Pattern Vectors Research Articles

Diabetic Retinopathy Detection Using Optimization Assisted Deep Learning Model: Outlook on Improved Grey Wolf Algorithm

In recent days, study on retinal image remains a significant area for analysis. Several retinal diseases are identified by examining the differences occurring in the retina. Anyhow, the major shortcoming between these analyses was that the identification accuracy is not satisfactory. The adopted framework includes two phases namely; (i) feature extraction and (ii) classification. Initially, the input fundus image is subjected to the feature extraction process, where the features like Local Binary Pattern (LBP), Local Vector Pattern (LVP) and Local Tetra Patterns (LTrP) are extracted. These extracted features are subjected to the classification process, where the Deep Belief Network (DBN) is used as the classifier. In addition, to improve the accuracy, the activation function and hidden neurons of DBN are optimally tuned by means of the Self Improved Grey Wolf Optimization (SI-GWO). Finally, the performance of implemented work is compared and proved over the conventional models.

LSTM training set analysis and clustering model development for short-term traffic flow prediction

Long short-term memory (LSTM) is becoming increasingly popular in the short-term flow. In order to develop high-quality prediction models, it is worth investigating the LSTM potential deeply for traffic flow prediction. This study has two objectives: first, to observe the effect of using different sized training sets in LSTM training for various and numerous databases; second, to develop a clustering model that contributes to adjusting the training set size. For this purpose, 83 datasets were divided into certain sizes and LSTM model performances were examined depending on these training set sizes. As a result, enlargement of the training set size reduced LSTM errors monotonic for certain datasets. This phenomenon was modeled with the state-of-the-art clustering algorithms, such as K-nearest neighbor, support vector machine (SVM), logistic regression and pattern recognition networks (PRNet). In these models, statistical properties of datasets were utilized as input. The best results were obtained by PRNet, and SVM model performance was closest to PRNet. This study indicates that enlarging the training set size in traffic flow prediction increases the LSTM performance monotonically for specific datasets. In addition, a high-precision clustering model is presented to assist researchers in short-term traffic forecasting to adjust the size of the training set.

Modified PLVP with Optimised Deep Learning for Morphological based Road Extraction

ABSTRACT This paper introduces a new modified local pattern descriptor to extract road from rural areas’ aerial imagery. The introduced local pattern descriptor is actually the modification of the proposed local vector pattern (P-LVP), and it is named as Modified-PLVP (M-PLVP). In fact, M-PLVP extracts the texture features from both road and non-road pixels. The features are subjected to train the Deep belief Network (DBN); thereby the unknown aerial imagery is classified into road and non-road pixel. Further, to improve the classification rate of DBN, morphological operations and grey thresholding operations are performed and so that the road segmentation is performed. Apart from this improvement, this paper incorporates the optimisation concept in the DBN classifier, where the activation function and the count of hidden neurons are optimally selected by a new Trail-based WOA (T-WOA) algorithm, which is the improvement of the Whale Optimisation Algorithm (WOA). Finally, the performance of proposed M-PLVP is compared over other local pattern descriptors concerning measures like Accuracy, Sensitivity, Specificity, Precision, Negative Predictive Value (NPV), F1Score and Mathews correlation coefficient (MCC), False positive rate (FPR), False negative rate (FNR), and False Discovery Rate (FDR), and proves the betterments of M-PLVP over others.

Simulation Study on Geometric Anisotropic Estimators for Spatial Point Process

The method by Fry for detecting geometric anisotropy in stationary spatial point pattern is investigated. We quantify anisotropy by stretching and compressing the point process about the axis. Using a simulated Strauss point pattern, we first fit ellipsoids to the compressed pattern of pairwise difference vectors to estimate the direction of anisotropy. The strength of compression and the regularity of the point process are varied at different times and the corresponding effect on the estimated ellipsoids is investigated as the level of contour ellipsoid increases. Parameters and contours good for estimation were discussed.

Research on Evaluation Model of Regional Financial Science and Technology Development Based on Local Variable Weight

With the development of financial science and technology, how to accurately evaluate the development level of regional financial science and technology has become particularly important. This paper first establishes the evaluation index system of regional financial science and technology development, which is composed of six first-class indicators and fourteen second-class indicators, which comes from the identification of influencing factors of financial science and technology development. Then, based on the idea of local variable weight, a comprehensive evaluation method of regional financial science and technology based on local variable weight is designed, and the scientificity and feasibility of the method are verified by data. The local variable weight comprehensive evaluation method can realize the objective and flexible weight setting, and the future research can do more in-depth research on parameter optimization and vector pattern construction.

