Iterative Framework Research Articles

Train schedule optimization for commuter-metro networks

The interconnection and synchronization among different transport modes have been more and more attractive as the modern transportation system is moving towards Mobility-as-a-Service. In this study, we address the train scheduling problem for “commuter rail-metro” systems, where the trains from commuter rail lines can go directly into metro systems to provide seamless services for passengers. To optimize the schedule of trains for both commuter rail lines and metro lines, we propose a job shop scheduling model where precedence constraints from commuter-metro networks are taken into account and develop a mixed-integer programming (MIP) model with quadratic constraints. Our model considers the orders of different types of trains and the safety constraints, due to different types of signalling equipment in commuter and metro systems. Since these constraints involve a set of IF-THEN rules, we prove that these constraints can be equivalently reformulated as linear inequalities, without adding new variables. To solve the proposed model efficiently, we design an iterative solution framework, which generates a feasible solution using dynamic programming, next solves a MIP model, then calculates the train speed profiles, and if train speed profiles violate the safety constraints, re-optimizes the MIP model with modified alternative constraints. To verify the effectiveness of the proposed approaches, numerical experiments are performed on small and real-world instances based on the Beijing metro Line 1 and the Batong Line operational data.

Establishing a Novel Diagnostic Framework Using Handheld Point-of-Care Focused-Echocardiography (HoPE) for Acute Left-Sided Cardiac Valve Emergencies: A Bayesian Approach for Emergency Physicians in Resource-Limited Settings.

Acute severe cardiac valve emergencies, such as acute severe mitral regurgitation (AMR) and acute severe aortic regurgitation (AAR), present significant challenges in terms of diagnosis and management. Handheld point-of-care ultrasound devices have emerged as potentially pivotal tools in ensuring the prompt and accurate diagnosis of these left-sided valve emergencies by emergency physicians, particularly in resource-limited settings. Despite the increased utilisation of point-of-care ultrasound by emergency physicians for the management of patients in states of acute cardiorespiratory failure, current diagnostic protocols cannot perform sufficient quantitative assessments of the left-sided cardiac valves. This review elucidates and evaluates the diagnostic utility of handheld point-of-care focused-echocardiography (HoPE) in native AMR and AAR by reviewing the relevant literature and the use of clinical case examples from the Emergency Department at Port Shepstone Regional Hospital (PSRH-ED)-a rural, resource-limited hospital located in KwaZulu-Natal, South Africa. Combining the findings of the review and clinical case illustrations, this review proceeds to synthesise a novel, Bayesian-inspired, iterative diagnostic framework that integrates HoPE into the evaluation of patients with acute cardiorespiratory failure and suspected severe left-sided valve lesions.

A Cross-Scale Iterative Attentional Adversarial Fusion Network for Infrared and Visible Images

Recent existing methods generally adopt a simple concatenation or addition strategy to integrate features at the fusion layer, failing to adequately consider the intrinsic characteristics of different modal images and feature interaction of different scales, which may produce a limited fusion performance. Toward this end, we introduce a cross-scale iterative attentional adversarial fusion network, namely CrossFuse. More specifically, in the generator, we design a cross-modal attention integrated module to merge the intrinsic content of different modal images. The parallel spatial-independent and channel-independent pathways are proposed to calculate the attentional weights, which are assigned to measure the activity levels of source images at the same scale. Moreover, we construct a cross-scale iterative decoder framework to interact with different modality features at different scales, which can constantly optimize their activity levels. By this means, the generator learns to integrate their modality characteristics via attentional weights in an iterative manner, and the generated result characterizes competitive infrared radiant intensity and distinct visible detail description. Extensive experiments on three different benchmarks demonstrate that our CrossFuse outperforms other nine state-of-the-art methods in terms of fusion performance, generalization ability and computational efficiency. Our codes will be released at https://github.com/Zhishe-Wang/CrossFuse.

