Computational Challenges Research Articles

Patch-based convolutional neural networks for automatic landmark detection of 3D facial images in clinical settings.

The facial landmark annotation of 3D facial images is crucial in clinical orthodontics and orthognathic surgeries for accurate diagnosis and treatment planning. While manual landmarking has traditionally been the gold standard, it is labour-intensive and prone to variability. This study presents a framework for automated landmark detection in 3D facial images within a clinical context, using convolutional neural networks (CNNs), and it assesses its accuracy in comparison to that of ground-truth data. Initially, an in-house dataset of 408 3D facial images, each annotated with 37 landmarks by an expert, was constructed. Subsequently, a 2.5D patch-based CNN architecture was trained using this dataset to detect the same set of landmarks automatically. The developed CNN model demonstrated high accuracy, with an overall mean localization error of 0.83 ± 0.49mm. The majority of the landmarks had low localization errors, with 95% exhibiting a mean error of less than 1mm across all axes. Moreover, the method achieved a high success detection rate, with 88% of detections having an error below 1.5mm and 94% below 2mm. The automated method used in this study demonstrated accuracy comparable to that achieved with manual annotations within clinical settings. In addition, the proposed framework for automatic landmark localization exhibited improved accuracy over existing models in the literature. Despite these advancements, it is important to acknowledge the limitations of this research, such as that it was based on a single-centre study and a single annotator. Future work should address computational time challenges to achieve further enhancements. This approach has significant potential to improve the efficiency and accuracy of orthodontic and orthognathic procedures.

Separable physics-informed DeepONet: Breaking the curse of dimensionality in physics-informed machine learning

The deep operator network (DeepONet) has shown remarkable potential in solving partial differential equations (PDEs) by mapping between infinite-dimensional function spaces using labeled datasets. However, in scenarios lacking labeled data, the physics-informed DeepONet (PI-DeepONet) approach, which utilizes the residual loss of the governing PDE to optimize the network parameters, faces significant computational challenges, particularly due to the curse of dimensionality. This limitation has hindered its application to high-dimensional problems, making even standard 3D spatial with 1D temporal problems computationally prohibitive. Additionally, the computational requirement increases exponentially with the discretization density of the domain. To address these challenges and enhance scalability for high-dimensional PDEs, we introduce the Separable physics-informed DeepONet (Sep-PI-DeepONet). This framework employs a factorization technique, utilizing sub-networks for individual one-dimensional coordinates, thereby reducing the number of forward passes and the size of the Jacobian matrix required for gradient computations. By incorporating forward-mode automatic differentiation (AD), we further optimize computational efficiency, achieving linear scaling of computational cost with discretization density and dimensionality, making our approach highly suitable for high-dimensional PDEs. We demonstrate the effectiveness of Sep-PI-DeepONet through three benchmark PDE models: the viscous Burgers’ equation, Biot’s consolidation theory, and a parametrized heat equation. Our framework maintains accuracy comparable to the conventional PI-DeepONet while reducing training time by two orders of magnitude. Notably, for the heat equation solved as a 4D problem, the conventional PI-DeepONet was computationally infeasible (estimated 289.35 h), while the Sep-PI-DeepONet completed training in just 2.5 h. These results underscore the potential of Sep-PI-DeepONet in efficiently solving complex, high-dimensional PDEs, marking a significant advancement in physics-informed machine learning.

Quantum Algorithms for Image Processing: Enhancing Computational Efficiency and Accuracy in High-Dimensional Visual Data Analysis

Quantum algorithms have emerged as a transformative approach to address the computational challenges of high-dimensional image processing tasks. This research investigates the integration of quantum computing principles, such as Quantum Fourier Transform (QFT) and Quantum Principal Component Analysis (QPCA), to optimize processes like edge detection, noise reduction, and image segmentation. These quantum-enhanced techniques promise significant improvements in computational efficiency and accuracy compared to classical methods, especially when handling complex visual data in real-time applications like medical imaging, satellite imagery, and autonomous systems. Additionally, the study explores hybrid quantum-classical architectures to bridge current limitations in noisy intermediate-scale quantum (NISQ) devices, ensuring resource optimization and scalability. The potential of quantum algorithms to provide faster, more precise solutions is evaluated alongside challenges like error mitigation and algorithmic stability. This research highlights the future role of quantum computing in revolutionizing image processing, paving the way for breakthroughs in computer vision and artificial intelligence.