EMC Chamber Quiet Zone Qualification for Applications Above 1 GHz Using Frequency Domain Mode Filtering

Anechoic chambers used for electromagnetic compatibility (EMC) measurements above 1 GHz are qualified based on the site voltage standing wave ratio (SVSWR) method as per the international standard CISPR 16-1-4. With one antenna at the fixed position, some distance away from the quiet zone (QZ), the SVSWR is acquired by moving a dipole-like antenna along several linear paths that are located at the edge of the QZ. To reduce test burden, the SVSWR method under-samples the measurement by design, in that only six discrete points along each 40 cm linear travel path are measured. As a result, the test results are generally overly optimistic. In this article, we propose to use a novel cylindrical mode coefficient (CMC)-based frequency domain mode filtering techniques to obtain the VSWR. Here, we measure the vector pattern cut of the dipole-like test antenna with an offset placement at the outer edge of QZ. The antenna is then mathematically translated to the rotation center, whereupon a bandpass filter that tightly encloses the test antenna mode spectrum is applied. Two approaches are studied herein for translating the rotation center. One is by applying a path length correction to both magnitude and phase, and the other is by performing a cylindrical far-field transformation on the quasi-far-field data. The difference between the mode filtered antenna pattern and the original perturbed pattern is used to derive the chamber SVSWR. In contrast to the conventional technique, the proposed, novel method does not suffer from positional under-sampling, so it is well-placed to be applied at microwave frequencies and above.

Bioelectrical Impedance Vector Pattern and Biomarkers of Physical Functioning of Prostate Cancer Survivors in Rehabilitation.

Background:Knowledge of clinically established factors of physical function such as body composition, bioelectrical phase angle (PhA) and handgrip strength (HGS) with mortality predictive and health-related relevance is limited in prostate cancer survivors (PCS). Therefore, the aim of this study was to characterise and compare body composition data of PCS with extensive reference data as well as to analyse PhA and HGS and the prevalence of critical prognostic values at an early stage of cancer survivorship.Methods:One hundred and forty-eight PCS were examined at the start (T1) and end (T2) of a 3-week hospitalised urooncological rehabilitation, which began median 28 days after acute cancer therapy. Examinations included a bioimpedance analysis and HGS test. Comparison of body composition between PCS and reference data was performed using bioimpedance vector analysis (BIVA).Results:BIVA of the whole PCS group showed abnormal physiology with a cachectic state and a state of overhydration/oedema, without significant changes between T1 and T2. The age- and BMI-stratified subgroup analysis showed that PCS aged 60 years and older had this abnormal pattern compared to the reference population. HGS (T1: 38.7 ± 8.9 vs T2: 40.8 ± 9.4, kg), but not PhA (T1/T2: 5.2 ± 0.7, °), changed significantly between T1 and T2. Values below a critical threshold reflecting a potentially higher risk of mortality and impaired function were found for PhA in 20% (T1) and 22% (T2) of PCS and in 41% (T1) and 29% (T2) for HGS.Conclusions:BIVA pattern and the prevalence of critically low HGS and PhA values illustrate the necessity for intensive continuation of rehabilitation and survivorship care especially in these ‘at risk’ cases. The routine assessment of body composition, PhA and HGS offer the opportunity to conduct a risk stratification for PCS and could help personalising and optimising treatment in rehabilitation and ongoing survivorship care.

Local Derivative Vector Pattern: Hybrid Pattern for Content-Based Medical Image Retrieval

This paper examines a hybrid pattern i.e. Local derivative Vector pattern and comparasion of this pattern over other different patterns for content-based medical image retrieval. In recent years Pattern-based texture analysis has significant popularity for a variety of tasks like image recognition, image and texture classification, and object detection, etc. In literature, different patterns exist for texture analysis. This paper aims at forming a hybrid pattern compared in terms of precision, recall and F1-score with different patterns like Local Binary Pattern (LBP), Local Derivative Pattern (LDP), Completed Local Binary Pattern (CLBP), Local Tetra Pattern (LTrP), Local Vector Pattern (LVP) and Local Anisotropic Pattern (LAP) which were applied on medical images for image retrieval. The proposed method is evaluated on different modalities of medical images. The results of the proposed hybrid pattern show biased performance compared to the state-of-the-art. So this can further extended with other pattern to form a hybrid pattern.

