Prior Information Research Articles

Structural prior-driven feature extraction with gradient-momentum combined optimization for convolutional neural network image classification

Recent image classification efforts have achieved certain success by incorporating prior information such as labels and logical rules to learn discriminative features. However, these methods overlook the variability of features, resulting in feature inconsistency and fluctuations in model parameter updates, which further contribute to decreased image classification accuracy and model instability. To address this issue, this paper proposes a novel method combining structural prior-driven feature extraction with gradient-momentum (SPGM), from the perspectives of consistent feature learning and precise parameter updates, to enhance the accuracy and stability of image classification. Specifically, SPGM leverages a structural prior-driven feature extraction (SPFE) approach to calculate gradients of multi-level features and originalimages to construct structural information, which is then transformed into prior knowledge to drive the network to learn features consistent with the original images. Additionally, an optimization strategy integrating gradients and momentum (GMO) is introduced, dynamically adjusting the direction and step size of parameter updates based on the angle and norm of the sum of gradients and momentum, enabling precise model parameter updates. Extensive experiments on CIFAR10 and CIFAR100 datasets demonstrate that the SPGM method significantly reduces the top-1 error rate in image classification, enhances the classification performance, and outperforms state-of-the-art methods.

Information aggregation with heterogeneous traders

The efficient market hypothesis predicts that asset prices reflect all available information. Recent experimental work found the rational expectation model to outperform the prior information model in contingent claim markets when traders hold homogeneous values, despite the no trade equilibrium. However, recent experiments have also demonstrated the inability of contingent claim markets to successfully aggregate information when traders hold highly differentiated asset values. These prior findings beg the question of whether homogeneous values are a necessary condition for efficient market outcomes in contingent claim markets. The experiments reported in this paper show that homogeneous values are not a necessary condition for information aggregation.

A weighted prior tensor train decomposition method for community detection in multi-layer networks

Community detection in multi-layer networks stands as a prominent subject within network analysis research. However, the majority of existing techniques for identifying communities encounter two primary constraints: they lack suitability for high-dimensional data within multi-layer networks and fail to fully leverage additional auxiliary information among communities to enhance detection accuracy. To address these limitations, a novel approach named weighted prior tensor training decomposition (WPTTD) is proposed for multi-layer network community detection. Specifically, the WPTTD method harnesses the tensor feature optimization techniques to effectively manage high-dimensional data in multi-layer networks. Additionally, it employs a weighted flattened network to construct prior information for each dimension of the multi-layer network, thereby continuously exploring inter-community connections. To preserve the cohesive structure of communities and to harness comprehensive information within the multi-layer network for more effective community detection, the common community manifold learning (CCML) is integrated into the WPTTD framework for enhancing the performance. Experimental evaluations conducted on both artificial and real-world networks have verified that this algorithm outperforms several mainstream multi-layer network community detection algorithms.

Structural prior-driven feature extraction with gradient-momentum combined optimization for convolutional neural network image classification

Recent image classification efforts have achieved certain success by incorporating prior information such as labels and logical rules to learn discriminative features. However, these methods overlook the variability of features, resulting in feature inconsistency and fluctuations in model parameter updates, which further contribute to decreased image classification accuracy and model instability. To address this issue, this paper proposes a novel method combining structural prior-driven feature extraction with gradient-momentum (SPGM), from the perspectives of consistent feature learning and precise parameter updates, to enhance the accuracy and stability of image classification. Specifically, SPGM leverages a structural prior-driven feature extraction (SPFE) approach to calculate gradients of multi-level features and originalimages to construct structural information, which is then transformed into prior knowledge to drive the network to learn features consistent with the original images. Additionally, an optimization strategy integrating gradients and momentum (GMO) is introduced, dynamically adjusting the direction and step size of parameter updates based on the angle and norm of the sum of gradients and momentum, enabling precise model parameter updates. Extensive experiments on CIFAR10 and CIFAR100 datasets demonstrate that the SPGM method significantly reduces the top-1 error rate in image classification, enhances the classification performance, and outperforms state-of-the-art methods.

