Bimodal Data Research Articles

A Generalized Suja Distribution with Application to Lifetime Data

This paper introduces a generalized Suja distribution called the Kumaraswamy-Suja (KW-Suja) distribution using the Kumaraswamy generator. The proposed distribution has Suja distribution as a special case. Some statistical and reliability properties of the new distribution were derived and the method of maximum likelihood was employed for estimating the model parameters. The usefulness and flexibility of the KW-Suja distribution were illustrated with a real lifetime data. Results based on the log-likelihood and goodness of fit statistics values showed that the KW-Suja distribution provides a better fit to the data than the other competing distributions considered in this study. The KW-Suja distribution is therefore recommended for effective modelling of the unimodal or bimodal continuous lifetime data with non-decreasing shape and bathtub-shaped failure rate.

A new regression model for the analysis of bimodal censored data: A comparison with random survival forest

A new regression model for the analysis of bimodal censored data: A comparison with random survival forest

Subject-Specific Probability Maps of Scalp, Skull and Cerebrospinal Fluid for Cranial Bones Segmentation in Neonatal Cerebral MRIs

ObjectivesSegmentation of cranial bones in magnetic resonance images (MRIs) is a challenging and indispensable task to study neonatal brain development and injury. This paper presents a new approach for creating subject-specific probability maps of the scalp, skull and cerebrospinal fluid (CSF) from retrospective bimodal (MR and CT) images acquired from neonates in the gestational age range of 39 to 42 weeks. These maps are subsequently employed for the segmentation of cranial bones in cerebral MRIs from neonates in the same age range. Material and methodsRetrospective MR and CT of neonates with normal head in the gestational age range of 39-42 weeks were preprocessed, segmented semi-automatically and employed as atlas data. For an input MR image acquired from a subject under study, a preprocessing stage and three main processing blocks were performed: First, subject-specific head and intracranial templates and CSF probability map were created using retrospective MR atlas data. Second, the CT atlas data were coregistered to MR templates and the resulted deformation matrices were fed to the next block to create subject-specific scalp and skull probability maps. Finally, some novel performance measures were presented to evaluate the performance of subject-specific CSF, scalp and skull probability maps for skull and intracranial segmentation in neonatal MRIs. ResultsThe subject-specific probability maps were employed for brain tissue extraction and compared with two public methods such as Brain Extraction Tool (BET) and Brain Surface Extractor (BSE). They were also applied for cranial bone extraction. Then, the similarity in shape between the frontal and occipital sutures (which had been reconstructed from segmented cranial bones) and the ground truth landmarks was evaluated. For this purpose, modified versions of the Dice similarity coefficient (DSC) were used. Finally, a retrospective bimodal (MR-CT) data acquired from a neonate within a short time interval was used for evaluation. After co-alignment of the two images, the DSC and modified Hausdorff distance (MHD) were used to compare the similarity of cranial bones in the MR and CT images. ConclusionSignificant improvements were achieved compared to conventional methods which rely solely on MR image intensities. These advancements hold promise for enhancing neurodevelopmental studies in neonates. The algorithm for creating subject-specific atlases is publicly accessible through a graphical user interface at medvispy.ee.kntu.ac.ir.

Seeing and Thinking about Urban Blue–Green Space: Monitoring Public Landscape Preferences Using Bimodal Data

Urban blue–green spaces (UBGSs) are a significant avenue for addressing the worldwide mental health crisis. To effectively optimise landscape design and management for the promotion of health benefits from UBGS, it is crucial to objectively understand public preferences. This paper proposes a method to evaluate public landscape preference from the perspective of seeing and thinking, takes the examples of seven parks around the Dianchi Lake in Kunming, China, and analyses the social media data by using natural language processing technology and image semantic segmentation technology. The conclusions are as follows: (1) The public exhibits significantly high positive sentiments towards various UBGSs, with over 93% of comments expressed positive sentiments. (2) Differences exist in the frequency and perception of landscape features between image and text modalities. Landscape elements related to stability are perceived more in images than in text, while dynamic and experiential elements are perceived more in text than in images. (3) In both modalities, the distinctive landscape features of parks are more frequently perceived and preferred by the public. In the end, the intrinsic links between landscape elements and public sentiment and preferences are discussed, and suggestions for design and management improvements are made to consolidate their health benefits to the public.

