Distribution Histograms Research Articles

Methodology for determining bottlenecks on the city's street-road network by analyzing GPS track data

Problem. The article considers the issue of determining the location of "bottlenecks" on the highways of large cities based on the study of the vehicle's driving mode, obtained as a result of GPS data processing and analysis. Purpose. The purpose of this study is to develop and test the methodology for identifying potential "bottlenecks" on the city's freeway by analyzing the GPS track data of the car. The subject of the study is the interrelationship of the characteristics of the sections of the city’s street-road network (SRN) with the parameters characterizing the vehicle movement mode in the traffic flow. Methodology. Two experimental routes with the same starting and ending points were chosen to obtain data on traffic conditions on the SRN of the city of Kharkiv, which correspond to typical routes of official movement of personal transport on weekdays. During the movement of the car along the specified routes, GPS tracks were obtained, whose processing made it possible to determine the driving conditions along the entire length of the routes. Results. The work presents a method of researching the vehicle's driving mode by analyzing GPS track data; the determined indicators of the traffic regime, which can be effectively used as criteria for determining potential "bottlenecks" on the city's SRN; the methodology was tested on real traffic routes on the SRN of the city of Kharkiv. For selected routes, the work presents histograms of instantaneous speed distribution, graphs of car movement in "distance - speed" and "time - speed" coordinates. Graphs of changes in specific time in motion, specific idle time, speed gradient, energy gradient, Hermann-Prygozhin criterion were obtained for individual kilometer segments of routes. The specific idle time and the Herman-Prygozhin criterion turned out to be the most effective criteria for the purposes of determining the "bottlenecks" of SRN. Originality. An experimental technique was developed and tested, which allows to determine the potential "bottlenecks" of the city's SRN as a result of conducting short-term and not labor-intensive research. The proposed approach does not require the presence of specialized equipment or software, which makes this method effective when conducting scientific research. Practical value. The possibility of using the proposed method of data processing of GPS tracks to analyze traffic conditions on the city highway and identify potential "bottlenecks" was shown. For the selected routes in Kharkiv, such sections turned out to be Vesnina St. (beyond the intersection with Pushkinska St.); Heroes of Stalingrad Ave. (access to the intersection from Leva Landau Ave.); Gagarina Ave. (access to the intersection with Kashtanova St.)

SpineTool is an open-source software for analysis of morphology of dendritic spines

Dendritic spines form most excitatory synaptic inputs in neurons and these spines are altered in many neurodevelopmental and neurodegenerative disorders. Reliable methods to assess and quantify dendritic spines morphology are needed, but most existing methods are subjective and labor intensive. To solve this problem, we developed an open-source software that allows segmentation of dendritic spines from 3D images, extraction of their key morphological features, and their classification and clustering. Instead of commonly used spine descriptors based on numerical metrics we used chord length distribution histogram (CLDH) approach. CLDH method depends on distribution of lengths of chords randomly generated within dendritic spines volume. To achieve less biased analysis, we developed a classification procedure that uses machine-learning algorithm based on experts’ consensus and machine-guided clustering tool. These approaches to unbiased and automated measurements, classification and clustering of synaptic spines that we developed should provide a useful resource for a variety of neuroscience and neurodegenerative research applications.

Color restoration based on digital pathology image.

Protective color restoration of faded digital pathology images based on color transfer algorithm. Twenty fresh tissue samples of invasive breast cancer from the pathology department of Qingdao Central Hospital in 2021 were screened. After HE staining, HE stained sections were irradiated with sunlight to simulate natural fading, and every 7 days was a fading cycle, and a total of 8 cycles were experienced. At the end of each cycle, the sections were digitally scanned to retain clear images, and the color changes of the sections during the fading process were recorded. The color transfer algorithm was applied to restore the color of the faded images; Adobe Lightroom Classic software presented the histogram of the image color distribution; UNet++ cell recognition segmentation model was used to identify the color restored images; Natural Image Quality Evaluator (NIQE), Information Entropy (Entropy), and Average Gradient (AG) were applied to evaluate the quality of the restored images. The restored image color met the diagnostic needs of pathologists. Compared with the faded images, the NIQE value decreased (P<0.05), Entropy value increased (P<0.01), and AG value increased (P<0.01). The cell recognition rate of the restored image was significantly improved. The color transfer algorithm can effectively repair faded pathology images, restore the color contrast between nucleus and cytoplasm, improve the image quality, meet the diagnostic needs and improve the cell recognition rate of the deep learning model.