Iterative graph filtering network for 3D human pose estimation

Graph convolutional networks (GCNs) have proven to be an effective approach for 3D human pose estimation. By naturally modeling the skeleton structure of the human body as a graph, GCNs are able to capture the spatial relationships between joints and learn an efficient representation of the underlying pose. However, most GCN-based methods use a shared weight matrix, making it challenging to accurately capture the different and complex relationships between joints. In this paper, we introduce an iterative graph filtering framework for 3D human pose estimation, which aims to predict the 3D joint positions given a set of 2D joint locations in images. Our approach builds upon the idea of iteratively solving graph filtering with Laplacian regularization via the Gauss–Seidel iterative method. Motivated by this iterative solution, we design a Gauss–Seidel network (GS-Net) architecture, which makes use of weight and adjacency modulation, skip connection, and a pure convolutional block with layer normalization. Adjacency modulation facilitates the learning of edges that go beyond the inherent connections of body joints, resulting in an adjusted graph structure that reflects the human skeleton, while skip connections help maintain crucial information from the input layer’s initial features as the network depth increases. We evaluate our proposed model on two standard benchmark datasets, and compare it with a comprehensive set of strong baseline methods for 3D human pose estimation. Our experimental results demonstrate that our approach outperforms the baseline methods on both datasets, achieving state-of-the-art performance. Furthermore, we conduct ablation studies to analyze the contributions of different components of our model architecture and show that the skip connection and adjacency modulation help improve the model performance.

An Iterative Learning Scheme with Binary Classifier for Improved Event Detection in Surveillance Video

This paper presents an iterative training framework with a binary classifier to improve the learning capability of a deep learning model for detecting abnormal behaviors in surveillance video. When a deep learning model trained on data from one surveillance video is deployed to monitor another video stream, its abnormal behavior detection performance often decreases significantly. To ensure the desired performance in new environments, the deep learning model needs to be retrained with additional training data from the new video stream. Iterative training requires manual annotation of the additional training data during the fine-tuning process, which is a tedious and error-prone task. To address this issue, this paper proposes a binary classifier to automatically label false positive data without human intervention. The binary classifier is trained on bounding boxes extracted from the detection model to identify which boxes are true positives or false positives. The proposed learning framework incrementally enhances the performance of the deep learning model for detecting abnormal behaviors in a surveillance video stream through repeated iterative learning cycles. Experimental results demonstrate that the accuracy of the detection model increases from 0.35 (mAP = 0.74) to 0.91 (mAP = 0.99) in just a few iterations.

ResQ-IOS: An iterative optimization-based simulation framework for quantifying the resilience of interdependent critical infrastructure systems to natural hazards

Critical Infrastructure Systems are highly complex and interdependent. Growing complexity and interdependency between infrastructure systems and frequent exposure to extreme events have inevitably increased the probability of cascading failures and the prolonged lack of serviceability in urban communities, especially so for energy systems. The resilience analysis of interdependent infrastructure systems against natural hazards provides stakeholders with a comprehensive outlook on recovery strategies to minimize the damage costs and losses caused by extreme events. This paper introduces the ResQ-IOS, a Resilience Quantification Iterative Optimization-based Simulation (IOS) framework for quantifying the resilience of interdependent infrastructure systems to natural hazards with the capability of considering the real-world conditions for the status of infrastructure systems' components. The ResQ-IOS framework consists of five modules: risk assessment, simulation, optimization, database, and controller. To evaluate the capabilities of this framework, the seismic resilience of interdependent energy infrastructure networks (power, natural gas, and water) in Shelby County (TN), USA, was assessed. The results of the resilience analysis of the case study suggest that the water network is the best candidate for implementing pre-disaster Resilience Enhancement Measures (REMs), like increasing the supply capacity. Due to the controlling role of the power network in the community's recovery process, it is recommended that post-disaster REMs, such as increasing the number of Repair and Maintenance (R&M) teams, should be applied to the power network to speed up the restoration of failed components in that network and consequently, shorten the recovery duration of the community. The ResQ-IOS can be employed as a useful computational tool for planning the resilience-oriented sustainable development of urban communities by, for example, deploying Renewable Energy (RE)-based strategies to enhance their disaster resilience.

A RBFNN based active learning surrogate model for evaluating low failure probability in reliability analysis

This paper presents a novel active learning surrogate model for estimating low failure probability in the reliability analysis of complex structures based on a radial basis function neural network (RBFNN). The RBFNN surrogate model, which possesses global approximation capability, is constructed by randomly selecting an initial design of experiments (DoEs) from a Monte Carlo Simulation (MCS) population using the minimax distance method. Furthermore, the RBFNN surrogate model is updated by sequentially adding highly representative samples to improve the local prediction accuracy. The highly representative samples are selected using minimax distance method from each level’s failure region of subset simulation (SS), and are further modified by the calculation of actual limit state function (LSF). Consequently, the low failure probability is obtained through an iterative framework that combines SS and RBFNN surrogate model. The proposed approach significantly reduces the number of experiments required, resulting in lower costs and higher efficiency. Three examples are provided to demonstrate the effectiveness and accuracy of the proposed method.

