Applied Soft Computing最新文献

{"title":"Joint hierarchical multi-granularity adaptive embedding discriminative learning for unsupervised domain adaptation","authors":"Pufei Li ,&nbsp;Pin Wang ,&nbsp;Yongming Li ,&nbsp;Yinghua Shen ,&nbsp;Witold Pedrycz","doi":"10.1016/j.asoc.2025.113026","DOIUrl":"10.1016/j.asoc.2025.113026","url":null,"abstract":"<div><div>Unsupervised domain adaptation (UDA) is an effective technique that aims to transfer knowledge from well-labeled source data to target data that lacks labels and has a different distribution. Most existing methods only considered domain center-wise alignment to reduce global differences across domains, resulting in a coarse alignment. In recent years, researchers further considered aligning class centers to ensure the consistency of local distributions. However, these methods utilized a solely mean vector to represent the entire class distribution, which is still coarse and cannot fully capture the distribution characteristics of intra-class data. Inspired by the “knowledge pyramid” theory, a novel UDA method termed adaptive hierarchical multi-granularity embedded learning (HMGEL) is proposed to solve this problem, which aims to minimize the distribution gap of samples across domains from the perspective of hierarchical multi-granularity. This method can reflect the distribution of samples from coarse to fine, which is helpful for better UDA. Firstly, granular envelopes are created to explore intra-class structures and complex distributional properties at a more fine-grained level. Based on the granular envelopes, domain centers and class centers are combined for cross-domain distribution alignment, allowing for the capture of sample information at hierarchical multi-granularity from coarse to fine. Then, a robust sample-to-granular envelope cross-domain local structure learning strategy is designed to improve the discrimination capability of target domain features under hierarchical multi-granularity. Extensive experiments on five benchmark datasets show that the proposed HMGEL method is effective at a significant level.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"175 ","pages":"Article 113026"},"PeriodicalIF":7.2,"publicationDate":"2025-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143821256","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A framework to undersample and refine the synthetic minority set","authors":"Payel Sadhukhan","doi":"10.1016/j.asoc.2025.113095","DOIUrl":"10.1016/j.asoc.2025.113095","url":null,"abstract":"<div><div>Oversampling the minority class is a popular strategy for coping with the imbalance of datasets. It improves the cognition of the minority points to an admissible extent. Nonetheless, the synthetic minority instances accentuate the overlap between the majority class and the augmented minority class. It is detrimental to the rightful cognition of both classes. To this end, this paper introduces a novel strategy to undersample the synthetic minority set. A multi-armed bandit (MAB) guided protocol is followed to [i] identify the synthetic minority instances that contribute to the increased overlap between the two classes and [ii] subsequently remove (undersample) them iteratively to obtain a refined synthetic minority set. Simulation on synthetic datasets shows that the proposed strategy is successful in increasing the Gromov–Wasserstein distance between the original majority class distribution and the synthetic minority points’ distribution (as compared to the regular oversampled data obtained through state-of-the-art techniques). Empirical evaluation in sixteen real-world datasets, four state-of-the-art minority oversamplers, and two refinement techniques manifest the competence of the proposed strategy over baseline results and against the two competing methods. The proposed strategy has improved the performance of the majority class without bringing down the minority class’s performance and can be incorporated in sensitive real-world domains.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"175 ","pages":"Article 113095"},"PeriodicalIF":7.2,"publicationDate":"2025-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143816145","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Advancement of artificial intelligence applications in hydrocarbon well drilling technology: A review","authors":"Shadfar Davoodi ,&nbsp;Mohammed Al-Shargabi ,&nbsp;David A. Wood ,&nbsp;Mohammad Mehrad","doi":"10.1016/j.asoc.2025.113129","DOIUrl":"10.1016/j.asoc.2025.113129","url":null,"abstract":"<div><div>In recent years, the petroleum upstream has increasingly relied on artificial intelligence (AI), with applications spanning machine/deep learning (ML/DL), hybrid models, and committee machine learning. Particularly in drilling engineering (DE), AI has become crucial for addressing complex subsurface challenges. Nevertheless, its implementation continues to be a significant obstacle owing to the technological, operational, and engineering challenges involved in real-time applications of DE approaches. This review examines AI technologies in DE, focusing on their practicality, performance, and associated challenges. It evaluates models for predicting drilling fluid properties, hole cleaning, rate of penetration, wellbore trajectory, fluid hydraulics, bit wear, borehole stability, subsurface problems, and fault diagnosis. It explores integrating AI models with downhole sensors and surface data for real-time/automated drilling control, alongside real-world AI application cases. It highlights the benefits of combining ML/DL with optimization algorithms in hybrid models and analyzes trends in AI research in DE through bibliometric and scientometric studies. Guidelines are provided for selecting and improving AI algorithms for various drilling applications and assessing their economic impacts. The review concludes by identifying future research directions to advance AI applications in the drilling industry.