Prediction of chloride ion concentration distribution in basalt-polypropylene fiber reinforced concrete based on optimized machine learning algorithm

The distribution characteristics of chloride ion concentration in basalt-polypropylene fiber reinforced concrete (BPFRC-CC) are important for assessing the durability of concrete structures under marine environment. This study collected the distribution data of BPFRC-CC in three different environments: tidal, submersible, and salt spray. Several optimized machine learning models were developed to predict the distribution of BPFRC-CC. The performance of these models was evaluated based on a comparison between actual and predicted values, residual distribution histograms, and performance indicators. The research results of this article showed that the particle swarm optimization support vector regression (PSO-SVR) model exhibits significant accuracy and generalization ability, with closer proximity to the actual values in both the training and testing sets. The residual distribution histogram of the PSO-SVR model approximated a normal distribution with a smaller mean and standard deviation. Evaluation indicators, including R2, MSE, RMSE, MAE, and MAPE, for the PSO-SVR model were 0.994, 6.92e-5, 0.0083, 0.0062, and 0.0453, respectively. The SHAP values revealed that depth and age were the most critical influencing factors. The decrease in age, water-cement ratio, and water-binder ratio, the addition of basalt fibers and polypropylene fibers, and the increase in depth reduced the BPFRC-CC. In addition, BPFRC-CC in tidal, salt spray, and submersible areas decreased in that order. Finally, a graphical user interface for BPFRC-CC was developed, providing researchers and production personnel with an intuitive, efficient, and visual production experience. This study has important implications for the optimization of BPFRC formulations and the prediction and assessment of the life of BPFRC structures.

Improved Algorithm for Estimation of Linear Energy Transfer in Carbon Ion Radiotherapy Plans.

This study aimed to develop an improved algorithm for linear energy transfer (LET) estimation in carbon ion radiotherapy (CIRT) using relative biological effectiveness (RBE) and to establish a clinical pipeline for LET assessment. New approximation functions for LET versus RBE were developed for the overkill region. LET estimation performance was examined at two facilities (A and B) using archival- and Monte Carlo simulation-derived LET data, respectively, as a reference. A clinical pipeline for LET assessment was developed using Python and treatment planning systems (TPS). In dataset A, LET estimation accuracy in the overkill region was improved by 80.0%. In dataset B, estimation accuracy was 2.3%±0.67% across 5 data points examined. LET distribution and LET-volume histograms were visualized for multiple CIRT plans. The new algorithm showed a greater LET estimation performance at multiple facilities using the same TPS. A clinical pipeline for LET assessment was established.

Statistical Comparison among Brain Networks with Popular Network Measurement Algorithms

In this research, a number of popular network measurement algorithms have been applied to several brain networks (based on applicability of algorithms) for finding out statistical correlation among these popular network measurements which will help scientists to understand these popular network measurement algorithms and their applicability to brain networks. By analyzing the results of correlations among these network measurement algorithms, statistical comparison among selected brain networks has also been summarized. Besides that, to understand each brain network, the visualization of each brain network and each brain network’s degree distribution histogram have been extrapolated. Six network measurement algorithms have been chosen to apply time to time on sixteen brain networks based on applicability of these network measurement algorithms and the results of these network measurements are put into a correlation method to show the relationship among these six network measurement algorithms for each brain network. At the end, the results of the correlations have been summarized to show the statistical comparison among these sixteen brain networks

Analysis Method of Full-Scale Pore Distribution Based on MICP, CT Scanning, NMR, and Cast Thin Section Imaging—A Case Study of Paleogene Sandstone in Xihu Sag, East China Sea Basin

