Computational Framework Research Articles

Revolutionizing healthcare: a comparative insight into deep learning’s role in medical imaging

Recently, Deep Learning (DL) models have shown promising accuracy in analysis of medical images. Alzeheimer Disease (AD), a prevalent form of dementia, uses Magnetic Resonance Imaging (MRI) scans, which is then analysed via DL models. To address the model computational constraints, Cloud Computing (CC) is integrated to operate with the DL models. Recent articles on DL-based MRI have not discussed datasets specific to different diseases, which makes it difficult to build the specific DL model. Thus, the article systematically explores a tutorial approach, where we first discuss a classification taxonomy of medical imaging datasets. Next, we present a case-study on AD MRI classification using the DL methods. We analyse three distinct models-Convolutional Neural Networks (CNN), Visual Geometry Group 16 (VGG-16), and an ensemble approach-for classification and predictive outcomes. In addition, we designed a novel framework that offers insight into how various layers interact with the dataset. Our architecture comprises an input layer, a cloud-based layer responsible for preprocessing and model execution, and a diagnostic layer that issues alerts after successful classification and prediction. According to our simulations, CNN outperformed other models with a test accuracy of 99.285%, followed by VGG-16 with 85.113%, while the ensemble model lagged with a disappointing test accuracy of 79.192%. Our cloud Computing framework serves as an efficient mechanism for medical image processing while safeguarding patient confidentiality and data privacy.

Detecting global and local hierarchical structures in cell-cell communication using CrossChat

Cell-cell communication (CCC) occurs across different biological scales, ranging from interactions between large groups of cells to interactions between individual cells, forming a hierarchical structure. Globally, CCC may exist between clusters or only subgroups of a cluster with varying size, while locally, a group of cells as sender or receiver may exhibit distinct signaling properties. Current existing methods infer CCC from single-cell RNA-seq or Spatial Transcriptomics only between predefined cell groups, neglecting the existing hierarchical structure within CCC that are determined by signaling molecules, in particular, ligands and receptors. Here, we develop CrossChat, a novel computational framework designed to infer and analyze the hierarchical cell-cell communication structures using two complementary approaches: a global hierarchical structure using a multi-resolution clustering method, and multiple local hierarchical structures using a tree detection method. This framework provides a comprehensive approach to understand the hierarchical relationships within CCC that govern complex tissue functions. By applying our method to two nonspatial scRNA-seq datasets sampled from COVID-19 patients and mouse embryonic skin, and two spatial transcriptomics datasets generated from Stereo-seq of mouse embryo and 10x Visium of mouse wounded skin, we showcase CrossChat’s functionalities for analyzing both global and local hierarchical structures within cell-cell communication.

Advancing Real-World Image Dehazing: Perspective, Modules, and Training.

Restoring high-quality images from degraded hazy observations is a fundamental and essential task in the field of computer vision. While deep models have achieved significant success with synthetic data, their effectiveness in real-world scenarios remains uncertain. To improve adaptability in real-world environments, we construct an entirely new computational framework by making efforts from three key aspects: imaging perspective, structural modules, and training strategies. To simulate the often-overlooked multiple degradation attributes found in real-world hazy images, we develop a new hazy imaging model that encapsulates multiple degraded factors, assisting in bridging the domain gap between synthetic and real-world image spaces. In contrast to existing approaches that primarily address the inverse imaging process, we design a new dehazing network following the "localization-and-removal" pipeline. The degradation localization module aims to assist in network capture discriminative haze-related feature information, and the degradation removal module focuses on eliminating dependencies between features by learning a weighting matrix of training samples, thereby avoiding spurious correlations of extracted features in existing deep methods. We also define a new Gaussian perceptual contrastive loss to further constrain the network to update in the direction of the natural dehazing. Regarding multiple full/no-reference image quality indicators and subjective visual effects on challenging RTTS, URHI, and Fattal real hazy datasets, the proposed method has superior performance and is better than the current state-of-the-art methods.