Explicit 3D reconstruction from images with dynamic graph learning and rendering-guided diffusion

High-quality 3D reconstruction is becoming increasingly important in a variety of fields. Recently, implicit representation methods have made significant progress in image-based 3D reconstruction. However, these methods tend to yield entangled neural representations which lack support for standard 3D pipelines, and their reconstruction results usually experience a sharp drop in quality when input views are reduced. To obtain high-quality 3D content, we propose an explicit 3D reconstruction method that directly extracts textured meshes from images and remains robust using reduced input views. Our central components include a dynamic graph convolutional network (GCN) and a rendering-guided diffusion model. The dynamic GCN aims to improve mesh reconstruction quality by effectively aggregating features from vertex neighborhoods. The aggregation is accelerated through sampling geometric-related neighbors with different SDF signs, which gradually converges in quantity during training. The rendering-guided diffusion model learns prior distributions for unseen regions to improve reconstruction performance using sparse-view inputs. It uses the rendered image under an interpolated camera pose as conditioned input and its diffusion strength can be controlled with the rendering loss of explicit reconstruction. In addition, the rendering-guided diffusion model can be jointly trained to generate plausible novel views with 3D consistency. Experiments demonstrate that our method can produce high-quality explicit reconstruction results and maintain realistic reconstruction using sparse-view inputs.

Adjustment for sparse data bias in odds ratios: Significance to appraisal of risk of diabetes due to occupational trichlorfon insecticide exposure

BackgroundBias away from the null in odds ratios (OR), aggravated by low power, is a well-known phenomenon in statistics (sparse data bias). Such bias increases in presence of selection of “significant” results on the basis of null hypothesis testing (effect size magnification, ESM). ObjectivesWe seek to illustrate these issues and adjust for suspected sparse data bias in the context of a reported more than doubling of the odds of new onset type 2 diabetes in presence of occupational trichlorfon insecticide exposure reported in the Agricultural Health Study. MethodsWe performed ESM analysis on the crude ORs extracted from the contingency table in the published report, which is done by simulating selected OR given a posited true OR. Next, we applied easily accessible methods that adjust for sparse data bias to the extracted contingency tables, including data augmentation, bootstrap, Firth's regression, and Bayesian methods with weakly informative priors. ResultsDuring the ESM analysis, we observed that there was a reasonable chance that a “statistically significant” OR of around 2.5–2.6 would be observed for true OR of 1.2. Adjustment for sparse data bias revealed that Bayesian methods outperformed alternative approaches in terms of yielding more precise inference, while not making unjustified distributional assumptions about estimates of OR. The OR in the original paper of about 2.5–2.6 was reduced on average to OR of 1.9 to 2.2, with 95% (Bayesian) credible intervals that included the null. DiscussionIt is reasonable to adjust ORs for sparse data bias when the reported association has societal importance, because policy must be informed by the least biased estimates of the effect. We think that such adjustment would lead to a more appropriate evaluation of the extent of evidence on the contribution of occupational exposure to trichlorfon pesticide to risk of new onset diabetes.

A model for galaxy–galaxy strong lensing statistics in surveys

ABSTRACT Photometric wide-area observations in the next decade will be capable of detecting a large number of galaxy-scale strong gravitational lenses, increasing the gravitational lens sample size by orders of magnitude. To aid in forecasting and analysis of these surveys, we construct a flexible model based on observed distributions for the lens and source properties and test it on the results of past lens searches, including SL2S, SuGOHI, and searches on the COSMOS HST and DES fields. We use this model to estimate the expected yields of some current and planned surveys, including Euclid Wide, Vera Rubin LSST, and Roman High Latitude Wide Area. The model proposed includes a set of free parameters to constrain on the identifiability of a lens in an image, allowing construction of prior probability distributions for different lens detection methods. The code used in this work is made publicly available.

A parsimonious Bayesian predictive model for forecasting new reported cases of West Nile disease

Upon researching predictive models related to West Nile virus disease, it is discovered that there are numerous parameters and extensive information in most models, thus contributing to unnecessary complexity. Another challenge frequently encountered is the lead time, which refers to the period for which predictions are made and often is too short. This paper addresses these issues by introducing a parsimonious method based on ICC curves, offering a logistic distribution model derived from the vector-borne SEIR model. Unlike existing models relying on diverse environmental data, our approach exclusively utilizes historical and present infected human cases (number of new cases). With a year-long lead time, the predictions extend throughout the 12 months, gaining precision as new data emerge. Theoretical conditions are derived to minimize Bayesian loss, enhancing predictive precision. We construct a Bayesian forecasting probability density function using carefully selected prior distributions. Applying these functions, we predict month-specific infections nationwide, rigorously evaluating accuracy with probabilistic metrics. Additionally, HPD credible intervals at 90%, 95%, and 99% levels is performed. Precision assessment is conducted for HPD intervals, measuring the proportion of intervals that does not include actual reported cases for 2020–2022.

