Artificial Intelligence Review最新文献

{"title":"A systematic survey on human pose estimation: upstream and downstream tasks, approaches, lightweight models, and prospects","authors":"Zheyan Gao,&nbsp;Jinyan Chen,&nbsp;Yuxin Liu,&nbsp;Yucheng Jin,&nbsp;Dingxiaofei Tian","doi":"10.1007/s10462-024-11060-2","DOIUrl":"10.1007/s10462-024-11060-2","url":null,"abstract":"<div><p>In recent years, human pose estimation has been widely studied as a branch task of computer vision. Human pose estimation plays an important role in the development of medicine, fitness, virtual reality, and other fields. Early human pose estimation technology used traditional manual modeling methods. Recently, human pose estimation technology has developed rapidly using deep learning. This study not only reviews the basic research of human pose estimation but also summarizes the latest cutting-edge technologies. In addition to systematically summarizing the human pose estimation technology, this article also extends to the upstream and downstream tasks of human pose estimation, which shows the positioning of human pose estimation technology more intuitively. In particular, considering the issues regarding computer resources and challenges concerning model performance faced by human pose estimation, the lightweight human pose estimation models and the transformer-based human pose estimation models are summarized in this paper. In general, this article classifies human pose estimation technology around types of methods, 2D or 3D representation of outputs, the number of people, views, and temporal information. Meanwhile, classic datasets and targeted datasets are mentioned in this paper, as well as metrics applied to these datasets. Finally, we generalize the current challenges and possible development of human pose estimation technology in the future.</p></div>","PeriodicalId":8449,"journal":{"name":"Artificial Intelligence Review","volume":"58 3","pages":""},"PeriodicalIF":10.7,"publicationDate":"2025-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10462-024-11060-2.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142925655","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Systematic review on neural architecture search","authors":"Sasan Salmani Pour Avval,&nbsp;Nathan D. Eskue,&nbsp;Roger M. Groves,&nbsp;Vahid Yaghoubi","doi":"10.1007/s10462-024-11058-w","DOIUrl":"10.1007/s10462-024-11058-w","url":null,"abstract":"<div><p>Machine Learning (ML) has revolutionized various fields, enabling the development of intelligent systems capable of solving complex problems. However, the process of manually designing and optimizing ML models is often time-consuming, labor-intensive, and requires specialized expertise. To address these challenges, Automatic Machine Learning (AutoML) has emerged as a promising approach that automates the process of selecting and optimizing ML models. Within the realm of AutoML, Neural Architecture Search (NAS) has emerged as a powerful technique that automates the design of neural network architectures, the core components of ML models. It has recently gained significant attraction due to its capability to discover novel and efficient architectures that surpass human-designed counterparts. This manuscript aims to present a systematic review of the literature on this topic published between 2017 and 2023 to identify, analyze, and classify the different types of algorithms developed for NAS. The methodology follows the guidelines of Systematic Literature Review (SLR) methods. Consequently, this study identified 160 articles that provide a comprehensive overview of the field of NAS, encompassing discussion on current works, their purposes, conclusions, and predictions of the direction of this science branch in its main core pillars: Search Space (SSp), Search Strategy (SSt), and Validation Strategy (VSt). Subsequently, the key milestones and advancements that have shaped the field are highlighted. Moreover, we discuss the challenges and open issues that remain in the field. We envision that NAS will continue to play a pivotal role in the advancement of ML, enabling the development of more intelligent and efficient ML models for a wide range of applications.</p></div>","PeriodicalId":8449,"journal":{"name":"Artificial Intelligence Review","volume":"58 3","pages":""},"PeriodicalIF":10.7,"publicationDate":"2025-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10462-024-11058-w.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142925653","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Artificial lemming algorithm: a novel bionic meta-heuristic technique for solving real-world engineering optimization problems","authors":"Yaning Xiao,&nbsp;Hao Cui,&nbsp;Ruba Abu Khurma,&nbsp;Pedro A. Castillo","doi":"10.1007/s10462-024-11023-7","DOIUrl":"10.1007/s10462-024-11023-7","url":null,"abstract":"<div><p>The advent of the intelligent information era has witnessed a proliferation of complex optimization problems across various disciplines. Although existing meta-heuristic algorithms have demonstrated efficacy in many scenarios, they still struggle with certain challenges such as premature convergence, insufficient exploration, and lack of robustness in high-dimensional, nonconvex search spaces. These limitations underscore the need for novel optimization techniques that can better balance exploration and exploitation while maintaining computational efficiency. In response to this need, we propose the Artificial Lemming Algorithm (ALA), a bio-inspired metaheuristic that mathematically models four distinct behaviors of lemmings in nature: long-distance migration, digging holes, foraging, and evading predators. Specifically, the long-distance migration and burrow digging behaviors are dedicated to highly exploring