Advancements and Prospects in Large Integer Factorization: A Comprehensive Review of the Number Field Sieve Method

The Number Field Sieve (NFS) stands as one of the most effective algorithms for the factorization of large integers, playing a critical role in cryptographic security, particularly in breaking RSA encryption systems. This review paper provides an in-depth analysis of NFS, highlighting its structure, key processes, and computational challenges. NFS is notably effective for integers larger than 110 digits and is recognized for its sub-exponential computational complexity, making it superior to other classical factorization algorithms. The core processes of NFSpolynomial selection, number pair sieving, matrix solving, and square root extractionare systematically examined to illustrate their roles in factorization. This study also reviews the latest advancements in NFS, including improvements in polynomial selection methods and optimizations in sieving and matrix-solving stages, which have significantly enhanced the algorithms efficiency. Moreover, the paper discusses the future prospects of NFS, emphasizing the need for further optimization to reduce computational resource demands and increase practicality in large-scale applications. The ongoing evolution of NFS continues to push the boundaries of cryptographic analysis, driving future research towards even more efficient factorization methods.

Progress and Application of Unsupervised Feature Extraction Methods

Unsupervised feature extraction is crucial in machine learning and data mining for handling high-dimensional and unlabeled data. However, existing methods often ignore feature relationaships, resulting in suboptimal feature subsets. This paper reviews the current state of unsupervised feature extraction methods, discussing the limitations of traditional methods such as Principal Component Analysis (PCA) and Independent Component Analysis (ICA), particularly in terms of interpretability, sensitivity to outliers, and computational resource challenges. In recent years, improvement strategies such as information theory, sparse learning, and deep learning (e.g., deep autoencoders and generative adversarial networks) have significantly progressed in feature extraction. This paper analyzes the practical applications of these methods in image processing, gene analysis, text mining, and network security. For example, in image processing, deep autoencoder-based methods such as Matrix Capsules with EM Routing can effectively extract key features from complex images. In text mining, unsupervised feature selection methods combined with generative adversarial networks significantly improve the efficiency of processing high-dimensional text data. Additionally, this paper explores future research directions such as multimodal data processing, improving real-time processing capabilities, and integration with other machine learning techniques (e.g., reinforcement learning, transfer learning), providing insights for further development of unsupervised feature extraction technologies.

Optimization of SM2 Algorithm Based on Polynomial Segmentation and Parallel Computing

The SM2 public key cryptographic algorithm is widely utilized for secure communication and data protection due to its strong security and compact key size. However, the intensive large integer operations it requires pose significant computational challenges, which can limit the performance of Internet of Things (IoT) terminal devices. This paper introduces an optimized implementation of the SM2 algorithm specifically designed for IoT contexts. By segmenting large integers as polynomials within a modified Montgomery modular multiplication algorithm, the proposed method enables parallel modular multiplication and reduction, thus addressing storage constraints and reducing computational redundancy. For scalar multiplication, a Co-Z Montgomery ladder algorithm is employed alongside Single Instruction Multiple Data (SIMD) instructions to enhance parallelism, significantly improving efficiency. Experimental results demonstrate that the proposed scheme reduces the computation time for the SM2 algorithm’s digital signature by approximately 20% and enhances data encryption and decryption efficiency by about 15% over existing methods, marking a substantial performance gain for IoT applications.