Adaptive Hybrid Optimized LSTM Models: A Novel Computational Framework for Algorithmic Financial Trading System

In our modern society, with the development of Internet and information system, pre-programing algorithmic trading strategies for online automatic trading has also flourished, especially in the rapidly fluctuating trading market. Using quantitative trading programs that can automatically trade in response to market conditions has attracted the attention of major financial institutions and governments in the financial market. How to use self-adaptive programs to automatically trade in the ever-changing financial market has become a popular research topic for the development and pursuit of all financial markets in recent years. This research proposes an online self-adaptive trading algorithm that can be applied to financial markets such as stock market, currency markets, cryptocurrency markets, futures markets, etc. In the first part of the algorithm, the simplified swarm optimization will be used to optimize the parameters of the newly proposed flexible grid in this research. Then the data will be imported into the artificial neural network model for training in the latter part, helping the trading model automatically select the appropriate parameters for construction flexible grid corresponding to the market conditions. The greatest contribution of the research is to provide a whole new trading algorithm that can adapt to the dynamic trading market, automatically make suitable adjustments to current trading strategy and place real-time orders. The algorithm controlling both profit and risk, which can seem like a balanced trading algorithm that are robust and profitable.

Computational Intelligence for Modeling the Rheological Properties of the Developed Hydrated Lime-Based Alkali-Activated Materials

The development of alkali-activated materials (AAMs) has gained attention as a sustainable alternative to Portland cement-based concrete. A key factor in AAM performance is its rheological behavior, which influences workability and pumpability. Accurate prediction of these properties is vital for optimizing mix design. This study introduces a computational framework using ensemble and non-ensemble machine learning (ML) techniques to model the yield stress (YS) and plastic viscosity (PV) of AAMs. A comprehensive dataset from previous experiments was used to train models, including artificial neural networks (ANN), gene expression programming (GEP), decision tree, random forest, adaptive boosting, and gradient boosting. The models achieved R² values exceeding 0.95 and correlation coefficients above 0.97. Error metrics, such as MAPE, MAE, MSE, and RMSE, further validated the models’ generalizability. A parametric analysis showed that a 20% increase in hydrated lime (HL) content raised YS by 350Pa, which is similar to the effect of varying fly ash (FA) from 60% to 100%. A 40% increase in FA and HL content increased PV by 4Pa.s and 25Pa.s, respectively. A 3% rise in sodium silicate led to a 400Pa increase in YS, while a similar increase in sodium hydroxide raised YS by 170Pa and PV by 15Pa·s. Overall, this study provides an effective tool for optimizing AAM mix designs by accurately predicting rheological properties and quantifying the impact of key parameters, contributing to the advancement of sustainable cementitious materials in construction.

A multi-core makespan model for parallel scientific workflow execution in cloud computational framework

Researchers have shown a lot of potential in optimizing cloud-based workload-scheduling over the past few years. However, executing scientific workloads inside the cloud is time-consuming and costly, making it inefficient from both a financial and productivity standpoint. As a result, there are many investigations conducted, with the general trend being to speed up the rate of processing and establish a cost-effective system, whereby customers are billed according to their actual use. In addition, energy-consumption is capable of being reduced, especially if the available resources are heterogeneous; however, few investigations have optimized multi-core with analyzing makespan parameters collectively to fulfill the quality of service (QoS) and service level agreement (SLA) of the workload task. In this research, we introduce an optimal scheduling for a heterogeneous distributed cloud computing environment called task aware makespan optimized scheduler (TAMOS) that guarantees requirements across the task levels of scientific workflows. The energy and time required to carry out specific workflows are significantly reduced by using this TAMOS strategy. The TAMOS framework was studied using the scientific workflows namely, inspiral and sipht. When compared to the conventional method of scheduling work, our methodology used less energy and makespan.