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"176 ","pages":"Article 113129"},"PeriodicalIF":7.2,"publicationDate":"2025-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143829455","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Optimizing multi-drone patrol path planning under uncertain flight duration: A robust model and adaptive large neighborhood search with simulated annealing","authors":"Xiaoduo Li ,&nbsp;He Luo ,&nbsp;Guoqiang Wang ,&nbsp;Zhihong Song ,&nbsp;Qiwen Gou ,&nbsp;Fanhe Meng","doi":"10.1016/j.asoc.2025.113107","DOIUrl":"10.1016/j.asoc.2025.113107","url":null,"abstract":"<div><div>When conducting drone path planning, the flight duration of drones is a critical factor influencing the planning solution. Given the characteristics of drone batteries, accurately predicting the actual flight duration is challenging. It is crucial to reduce the impact of uncertain flight duration on path feasibility. To solve this problem, this paper proposes a robust optimization method that constructs a budget uncertainty set to describe the uncertain flight duration. To facilitate the solution process of the model, the strong duality theorem is employed to transform the robust model into a mixed integer linear programming model. To efficiently handle large-scale path planning problems, a hybrid heuristic algorithm with robust feasibility check (ALSA-RFC) is proposed. This algorithm combines the advantages of adaptive large neighborhood search and simulated annealing. Furthermore, to ensure the robustness of the solution, a method for generating robust initial solutions quickly and a robust feasibility checking method for solutions are constructed. Numerical experimental results demonstrate that ALSA-RFC can quickly find high-quality robust solutions. Additionally, through Monte Carlo simulations, the impact of robust parameters on the robustness of the solution scheme is analyzed, evaluating the performance of the algorithm in different scenarios. Comparisons with chance-constrained programming methods revealed that ALSA-RFC can significantly reduce the sensitivity of path planning results to fluctuations in flight duration without substantially increasing flight costs. Finally, a case study is conducted to further validate the practicality of ALSA-RFC in real-world applications.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"176 ","pages":"Article 113107"},"PeriodicalIF":7.2,"publicationDate":"2025-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143829449","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Digital twin-based pursuit-evasion gaming strategy optimization for underwater robot grasping","authors":"Xubo Yang,&nbsp;Jian Gao,&nbsp;Peng Wang,&nbsp;Siqing Sun,&nbsp;Yufeng Li","doi":"10.1016/j.asoc.2025.112993","DOIUrl":"10.1016/j.asoc.2025.112993","url":null,"abstract":"<div><div>Underwater robotic grasping challenges are essential for the advancement of underwater robotics and oceanic development. To tackle the difficulties encountered by these robots in grasping, we present an innovative multi-agent learning framework based on a pursuit-evasion game. This framework consists of three phases: initial learning, interactive learning, and independent learning, enabling a gradually enhanced learning experience. We propose a robot pursuit approach utilizing Improved Grey Wolf Optimization (IGWO) and implement the Soft Actor-Critic for learning target evasion strategies. The IGWO augments search and sample methodologies, markedly enhancing search efficacy relative to the conventional Grey Wolf Optimization. Furthermore, we have created virtual reality software for underwater robots and implemented a related digital twin system platform, facilitating the training and education of pursuers and evaders in a simulated environment. Ultimately, we implement this system in a practical underwater pursuit-evasion scenario. Through interactive training and iterative learning, the robotic arm exhibits the capability to strategically pursue an evasive target, while the target demonstrates adaptable escape. Both modeling and experimental results produce excellent outcomes, offering innovative approaches and insights for the dynamic grasping domain of underwater robotics.