Comparing cyclic behaviour of RBS, DFC and proposed rigid connections in a steel moment frame with CFT column

ABSTRACT Beam-to-column connection is one of the main parts of steel structures that its failure induces local and/or overall structural failure. This paper aims at examining the impact of different rigid connections (including conventional, reduced beam section (RBS), drilled flange connection (DFC), those stiffened with exchangeable box components and variable-diameter DFC with concrete-filled box columns on the flexural behavior of a steel moment frames. A rhombic connection with a cutting vector pattern like RBS is designed and proposed; then its behavior is compared to those of RBS and DFC connections. The connections are modeled in Abaqus software and then their moment-rotation diagrams are plotted and compared. The results reveal that the DFC connection with holes of different diameters has proper energy absorption and performance. In conclusion, the rhombus DFC connection has a more reliable performance than other DFC connections. In this research, by placing the proposed stiffening components in the connection, it is observed that these components act as dampers increasing the bearing capacity and improve the connection behavior by absorbing the imposed energy. The results indicate that the proposed connection prevents from beam failure as most of input energy is absorbed by the proposed components.

Shales of Palaeo-Mesoproterozoic Vindhyan Basin, central India: insight into sedimentation dynamics of Proterozoic shelf

AbstractThe Vindhyan Supergroup represents the largest Proterozoic sedimentary basin fill in the Indian shield. In addition to some significant palaeobiological discoveries, the sedimentary sequence of the Vindhyan, particularly its argillaceous intervals, holds crucial information for our understanding of sedimentation dynamics in Proterozoic clastic shelves. Here we attempt an extensive, although not exhaustive, review of the physical characteristics of six argillaceous (shale) intervals (Arangi, Koldaha, Rampur, Bijaygarh, Rewa and Sirbu shale) from the Son valley sector, Vindhyan Basin, augmented with new observations to unravel the status of current understanding in terms of palaeo-flow dynamics, shelf sedimentation processes and dispersal pattern, depositional cyclicity and basinal tectonics. The sedimentary attributes of Vindhyan shales reveal their deposition largely in relative bathymetry fluctuating from distal shoreface or inner shelf (near to fair-weather wave base) to distal shelf below storm wave base. More often than not, the Vindhyan shelf was storm-infested and the operation of both storm-generated return flow and Coriolis-force-guided geostrophic currents are documented from different stratigraphic intervals of argillaceous successions. The thick arenaceous intervals interrupting the deposits of the Koldaha, Rewa and Sirbu shales at multiple stratigraphic levels indicate the presence of a fan delta and braided fluvial system during intermittent regressive stands of sea level or event deposition during a sea-level highstand, respectively. Based on facies pattern and flow vectors, a rift-related half-graben model is inferred for Arangi and Koldaha shale and a low-gradient stable-shelf model with well-defined energy gradient is proposed for successions from Rampur shale onwards.

A novel melanoma detection model: adapted K-means clustering-based segmentation process

Abstract Objectives The main intention of this paper is to propose a new Improved K-means clustering algorithm, by optimally tuning the centroids. Methods This paper introduces a new melanoma detection model that includes three major phase’s viz. segmentation, feature extraction and detection. For segmentation, this paper introduces a new Improved K-means clustering algorithm, where the initial centroids are optimally tuned by a new algorithm termed Lion Algorithm with New Mating Process (LANM), which is an improved version of standard LA. Moreover, the optimal selection is based on the consideration of multi-objective including intensity diverse centroid, spatial map, and frequency of occurrence, respectively. The subsequent phase is feature extraction, where the proposed Local Vector Pattern (LVP) and Grey-Level Co-Occurrence Matrix (GLCM)-based features are extracted. Further, these extracted features are fed as input to Deep Convolution Neural Network (DCNN) for melanoma detection. Results Finally, the performance of the proposed model is evaluated over other conventional models by determining both the positive as well as negative measures. From the analysis, it is observed that for the normal skin image, the accuracy of the presented work is 0.86379, which is 47.83% and 0.245% better than the traditional works like Conventional K-means and PA-MSA, respectively. Conclusions From the overall analysis it can be observed that the proposed model is more robust in melanoma prediction, when compared over the state-of-art models.