Using different experimental methods, the pore radius ranges vary greatly, and most scholars use a single experiment to study pore structure, which is rarely consistent with reality. Moreover, the numerical models used in different experiments vary and cannot be directly compared. This article uniformly revised all experimental data into a cylinder model. Quantitative analysis of the full-scale pore distribution is established by mercury withdrawal–CT data, and semi-quantitative distribution is obtained by mercury–NMR–cast thin section imaging. In this paper, we introduce the tortuosity index (τ) to convert the CT ball-and-stick model into a cylinder model, and the pore shape factor (η) of the cast is used to convert the plane model into the cylinder model; the mercury withdrawal data is applied to void the influence of narrow throat cavities, and the NMR pore radius distribution is obtained using the mercury-T2 calibration method. Studies have shown that the thickness of bound water is 0.35~0.4 μm, so the pores with different radius ranges were controlled by different mechanisms in the NMR tests, with pores &lt; 0.35~0.4 μm completely controlled by surface relaxation, including strong bound water and weak bound water; pores in the 0.4~4 μm reange were controlled by surface relaxation; and pores &gt; 10 μm were completely controlled by free relaxation. The surface relaxivity rate of fine sandstone was 18~20 μm/s. The tortuosity index τ was generally 1~7; the larger the value, the more irregular the pores. The pore shape factor η was generally 0.2~0.5; the smaller the value, the more irregular the pores. Mercury withdrawal–CT scan data can quantitatively determine the pore radius distribution curve. The coefficient of the logarithm is positive considering porosity, and the constant is negative considering porosity. Permeability controls the maximum pore radius, with a max pore radius &gt; 100 μm and a permeability &gt; 1 mD. Mercury withdrawal–NMR–cast thin section imaging data can semi-quantitatively establish a pore radius distribution histogram. The histogram represents quasi-normal, stepped, and unimodal data. When 60 μm is the inflection point, if a large proportion of pores measure &gt; 60 μm, good reservoir quality is indicated. If a large proportion of pores measures &lt; 60 μm, the permeability is generally &lt;0.5 mD.

A methodological framework for specular return removal from photon-counting LiDAR data

The Ice, Cloud, and land Elevation Satellite-2 (ICESat-2) data may contain abundant noise photons induced by specular reflection, which make the signal photon detection and surface elevation extraction challenging, especially on flat surfaces with high reflectivity. However, no efficient algorithm for specular return noise removal has been proposed. Therefore, this study aims to propose a novel methodological framework based on statistical features to remove noise photons induced by specular reflection. First, ICESat-2 data preprocessing was performed to improve the speed and accuracy of subsequent processing. Second, the statistical features of outlier distance were calculated and utilized to filter out noise photons. Third, the specular return noise was removed according to the extreme points in the elevation distribution histogram. Finally, the manually labeled of photons and in-situ data were utilized to evaluate the performance of the proposed framework. Additionally, the proposed framework was compared with three existing signal photon extraction algorithms (ATL03, ATL13, AVEBM) for further assessment. The experimental results show that the F1-score of the proposed framework is 99.9 % and the accuracy of water level estimation is extremely high (bias = 0.041 m, and RMSE = 0.082 m). Further analysis demonstrates that our framework has the high robustness because it is not sensitive to input parameter. Meanwhile, the weak beam achieved higher water elevation accuracy than that of the strong beam. Besides, the proposed framework performs better than the existing methods in extracting water surface photons and water level. All in all, the proposed framework has been shown to effectively remove noise photons of specular returns in the raw ICESat-2 data and reduce the underestimation of the water level.

Synthesis of B&lt;sub&gt;4&lt;/sub&gt;C–TiB&lt;sub&gt;2&lt;/sub&gt; composition powder mixtures by carbidobor reduction using nanofibrous carbon for ceramic fabrication