Generating bimodal privacy-preserving data for face recognition

The performance of state-of-the-art face recognition systems depends crucially on the availability of large-scale training datasets. However, increasing privacy concerns nowadays accompany the collection and distribution of biometric data, which has already resulted in the retraction of valuable face recognition datasets. The use of synthetic data represents a potential solution, however, the generation of privacy-preserving facial images useful for training recognition models is still an open problem. Generative methods also remain bound to the visible spectrum, despite the benefits that multispectral data can provide. To address these issues, we present a novel identity-conditioned generative framework capable of producing large-scale recognition datasets of visible and near-infrared privacy-preserving face images. The framework relies on a novel identity-conditioned dual-branch style-based generative adversarial network to enable the synthesis of aligned high-quality samples of identities determined by features of a pretrained recognition model. In addition, the framework incorporates a novel filter to prevent samples of privacy-breaching identities from reaching the generated datasets and improve both identity separability and intra-identity diversity. Extensive experiments on six publicly available datasets reveal that our framework achieves competitive synthesis capabilities while preserving the privacy of real-world subjects. The synthesized datasets also facilitate training more powerful recognition models than datasets generated by competing methods or even small-scale real-world datasets. Employing both visible and near-infrared data for training also results in higher recognition accuracy on real-world visible spectrum benchmarks. Therefore, training with multispectral data could potentially improve existing recognition systems that utilize only the visible spectrum, without the need for additional sensors.

A vulnerability severity prediction method based on bimodal data and multi-task learning

Facing the increasing number of software vulnerabilities, the automatic analysis of vulnerabilities has become an important task in the field of software security. However, the existing severity prediction methods are mainly based on vulnerability descriptions and ignore the relevant features of vulnerability code, which only includes unimodal information and result in low prediction accuracy. This paper proposes a vulnerability severity prediction method based on bimodal data and multi-task learning. First the bimodal data, which consists of the description and source code of each vulnerability, is preprocessed. Next the GraphCodeBert is used for the word embedding module to extract different vulnerability features from the bimodal data. Then the Bi-GRU with attention mechanism is adopted for further feature extraction of vulnerability severity. Considering the strong correlation between the two tasks of vulnerability severity prediction and exploitability prediction, this paper proposes a multi-task learning approach, which allows the model to learn the connection and shared information between different tasks through a hard parameter sharing strategy, so as to achieve more accurate and reliable prediction of vulnerability severity. Experimental results show that the severity prediction method proposed in this paper outperforms state-of-the-art methods, and can achieve an average F1 score of 93.83 % on the public vulnerability dataset.

Urban flood vulnerability Knowledge-Graph based on remote sensing and textual bimodal data fusion

Flood disasters inflict extensive, serious damage on cities and society, significantly constraining urban construction and development. There is an urgent demand to reduce urban flood vulnerability, to explore the evolution mechanism of urban flood vulnerability, and to guide the construction and improvement of urban flood control resilience. An objective and accurate knowledge graph of urban flood vulnerability intuitively, quantitatively, and conveniently expresses the logical relationship between vulnerability indexes. This provides a theoretical and data-based foundation for enhancing urban flood resistance and improving the safety of urban flood control and drainage systems. To address this issue, first, the fusion extraction of text and remote sensing dual-mode data is achieved through technical means such as neural networks. Second, by using multiclass natural language processing (NLP) models, we create an objective index system for urban flood vulnerability that avoids subjective human influence. Finally, we construct an objective weight model group, calculate weights, and then, we establish a vulnerability knowledge graph. The results indicate that (1) by utilizing multidimensional remote sensing images and by adopting the robotic satellite (RoboSat) semantic segmentation model, we achieve high-precision extraction of the remote sensing parameters, such as those for urban roads, terrain, and buildings. Thus, we successfully transform remote sensing data into text data (accuracy is approximately 1 m). (2) We have confirmed the effectiveness of the subjective–objective combined weight method. (3) We introduce a novel approach to create an urban flood vulnerability index system based on bimodal objective data fusion. (4) Utilizing the flood vulnerability knowledge graph, we assess vulnerability levels within the primary urban areas of Zhengzhou City, and we propose governance strategies tailored to the current vulnerability status of each district.