Genomic Selection for Weaning Weight in Alpine Merino Sheep Based on GWAS Prior Marker Information.

This study aims to compare the accuracy of genomic estimated breeding values (GEBV) estimated using a genomic best linear unbiased prediction (GBLUP) method and GEBV estimates incorporating prior marker information from a genome-wide association study (GWAS) for the weaning weight trait in highland Merino sheep. The objective is to provide theoretical and technical support for improving the accuracy of genomic selection. The study used a population of 1007 highland Merino ewes, with the weaning weight at 3 months as the target trait. The population was randomly divided into two groups. The first group was used for GWAS analysis to identify significant markers, and the top 5%, top 10%, top 15%, and top 20% markers were selected as prior marker information. The second group was used to estimate genetic parameters and compare the accuracy of GEBV predictions using different prior marker information. The accuracy was obtained using a five-fold cross-validation. Finally, both groups were subjected to cross-validation. The study's findings revealed that the heritability of the weaning weight trait, as calculated using the GBLUP model, ranged from 0.122 to 0.394, with corresponding prediction accuracies falling between 0.075 and 0.228. By incorporating prior marker information from GWAS, the heritability was enhanced to a range of 0.125 to 0.407. The inclusion of the top 5% to top 20% significant SNPs from GWAS results as prior information into GS showed potential for improving the accuracy of predicting genomic breeding value.

Sensory choices as logistic classification.

Logistic classification is a simple way to make choices based on a set of factors: give each factor a weight, sum the results, and use the sum to set the log odds of a random draw. This operation is known to describe human and animal choices based on value (economic decisions). There is increasing evidence that it also describes choices based on sensory inputs (perceptual decisions), presented across sensory modalities (multisensory integration) and combined with non-sensory factors such as prior probability, expected value, overall motivation, and recent actions. Logistic classification can also capture the effects of brain manipulations such as local inactivations. The brain may implement by thresholding stochastic inputs (as in signal detection theory) acquired over time (as in the drift diffusion model). It is the optimal strategy under certain conditions, and the brain appears to use it as a heuristic in a wider set of conditions.

Updating direct methods II. Reduction of the structural complexity when triplet invariants are estimated via the Patterson map

Direct methods have practically solved the phase problem for small–medium-size molecules but have substantially failed in macromolecular crystallography. They have two main limitations: a strong dependence on structural complexity and the need to work with atomic-resolution data. Many attempts have been made to broaden their field of applicability, for example the use of some a priori information to make the estimate of the triplet invariant phases more effective. Unfortunately none of these new approaches allowed the successful application of direct methods to proteins and nucleic acids. Direct methods are still a niche tool in macromolecular crystallography. In a recent publication [Giacovazzo (2019). Acta Cryst. A75, 142–157] the method of joint probability distributions has been modified to take into account new sources of prior information, one of which is relevant to this article: the Patterson map. In practice, it has been shown that with prior knowledge of the interatomic vectors one is able to modify the classic Cochran reliability parameter for estimating the triplet invariant phases. The article was essentially theoretical in nature, and no attempt was described to test the practical usefulness of the new probabilistic formulas. This work is therefore the first application of the new method. It is shown that the use of the Patterson map as prior information substantially improves the Cochran estimate of triplet phases; the phase error distribution for the new estimates, even if it is related to macromolecular structures, becomes similar to that obtained for medium-size structures. In some ways, it is as if the use of the Patterson information reduces the structural complexity, thus allowing a more general use of direct methods in macromolecular crystallography. Atomic resolution no longer seems to be a necessary ingredient for the applicability of direct methods; tests show that the apparent reduction in structural complexity also occurs in macromolecular structures with experimental data having a resolution of 2.3 Å. A number of test structures have been used to show the potential of the new technique.

Stereo visual-inertial localization algorithm for orchard robots based on point-line features