The results of the researching process of obtaining composition powder material B4C–TiB2 by carbide reduction of titanium dioxide, using carbon reducing agent – carbon nanofibers, are presented. Furthermore, the results of studying of some properties of ceramics made using the synthesized powder are presented. The synthesis of composite materials was carried out in an induction crucible furnace for 20 min in the temperature range of 1200–1900 °C in an argon atmosphere. It has been established that the optimum temperature of the synthesis is 1650 °C, irrespective of the batch composition. The characteristics of the composite powders containing 10–30 mol. % of the TiB2 phase have been studied. X-ray electron microscopy has revealed that the particles of the powder are predominantly aggregated. There are two peaks in the particle size distribution histograms. The part of the histogram with a smaller particle size mainly characterizes the B4C phase. The part of the histogram with a larger particle size characterizes the TiB2 phase. The average particle size of the B4C phase is in the range of 5.3–5.5 µm, and that of the TiB2 phase is in the range of 33.6–41.9 µm. The average size of 50 % of composite powder’s particles for these contents does not exceed 13.4 μm. The surface area of the samples does not exceed 5 m2/g. The oxidation of the composite powder materials by atmospheric oxygen begins at a temperature of approximately 500 °C. At the same time, when the temperature reaches 1000 °C, no more than 45 wt. % of the studied powders is oxidized. Ceramics made with the synthesized powder mixture B4C + 30 mol. % TiB2 by hot pressing has shown rather high values of relative density (99.0±1.1 %) and fracture toughness (5.0±0.2 MPa∙m0.5).

Construction of Quasi-DOE on Sobol’s Sequences with Better Uniformity 2D Projections

Abstract In order to establish the projection properties of computer uniform designs of experiments on Sobol’s sequences, an empirical comparative statistical analysis of the homogeneity of 2D projections of the best known improved designs of experiments was carried out using the novel objective indicators of discrepancies. These designs show an incomplete solution to the problem of clustering points in low-dimensional projections graphically and numerically, which requires further research for new Sobol’s sequences without the drawback mentioned above. In the article, using the example of the first 20 improved Sobol’s sequences, a methodology for creating refined designs is proposed, which is based on the unconventional use of these already found sequences. It involves the creation of the next dimensional design based on the best homogeneity and projection properties of the previous one. The selection of sequences for creating an initial design is based on the analysis of numerical indicators of the weighted symmetrized centered discrepancy for two-dimensional projections. According to the algorithm, the combination of sequences is fixed for the found variant and a complete search of the added one-dimensional sequences is performed until the best one is detected. According to the proposed methodology, as an example, a search for more perfect variants of designs for factor spaces from two to nine dimensions was carried out. New combinations of Sobol’s sequences with better projection properties than those already known are given. Their effectiveness is confirmed by statistical calculations and graphically demonstrated box plots and histograms of the projection indicators distribution of the weighted symmetrized centred discrepancy. In addition, the numerical results of calculating the volumetric indicators of discrepancies for the created designs with different number of points are given.

Morphological structure of the Pb island films melted on the Ta layer surface

An effective way to create self-organizing arrays of metal particles is to melt thin layers of substance on a poorly wetted surface. Such arrays may improve the technological properties of functional structures, and are themselves functional elements of modern devices and systems. During the melting of a solid layer on a poorly wetted substrate, an array of spherical particles is formed, which are evenly distributed over the surface of the substrate. The distribution of particles by size is determined by the thickness of the fusible layer and conditions of the deposition. The location of islands, formed after the melting of vapour-crystal deposited solid films, is determined primarily by the initial stages of de-wetting, when the thin continuous film starts to decay while remaining in solid state. This work studied self-organizing processes during the melting of Pb films deposited on a Ta substrate. The films were deposited on glass plates in a high vacuum and then after deposition were heated to a temperature slightly above the Pb melting point. After the heat treatment the samples were removed from the vacuum chamber and examined using SEM microscopy and EDS analysis. It was discovered that arrays of spherical particles are formed during the melting of micron-thick Pb films. The histograms of the size distribution of such particles are quite wide and can be represented as bimodal with partially overlapping maxima. This can be explained by active coalescence processes in thicker samples. This study demonstrated that small temperature gradients can cause noticeable kinetic effects that allow separate particles to move macroscopic distances and capture the surrounding substance. The study also estimated the energy associated with the optimization of the morphological structure of vacuum condensate and which is a physical factor of de-wetting.