ExCS: accelerating code search with code expansion

Efficiently searching and reusing code from expansive codebases is pivotal for enhancing developers’ productivity. In recent times, the emergence of deep learning-driven neural ranking models, characterized by their vast dimensions and intricate interaction mechanisms, has been noteworthy. Yet, these models, in real-world scenarios, pose computational challenges due to their high dimensionality. Moreover, models rooted in interaction necessitate querying every piece of code within a voluminous corpus. While these methodologies offer superior accuracy, their online retrieval process is considerably more time-consuming compared to traditional Information Retrieval (IR) techniques. Addressing this, we introduce “ExCS”, an innovative code search tool designed to expedite the code search process without compromising on accuracy. ExCS innovatively employs code expansion in its offline phase, leveraging predictions on potential queries for specific codes, thereby enriching the code’s semantic depth. During online retrieval, ExCS prioritizes IR-based methods to pinpoint a concise set of persuasive candidates. Our evaluations, conducted on the Java dataset from CodeSearchNet, reveal that ExCS achieves a remarkable 90% reduction in retrieval duration while maintaining an impressive 99% retrieval accuracy.

Joint Design and Pricing Problem for Symbiotic Bioethanol Supply Chain Network: Model and Resolution Approach

To fight climate change, the Province of Quebec, Canada, has set targets to reduce greenhouse gas emissions by reducing fossil fuel consumption and integrating biofuel content into gasoline and diesel fuel. Motivated by a real-world case study, this paper presents a novel distributed decision model for designing a symbiotic supply chain network and supporting pricing decisions. A distributed decision-making problem is formulated as a game theoretic approach considering a Stackelberg–Nash equilibrium. A novel mathematical model is proposed to support the decisions of four actors: corn farms, processing depots, pig farms, and biorefineries. In addition to the configuration of a biofuel-based industrial symbiosis, the model offers the possibility of setting purchase prices and supply levels for biomass (corn stover supplied by farms), as well as determining sales prices and production levels for the main product (the cellulosic sugar used for the bioethanol production) and a coproduct (pig feed sold to pig farmers). A three-step optimization process involving the user is proposed to address the computational challenges posed by large design problem instances. The case study of the Province of Quebec is used to evaluate the performance of the proposed resolution approach.

2025 Roadmap on 3D Nano-magnetism.

The transition from planar (2D) to three-dimensional (3D) magnetic nanostructures represents a significant advancement in both fundamental research and practical applications, offering vast potential for next-generation technologies like ultrahigh-density storage, memory, logic, and neuromorphic computing. Despite being a relatively new field, the emergence of 3D nanomagnetism presents numerous opportunities for innovation, prompting the creation of a comprehensive roadmap by leading international researchers. This roadmap aims to facilitate collaboration and interdisciplinary dialogue to address challenges in materials science, physics, engineering, and computing.
The roadmap comprises eighteen sections, roughly divided into three parts. The first section explores the fundamentals of 3D nanomagnetism, focusing on recent trends in fabrication techniques and imaging methods crucial for understanding complex spin textures, curved surfaces, and small-scale interactions. Techniques such as two-photon lithography and focused electron beam-induced deposition enable the creation of intricate 3D architectures, while advanced imaging methods like electron holography and Lorentz electron Ptychography provide sub-nanometer resolution for studying magnetization dynamics in three dimensions. Various 3D magnetic systems, including coupled multilayer systems, artificial spin ice, magneto-plasmonic systems, topological spin textures, and molecular magnets, are discussed.
The second section introduces analytical and numerical methods for investigating 3D nanomagnetic structures and curvilinear systems, highlighting geometrically curved architectures, interconnected nanowire systems, and other complex geometries. Finite element methods are emphasized for capturing complex geometries, along with direct frequency domain solutions for addressing magnonic problems.
The final section focuses on 3D magnonic crystals and networks, exploring their fundamental properties and potential applications in magnonic circuits, memory, and spintronics. Computational approaches using 3D nanomagnetic systems and complex topological textures in 3D spintronics are highlighted for their potential to enable faster and more energy-efficient computing.&#xD.