Enhancing Infrared Optical Flow Network Computation through RGB-IR Cross-Modal Image Generation.

Due to the complexity of real optical flow capture, the existing research still has not performed real optical flow capture of infrared (IR) images with the production of an optical flow based on IR images, which makes the research and application of deep learning-based optical flow computation limited to the field of RGB images only. Therefore, in this paper, we propose a method to produce an optical flow dataset of IR images. We utilize the RGB-IR cross-modal image transformation network to rationally transform existing RGB image optical flow datasets. The RGB-IR cross-modal image transformation is based on the improved Pix2Pix implementation, and in the experiments, the network is validated and evaluated using the RGB-IR aligned bimodal dataset M3FD. Then, RGB-IR cross-modal transformation is performed on the existing RGB optical flow dataset KITTI, and the optical flow computation network is trained using the IR images generated by the transformation. Finally, the computational results of the optical flow computation network before and after training are analyzed based on the RGB-IR aligned bimodal data.

A Tightness Detection Method for Railway Fasteners Based on RGB-P Bimodal Data

A Tightness Detection Method for Railway Fasteners Based on RGB-P Bimodal Data

Bimodal data fusion of LIBS spectroscopy and plasma acoustic emission signals: improving the accuracy of machining process identification for low roughness samples

The fusion of LIBS spectral data with PAES data improves machining process classification identification accuracy.

New generalized extreme value distribution with applications to extreme temperature data

AbstractA new generalization of the extreme value distribution is presented with its density function, having a wide variety of density and tail shapes for modeling extreme value data. This generalized extreme value distribution will be referred to as the odd generalized extreme value distribution. It is derived by considering the distributions of the odds of the generalized extreme value distribution. Consequently, the new distribution is enlightened by not only having all six families of extreme value distributions; Gumbel, Fréchet, Weibull, reverse‐Gumbel, reverse‐Fréchet, and reverse‐Weibull as submodels but also convenient for modeling bimodal extreme value data that are frequently found in environmental sciences. Basic properties of the distribution, including tail behavior and tail heaviness, are studied. Also, quantile‐based aliases of the new distribution are illustrated using Galton's skewness and Moor's kurtosis plane. The adequacy of the new distribution is illustrated using well‐known goodness‐of‐fit measures. A simulation is performed to validate the estimated risk measures due to repeated data points frequently found in temperature data. The Grand Rapids and well‐known Wooster temperature data sets are analyzed and compared to nine different extreme value distributions to illustrate the new distribution's bimodality, flexibility, and overall fitness.

A flexible partially linear regression with random effects for bimodal data with application in postharvest

In the postharvest area of agricultural products, it is common to have data sets in which the dependent variable in general may not be symmetrical and unimodal, therefore, the use of usual regression models is not always appropriate. In addition, the data can also have repeated measurements over time. With this in mind, the aim of this article is to propose a partially linear regression model with random effects for postharvest bimodal data, this extended regression is based on the Birnbaum–Saunders distribution. Additionally we present different mathematical properties of this new model. To verify the impartiality and accuracy of the estimators, a simulation study was carried out. The parameters of partially linear regression with random effects are estimated using the penalized maximum likelihood. The results of the developed model are presented empirically and indicate that the storage temperature can cause a significant change in the lychee’s respiratory metabolism. Thus, according to the model selection and residue analysis measures, it can be concluded that the proposed model is a statistical tool for postharvest data, providing an adequate analysis.