Over-the-Air Calibration of Active Antenna Arrays Using Multisine

A novel over-the-air (OTA) beamforming calibration procedure is proposed, which can be applied to different types of multiple-input multiple-output (MIMO) transmitting antennas. The method consists of using two tones on each antenna element, the main tone, and the tickle tone. The latter one operates in a different frequency for each antenna element and is used to obtain the optimum phase that needs to be set for each element to generate a beam in the desired direction, at the main tone frequency. The novel method was applied to linear, planar, 3-D antennas, and noncollocated multiantennas to validate its applicability to different antenna types. Line-of-Sight (LOS) and non-LOS experimental results demonstrate that the method can be used to retrieve the required phase to fully control the antenna radiation pattern. An optimum radiation pattern and lowest error vector magnitude (EVM) can be achieved even under high multipath effects/non-LOS conditions. A comparison between the performance and the application of the array factor (AF) theory is presented for practical indoor scenarios, demonstrating the effectiveness of the method. It is demonstrated that the method may be an alternative to the calibration of nonstandard MIMO antennas, where the AF computation is complex or not possible.

Development of a system based on aerial images for the morphological patterns classification using support vector machine

Oil palm cultivation is one of the major agricultural activities in Colombia. Production performance is related to the good practices in the plantation, mainly regarding the management of phytosanitary conditions. Bud rot disease is the one with the greatest impact in Colombia. The most commonly used technique for its detection is from routine visual inspection on each palm, being costly and inefficient. For this reason, the aim of this study is the development of a classification algorithm based on binary support vector machines for the detection of Bud Rot. The model was obtained from 798 aerial images acquired by unmanned aerial vehicles. Each image was tagged by an expert palm grower based on the presence or absence of the disease. These images were described by 531 morphological features extracted using the concatenation of uniform binary local pattern vectors. Bootstrapping was used to balance the classes, obtaining 507 observations per class. To evaluate the performance metrics of the classifier, an 8-fold Monte Carlo cross-validation was implemented by randomly splitting the data set into training (80%), validation (10%), and test (10%) sets with balanced classes. Finally, the model achieved a performance greater than 96.0%. This indicates that the model developed could be a great technique to automate bud rot detection with high reliability, increasing the efficiency in the recognition. All these thanks to the fusion of Machine Learning techniques with the phenomena of optical physics.

Cavitation streamlining of a round cylinder in the critical range

The paper presents experimental results on the transverse cavitation streamlining of a circular cylinder by a turbulent water flow in the critical range of Reynolds numbers determined on diameter. Using the PIV method, averaged velocity fields are obtained. Their vector patterns serve to determine the lengths of the reverse flow and the distance between vortices in the near wake behind the cylinder. The presence of a minimum of spatial characteristics of the vortex zone for the initial cavitation modes is shown. Initial cavitation, transient modes, and developed cavitation are determined for different flow rates. The beginning of cavitation is found to depend on the Reynolds number. With smooth decrease in static pressure in front of the cylinder, critical anomalous phenomena, probably related to the rearrangement of cavitation modes, are detected in very narrow range. Vortex shedding from the cylinder surface is found to occur quasi-periodically despite the possibility of simultaneous shedding and breakdown of vortices.

Larval ecology and infestation indices of two major arbovirus vectors, Aedes aegypti and Aedes albopictus (Diptera: Culicidae), in Brazzaville, the capital city of the Republic of the Congo