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"175 ","pages":"Article 112993"},"PeriodicalIF":7.2,"publicationDate":"2025-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143807429","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Heterogeneous space co-sparse representation: Leveraging fuzzy dependency and feature reconstruction for feature selection","authors":"Yang Huang ,&nbsp;Tingquan Deng ,&nbsp;Ge Yang ,&nbsp;Changzhong Wang","doi":"10.1016/j.asoc.2025.113080","DOIUrl":"10.1016/j.asoc.2025.113080","url":null,"abstract":"<div><div>Feature selection is an efficient approach to dimensionality reduction. There is a large number of literatures tackling this issue. Most of them prioritize classification ability of features, but often fail to fully consider the synergistic effect of local and global subspace information, thus limit the performance of feature selection in revealing the intrinsic structure of data. In this paper, a novel embedded feature selection model, called the heterogeneous space collaborative sparse representation for feature selection through leveraging fuzzy dependency and feature reconstruction (HCoSRDC), is proposed. In the proposed model, a fuzzy self-information operator is constructed to nonlinearly map samples from their feature space to a fuzzy dependency space, where the fuzzy dependency discloses classification ability of features and the local subspace structure in data is captured. Furthermore, samples are sparsely self-represented in their feature reconstruction space to extract global subspace structure while emphasizing feature distinctiveness. The consistency between local sparse representation and global sparse representation is integrated to learn weights of features for feature selection. An algorithm is designed to solve HCoSRDC. Extensive experiments on various benchmark datasets are conducted and experimental results demonstrate the superior performance of the proposed model in comparison with the state-of-the-art models for feature selection.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"175 ","pages":"Article 113080"},"PeriodicalIF":7.2,"publicationDate":"2025-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143816144","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An automated brain tumor segmentation and classification using adaptive Bayesian fuzzy clustering","authors":"Veesam Pavan Kumar ,&nbsp;Satya Ranjan Pattanaik ,&nbsp;V.V. Sunil Kumar","doi":"10.1016/j.asoc.2025.113061","DOIUrl":"10.1016/j.asoc.2025.113061","url":null,"abstract":"<div><div>An uncontrolled growth of malignant cells in the brain is known as a brain tumor. Rapid treatment response follows an early identification of tumors in the brain that increases the chance of patient survival. Adequate tumor classification and segmentation are necessary for treatment planning and best evaluation. It would be ideal and beneficial to have regular detection and identification. The design of medical imaging systems has been greatly influenced by the introduction of deep learning in recent years. Hence, an innovative brain tumor classification model is suggested in this work that resolves the drawbacks of traditional methods such as computational complexity, and low accuracy. At first, the necessary images are garnered from the online benchmark for the subsequent process. Further, the garnered images are given to the segmentation procedure, where an Adaptive Bayesian Fuzzy Clustering (ABFC) is utilized for segmenting the abnormalities. Moreover, an Improved Eurasian Oystercatcher Optimizer (IEOO) is adopted in the segmentation process for tuning the parameters in the ABFC technique, which increases the performance. The segmented images are subjected to the Multi-scale Residual Attention Network with Long Short Term Memory (MRAN-LSTM) layer for classifying the brain tumors. Finally, the simulations are done to verify the success rate of the implemented brain tumor segmentation and classification approach by contrasting it with traditional models.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"175 ","pages":"Article 113061"},"PeriodicalIF":7.2,"publicationDate":"2025-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143823548","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A multi-objective sustainable multipath delivery problem in hilly regions with customer-satisfaction using TLBO","authors":"Somnath Maji ,&nbsp;Samir Maity ,&nbsp;Izabela Ewa Nielsen ,&nbsp;Debasis Giri ,&nbsp;Manoranjan Maiti","doi":"10.1016/j.asoc.2025.113100","DOIUrl":"10.1016/j.asoc.2025.113100","url":null,"abstract":"<div><div>Logistic delivery through road contributes substantial carbon emission (CE). In business, timely goods delivery i.e. customer satisfaction, is important. With these facts, a sustainable multi-objective 3D delivery problem with customer satisfaction (SMO3DDPwCS) in a hilly region (HR) is developed to minimize total CE and customer dissatisfaction (CDS) simultaneously. Here, one supplier’s vehicle starts from the depot with goods equal to retailers’ demands, distributes among the retailers as per their orders within their preferred times, and comes back. The retailers’ shops and depot are connected through multiple hilly tracks, which have up and down slopes and are susceptible to landslide. The cautious driving through these tracks produces extra CE and CDS. The SMO3DDPwCS is solved by a modified MOTLBO (mMOTLBO) algorithm. This algorithm incorporates self-learning concepts after both the teaching and learning phases, introduces innovative upgrading strategies, and employs a group-based learning approach. Some statistical tests are performed using mMOTLBO on the standard TSPLIB instances. The efficiency of mMOTLBO is established against NSGA-II and MOEA/D. Multiple solutions in Pareto front are ranked using TOPSIS. Some managerial decisions are drawn. The optimum routing plan for SMO3DDPwCS in a hilly region is presented and gives better results (31% total CE and 8% total CDS) than the single path formulation. mMOTLBO showed superiority over other algorithms in most cases concerning the Pareto front for the objectives. On the benchmark instances, mMOTLBO demonstrated its superiority by outperforming NSGA-II and MOEA/D, showing improvements of 0.11 in IGD and 4.12 in GD.