The vision-based localization of orchard mobile robots is an indispensable component of orchard intelligent management, applicable to scenarios such as navigation and harvesting. Due to the rugged terrain and lack of texture features in orchard environments, the accuracy of Visual-Inertial Odometry (VIO) based on feature point is compromised, making it challenging to meet practical application requirements. Addressing these issues, this paper proposes an algorithm for stereo visual-inertial localization based on point-line features, by enhancing VINS-Fusion. The algorithm incorporates the line feature detector algorithm (LSD) into the odometry front-end to detect line features, addressing the insufficient effective feature points and low-quality feature matching issues in orchard environments. Simultaneously, strategies for length filtering and feature matching are introduced for line features, eliminating poor-quality line features and matches caused by rugged terrain, thereby reducing adverse impacts on localization accuracy. To prevent keyframe redundancy due to a scarcity of stable feature points in areas with missing textures, such as tree trunks and leaves, a keyframe criteria optimization method based on point-line features is designed. Back-end optimization minimizes the cost function containing residuals of point-line features, prior information, and IMU, ultimately improving the localization accuracy of mobile robots. To validate the effectiveness and practicality of the proposed algorithm, a self-built dataset was created in real orchard environments, including scenes from banana plantation, mango orchard, and wampee orchard. Localization experiments were conducted using Rosario, EuRoC public datasets and self-built orchard dataset. Results indicate that the proposed algorithm consistently achieves lower ATE-RMSE than VINS-Fusion, with a maximum reduction of 79.2 % in the Rosario dataset sequence, 23.3 % in the EuRoC dataset sequence, and ATE-RMSE values of 0.091 m, 0.107 m, and 0.093 m in banana plantation, mango orchard, and wampee orchard, respectively. These represent reductions of 22.9 %, 7.6 %, and 27.3 % compared to VINS-Fusion. In the self-built orchard dataset, the average frame processing times for the algorithm front-end is 56.3 ms, while for the back-end is 31 ms, meeting the practical localization requirements. The proposed algorithm effectively enhances the localization accuracy of orchard mobile robots, offering a viable solution for autonomous navigation in orchard robot systems.

Dose rationale for the use of meropenem/vaborbactam combination in paediatric patients with Gram-negative bacterial infections.

Meropenem/vaborbactam combination is approved in adults by FDA and EMA for complicated urinary tract infections and by EMA also for other Gram-negative infections. We aimed to characterise the pharmacokinetics of both moieties in an ongoing study in children and use a model-based approach to inform adequate dosing regimens in paediatric patients. Over 4196 blood samples of meropenem and vaborbactam (n = 414 subjects) in adults, together with 114 blood samples (n = 39) in paediatric patients aged 3 months to 18 years were available for this analysis. Data were analysed using a population with prior information from a pharmacokinetic model in adults to inform parameter estimation in children. Simulations were performed to assess the suitability of different dosing regimens to achieve adequate probability of target attainment (PTA). Meropenem/vaborbactam PK was described with two-compartment models with first-order elimination. Body weight and CLcr were significant covariates on the disposition of both drugs. A maturation function was evaluated to explore changes in clearance in neonates. PTA ≥90% was derived for children aged ≥3 months after 3.5-h IV infusion of 40 mg/kg Q8h of both meropenem and vaborbactam and 2 g/2 g for those ≥50 kg. Extrapolation of disposition parameters suggest that adequate PTA is achieved after a 3.5-h IV infusion of 20 mg/kg for neonates and infants (3 months). An integrated analysis of adult and paediatric data allowed accurate description of sparsely sampled meropenem/vaborbactam PK in paediatric patients and provided recommendations for the dosing in neonates and infants (3 months).

Vessel-targeted compensation of deformable motion in interventional cone-beam CT

The present standard of care for unresectable liver cancer is transarterial chemoembolization (TACE), which involves using chemotherapeutic particles to selectively embolize the arteries supplying hepatic tumors. Accurate volumetric identification of intricate fine vascularity is crucial for selective embolization. Three-dimensional imaging, particularly cone-beam CT (CBCT), aids in visualization and targeting of small vessels in such highly variable anatomy, but long image acquisition time results in intra-scan patient motion, which distorts vascular structures and tissue boundaries. To improve clarity of vascular anatomy and intra-procedural utility, this work proposes a targeted motion estimation and compensation framework that removes the need for any prior information or external tracking and for user interaction. Motion estimation is performed in two stages: (i) a target identification stage that segments arteries and catheters in the projection domain using a multi-view convolutional neural network to construct a coarse 3D vascular mask; and (ii) a targeted motion estimation stage that iteratively solves for the time-varying motion field via optimization of a vessel-enhancing objective function computed over the target vascular mask. The vessel-enhancing objective is derived through eigenvalues of the local image Hessian to emphasize bright tubular structures. Motion compensation is achieved via spatial transformer operators that apply time-dependent deformations to partial angle reconstructions, allowing efficient minimization via gradient backpropagation. The framework was trained and evaluated in anatomically realistic simulated motion-corrupted CBCTs mimicking TACE of hepatic tumors, at intermediate (3.0 mm) and large (6.0 mm) motion magnitudes. Motion compensation substantially improved median vascular DICE score (from 0.30 to 0.59 for large motion), image SSIM (from 0.77 to 0.93 for large motion), and vessel sharpness (0.189 mm−1 to 0.233 mm−1 for large motion) in simulated cases. Motion compensation also demonstrated increased vessel sharpness (0.188 mm−1 before to 0.205 mm−1 after) and reconstructed vessel length (median increased from 37.37 to 41.00 mm) on a clinical interventional CBCT. The proposed anatomy-aware motion compensation framework presented a promising approach for improving the utility of CBCT for intra-procedural vascular imaging, facilitating selective embolization procedures.