A fuzzy computational framework for the train-bridge system based on Chebyshev polynomials method

A fuzzy computational framework for the train-bridge system based on Chebyshev polynomials method

An efficient computational framework for data assimilation of fractional-order dynamical system with sparse observations

We introduce an efficient computational framework for data assimilation of fractional dynamical systems, extending traditional data assimilation techniques to fractional models. This framework offers effective computational methods that eliminate the need for complex adjoint model derivations and algorithm redesign. We establish the fundamental problem formulation, develop both the AtD and DtA approaches, and derive adjoint forms and numerical schemes for each method. Additionally, we create a unified fractional-order variational data assimilation framework applicable to both linear and nonlinear models, incorporating both explicit and implicit discrete methods. Specific discretization schemes and gradient formulas are derived for three distinct types of fractional-order models. The method's reliability and convergence are verified, and the effect of observation sparsity and quality is examined through numerical examples.

Enhancing Accuracy in Gas–Water Two-Phase Flow Sensor Systems Through Deep-Learning- Based Computational Framework

Enhancing Accuracy in Gas–Water Two-Phase Flow Sensor Systems Through Deep-Learning- Based Computational Framework

Dual Solutions of Two-Dimensional Hybrid Nanofluid Flow and Heat Transfer Past a Porous Medium Permeable Shrinking Sheet with Influence of Heat GenerationAbsorption and Convective Boundary Condition

In this study, the dual solutions of two-dimensional hybrid nanofluid flow and heat transfer past a porous medium permeable shrinking sheet with influence of heat generation/absorption and convective boundary condition were examined using the bvp4c solver with the MATLAB computational framework. The utilization of two-dimensional hybrid nanofluid flow and heat transfer in the presence of a porous medium permeable shrinking sheet, considering the effects of heat generation/absorption and convective boundary conditions, has wide-ranging applications in industries such as cooling systems, aerospace, chemical engineering, biomedical applications, energy systems, microfluidics, automotive thermal management, industrial drying, and nuclear reactor cooling, etc. These applications employ the improved thermal characteristics of hybrid nanofluids and the efficient heat control offered by porous media and convective boundary conditions. The governing partial differential equations (PDEs) are transformed into a collection of higher-order ordinary differential equations (ODEs) together with their corresponding boundary conditions. These equations are subsequently shown both numerically and graphically. The main objective of this inquiry is to examine the relationship between the solid volume fraction of copper and the permeability parameter of the porous medium, specifically focusing on the values of f''(0) and - (0) according to the suction effect. The current research has also integrated the temperature and velocity profile of a hybrid nanofluid flow, which corresponds to the influence of porous medium permeability, heat generation/absorption, and convective boundary condition. Dual solutions are acquired by certain combinations of parameters. Non unique solutions are obtained when the critical point reaches , for suction effects. Increasing the intensity of heat generation absorption and convective boundary condition leads to a more pronounced temperature profile and thicker boundary layer.

Mathematical modeling framework enhances clinical trial design for maintenance treatment in oncology

Clinical trials are costly and time-intensive endeavors, with a high rate of drug candidate failures. Moreover, the standard approaches often evaluate drugs under a limited number of protocols. In oncology, where multiple treatment protocols can yield divergent outcomes, addressing this issue is crucial. Here, we present a computational framework that simulates clinical trials through a combination of mathematical and statistical models. This approach offers a means to explore diverse treatment protocols efficiently and identify optimal strategies for oncological drug administration. We developed a computational framework with a stochastic mathematical model as its core, capable of simulating virtual clinical trials closely recapitulating the clinical scenarios. Testing our framework on the landmark SOLO-1 clinical trial investigating Poly-ADP-Ribose Polymerase maintenance treatment in high-grade serous ovarian cancer, we demonstrate that managing toxicity through treatment interruptions or dose reductions does not compromise treatment’s clinical benefits. Additionally, we provide evidence suggesting that further reduction of hematological toxicity could significantly improve the clinical outcomes. The value of this computational framework lies in its ability to expedite the exploration of new treatment protocols, delivering critical insights pivotal to shaping the landscape of upcoming clinical trials.