BiMNet: A Multimodal Data Fusion Network for continuous circular capsulorhexis Action Segmentation

Completing continuous circular capsulorhexis (CCC) requires the operator to perform fine operations, which is difficult to do accurately when continuous fine actions are out of balance in the classification of CCC procedures. Multimodal deep learning can improve the classifier’s performance, but the recognition accuracy of inferior classes is difficult to improve. To solve these problems, a bidirect-gate recurrent unit (Bi-GRU)-attention-based multimodal, multi-timescale data fusion network (BiMNet) is proposed, which contains a data extraction module called a skip-concatenate gate recurrent unit (SC-GRU), a bimodal data fusion attention computation, and a decoder module. The combination of these modules can fully extract the features of different temporal scales in multimodal action data and fuse them effectively. The model is validated using the ophthalmologist CCC multimodal maneuver dataset, which was collected by the data collection platform constructed in this research, achieving an accuracy of 0.9124 ± 0.0125 in continuous action sequence segmentation and improving the F1-score of minority class recognition to over 80%, making it more effective than baseline algorithms.

Joint Bi-Modal Tomographic Reconstruction from Observations with Missing Data

A method for tomographic reconstruction of bi-modal data sets using cross modal regularization was developed. The method constrains the Simultaneous Algebraic Reconstruction Technique by using clustering-based segmented images and quality controlled fused images, to jointly regularize the reconstruction of structures imaged with different methods. The joint regularized reconstruction method was tested using a synthetic X-Ray and neutron data set with a mix of attenuation driven data starvation. Assuming consistent material boundaries in the different imaging modalities, it was shown that improvements in terms of the Feature Similarity Index Measure are made compared to a traditional SART-TV reconstruction. UK Ministry of Defence ©Crown Owned Copyright 2023/AWE

The Log-Bimodal Asymmetric Generalized Gaussian Model with Application to Positive Data

One of the most widely known probability distributions used to explain the probabilistic behavior of positive data is the log-normal (LN). Although the LN distribution is capable of adjusting data types, it is not always fully true that the model manages to adequately model the behavior of the response of interest since in some cases, the degree of skewness and/or kurtosis of the data are greater or less than those that the LN distribution can capture. Another peculiarity of the LN distribution is that it only fits unimodal positive data, which constitutes a limitation when dealing with data that present more than one mode (bimodality). On the other hand, the log-normal model only fits unimodal positive data and in reality there are multiple applications where the behavior of materials is bimodal. To fill this gap, this paper introduces a new probability distribution that is capable of fitting unimodal or bimodal positive data with a high or low degree of skewness and/or kurtosis. The new distribution is a generalization of the LN distribution. For the new proposal, its main properties are studied and the process of estimation of the parameters involved in the model is carried out from a classical perspective using the maximum likelihood method. An important feature of this distribution is the non-singularity of the Fisher information matrix, which guarantees the use of asymptotic theory to study the properties of the parameter estimators. A Monte Carlo type simulation study is carried out to evaluate the properties of the estimators and finally, an illustration is presented with a set of data related to the concentration of nickel in soil samples, allowing to show that the proposed distribution fits extremely well in certain situations.

A New Lindley Extension: Estimation, Risk Assessment and Analysis Under Bimodal Right Skewed Precipitation Data

A New Lindley Extension: Estimation, Risk Assessment and Analysis Under Bimodal Right Skewed Precipitation Data

Multi-physics simulations and experimental comparisons for the optical and electrical forces acting on a silica nanoparticle trapped by a double-nanohole plasmonic nanopore sensor

Bimodal optical-electrical data generated when a 20 nm diameter silica (SiO2) nanoparticle was trapped by a plasmonic nanopore sensor were simulated using Multiphysics COMSOL and compared with sensor measurements for closely matching experimental parameters. The nanosensor, employed self-induced back action (SIBA) to optically trap nanoparticles in the center of a double nanohole (DNH) structure on top a solid-state nanopores (ssNP). This SIBA actuated nanopore electrophoresis (SANE) sensor enables simultaneous capture of optical and electrical data generated by several underlying forces acting on the trapped SiO2 nanoparticle: plasmonic optical trapping, electroosmosis, electrophoresis, viscous drag, and heat conduction forces. The Multiphysics simulations enabled dissecting the relative contributions of those forces acting on the nanoparticle as a function of its location above and through the sensor's ssNP. Comparisons between simulations and experiments demonstrated qualitative similarities in the optical and electrical time-series data generated as the nanoparticle entered and exited from the SANE sensor. These experimental parameter-matched simulations indicated that the competition between optical and electrical forces shifted the trapping equilibrium position close to the top opening of the ssNP, relative to the optical trapping force maximum that was located several nm above. The experimentally estimated minimum for the optical force needed to trap a SiO2 nanoparticle was consistent with corresponding simulation predictions of optical-electrical force balance. The comparison of Multiphysics simulations with experiments improves our understanding of the interplay between optical and electrical forces as a function of nanoparticle position across this plasmonic nanopore sensor.