the search domain, whereas the foraging and evading predators behaviors provide exploitation during the optimization process. In addition, ALA incorporates an energy-decreasing mechanism that enables dynamic adjustments to the balance between exploration and exploitation, thereby enhancing its ability to evade local optima and converge to global solutions more robustly. To thoroughly verify the effectiveness of the proposed method, ALA is compared with 17 other state-of-the-art meta-heuristic algorithms on the IEEE CEC2017 benchmark test suite and the IEEE CEC2022 benchmark test suite. The experimental results indicate that ALA has reliable comprehensive optimization performance and can achieve superior solution accuracy, convergence speed, and stability in most test cases. For the 29 10-, 30-, 50-, and 100-dimensional CEC2017 functions, ALA obtains the lowest Friedman average ranking values among all competitor methods, which are 1.7241, 2.1034, 2.7241, and 2.9310, respectively, and for the 12 CEC2022 functions, ALA again wins the optimal Friedman average ranking of 2.1667. Finally, to further evaluate its applicability, ALA is implemented to address a series of optimization cases, including constrained engineering design, photovoltaic (PV) model parameter identification, and fractional-order proportional-differential-integral (FOPID) controller gain tuning. Our findings highlight the competitive edge and potential of ALA for real-world engineering applications. The source code of ALA is publicly available at https://github.com/StevenShaw98/Artificial-Lemming-Algorithm.</p></div>","PeriodicalId":8449,"journal":{"name":"Artificial Intelligence Review","volume":"58 3","pages":""},"PeriodicalIF":10.7,"publicationDate":"2025-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10462-024-11023-7.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142925732","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Beyond one-shot explanations: a systematic literature review of dialogue-based xAI approaches","authors":"Dimitry Mindlin,&nbsp;Fabian Beer,&nbsp;Leonie Nora Sieger,&nbsp;Stefan Heindorf,&nbsp;Elena Esposito,&nbsp;Axel-Cyrille Ngonga Ngomo,&nbsp;Philipp Cimiano","doi":"10.1007/s10462-024-11007-7","DOIUrl":"10.1007/s10462-024-11007-7","url":null,"abstract":"<div><p>In the last decade, there has been increasing interest in allowing users to understand how the predictions of machine-learned models come about, thus increasing transparency and empowering users to understand and potentially contest those decisions. Dialogue-based approaches, in contrast to traditional one-shot eXplainable Artificial Intelligence (xAI) methods, facilitate interactive, in-depth exploration through multi-turn dialogues, simulating human-like interactions, allowing for a dynamic exchange where users can ask questions and receive tailored, relevant explanations in real-time. This paper reviews the current state of dialogue-based xAI, presenting a systematic review of 1339 publications, narrowed down to 15 based on inclusion criteria. We explore theoretical foundations of the systems, propose key dimensions along which different solutions to dialogue-based xAI differ, and identify key use cases, target audiences, system components, and the types of supported queries and responses. Furthermore, we investigate the current paradigms by which systems are evaluated and highlight their key limitations. Key findings include identifying the main use cases, objectives, and audiences targeted by dialogue-based xAI methods, in addition to an overview of the main types of questions and information needs. Beyond discussing avenues for future work, we present a meta-architecture for these systems from existing literature and outlined prevalent theoretical frameworks.</p></div>","PeriodicalId":8449,"journal":{"name":"Artificial Intelligence Review","volume":"58 3","pages":""},"PeriodicalIF":10.7,"publicationDate":"2025-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10462-024-11007-7.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142925630","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Advancing paleontology: a survey on deep learning methodologies in fossil image analysis","authors":"Mohammed Yaqoob,&nbsp;Mohammed Ishaq,&nbsp;Mohammed Yusuf Ansari,&nbsp;Yemna Qaiser,&nbsp;Rehaan Hussain,&nbsp;Harris Sajjad Rabbani,&nbsp;Russell J. Garwood,&nbsp;Thomas D. Seers","doi":"10.1007/s10462-024-11080-y","DOIUrl":"10.1007/s10462-024-11080-y","url":null,"abstract":"<div><p>Understanding ancient organisms and their interactions with paleoenvironments through the study of body fossils is a central tenet of paleontology. Advances in digital image capture now allow for efficient and accurate documentation, curation, and interrogation of fossil forms and structures in two and three dimensions, extending from microfossils to larger specimens. Despite these developments, key fossil image processing and analysis tasks, such as segmentation and classification, still require significant user intervention, which can be labor-intensive and subject to human bias. Recent advances in deep learning offer the potential to automate fossil image analysis, improving throughput and limiting operator bias. Despite the emergence of deep learning within paleontology in the last decade, challenges such as the scarcity of diverse, high quality image datasets and the complexity of fossil morphology necessitate further advancement which will be aided by the adoption of concepts from other scientific domains. Here, we comprehensively review state-of-the-art deep learning based methodologies applied to fossil analysis, grouping the studies based on the fossil type and nature of the task. Furthermore, we analyze existing literature to tabulate dataset information, neural network architecture type, and key results, and provide textual summaries. Finally, we discuss novel techniques for fossil data augmentation and fossil image enhancements, which can be combined with advanced neural network architectures, such as diffusion models, generative hybrid networks, transformers, and graph neural networks, to improve body fossil image analysis.