Anatomic Location, Age, Gender and Staging of Osteosarcoma Patients Presenting to a Tertiary Care Centre

Osteosarcoma is a high grade primary skeletal malignancy characterised by spindle cells of mesenchymal origin depositing immature osteoid matrix. With an annual incidence rate of 3.1 cases per million in the US, Osteosarcoma accounts for less than 1% of all newly diagnosed cancer in adults and 3-5% of those in children, but it is the most common malignancy in adolescents outside of leukemia and lymphoma. In India, the incidence varies from 4.7% to 11.6%, where this malignancy is associated with significant morbidity and mortality. Our study shows that Age distribution histogram shows a bimodal distribution. We observed that the most common site of osteosarcoma is around the knee joint in proximal tibia and distal femur. In our study we found that the tumour has higher prevalence in males than females. Most of the patients presented to us at Enneking stage 2b and AJCC stage 2a and 2b. Keywords: AJCC-American Joint Commission on Cancer

Extraterrestrial dust flux monitoring at Antarctic Vostok station: New collection of extraterrestrial spherules fallen from May to September 2017

AbstractDust particles obtained by filtering fresh snow collected from May to September 2017 in the vicinity of Vostok station in Antarctica were examined using a scanning electron microscope. The collection of dust particles contains 197 spherules ranging from 0.5 to 117 μm in diameter, the most abundant ones (n = 188) by far being iron oxide spherules. Analyses of meteorological and human activity data suggest an extraterrestrial origin of most of the spherical particles. The particle size distribution histogram showed a smooth increase in their number with decreasing size and a dramatic drop at sizes smaller than 3 μm. The number of spherical particles has an uneven distribution over time, with an intense peak in July 27–28, 2017 which correlates by dates with the peak of the Southern Delta Aquariids meteor shower. The size distribution of the particles collected during the same period indicates the presence of a mechanism that accelerates their fall to the Earth. We propose that they are effective centers of condensation of ice crystals in stratospheric clouds. Our data indicate that collection of micrometeorites with sizes of several microns from the fresh snow is possible, opening a new way for sampling micrometeorites, including separate meteor showers.

Machine learning - a novel approach to predict the porosity curve using geophysical logs data: An example from the Lower Goru sand reservoir in the Southern Indus Basin, Pakistan

Porosity estimation is one of the essential issues in oil and natural gas industries to evaluate the reservoir characteristics properly. Therefore, it is imperative to predict porosity with the optimum way to reduce logging tests. In this paper, fuzzy logic (FL) and neural networks (NNs) are considered effective approaches to predict the Lower Goru sand reservoir's porosity curve. The input dataset for the study contained four known logs, gamma ray (GR), neutron porosity (NPHI), density (RHOB), and sonic (DT) of five wells drilled. For the fuzzy logic model, ten bins were used. The closeness of fit (Cfit) curves were computed using the most likely and second most likely curves. The weighted average final probability Pi, or the most likely solution, was also calculated. The curve histogram distribution and set of curve bin distribution cross plots were built using a fuzzy model. In the fuzzy logic model, the Gaussian membership function provided the optimum match for the examined geophysical log data. Fuzzy logic models indicate Cfit values ranging from 94 to 100% for Sawan-01, Sawan-02, Sawan-03, Sawan-07, and Sawan-08, with standard deviations of 1.248, 1.241, 1.254, 1.336, and 1.374, respectively. The neural networks model was trained using the backpropagation (BP) algorithm. The neural networks model has a Cfit_nn of 88%–100% across five wells with standard deviations of 0.016, 0.014, 0.015, 0.017, and 0.018. The results show that the predicted modeling evaluations using fuzzy logic and neural networks techniques fit the geophysical log data quite well. The multiple linear regression (MLR) assessments were conducted using the same geophysical log datasets of five studied boreholes for comparison. The coefficients of determination (R2) for the fuzzy logic (PHIT_ml) and neural networks (PHIT_nn) models were 0.960127, and 0.973039, respectively, whereas the values of the PHIT curve for multiple linear regression (PHIT_mlr) 0.926329. The high R2 values show that fuzzy logic and neural networks are more effective methods for PHIT curve prediction than the multiple linear regression approach. The relevant correlation was derived by comparing synthetic log values to actual log values. The evaluations between recorded and predicted values applying the two distinct approaches fuzzy logic and neural networks revealed that both are effective at synthesizing PHIT logs. The confirmation of this efficiency was further verified by the low values obtained in the root mean square error (RMSE) analysis. The study conducted on the Sawan Gas Field wells revealed that both fuzzy logic and neural networks are reliable approaches for predicting the PHIT curve. By using a composite of GR, RHOB, NPHI, and DT logs, these techniques can provide a realistic fit for both actual and synthesized PHIT curves. The findings of this study suggest that the implementation of these methods can contribute to the improvement of hydrocarbon exploration and production in the region by reducing uncertainty in predicting the PHIT curve. Moreover, the methods used in this study have the potential for wider application beyond the Sawan Gas Field. These methods can be applied globally to predict the PHIT curve and evaluate the reservoir prospects. The successful application of fuzzy logic and neural networks in this paper provides a solid foundation for future research on using machine learning techniques in reservoir characterization and modeling.