Randomized Controlled Trial of Enteral Vitamin D Supplementation (ViDES) in Infants

Vitamin D is necessary to develop healthy lungs and other organs early in life. Most infants born before 28 weeks' gestation have low vitamin D levels at birth and a limited intake during the first month. Enteral vitamin D supplementation is inexpensive and widely used. The appropriate supplementation regimen for extremely preterm infants is controversial, and the effect of different regimens on their blood levels and outcomes is unclear. Randomized, blinded comparative effectiveness trial to compare two vitamin D supplementation regimens for inborn infants <28 weeks gestation or <1000 grams birth weight at a large academic center in the United States.Infants are stratified by birth weight and randomized within 96 hours after birth to either routine supplementation (400 IU/day with established feedings) or increased supplementation (800 IU/day with any feedings) during the first 28 days after birth.We hypothesize that the higher and early vitamin D dose (800 IU/d with early feeding) compared to placebo plus routine dose (400 IU/d with established feeding) will substantially increase total 25-hydroxyvitamin D3 levels measured as state-of-art at one month, reduce respiratory support at 36 weeks' postmenstrual age (on an ordinal scale predictive of later adverse outcomes) and improve or at least not worsen other important secondary outcomes. The infants in the study will follow up at 22-26 months' corrected age (~2 years) with blinded certified examiners to evaluate neurodevelopmental outcomes.The sample size of a minimum of 180 infants provides >90% power to detect a >95% posterior probability of a 33% increase in serum 25-hydroxy vitamin D3 and >80% power to detect a >80% posterior probability of a relative risk decrease of 20% of reducing respiratory support by intention-to-treat Bayesian analyses using a neutral prior probability. Our study will help clarify the uncertain relationship of vitamin D supplementation and its associated serum metabolites to clinical outcomes of extremely preterminfants. Confirmation of our hypotheses would prompt reconsideration of the supplementation regimens used in extremely preterm infants and justify a large multicenter study to verify the generalizability of the results. ClinicalTrials.gov registered on July 14, 2022 (NCT05459298).

Monocular Depth Estimation via Self-Supervised Self-Distillation.

Self-supervised monocular depth estimation can exhibit excellent performance in static environments due to the multi-view consistency assumption during the training process. However, it is hard to maintain depth consistency in dynamic scenes when considering the occlusion problem caused by moving objects. For this reason, we propose a method of self-supervised self-distillation for monocular depth estimation (SS-MDE) in dynamic scenes, where a deep network with a multi-scale decoder and a lightweight pose network are designed to predict depth in a self-supervised manner via the disparity, motion information, and the association between two adjacent frames in the image sequence. Meanwhile, in order to improve the depth estimation accuracy of static areas, the pseudo-depth images generated by the LeReS network are used to provide the pseudo-supervision information, enhancing the effect of depth refinement in static areas. Furthermore, a forgetting factor is leveraged to alleviate the dependency on the pseudo-supervision. In addition, a teacher model is introduced to generate depth prior information, and a multi-view mask filter module is designed to implement feature extraction and noise filtering. This can enable the student model to better learn the deep structure of dynamic scenes, enhancing the generalization and robustness of the entire model in a self-distillation manner. Finally, on four public data datasets, the performance of the proposed SS-MDE method outperformed several state-of-the-art monocular depth estimation techniques, achieving an accuracy (δ1) of 89% while minimizing the error (AbsRel) by 0.102 in NYU-Depth V2 and achieving an accuracy (δ1) of 87% while minimizing the error (AbsRel) by 0.111 in KITTI.

Multi-Armed Bandit-Based User Network Node Selection.