Volumetric registration framework for multimodal functional magnetic resonance and optoacoustic tomography of the rodent brain

Optoacoustic tomography (OAT) provides a non-invasive means to characterize cerebral hemodynamics across an entire murine brain while attaining multi-parametric readouts not available with other modalities. This unique capability can massively impact our understanding of brain function. However, OAT largely lacks the soft tissue contrast required for unambiguous identification of brain regions. Hence, its accurate registration to a reference brain atlas is paramount for attaining meaningful functional readings. Herein, we capitalized on the simultaneously acquired bi-modal data from the recently-developed hybrid magnetic resonance optoacoustic tomography (MROT) scanner in order to devise an image coregistration paradigm that facilitates brain parcellation and anatomical referencing. We evaluated the performance of the proposed methodology by coregistering OAT data acquired with a standalone system using different registration methods. The enhanced performance is further demonstrated for functional OAT data analysis and characterization of stimulus-evoked brain responses. The suggested approach enables better consolidation of the research findings thus facilitating wider acceptance of OAT as a powerful neuroimaging tool to study brain functions and diseases.

Disaster loss calculation method of urban flood bimodal data fusion based on remote sensing and text

Study regionMajor urban areas in Henan Province of central China. Study focusdata fusion technology is also a key and difficult point in the field of flood research. Remote sensing and text data have different modalities and scales, making fusion difficult. This study proposed a remote sensing and text bimodal data fusion model based on UFCLI, and we validated the spatiotemporal distribution of floods and the calculation results of disaster losses. The results show that through the coupling analysis of remote sensing and text bimodal data, rainstorm and flood events can be fully reproduced in space and time. The proposed UFCLI effectively improves the accuracy of remote sensing single-data inversion for urban flood disaster losses. The flood loss in Henan is 121.98 billion yuan, and the accuracy improvement result is R² increased by 0.08 and MAPE decreased by 0.88. New hydrological insights for the regionIn the case of sudden urban storm flooding with complex spatial and temporal evolution, the traditional hydrological-hydraulic model has many pending parameters, which makes it difficult to accurately calculate large-scale disaster losses. By establishing a theoretical model of bimodal data fusion, we effectively use the complementary spatiotemporal information using remote sensing and text to solve the differences in spatiotemporal scales existing between remote sensing and text data. The timeliness and accuracy of urban flood damage estimation have further improved. Data Availability StatementNot applicable.

Risk Analysis and Estimation of a Bimodal Heavy-Tailed Burr XII Model in Insurance Data: Exploring Multiple Methods and Applications

Actuarial risks can be analyzed using heavy-tailed distributions, which provide adequate risk assessment. Key risk indicators, such as value-at-risk, tailed-value-at-risk (conditional tail expectation), tailed-variance, tailed-mean-variance, and mean excess loss function, are commonly used to evaluate risk exposure levels. In this study, we analyze actuarial risks using these five indicators, calculated using four different estimation methods: maximum likelihood, ordinary least square, weighted least square, and Cramer-Von-Mises. To achieve our main goal, we introduce and study a new distribution. Monte Carlo simulations are used to assess the performance of all estimation methods. We provide two real-life datasets with two applications to compare the classical methods and demonstrate the importance of the proposed model, evaluated via the maximum likelihood method. Finally, we evaluate and analyze actuarial risks using the abovementioned methods and five actuarial indicators based on bimodal insurance claim payments data.