The Pareto Principle in the Functions Approximating Processing the Results of Psychological and Sociological Research

The possibilities of approximating functions in the processing of large data arrays of the results of psychological and sociological research are analyzed. An approach to the processing of areas limited by approximating functions is substantiated in accordance with the Pareto principle. Threshold values are obtained that ensure the division of areas in the ratio 1/4 for the most frequently used for approximating the results of studies of approximating functions. The conformity of the law of distribution of histograms of scientific achievements of scientists, approximating them with curves, according to Pearson's goodness-of-fit criterion is checked.

Research of the lithofacies properties of the Productive series rocks in the north-west flank Bulla-Project field

The Bulla-deniz field belongs to the oil-gas region of the Baku archipelago and is located on the Kanizadag-Babek anticline. During the tectonic subsidence and rapid sedimentation process in the region in the upper parts of the development period for the productive layer, the flow of large and coarse-grained materials increased and there were favorable conditions for the formation of hydrocarbon deposits. Quaternary – QLD ages sediments were discovered by drilling in the Bulla-deniz field. Gas and condensate products have been discovered in the North-East wing of the field, and along the depth in the V, VII and VIII horizons of the productive series, and the exploitation is continued. In the article, the lithological-facies characteristics of the rocks are analyzed by following the stratigraphic cross-section of the horizons and layers within the Productive series in the area and depth of the Bulla-deniz field. On the basis of well logging diagrams, the well picks depths of the V, VII and VIII horizons in the North-East wing of the field were monitored and specified. A 3D facial model was created using Irap RMS modeling software. In the model, the change of two facies – sand and clay – is monitored by the stochastic distribution algorithm. It is discussed, to determine the areas with more favorable collecting capacity for collecting oil and gas in the field by constructing trend maps and distribution histogram of sand thicknesses on horizons within the Productive series.

Steganalysis of Neural Networks Based on Symmetric Histogram Distribution

Deep neural networks have achieved remarkable success in various fields of artificial intelligence. However, these models, which contain a large number of parameters, are widely distributed and disseminated by researchers, engineers, and even unauthorized users. Except for intelligent tasks, typically overparameterized deep neural networks have become new digital covers for data hiding, which may pose significant security challenges to AI systems. To address this issue, this paper proposes a symmetric steganalysis scheme specifically designed for neural networks trained for image classification tasks. The proposed method focuses on detecting the presence of additional data without access to the internal structure or parameters of the host network. It employs a well-designed method based on histogram distribution to find the optimal decision threshold, with a symmetric determining rule where the original networks and stego networks undergo two highly symmetrical flows to generate the classification labels; the method has been shown to be practical and effective. SVM and ensemble classifiers were chosen as the binary classifier for their applicability to feature vectors output from neural networks based on different datasets and network structures. This scheme is the first of its kind, focusing on steganalysis for neural networks based on the distribution of network output, compared to conventional digital media such as images, audio, and video. Overall, the proposed scheme offers a promising approach to enhancing the security of deep neural networks against data hiding attacks.

Trend Change Analysis as a New Tool to Complement the Evaluation of Human Body Balance in the Time and Frequency Domains.