NUMERICAL STUDY OF FLOW PARAMETERS IN THE HIGH-HEAD FRANCIS TURBINE

The scientific exploration of numerical computation regarding spatial flow within hydraulic machinery components is examined. A survey of contemporary software systems is conducted, and the benefits of their utilization over experimental studies are evaluated. It is indicated that the optimal approach involves a blend of experimental investigations and numerical simulation. This methodology facilitates the validation of simulation outcomes under real-world conditions and iteratively enhances the model based on acquired data. A review of the widely utilized Ansys software program is provided, emphasizing its pivotal features and capabilities for analyzing flow components of hydraulic turbines. An algorithm for computing flow parameters in hydraulic turbines using the Ansys software suite is outlined. The subject of this study is the high-head Francis hydraulic turbine Fr 500. The turbine's geometry was constructed employing a sector-based approach. This technique allows for significant simplification of calculations within the computational fluid dynamics framework, thereby reducing computational workload while preserving result accuracy. In selecting mathematical and turbulence models, a comprehensive analysis of the problem was undertaken, identifying models most suitable for the specific situation to ensure dependable numerical simulation outcomes. For spatial flow calculations in the turbine's flow component, the standard k-ε turbulence model was adopted. Considerable attention was devoted to mesh generation, as mesh quality strongly influences result accuracy and reliability. An unstructured mesh comprising tetrahedral-shaped cells was employed for discretizing the flow component, with local mesh refinement at the edges of the runner blades and guide vanes. As a result of numerical computations, the values of primary flow parameters for the design operating mode were determined. A visualization of the flow within the flow component is provided, alongside the assessment of hydraulic losses and turbine efficiency. The efficiency values obtained differ from corresponding experimental values by no more than 1 %. A thorough examination of the flow structure within the flow path was conducted, yielding recommendations for adjusting the blade angle β1 to reduce inlet impact losses.

Integrative mapping of human CD8+ T cells in inflammation and cancer.

CD8+ T cells exhibit remarkable phenotypic diversity in inflammation and cancer. However, a comprehensive understanding of their clonal landscape and dynamics remains elusive. Here we introduce scAtlasVAE, a deep-learning-based model for the integration of large-scale single-cell RNA sequencing data and cross-atlas comparisons. scAtlasVAE has enabled us to construct an extensive human CD8+ T cell atlas, comprising 1,151,678 cells from 961 samples across 68 studies and 42 disease conditions, with paired T cell receptor information. Through incorporating information in T cell receptor clonal expansion and sharing, we have successfully established connections between distinct cell subtypes and shed light on their phenotypic and functional transitions. Notably, our approach characterizes three distinct exhausted T cell subtypes and reveals diverse transcriptome and clonal sharing patterns in autoimmune and immune-related adverse event inflammation. Furthermore, scAtlasVAE facilitates the automatic annotation of CD8+ T cell subtypes in query single-cell RNA sequencing datasets, enabling unbiased and scalable analyses. In conclusion, our work presents a comprehensive single-cell reference and computational framework for CD8+ T cell research.

Improvements of the damage responses and failure modes of an RC vehicle over pass bridge under contact explosion using FEM-SPH coupled computational frameworks

Winds, earthquakes, and blasts are unpredictable and most challenging dynamic loads. However, the blast is relatively new, and its protection over infrastructure is a vital concern. Conversely, bridges play a critical role in the transport system, and their loss may affect the Nation’s growth. However, the literature says that experimental and numerical simulation is an excellent option to predict the blast impacts. Most of the data from the experiments are collected by photos or videography at high temperatures. Therefore, the reliability of those data is a genuine concern, particularly for bridges. Conversely, if correctly explored, numerical simulation is an option to get into the blast field with high accuracy. A mesh-based method like Finite Element Method (FEM) is excellent for numerical simulation up to a specific temperature. Beyond that, it starts a mesh tangling. Element erosion and remeshing processes may overcome this issue if the mesh-free method simulates. Smoothed Particle Hydrodynamics (SPH) is a mesh-free particle method that can naturally handle massive deformation due to adaptive features. Finally, the current study has coupled two discretisation systems to avoid instability and increase run time. Therefore, FEM-SPH coupling has been adopted to explore the direct damage-reduction, complete damage-time response, damaged contours of the shock wave propagations, damaged contours of particle formation, the effective plastic strain (EPS) and different failure modes of the Vehicle Over Pass typed bridge without and with the protective layer of non-Explosive Reactive Armour (nERA). Finally, the improvement of the bridge is eye-catching as the nERA effectively reduces the deformation, damage, particle formation, EPS, and failure modes.