GenKL: An Iterative Framework for Resolving Label Ambiguity and Label Non-conformity in Web Images Via a New Generalized KL Divergence

Web image datasets curated online inherently contain ambiguous in-distribution instances and out-of-distribution instances, which we collectively call non-conforming (NC) instances. In many recent approaches for mitigating the negative effects of NC instances, the core implicit assumption is that the NC instances can be found via entropy maximization. For “entropy” to be well-defined, we are interpreting the output prediction vector of an instance as the parameter vector of a multinomial random variable, with respect to some trained model with a softmax output layer. Hence, entropy maximization is based on the idealized assumption that NC instances have predictions that are “almost” uniformly distributed. However, in real-world web image datasets, there are numerous NC instances whose predictions are far from being uniformly distributed. To tackle the limitation of entropy maximization, we propose (alpha , beta )-generalized KL divergence, {mathcal {D}}_{text {KL}}^{alpha , beta }(pVert q), which can be used to identify significantly more NC instances. Theoretical properties of {mathcal {D}}_{text {KL}}^{alpha , beta }(pVert q) are proven, and we also show empirically that a simple use of {mathcal {D}}_{text {KL}}^{alpha , beta }(pVert q) outperforms all baselines on the NC instance identification task. Building upon (alpha ,beta )-generalized KL divergence, we also introduce a new iterative training framework, GenKL, that identifies and relabels NC instances. When evaluated on three web image datasets, Clothing1M, Food101/Food101N, and mini WebVision 1.0, we achieved new state-of-the-art classification accuracies: 81.34%, 85.73% and 78.99%/92.54% (top-1/top-5), respectively.

Knowledge-Fusion-Based Iterative Graph Structure Learning Framework for Implicit Sentiment Identification.

Implicit sentiment identification is a significant classical task in text analysis. Graph neural networks (GNNs) have recently been successful in implicit sentiment identification, but the current approaches still suffer from two problems. On the one hand, there is a lack of structural information carried by the single-view graph structure of implicit sentiment texts to accurately capture obscure sentiment expressions. On the other hand, the predefined fixed graph structure may contain some noisy edges that cannot represent semantic information using an accurate topology, which can seriously impair the performance of implicit sentiment analysis. To address these problems, we introduce a knowledge-fusion-based iterative graph structure learning framework (KIG). Specifically, for the first problem, KIG constructs graph structures based on three views, namely, co-occurrence statistics, cosine similarity, and syntactic dependency trees through prior knowledge, which provides rich multi-source information for implicit sentiment analysis and facilitates the capture of implicit obscure sentiment expressions. To address the second problem, KIG innovatively iterates the three original graph structures and searches for their implicit graph structures to better fit the data themselves to optimize the downstream implicit sentiment analysis task. We compared our method with the mainstream implicit sentiment identification methods on two publicly available datasets, and ours outperformed both benchmark models. The accuracy, recall, and F1 values of KIG on the Pun of the Day dataset reached 89.2%, 93.7%, and 91.1%, respectively. Extensive experimental results demonstrate the superiority of our proposed method for the implicit sentiment identification task.

Data Imputation with Iterative Graph Reconstruction

Effective data imputation demands rich latent ``structure" discovery capabilities from ``plain" tabular data. Recent advances in graph neural networks-based data imputation solutions show their structure learning potentials by translating tabular data as bipartite graphs. However, due to a lack of relations between samples, they treat all samples equally which is against one important observation: ``similar sample should give more information about missing values." This paper presents a novel Iterative graph Generation and Reconstruction framework for Missing data imputation(IGRM). Instead of treating all samples equally, we introduce the concept: ``friend networks" to represent different relations among samples. To generate an accurate friend network with missing data, an end-to-end friend network reconstruction solution is designed to allow for continuous friend network optimization during imputation learning. The representation of the optimized friend network, in turn, is used to further optimize the data imputation process with differentiated message passing. Experiment results on eight benchmark datasets show that IGRM yields 39.13% lower mean absolute error compared with nine baselines and 9.04% lower than the second-best. Our code is available at https://github.com/G-AILab/IGRM.