Trend change analysis is a tool that complements the assessment of human body stability and provides information on the number and frequency of postural corrections during an examination. The present research aims to determine the possibility of using this method of analysis to investigate postural stability during tests of standing with open eyes (OE) and closed eyes (CE). A total of 118 participants (67 females, 51males) aged 23 (SD 1.3) were assessed. Tests involved standing on a stabilographic platform for 50 s. Trend change analysis was used to evaluate displacement values of the center of pressure (COP). Values for the COP courses as well as values associated with trend change analysis, such as: TCI, MACD_t and MACD_V were determined. Histograms of distribution were plotted for TCI values. The present study provides information on alterations of the strategy used for maintaining balance, which are associated with the number of postural corrections and COP displacement between corrections for measurements taken during the standing test with CE in relation to OE measurements. The strategy demonstrated an ability to detect a smaller number of quick corrections, an increased number of corrections of longer duration, and the elongation of displacement between subsequent postural corrections. Slight standard deviations in TCI and MACD_t values calculated during trend change analysis, for both the OE and CE conditions, made it possible to classify these values as indexes of postural stability with significant sensitivity to slight changes.

A comparative assessment of machine learning algorithms with the Least Absolute Shrinkage and Selection Operator for breast cancer detection and prediction

Breast cancer is the most common life-threatening cancer in women and one of the leading causes of death. Early diagnosis is one of the best defenses against the spread of breast cancer. Machine learning (ML) tools are now available for cancer detection and prediction. This study presents a comparative assessment of machine learning models for diagnosing breast cancer based on various classification schemes. Our classification methodology is based on well-organized data collection, preparation, transformation, and exploratory analysis (including correlation matrix, histogram, and data distribution). All characteristics are compared with the results of applying the Least Absolute Shrinkage and Selection Operator (LASSO) approach, which selects the most important attributes. Logistic Regression (LR), K-Nearest Neighbors (KNN), Extreme Gradient Boosting (XGB), Gradient Boosting (GB), Random Forest (RF), Multilayer Perceptron (MLP), and Support Vector Machine (SVM) algorithms have been applied in this study. We have achieved the maximum accuracy of 90.68% by RF compared with LASSO. Similarly, the recall in KNN was 98.80%, the precision in MLP was 92.50%, and the F1 score in RF was 94.60%.

Spatio-temporal changes of evapotranspiration over the Zoige Wetland Basin in China using TSEB and GF satellites

ABSTRACT The Zoige wetland located in the eastern margin of the Tibet Plateau, is very important for the runoff regulation and biodiversity in the Yellow River basin. Due to the large non-uniformity of the alpine wetland surface, the use of higher spatial resolution satellite remote sensing data is essential to match or validate the results of ground observation. The land evapotranspiration in this survey was estimated by using the GF-4 satellite data from 2016 to 2020 into the Two Source Energy Balance (TSEB) model, and the estimated evapotranspiration is compared to the ground observation. The results show that: (1) the regression analysis of the actual observed evapotranspiration and the evapotranspiration estimated by the TSEB model shows that the actual evapotranspiration and the evapotranspiration calculated by the TSEB model have a good positive linear correlation (R2 > 0.8) at the Maqu observation site and the Huahu wetland observation site. Therefore, the accuracy of the evapotranspiration calculated by the TSEB model is high. (2) The spatio-temporal distribution of evapotranspiration and relevant land surface variables is generally characterized by high in the southeast and low in the northwest over the Zoige wetland basin. (3) The mean daily evapotranspiration for different GF-4 observation over the Zoige area is as follows: 1.8 mm on 8 April 2018, 3.6 mm on 20 July 2016, 1.4 mm on 29 November 2020 and 0.9 mm on 15 December 2017, and the magnitudes of evapotranspiration of the different surface are as follows: waterbody > grassland > bare land. (4) The histogram of the frequency distribution of evapotranspiration show that 3.2–4.0 mm on 20 July 2016, 0–0.8 mm on 15 December 2017, 0.8–1.6 mm on 8 April 2018 and 1.6–2.4 mm on 29 November 2020 are the maximum evapotranspiration range over the Zoige wetlands area.