In the scenario of an integrated space-air-ground emergency communication network, users encounter the challenge of rapidly identifying the optimal network node amidst the uncertainty and stochastic fluctuations of network states. This study introduces a Multi-Armed Bandit (MAB) model and proposes an optimization algorithm leveraging dynamic variance sampling (DVS). The algorithm posits that the prior distribution of each node's network state conforms to a normal distribution, and by constructing the distribution's expected value and variance, it maximizes the utilization of sample data, thereby maintaining an equilibrium between data exploitation and the exploration of the unknown. Theoretical substantiation is provided to illustrate that the Bayesian regret associated with the algorithm exhibits sublinear growth. Empirical simulations corroborate that the algorithm in question outperforms traditional ε-greedy, Upper Confidence Bound (UCB), and Thompson sampling algorithms in terms of higher cumulative rewards, diminished total regret, accelerated convergence rates, and enhanced system throughput.

Consensus Subspace Graph Regularization based on prior information for multiplex network clustering

Multiplex network clustering can identify the common cluster structure shared by all layers, which is of great significance for downstream research such as personalized recommendations of social relationships and the mining of social media communication behaviors. Traditional multiplex network clustering methods rely only on the topological structure and are suitable for networks with clear structures. However, real-world networks often suffer from sparse connectivity and noisy edges. In addition, the current methods based on prior information only use the obtained consensus prior information as a preprocessing method for multiplex networks, and do not fully utilize and integrate the prior information in the clustering process, resulting in a low accuracy. To solve the problem of insufficient utilization of prior information, we propose a Consensus Subspace Graph Regularization (CSGR) approach for multiplex network clustering, which integrates topological information with the consensus prior information of a network. We first construct the consensus prior matrix of a network by a non-overlapping greedy search method, which represents a subset of the network that consists of nodes with high edge density. Then we construct a graph regularization term, which encodes the consensus prior information, to optimize the generation of a joint low-dimensional representation within the consensus subspace for the entire multiplex network. Finally, we employ the consensus prior matrix to denoise each network layer, thereby yielding a precise low-dimensional representation of each layer for consensus subspace fusion. In addition, comprehensive experiments have demonstrated that CSGR improves the clustering accuracy of real-world networks by an average of 1.56%.

HomoR-CS: A homogeneous region-based compressed sensing method for SAR tomography

The performance of most existing tomographic synthetic aperture radar (SAR) (TomoSAR) methods that reconstruct the scene pixel-by-pixel is degraded by speckle noise and low signal-to-noise ratio. To solve these problems, we propose a homogeneous region-based compressed sensing (HomoR-CS) method for SAR tomography. This method enhances the processing approach by transitioning from the traditional pixel-by-pixel processing to the joint processing based on multiple adjacent pixels in homogeneous regions. First, a similarity measure is designed to cluster pixels that have similar electromagnetic scattering intensities and three-dimensional (3-D) positions into homogeneous regions. Then, the homogeneous region-oriented TomoSAR signal model is proposed and the solution is given. Sparse approximation at the homogeneous region level is used to estimate the elevation for every pixel. The multiple adjacent pixels within the homogeneous region are jointly processed to determine the initial elevation centers, which are used as the prior information for the subsequent accurate elevation estimation of each pixel. Finally, the experimental analyses using both simulated and measured data validate the effectiveness of the HomoR-CS method. The results show that the HomoR-CS method reduces the outliers of 3-D reconstruction results and enhances the recovery of weak scattering targets.

A Data Matrix Code Recognition Method Based on L-Shaped Dashed Edge Localization Using Central Prior.

The recognition of data matrix (DM) codes plays a crucial role in industrial production. Significant progress has been made with existing methods. However, for low-quality images with protrusions and interruptions on the L-shaped solid edge (finder pattern) and the dashed edge (timing pattern) of DM codes in industrial production environments, the recognition accuracy rate of existing methods sharply declines due to a lack of consideration for these interference issues. Therefore, ensuring recognition accuracy in the presence of these interference issues is a highly challenging task. To address such interference issues, unlike most existing methods focused on locating the L-shaped solid edge for DM code recognition, we in this paper propose a novel DM code recognition method based on locating the L-shaped dashed edge by incorporating the prior information of the center of the DM code. Specifically, we first use a deep learning-based object detection method to obtain the center of the DM code. Next, to enhance the accuracy of L-shaped dashed edge localization, we design a two-level screening strategy that combines the general constraints and central constraints. The central constraints fully exploit the prior information of the center of the DM code. Finally, we employ libdmtx to decode the content from the precise position image of the DM code. The image is generated by using the L-shaped dashed edge. Experimental results on various types of DM code datasets demonstrate that the proposed method outperforms the compared methods in terms of recognition accuracy rate and time consumption, thus holding significant practical value in an industrial production environment.