Predicting potential small molecule-miRNA associations utilizing truncated schatten p-norm.

MicroRNAs (miRNAs) have significant implications in diverse human diseases and have proven to be effectively targeted by small molecules (SMs) for therapeutic interventions. However, current SM-miRNA association prediction models do not adequately capture SM/miRNA similarity. Matrix completion is an effective method for association prediction, but existing models use nuclear norm instead of rank function, which has some drawbacks. Therefore, we proposed a new approach for predicting SM-miRNA associations by utilizing the truncated schatten p-norm (TSPN). First, the SM/miRNA similarity was preprocessed by incorporating the Gaussian interaction profile kernel similarity method. This identified more SM/miRNA similarities and significantly improved the SM-miRNA prediction accuracy. Next, we constructed a heterogeneous SM-miRNA network by combining biological information from three matrices and represented the network with its adjacency matrix. Finally, we constructed the prediction model by minimizing the truncated schatten p-norm of this adjacency matrix and we developed an efficient iterative algorithmic framework to solve the model. In this framework, we also used a weighted singular value shrinkage algorithm to avoid the problem of excessive singular value shrinkage. The truncated schatten p-norm approximates the rank function more closely than the nuclear norm, so the predictions are more accurate. We performed four different cross-validation experiments on two separate datasets, and TSPN outperformed various most advanced methods. In addition, public literature confirms a large number of predictive associations of TSPN in four case studies. Therefore, TSPN is a reliable model for SM-miRNA association prediction.

Delving Deep into Pixel Alignment Feature for Accurate Multi-View Human Mesh Recovery

Regression-based methods have shown high efficiency and effectiveness for multi-view human mesh recovery. The key components of a typical regressor lie in the feature extraction of input views and the fusion of multi-view features. In this paper, we present Pixel-aligned Feedback Fusion (PaFF) for accurate yet efficient human mesh recovery from multi-view images. PaFF is an iterative regression framework that performs feature extraction and fusion alternately. At each iteration, PaFF extracts pixel-aligned feedback features from each input view according to the reprojection of the current estimation and fuses them together with respect to each vertex of the downsampled mesh. In this way, our regressor can not only perceive the misalignment status of each view from the feedback features but also correct the mesh parameters more effectively based on the feature fusion on mesh vertices. Additionally, our regressor disentangles the global orientation and translation of the body mesh from the estimation of mesh parameters such that the camera parameters of input views can be better utilized in the regression process. The efficacy of our method is validated in the Human3.6M dataset via comprehensive ablation experiments, where PaFF achieves 33.02 MPJPE and brings significant improvements over the previous best solutions by more than 29%. The project page with code and video results can be found at https://kairobo.github.io/PaFF/.

Adaptive constraints by morphological operations for single-shot digital holography

Digital holography provides access to quantitative measurement of the entire complex field, which is indispensable for the investigation of wave-matter interactions. The emerging iterative phase retrieval approach enables to solve the inverse imaging problem only from the given intensity measurements and physical constraints. However, enforcing imprecise constraints limits the reconstruction accuracy and convergence speed. Here, we propose an advanced iterative phase retrieval framework for single-shot in-line digital holography that incorporates adaptive constraints, which achieves optimized convergence behavior, high-fidelity and twin-image-free reconstruction. In conjunction with morphological operations which can extract the object structure while eliminating the irrelevant part such as artifacts and noise, adaptive constraints allow the support region to be accurately estimated and automatically updated at each iteration. Numerical reconstruction of complex-valued objects and the capability of noise immunity are investigated. The improved reconstruction performance of this approach is experimentally validated. Such flexible and versatile framework has promising applications in biomedicine, X-ray coherent diffractive imaging and wavefront sensing.

