconstructed inherent and hidden dynamical characteristics of the one-dimensional vibration signal. To explore intrinsic dynamical properties, interquartile range (IQR) of Euclidean distance (ED) values of high-dimensional IMFs are extracted as condition indicators and used as input of back propagation (BP) neural network to fulfill fault identification of rolling bearings. The effectiveness and superiority of the proposed approach have been validated by theoretical derivations, numerical simulations and experimental data. The results show that the proposed approach is promising in fault diagnosis of rotary machinery under various operating conditions.