Enhancing human behavior recognition with dynamic graph convolutional networks and multi-scale position attention

PurposeHuman behavior recognition poses a pivotal challenge in intelligent computing and cybernetics, significantly impacting engineering and management systems. With the rapid advancement of autonomous systems and intelligent manufacturing, there is an increasing demand for precise and efficient human behavior recognition technologies. However, traditional methods often suffer from insufficient accuracy and limited generalization ability when dealing with complex and diverse human actions. Therefore, this study aims to enhance the precision of human behavior recognition by proposing an innovative framework, dynamic graph convolutional networks with multi-scale position attention (DGCN-MPA) to sup.Design/methodology/approachThe primary applications are in autonomous systems and intelligent manufacturing. The main objective of this study is to develop an efficient human behavior recognition framework that leverages advanced techniques to improve the prediction and interpretation of human actions. This framework aims to address the shortcomings of existing methods in handling the complexity and variability of human actions, providing more reliable and precise solutions for practical applications. The proposed DGCN-MPA framework integrates the strengths of convolutional neural networks and graph-based models. It innovatively incorporates wavelet packet transform to extract time-frequency characteristics and a MPA module to enhance the representation of skeletal node positions. The core innovation lies in the fusion of dynamic graph convolution with hierarchical attention mechanisms, which selectively attend to relevant features and spatial relationships, adjusting their importance across scales to address the variability in human actions.FindingsTo validate the effectiveness of the DGCN-MPA framework, rigorous evaluations were conducted on benchmark datasets such as NTU-RGB + D and Kinetics-Skeleton. The results demonstrate that the framework achieves an F1 score of 62.18% and an accuracy of 75.93% on NTU-RGB + D and an F1 score of 69.34% and an accuracy of 76.86% on Kinetics-Skeleton, outperforming existing models. These findings underscore the framework’s capability to capture complex behavior patterns with high precision.Originality/valueBy introducing a dynamic graph convolutional approach combined with multi-scale position attention mechanisms, this study represents a significant advancement in human behavior recognition technologies. The innovative design and superior performance of the DGCN-MPA framework contribute to its potential for real-world applications, particularly in integrating behavior recognition into engineering and autonomous systems. In the future, this framework has the potential to further propel the development of intelligent computing, cybernetics and related fields.

Deep learning insights into distinct patterns of polygenic adaptation across human populations.

Response to spatiotemporal variation in selection gradients resulted in signatures of polygenic adaptation in human genomes. We introduce RAISING, a two-stage deep learning framework that optimizes neural network architecture through hyperparameter tuning before performing feature selection and prediction tasks. We tested RAISING on published and newly designed simulations that incorporate the complex interplay between demographic history and selection gradients. RAISING outperformed Phylogenetic Generalized Least Squares (PGLS), ridge regression and DeepGenomeScan, with significantly higher true positive rates (TPR) in detecting genetic adaptation. It reduced computational time by 60-fold and increased TPR by up to 28% compared to DeepGenomeScan on published data. In more complex demographic simulations, RAISING showed lower false discoveries and significantly higher TPR, up to 17-fold, compared to other methods. RAISING demonstrated robustness with least sensitivity to demographic history, selection gradient and their interactions. We developed a sliding window method for genome-wide implementation of RAISING to overcome the computational challenges of high-dimensional genomic data. Applied to African, European, South Asian and East Asian populations, we identified multiple genomic regions undergoing polygenic selection. Notably, ∼70% of the regions identified in Africans are unique, with broad patterns distinguishing them from non-Africans, corroborating the Out of Africa dispersal model.