BackgroundInvasive mosquito species, such as Aedes albopictus in Congo can affect the distribution of native species, changing the vector composition and pattern of disease transmission. Here, we comparatively establish the geographical distribution and larval habitat preference of Ae. aegypti and Ae. albopictus and the risk of arbovirus disease outbreaks using Stegomyia indices in the city of Brazzaville, the capital of the Republic of the Congo.MethodsHuman dwelling surveys of water-holding containers for immature stages of Aedes was carried out in December 2017 in Brazzaville through a random cluster sampling method. A total of 268 human dwellings distributed in 9 boroughs and 27 neighbourhoods were surveyed across the city.ResultsOverall, 455 potential larval habitats were surveyed. Both Ae. aegypti and Ae. albopictus were collected across the city with an overall high prevalence of Ae. aegypti (53.1%) compared to Ae. albopictus (46.9%). Geographical distribution analysis showed that Ae. aegypti was more abundant (mean = 6.6 ± 1.4) in neighbourhoods located in downtown, while the abundance of Ae. albopictus was low (mean = 3.5 ± 0.6) in suburbs. Peridomestic containers, especially discarded tanks, were the most strongly colonized productive larval habitat for both mosquito species with the prevalence of 56.4% and 53.1% for Ae. aegypti and Ae. albopictus, respectively. Globally, the house index (HI), Breteau index (BI) and container index (CI) were high for Ae. aegypti (26.6%, 38.4% and 22.6%) and Ae. albopictus (33.3%, 49.6% and 26.6%) compared to the transmission risk threshold (5%, 5% and 20%) established by the WHO/PAHO. Overall, pupae-based indices (the pupae index and the pupae per person index) were not significantly different between Ae. aegypti (273.4% and 23.2%) and Ae. albopictus (228.8% and 19.5%).ConclusionsThe findings of this study suggest a high risk for transmission of arbovirus diseases in Brazzaville and call for an urgent need to implement vector control strategies against these vectors in the Republic of the Congo.

Optimal weighted hybrid pattern for content based medical image retrieval using modified spider monkey optimization

AbstractThe current approaches for image retrieval are more concentrating on numerous image features. Texture, shape, spatial information, and color are the fundamental features to deal with flexible image datasets. This paper aims to develop new Content‐Based Image Retrieval System based on Optimal Weighted Hybrid Pattern. Two relevant patters like Local Vector Pattern and Local Derivative Pattern are intended to develop a novel Content‐Based Image Retrieval system. The optimal weighted hybrid pattern is implemented to derive a new feature vector, so that the weight is optimized by a modified optimization algorithm called Improved Local Leader‐based Spider Monkey Optimization to maximize the precision and recall of the retrieved images. The retrieval of the image is done by measuring the similarity based on Mean Square Distance between the features of query image as well as training image. Finally, the performance comparison of the proposed and the traditional patterns shows its reliable performance.

Body Water Content and Morphological Characteristics Modify Bioimpedance Vector Patterns in Volleyball, Soccer, and Rugby Players.

Background: Bioimpedance vector analysis (BIVA) is a widely used method based on the interpretation of raw bioimpedance parameters to evaluate body composition and cellular health in athletes. However, several variables contribute to influencing BIVA patterns by militating against an optimal interpretation of the data. This study aims to explore the association of morphological characteristics with bioelectrical properties in volleyball, soccer, and rugby players. Methods: 164 athletes belonging to professional teams (age 26.2 ± 4.4 yrs; body mass index (BMI) 25.4 ± 2.4 kg/m2) underwent bioimpedance and anthropometric measurements. Bioelectric resistance (R) and reactance (Xc) were standardized for the athlete’s height and used to plot the vector in the R-Xc graph according to the BIVA approach. Total body water (TBW), phase angle (PhA), and somatotype were determined from bioelectrical and anthropometric data. Results: No significant difference (p > 0.05) for age and for age at the start of competition among the athletes was found. Athletes divided into groups of TBW limited by quartiles showed significant differences in the mean vector position in the R-Xc graph (p < 0.001), where a higher content of body fluids resulted in a shorter vector and lower positioning in the graph. Furthermore, six categories of somatotypes were identified, and the results of bivariate and partial correlation analysis highlighted a direct association between PhA and mesomorphy (r = 0.401, p < 0.001) while showing an inverse correlation with ectomorphy (r = −0.416, p < 0.001), even adjusted for age. On the contrary, no association was observed between PhA and endomorphy (r = 0.100, p = 0.471). Conclusions: Body fluid content affects the vector length in the R-Xc graph. In addition, the lateral displacement of the vector, which determines the PhA, can be modified by the morphological characteristics of the athlete. In particular, higher PhA values are observed in subjects with a high mesomorphic component, whereas lower values are found when ectomorphy is dominant.