Distributed RMI-DBG model: Scalable iterative de Bruijn graph algorithm for short read genome assembly problem

Genome assembly is the computational process of merging short parts of DNA into larger sequences called contigs. Rapid growth of high-throughput genome sequencing technologies and production of large amount of data have led to the genome assembly paradigms shift from shared memory to distributed memory systems in the recent years. Among the existing assembly algorithms, the iterative de Bruijn Graph is a leading approach for assembling short reads. This approach by exploring the advantages of all k between kmin to kmax, generates high quality assembly. However, the assembly operations are decelerated especially in the larger data sets. RMI-DBG is an agile iterative de Bruijn Graph algorithm that has the computational efficiency of de Bruijn Graph methods and the flexibility of overlap-based algorithms. In this paper, we suggest a distributed iterative DBG model based on RMI-DBG, named DRMI-DBG. The proposed idea is to address the problem of parallelizing the de Bruijn Graph construction and processing on distributed memory systems at each iteration of the algorithm. DRMI-DBG is a scalable iterative DBG framework over a Hadoop cluster by applying the power of Spark (a batch processing engine) and Giraph (a distributed big graph processing system). Experiments on a variety of real data sets show that DRMI-DBG accelerates the performance of RMI-DBG algorithm and IDBA-UD assembler up to 4.8 times with comparable or better results in the quality of the assembly. For more evaluation, performance of the proposed model is compared to ScalaDBG, as the state-of-the-art distributed assembler based on the multiple k-values strategy.

Development of an intravenous chemotherapy intervention for children and adolescents with cancer administered by their parents at home (INTACTatHome)

BackgroundFamilies of children and adolescents with cancer strive to maintain routines and normalcy during the child’s treatment trajectory that requires frequent hospital visits. Intravenous chemotherapy at home can reduce time spent on the frequent hospital visits and mitigate disruption in daily life. Studies on home chemotherapy for children and adolescents with cancer are limited, as is knowledge of family and health care professionals’ needs, and knowledge required to inform adaptation or replication of interventions in other settings. The aim of this study was to develop and describe an evidence-based home chemotherapy intervention that is feasible and safe for children and adolescents and suitable for future feasibility testing.MethodsThe Medical Research Council’s guidance for developing complex interventions in health care and the framework of action developed by O’Cathain et al. was used as theoretical frameworks to structure the development process. A literature search, an ethnographic study, and interviews with clinical nurse specialists from adult cancer departments formed the evidence base. Educational learning theory to support and understand the intervention was identified. Stakeholder perspectives were explored in workshops with health care professionals and parent-adolescent interviews. Reporting was qualified using the GUIDED checklist.ResultsA stepwise educational program to teach parents how to administer low-dose chemotherapy (Ara-C) to their child at home and a simple and safe administration procedure were developed. Key uncertainties were identified, including barriers and facilitators impacting future testing, evaluation, and implementation. Causal assumptions and reasoning for how the intervention leads to short-term outcomes and long-term impact were clarified in a logic model.ConclusionsThe iterative and flexible framework allowed for integration of existing evidence and new data and was successfully applied to the development process. The detailed report on the development process of the home chemotherapy intervention can enhance adaptation or replication of the intervention to other settings and thereby mitigate family disruption and stress of frequent hospital visits for these treatments. The study has informed the next phase of the research project that aims to test the home chemotherapy intervention in a prospective single-arm feasibility study.Trial registrationClinicalTrials.gov ID: NCT05372536.

The Development of Agile Enterprise Architecture for Digital Transformation in Higher Education Institutions

The rapid evolution of digital technologies has led to significant transformations in various industries, including higher education. This study explores the role of Agile Enterprise Architecture (AEA) in supporting digital transformation initiatives within Higher Education Institutions (HEIs). AEA provides a flexible, adaptive, and iterative framework to manage the complex and dynamic nature of digital transformation. We conducted a qualitative study using a multiple case-study approach, investigating four HEIs that implemented AEA in their digital transformation initiatives. Data were collected through semi-structured interviews, document analysis, and participant observation. We employed thematic analysis to identify the key factors contributing to the successful implementation of AEA in these institutions. Our findings revealed that AEA plays a crucial role in facilitating digital transformation by providing a holistic, systematic, and adaptive framework. The AEA approach enables HEIs to effectively manage the complexities of digital transformation, enhance their agility, and respond to changing stakeholder needs. Key success factors include strong leadership, effective communication, a skilled workforce, and a culture of collaboration and continuous improvement. The study contributes to the understanding of AEA's role in promoting digital transformation in higher education and offers practical implications for HEIs looking to leverage digital technologies for improved performance and stakeholder satisfaction. Further research is needed to explore the generalizability of these findings to other contexts and industries.