A feasibility restoration particle swarm optimizer with chaotic maps for two-stage fixed-charge transportation problems

This paper delves into solving the two-stage non-linear fixed-charge transportation problem (two-stage NFCTP), where each arc is associated with fixed and variable costs that increase proportionally to the square of the units transported. The presence of fixed charges and non-linear components categorizes this problem as NP−hard, leading to computational challenges, inefficiencies, and the risk of local optima. To address these challenges, a feasibility restoration particle swarm optimizer with chaotic maps (CEPSO) is presented. The proposed algorithm introduces (i) non-linear adaptive inertia weight and acceleration coefficients to maintain better exploration and exploitation rates during the search. (ii) Ten chaotic maps are integrated into the acceleration coefficients to enhance optimization capabilities further. (iii) Feasibility restoration mechanisms, including constraint compliance adjustment and ratio adjustment procedures, are incorporated to ensure the feasibility of solutions generated by CEPSO. The algorithm’s performance is evaluated across small and large-scale NFCTPs, ranging from 35 to 1044 dimensions, and compared to existing PSO variants using various evaluation metrics. Experimental analyses demonstrate CEPSO’s superior optimization performance for two-stage NFCTPs, positioning it as an advanced framework in this domain and contributing to the novelty of this study. The related codes can be found using this link: https://github.com/ChauhanDikshit.

Heat transfer analysis of Cu-Water nanofluid in a square enclosure using Caputo fractional derivative and machine learning

Fractional-based fluid transport modeling provides a deeper and more comprehensive understanding of the thermophysical properties of small-scale fluids and polymer solutions. Moreover, the fractional-order fluid dynamics framework finds applications in various fields, including renewable energy systems, thermal energy storage, and oil storage tanks. Inspired by these developments, the current study addresses the computational challenges inherent in modeling nanofluid dynamics within a square enclosure by introducing a fractional-order approach to enhance the simulation of buoyant flow and heat transport. Our model integrates the linear interpolation (L1 approach) and finite difference approximation for temporal and spatial derivatives by utilizing the Caputo time-fractional derivative instead of the conventional time derivative. This integration facilitates the use of the Backward Difference Alternating Direction Implicit (BD-ADI) method, which was specifically chosen to reduce the computational burden associated with the non-local characteristics of fractional models. Our results show that by altering the fractional order, significant improvements in heat transfer efficiency are achieved compared to classical models. For instance, compared to the integer order, a lower fractional-order parameter of γ=0.80 with a 4% nanoparticle volume fraction at a Rayleigh number of 103 increases the heat transfer rate by 15.77%. However, at a Rayleigh number of 106, the enhancement reduces to 4.15%, indicating that fractional adjustments’ influence diminishes at higher thermal buoyancy levels. This behavior of the fractional-order nanofluid model, influenced by thermal buoyancy force, has been investigated by using a Multiple Linear Regression(MLR) analysis with 258 numerical samples. Besides, MLR analysis further identifies the nanoparticle volume fraction as a critical factor, influencing the heat transfer rate by 10.48% at lower fractional-order settings.

A genetic algorithm-based solution for multi-type maximal covering location problem (MMCLP): application to defense and deterrence

PurposeWe study the problem of finding optimal locations for a suite of defense assets in order to protect high-value tactical and strategic infrastructure across a vast geographical area. To this end, we present a multi-type with non-overlapping coverage requirement as an extension to the classical formulation for the maximal covering location problem (MCLP).Design/methodology/approachIn our case study, we use open source geographic and demographic data from Canadian sources as inputs to our optimization problem. Due to the complexity of the MIP formulation, we propose a hybrid metaheuristic solution approach, for which a genetic algorithm (GA) is proposed and integrated with local and large neighborhood search operators.FindingsExtensive numerical experiments over different instances of the proposed problem indicate the effectiveness of the GA-based solution in reducing the solution time by a factor of ten compared to the CPLEX commercial solver while both approaches obtain solutions of similar quality.Research limitations/implicationsThis research is limited to location planning of defense assets leveraging geospatial data of Canada. However, the diverse Canadian geography is among the most challenging given broad variability in population density and the vast size of the country leading to a large search space having substantial variability in fitness performance.Practical implicationsOur findings demonstrate that for large-scale location searches, the GA with a local neighborhood search performs very well in comparison to CPLEX but at a fraction of the execution time.Originality/valueOur findings provide insight into how to make improved decisions for the placement of deterrence and defense systems and the effectiveness of a hybrid metaheuristic in addressing associated computational challenges.