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"176 ","pages":"Article 113100"},"PeriodicalIF":7.2,"publicationDate":"2025-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143829454","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multi-trajectory optimization for train using distributional reinforcement learning with conditional value-at-risk","authors":"Yalan Chen ,&nbsp;Jing Xun ,&nbsp;Shibo He ,&nbsp;Xin Wan ,&nbsp;Yafei Liu","doi":"10.1016/j.asoc.2025.113079","DOIUrl":"10.1016/j.asoc.2025.113079","url":null,"abstract":"<div><div>Artificial intelligence methods like reinforcement learning (RL) have been widely studied to train trajectory optimization problems to achieve flexible driving. To meet the demand for flexible driving strategies in actual operations, N optimized trajectories for the single train are usually generated based on different scheduled times. It brings up two issues: the computational cost of N trajectories is N times that of a single trajectory, and manual intervention is required to adjust the initial conditions, such as schedule time. This paper proposes a conditional value-at-risk (CVaR) distributional Q-learning approach (CDQ) to generate trajectories with different driving styles, balancing safety and efficiency. First, analyzing the actual control deviations, the distribution of returns is modeled using the quantile of distributional RL. Then, we introduce CVaR as a risk metric to evaluate the risk of actions and develop risk-sensitive strategies based on various confidence levels, simultaneously optimizing multiple trajectories for the single train. Finally, we simulate the experiments with data from an actual line. The results demonstrate that the CDQ algorithm can simultaneously optimize multiple train trajectories without requiring human intervention. Through a two-layer selection mechanism, five trajectories with varying driving styles can be selected to fulfill scheduling flexibility requirements. Compared to standard Q-learning, distributional Deep Q-Network and other risk-sensitive RL, CDQ shows improved performance in both energy-saving and punctuality. The total computation time of CDQ is only 31.47% and 35.44% of Q-learning and risk-sensitive RL.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"176 ","pages":"Article 113079"},"PeriodicalIF":7.2,"publicationDate":"2025-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143838475","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Proximal recursive generalized hyper-gradient descent method","authors":"Hao Zhang,&nbsp;Shuxia Lu","doi":"10.1016/j.asoc.2025.113073","DOIUrl":"10.1016/j.asoc.2025.113073","url":null,"abstract":"<div><div>This paper focuses on the non-convex, non-smooth composite optimization problem. It consists of a non-convex loss function and a non-smooth regularizer function that admits a proximal mapping. However, the method is still limited in handling objective functions that involve non-smooth regularizer. How to determine the step size for solving composite optimization problems can be a challenge. To address this gap, we propose a recursive gradient descent algorithm using generalized hyper-gradient descent, named ProxSarah-GHD, which utilizes variance reduction techniques and provides update rules for adaptive step sizes. To improve its generalization in proximal gradient descent, a generalized variant of hyper-gradient descent, named <strong>G</strong>eneralized <strong>H</strong>yper-gradient <strong>D</strong>escent (GHD), is proposed in this paper. We prove that ProxSarah-GHD attains a linear convergence rate. Moreover, we provide the oracle complexity of ProxSarah-GHD as <span><math><mrow><mi>O</mi><mfenced><mrow><msup><mrow><mi>ϵ</mi></mrow><mrow><mo>−</mo><mn>3</mn></mrow></msup></mrow></mfenced></mrow></math></span> and <span><math><mrow><mi>O</mi><mfenced><mrow><msqrt><mrow><mi>n</mi></mrow></msqrt><msup><mrow><mi>ϵ</mi></mrow><mrow><mo>−</mo><mn>2</mn></mrow></msup><mo>+</mo><mi>n</mi></mrow></mfenced></mrow></math></span> in the online setting and finite-sum setting, respectively. In addition, to avoid the trouble of manually adjusting the batch size, we develop a novel <strong>E</strong>xponentially <strong>I</strong>ncreasing <strong>M</strong>ini-batch scheme for ProxSarah-GHD, named ProxSarah-GHD-EIM. The theoretical analysis that shows ProxSarah-GHD-EIM achieves a linear convergence rate is also provided, and shows that its total complexity is <span><math><mrow><mi>O</mi><mfenced><mrow><msup><mrow><mi>ϵ</mi></mrow><mrow><mo>−</mo><mn>4</mn></mrow></msup><mo>+</mo><msup><mrow><mi>ϵ</mi></mrow><mrow><mo>−</mo><mn>2</mn></mrow></msup></mrow></mfenced></mrow></math></span> and <span><math><mrow><mi>O</mi><mfenced><mrow><mi>n</mi><mo>+</mo><msup><mrow><mi>ϵ</mi></mrow><mrow><mo>−</mo><mn>4</mn></mrow></msup><mo>+</mo><msup><mrow><mi>ϵ</mi></mrow><mrow><mo>−</mo><mn>2</mn></mrow></msup></mrow></mfenced></mrow></math></span> in the online setting and finite-sum setting, respectively. Numerical experiments on standard datasets verify the superiority of the ProxSarah-GHD over other methods. We further analyze the sensitivity of the ProxSarah-GHD-EIM to its hyperparameters, conducting experiments on standard datasets.</div></div>","PeriodicalId":50737,"journal":{"name":"Applied Soft Computing","volume":"175 ","pages":"Article 113073"},"PeriodicalIF":7.2,"publicationDate":"2025-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143821258","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}