Modeling the uncoupled damage-healing behavior of self-healing cementitious material with phase-field method

Microbially induced calcium carbonate precipitation (MICCP), which is a biochemical process that utilizes microbial metabolic activities to precipitate calcium carbonate (CaCO3), can be used for damage-healing by crack filling. In this study, we develop a computational uncoupled damage-healing framework to predict the fracture-healing responses of a multifunctional vascular cementitious composite. The framework integrates a numerical model for self-healing cementitious materials into a damage model developed using the phase-field method. The numerical self-healing model is utilized to compute the MICCP healing based on the chemical and enzyme kinetics of microbial activities, whereas the phase-field method is employed to capture the fracture response of the material. This framework comprises three stages: Stage 1 — damage, Stage 2 — healing, and Stage 3 — re-damage of the healed structure. Using the load–displacement curve of the healed cementitious material, the proposed uncoupled damage-healing models can predict the recovery in material stiffness based on the MICCP healing ratio. The proposed framework can be applied to a wide range of fracture-healing problems in self-healing cementitious materials utilizing MICCP as the healing methodology.

Machine learning-enhanced immunopeptidomics applied to T-cell epitope discovery for COVID-19 vaccines

Next-generation T-cell-directed vaccines for COVID-19 focus on establishing lasting T-cell immunity against current and emerging SARS-CoV-2 variants. Precise identification of conserved T-cell epitopes is critical for designing effective vaccines. Here we introduce a comprehensive computational framework incorporating a machine learning algorithm—MHCvalidator—to enhance mass spectrometry-based immunopeptidomics sensitivity. MHCvalidator identifies unique T-cell epitopes presented by the B7 supertype, including an epitope from a + 1-frameshift in a truncated Spike antigen, supported by ribosome profiling. Analysis of 100,512 COVID-19 patient proteomes shows Spike antigen truncation in 0.85% of cases, revealing frameshifted viral antigens at the population level. Our EpiTrack pipeline tracks global mutations of MHCvalidator-identified CD8 + T-cell epitopes from the BNT162b4 vaccine. While most vaccine epitopes remain globally conserved, an immunodominant A*01-associated epitope mutates in Delta and Omicron variants. This work highlights SARS-CoV-2 antigenic features and emphasizes the importance of continuous adaptation in T-cell vaccine development.

A multi-domain computational framework investigating the short- and long-term viability of bioabsorbable magnesium fixation for tibial fractures

This study presents a multi-domain computational framework to investigate the long-term performance of permanent and bioabsorbable magnesium fixation devices in orthopaedic fracture applications. The framework integrates a coupled model for bone fracture healing and remodeling, with an enhanced surface-based corrosion model to predict the performance of bioabsorbable magnesium devices. It was found that plated fracture fixation enabled fracture healing outcomes compare to non-plated models by facilitating direct fracture healing. During the fracture healing phase, it was found that the stiff titanium plate provided a better healing response compared to the less stiff bioabsorbable magnesium plates. However, in the longer-term remodeling phase, the titanium plate showed evidence of stress-shielding and inhibited bone remodeling. On the other hand, the magnesium plates showed that there was continued remodeling, which meant that the bone tissue gradually returned to the pre-fracture stress state. While the corrosion rate and pit severity heavily influenced the mechanical support provided by the corroding magnesium fixator, the results showed that fixation was only required to provide mechanical stability to the fracture region for approximately the first 30 days for successful fracture union to occur. This coupled computational framework provides a platform to investigate the role of a wide range of magnesium fixation devices and their design and optimisation in orthopaedic applications.