Toward Ontological Alignment: Coordinating Student Ideas with the Representational System of a Computational Modeling Unit for Science Learning

Computational modeling tools present unique opportunities and challenges for student learning. Each tool has a representational system that impacts the kinds of explorations students engage in. Inquiry aligned with a tool’s representational system can support more productive engagement toward target learning goals. However, little research has examined how teachers can make visible the ways students’ ideas about a phenomenon can be expressed and explored within a tool’s representational system. In this paper, we elaborate on the construct of ontological alignment—that is, identifying and leveraging points of resonance between students’ existing ideas and the representational system of a tool. Using interaction analysis, we identify alignment practices adopted by a science teacher and her students in a computational agent-based modeling unit. Specifically, we describe three practices: (1) Elevating student ideas relevant to the tool’s representational system; (2) Exploring and testing links between students’ conceptual and computational models; and (3) Drawing on evidence resonant with the tool’s representational system to differentiate between theories. Finally, we discuss the pedagogical value of ontological alignment as a way to leverage students’ ideas in alignment with a tool’s representational system and suggest the presented practices as exemplary ways to support students’ computational modeling for science learning.

Enhancing classification efficiency in capsule networks through windowed routing: tackling gradient vanishing, dynamic routing, and computational complexity challenges

Capsule networks overcome the two drawbacks of convolutional neural networks: weak rotated object recognition and poor spatial discrimination. However, they still have encountered problems with complex images, including high computational cost and limited accuracy. To address these challenges, this work has developed effective solutions. Specifically, a novel windowed dynamic up-and-down attention routing process is first introduced, which can effectively reduce the computational complexity from quadratic to linear order. A novel deconvolution-based decoder is also used to further reduce the computational complexity. Then, a novel LayerNorm strategy is used to pre-process neuron values in the squash function. This prevents saturation and mitigates the gradient vanishing problem. In addition, a novel gradient-friendly network structure is developed to facilitate the extraction of complex features with deeper networks. Experiments show that our methods are effective and competitive, outperforming existing techniques.

Two-Dimensional Prediction of Transient Cavitating Flow Around Hydrofoils Using a DeepCFD Model

Cavitation is a common phenomenon in naval and ocean engineering, typically occurring in the wakes of high-speed rotating propellers and on the surfaces of fast-moving underwater vehicles. To investigate cavitation phenomena, computational fluid dynamics (CFD) simulations are indispensable. Nevertheless, the inherently complex nature of cavitation, which involves phase transitions, heat transfer, and significant pressure fluctuations, often results in high computational costs for these simulations. To address the computational challenges associated with cavitation simulations, a DeepCFD model, which leverages convolutional neural networks (CNNs), was employed to accurately predict cavitation around hydrofoils. Through specific modifications, the DeepCFD model was trained on 400 hydrofoil configurations, learned from CFD simulations. The numerical methods were validated against a modified NACA66 hydrofoil. It was found that the model could accurately predict cavitation shapes under various flow conditions, although it showed some discrepancies in velocity predictions, especially for detached cavitating flows. The significance of this study lies in its potential to simply predict cavitating flows and expedite marine vehicle design through the application of CNNs in cavitation prediction, offering a novel and impactful approach to computational fluid dynamics in the field.

Quantum Computing: Navigating the Future of Computation, Challenges, and Technological Breakthroughs

Quantum computing stands at the precipice of technological revolution, promising unprecedented computational capabilities to tackle some of humanity’s most complex problems. The field is highly collaborative and recent developments such as superconducting qubits with increased scaling, reduced error rates, and improved cryogenic infrastructure, trapped-ion qubits with high-fidelity gates and reduced control hardware complexity, and photonic qubits with exploring room-temperature quantum computing are some of the key developments pushing the field closer to demonstrating real-world applications. However, the path to realizing this promise is fraught with significant obstacles across several key platforms, including sensitivity to errors, decoherence, scalability, and the need for new materials and technologies. Through an exploration of various quantum systems, this paper highlights both the potential and the challenges of quantum computing and discusses the essential role of middleware, quantum hardware development, and the strategic investments required to propel the field forward. With a focus on overcoming technical hurdles through innovation and interdisciplinary research, this review underscores the transformative impact quantum computing could have across diverse sectors.