IDEAcology: An interface to streamline and facilitate efficient, rigorous expert elicitation in ecology

AbstractHere, we demonstrate how IDEAcology aids in preparing for and implementing a structured expert elicitation using the IDEA protocol, an iterative quantitative expert elicitation framework.Expert judgement is used to inform decision‐making on environmental assessment and management when imminent decisions are required, and quantitative data are absent or uninformative. Structured elicitation protocols can help improve the final judgements derived from experts, but they can also be administratively heavy and time‐consuming, requiring manual collation of experts' estimates and rationales, construction and dissemination of summary plots for discussion and collating final estimates post‐discussion. These challenges highlight the need for a centralised portal that enables synchronous access by all contributors, real‐time structured facilitation of discussion, whether in person or online, and streamlined data management.To meet this need, we developed the IDEAcology interface (www.ideacology.com) to support data collation, summary, interactions and ultimately the deployment of structured expert elicitation using the IDEA protocol. The IDEAcology interface is designed to be a central portal for scientists and practitioners to easily implement structured expert elicitation projects, while also facilitating data management by providing a reliable and efficient way for elicitation managers to design and run an elicitation, and for experts to input, visualise and cross‐examine estimates.The key advantages that IDEAcology provides include an easy‐to‐use interface with synchronous access to a single platform, reducing logistic difficulties, facilitating transparent discussion, improving the accuracy of estimates, enabling fast and efficient reporting by providing analysis‐ready data outputs and lastly, flexibility in the types of elicitation questions that can be accommodated in the interface.

Noniterative Generalized Camera Model for Near-Central Camera System.

This paper proposes a near-central camera model and its solution approach. 'Near-central' refers to cases in which the rays do not converge to a point and do not have severely arbitrary directions (non-central cases). Conventional calibration methods are difficult to apply in such cases. Although the generalized camera model can be applied, dense observation points are required for accurate calibration. Moreover, this approach is computationally expensive in the iterative projection framework. We developed a noniterative ray correction method based on sparse observation points to address this problem. First, we established a smoothed three-dimensional (3D) residual framework using a backbone to avoid using the iterative framework. Second, we interpolated the residual by applying local inverse distance weighting on the nearest neighbor of a given point. Specifically, we prevented excessive computation and the deterioration in accuracy that may occur in inverse projection through the 3D smoothed residual vectors. Moreover, the 3D vectors can represent the ray directions more accurately than the 2D entities. Synthetic experiments show that the proposed method can achieve prompt and accurate calibration. The depth error is reduced by approximately 63% in the bumpy shield dataset, and the proposed approach is noted to be two digits faster than the iterative methods.

Finite-time general function consensus for multi-agent systems over signed digraphs

This paper solves the finite-time consensus problem for discrete time multi-agent systems (MASs) where agents update their values via linear iteration and the interactions between them are described by signed digraphs. A sufficient condition is presented that the agents can reach consensus on any given linear function of multiple initial signals in finite time, i.e., there exists an eventually positive Laplacian-based matrix associated with the underlying graph. We prove that the linear iterative framework “ratio consensus” developed for unsigned graphs in the literature can be extended to the computation for signed graphs with appropriate modifications. Our method weakens the limitation of the iterative framework on the “marginal Schur stability” of the weight matrix without increasing the computational complexity. Reaching average consensus on unsigned graphs as in the literature is regarded as a special case of our algorithm. Two illustrative examples are presented to demonstrate the correctness of the proposed results.

Robust Matrix Completion Method Based on TNNR and Total Row Difference for Recovering Optical Image

Matrix completion aims to recover a matrix from an incomplete matrix with many unknown elements and has wide applications in optical image recovery and machine learning, in which the popular method is to formulate it as a general low-rank matrix approximation problem. However, the traditional optimization model for matrix completion is less robust. This paper proposes a robust matrix completion method in which the truncated nuclear norm regularization (TNNR) is used as the approximation of the rank function and the sum of absolute values of the row difference, which is called as the total row difference, is used to constrain the oscillations of the missing matrix. By minimizing the value of total row difference in the objective, the proposed model controls the oscillation and reduces the impact of missing part in the process of matrix completion continuously. Furthermore, we propose a two-step iterative algorithm framework and design an ADMM algorithm for subproblem model that includes minimizing the total row difference. Experiments show that the proposed algorithm has more stable performance and better recovery effect and obviously reduces the sensitivity of the traditional TNNR models to the truncated rank parameter.