Distribution of the number of fitness maxima in Fisher’s geometric model

Fisher’s geometric model describes biological fitness landscapes by combining a linear map from the discrete space of genotypes to an n-dimensional Euclidean phenotype space with a nonlinear, single-peaked phenotype-fitness map. Genotypes are represented by binary sequences of length L, and the phenotypic effects of mutations at different sites are represented by L random vectors drawn from an isotropic Gaussian distribution. Recent work has shown that the interplay between the genotypic and phenotypic levels gives rise to a range of different landscape topographies that can be characterised by the number of local fitness maxima. Extending our previous study of the mean number of local maxima, here we focus on the distribution of the number of maxima when the limit L → ∞ is taken at finite n. We identify the typical scale of the number of maxima for general n, and determine the full scaled probability density and two point correlation function of maxima for the one-dimensional case. We also elaborate on the close relation of the model to the anti-ferromagnetic Hopfield model with n random continuous pattern vectors, and show that many of our results carry over to this setting. More generally, we expect that our analysis can help to elucidate the fluctuation structure of metastable states in various spin glass problems.

Reservoir formation conditions and key technologies for exploration and development in Shengtuo oilfield in Bohai Bay Basin

The Shengtuo oilfield is the largest monolithic oilfield in the Bohai Bay Basin and even in the continental fault basins of Eastern China. Since discovered in 1963, the Shengtuo oilfield experiences the early exploration stage of rapid reserve discovery and production, the middle exploration stage of high and stable production and development, and the late exploration stage of theoretical and technological innovation for expanding the field of exploration, research on fine development technology of high-water-cut reservoir for enhanced oil recovery, and maintaining slow decline of oil production. Reserves of this oilfield increase in each stage. By the end of 2018, after more than 50 years of exploration and development, the Shengtuo oilfield has cumulative proven oil reserves of 0.512 × 109t, cumulative oil production of 0.193 × 109t, and it keeps stable annual production of more than 1.50 × 106t in 2018. Abundant hydrocarbon resources, large anticline structure near to oil source, multiple types of reservoirs and traps, and favorable hydrocarbon migration channels provide favorable hydrocarbon accumulation conditions for the Shengtuo oilfield. Fine development techniques such water-flooding in the early development stage, fine reservoir description in the high water-cut stage, stratigraphic subdivision and well pattern vector adjustment, tapping remaining oil in rhythmic layers, etc., as well as continuous progress in exploration technologies of glutenite and turbidite reservoirs around the main body of the oilfield in the high-level exploration stage, provide effective supports for continuous increase of reserves and long-term high and stable production of the Shengtuo oilfield.

DPWord2Vec: Better Representation of Design Patterns in Semantics

With the plain text descriptions of design patterns, developers could better learn and understand the definitions and usage scenarios of design patterns. To facilitate the automatic usage of these descriptions, e.g., recommending design patterns by free-text queries, design patterns and natural languages should be adequately associated. Existing studies usually use texts in design pattern books as the representations of design patterns to calculate similarities with the queries. However, this way is problematic. Lots of information of design patterns may be absent from design pattern books and many words would be out of vocabulary due to the content limitation of these books. To overcome these issues, a more comprehensive method should be constructed to estimate the relatedness between design patterns and natural language words. Motivated by Word2Vec, in this study, we propose DPWord2Vec that embeds design patterns and natural language words into vectors simultaneously. We first build a corpus containing more than 400 thousand documents extracted from design pattern books, Wikipedia, and Stack Overflow. Next, we redefine the concept of context window to associate design patterns with words. Then, the design pattern and word vector representations are learnt by leveraging an advanced word embedding method. The learnt design pattern and word vectors can be universally used in textual description based design pattern tasks. An evaluation shows that DPWord2Vec outperforms the baseline algorithms by 17.1%-96.5% in measuring the similarities between design patterns and words in terms of Spearman's rank correlation coefficient. Moreover, we adopt DPWord2Vec on two typical design pattern tasks. In the design pattern tag recommendation task, the DPWord2Vec based method outperforms two state-of-the-art algorithms by 6.6% and 32.7% respectively when considering Recall@10. In the design pattern selection task, DPWord2Vec improves the existing methods by 6.5%-70.7% in terms of MRR.