A Sequential Calibration Approach to Address Challenges of Repeated Calibration of a COVID-19 Model.

Mathematical models served a critical role in COVID-19 decision making throughout the pandemic. Model calibration is an essential, but often computationally burdensome, step in model development that provides estimates for difficult-to-measure parameters and establishes an up-to-date modeling platform for scenario analysis. In the evolving COVID-19 pandemic, frequent recalibration was necessary to provide ongoing support to decision makers. In this study, we address the computational challenges of frequent recalibration with a new calibration approach. We calibrated and recalibrated an age-stratified dynamic compartmental model of COVID-19 in Minnesota to statewide COVID-19 cumulative mortality and prevalent age-specific hospitalizations from March 22, 2020 through August 20, 2021. This period was divided into 10 calibration periods, reflecting significant changes in policies, messaging, and/or epidemiological conditions in Minnesota. When recalibrating the model from one period to the next, we employed a sequential calibration approach that leveraged calibration results from previous periods and adjusted only parameters most relevant to the calibration target data of the new calibration period to improve computational efficiency. We compared computational burden and performance of the sequential calibration approach to a more traditional calibration method, in which all parameters were readjusted with each recalibration. Both calibration methods identified parameter sets closely reproducing prevalent hospitalizations and cumulative deaths over time. By the last calibration period, both approaches converged to similar parameter values. However, the sequential calibration approach identified parameter sets that more tightly fit calibration targets and required substantially less computation time than traditional calibration. Sequential calibration is an efficient approach to maintaining up-to-date models with evolving, time-varying parameters and potentially identifies better-fitting parameter sets than traditional calibration. This study used a sequential calibration approach, which takes advantage of previous calibration results to reduce the number of parameters to be estimated in each round of calibration, improving computational efficiency and algorithm convergence to best-fitting parameter values.Both sequential and traditional calibration approaches were able to identify parameter sets that closely reproduced calibration targets. However, the sequential calibration approach generated parameter sets that yielded tighter fits and was less computationally burdensome.Sequential calibration is an efficient approach to maintaining up-to-date models with evolving, time-varying parameters.

DeepmiRNATar: A deep learning-based model for miRNA targets prediction

MicroRNAs (miRNAs) play a crucial role in regulating fundamental biological processes such as the cell cycle, differentiation, and apoptosis by directly interacting with multiple genes (mRNAs). This regulatory mechanism has a profound impact on cellular function and the overall physiological condition of an organism. However, the prediction of miRNA-mRNA interactions encounters computational challenges in the field of biology due to the diverse sequences and complex data patterns. To overcome these obstacles, this research effort introduced DeepmiRNATar, a tool designed to precisely pinpoint miRNA targets, offering essential assistance in the realm of disease management. DeepmiRNATar leverages the Word2vec-based DeepLncLoc approach for encoding miRNA sequence characteristics and utilizes the DNABERT pre-trained model for in-depth semantic comprehension of target sequences. Through the integration of TextCNN, BiLSTM, and SpatialConv Attention mechanisms, the model scrutinizes structural features, temporal relationships, and overall interactions within the sequences. Following a series of experimental assessments, DeepmiRNATar attained an impressive AUC of 99.15% on the evaluation dataset, on par with the current leading prediction methodologies. Notably, the precision-recall curve, sensitivity, and F-measure values reached 99.18%, 97.43%, and 95.47%, respectively. Compared to existing miRNA target prediction models, DeepmiRNATar demonstrates a notable enhancement in overall predictive accuracy. The successful creation and experimental validation of the DeepmiRNATar model signify a significant advancement in miRNA target identification technology.