ECG analysis of ventricular fibrillation dynamics reflects ischaemic progression subject to variability in patient anatomy and electrode location

BackgroundVentricular fibrillation (VF) is the deadliest arrhythmia, often caused by myocardial ischaemia. VF patients require urgent intervention planned quickly and non-invasively. However, the accuracy with which electrocardiographic (ECG) markers reflect the underlying arrhythmic substrate is unknown.MethodsWe analysed how ECG metrics reflect the fibrillatory dynamics of electrical excitation and ischaemic substrate. For this, we developed a human-based computational modelling and simulation framework for the quantification of ECG metrics, namely, frequency, slope, and amplitude spectrum area (AMSA) during VF in acute ischaemia for several electrode configurations. Simulations reproduced experimental and clinical findings in 21 scenarios presenting variability in the location and transmural extent of regional ischaemia, and severity of ischaemia in the remote myocardium secondary to VF.ResultsRegional acute myocardial ischaemia facilitated re-entries, potentially breaking up into VF. Ischaemia in the remote myocardium modulated fibrillation dynamics. Cases presenting a mildly ischaemic remote myocardium yielded sustained VF, enabled by the high proliferation of phase singularities (PS, 11–22) causing remarkably disorganised activation patterns. Conversely, global acute ischaemia induced stable rotors (3–12 PS). Changes in frequency and morphology of the ECG during VF reproduced clinical findings but did not show a direct correlation with the underlying wave dynamics. AMSA allowed the precise stratification of VF according to ischaemic severity in the remote myocardium (healthy: 23.62–24.45 mV Hz; mild ischaemia: 10.58–21.47 mV Hz; moderate ischaemia: 4.82–11.12 mV Hz). Within the context of clinical reference values, apex-anterior and apex-posterior electrode configurations were the most discriminatory in stratifying VF based on the underlying ischaemic substrate.ConclusionThis in silico study provides further insights into non-invasive patient-specific strategies for assessing acute ventricular arrhythmias. The use of reliable ECG markers to characterise VF is critical for developing tailored resuscitation strategies.

MLR-predictor: a versatile and efficient computational framework for multi-label requirements classification

IntroductionRequirements classification is an essential task for development of a successful software by incorporating all relevant aspects of users' needs. Additionally, it aids in the identification of project failure risks and facilitates to achieve project milestones in more comprehensive way. Several machine learning predictors are developed for binary or multi-class requirements classification. However, a few predictors are designed for multi-label classification and they are not practically useful due to less predictive performance.MethodMLR-Predictor makes use of innovative OkapiBM25 model to transforms requirements text into statistical vectors by computing words informative patterns. Moreover, predictor transforms multi-label requirements classification data into multi-class classification problem and utilize logistic regression classifier for categorization of requirements. The performance of the proposed predictor is evaluated and compared with 123 machine learning and 9 deep learning-based predictive pipelines across three public benchmark requirements classification datasets using eight different evaluation measures.ResultsThe large-scale experimental results demonstrate that proposed MLR-Predictor outperforms 123 adopted machine learning and 9 deep learning predictive pipelines, as well as the state-of-the-art requirements classification predictor. Specifically, in comparison to state-of-the-art predictor, it achieves a 13% improvement in macro F1-measure on the PROMISE dataset, a 1% improvement on the EHR-binary dataset, and a 2.5% improvement on the EHR-multiclass dataset.DiscussionAs a case study, the generalizability of proposed predictor is evaluated on softwares customer reviews classification data. In this context, the proposed predictor outperformed the state-of-the-art BERT language model by F-1 score of 1.4%. These findings underscore the robustness and effectiveness of the proposed MLR-Predictor in various contexts, establishing its utility as a promising solution for requirements classification task.

Long-term care comparative studies by agent-based simulation: a computational framework and a case study

Long-term care comparative studies by agent-based simulation: a computational framework and a case study