</p></div>","PeriodicalId":8449,"journal":{"name":"Artificial Intelligence Review","volume":"58 3","pages":""},"PeriodicalIF":10.7,"publicationDate":"2025-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10462-024-11080-y.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142925631","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Enhanced crayfish optimization algorithm with differential evolution’s mutation and crossover strategies for global optimization and engineering applications","authors":"Binanda Maiti,&nbsp;Saptadeep Biswas,&nbsp;Absalom El-Shamir Ezugwu,&nbsp;Uttam Kumar Bera,&nbsp;Ahmed Ibrahim Alzahrani,&nbsp;Fahad Alblehai,&nbsp;Laith Abualigah","doi":"10.1007/s10462-024-11069-7","DOIUrl":"10.1007/s10462-024-11069-7","url":null,"abstract":"<div><p>Optimization algorithms play a crucial role in solving complex challenges across various fields, including engineering, finance, and data science. This study introduces a novel hybrid optimization algorithm, the Hybrid Crayfish Optimization Algorithm with Differential Evolution (HCOADE), which addresses the limitations of premature convergence and inadequate exploitation in the traditional Crayfish Optimization Algorithm (COA). By integrating COA with Differential Evolution (DE) strategies, HCOADE leverages DE’s mutation and crossover mechanisms to enhance global optimization performance. The COA, inspired by the foraging and social behaviors of crayfish, provides a flexible framework for exploring the solution space, while DE’s robust strategies effectively exploit this space. To evaluate HCOADE’s performance, extensive experiments are conducted using 34 benchmark functions from CEC 2014 and CEC 2017, as well as six engineering design problems. The results are compared with ten leading optimization algorithms, including classical COA, Particle Swarm Optimization (PSO), Grey Wolf Optimizer (GWO), Whale Optimization Algorithm (WOA), Moth-flame Optimization (MFO), Salp Swarm Algorithm (SSA), Reptile Search Algorithm (RSA), Sine Cosine Algorithm (SCA), Constriction Coefficient-Based Particle Swarm Optimization Gravitational Search Algorithm (CPSOGSA), and Biogeography-based Optimization (BBO). The average rankings and results from the Wilcoxon Rank Sum Test provide a comprehensive comparison of HCOADE’s performance, clearly demonstrating its superiority. Furthermore, HCOADE’s performance is assessed on the CEC 2020 and CEC 2022 test suites, further confirming its effectiveness. A comparative analysis against notable winners from the CEC competitions, including LSHADEcnEpSin, LSHADESPACMA, and CMA-ES, using the CEC-2017 test suite, revealed superior results for HCOADE. This study underscores the advantages of integrating DE strategies with COA and offers valuable insights for addressing complex global optimization problems.</p></div>","PeriodicalId":8449,"journal":{"name":"Artificial Intelligence Review","volume":"58 3","pages":""},"PeriodicalIF":10.7,"publicationDate":"2025-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10462-024-11069-7.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142925684","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Systematic review of recent years: machine learning-based interactive therapy for people suffering from dementia","authors":"Coralie Rohrer,&nbsp;Souhir Ben Souissi,&nbsp;Mascha Kurpicz-Briki","doi":"10.1007/s10462-024-11084-8","DOIUrl":"10.1007/s10462-024-11084-8","url":null,"abstract":"<div><p>Medical advances over the last century have significantly extended life expectancy. Today, the world’s population is quite old, and will become even older in the years to come. Diseases that particularly concern the elderly are therefore more frequent, and dementia is one of them. This condition mainly affects the elderly and cannot be cured today. However, people suffering from dementia do require care, and this entails significant costs for our society. Machine learning could be useful in a context where it is difficult to find medical staff and where cost reduction is a priority. In recent years, research has been conducted to find ways of treating dementia with machine learning-based therapies in which the patient can actively participate. In this paper, a systematic literature review of these therapies is conducted: (a) paper metadata is analysed, (b) dataset characteristics are examined, (c) therapy types are compared, (d) suggested architectures are considered, (e) therapy performance is reviewed, (f) usability is discussed, and g) ethical considerations are taken into account. Twenty-three papers were selected in which various types of therapy were suggested for use with cell phones, computers, robots, or virtual reality. The results of the usability tests were very positive, both in terms of cognitive faculties evolution and patient satisfaction.</p></div>","PeriodicalId":8449,"journal":{"name":"Artificial Intelligence Review","volume":"58 3","pages":""},"PeriodicalIF":10.7,"publicationDate":"2025-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10462-024-11084-8.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142925691","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A systematic review for transformer-based long-term series forecasting","authors":"Liyilei Su,&nbsp;Xumin Zuo,&nbsp;Rui Li,&nbsp;Xin Wang,&nbsp;Heng Zhao,&nbsp;Bingding Huang","doi":"10.1007/s10462-024-11044-2","DOIUrl":"10.1007/s10462-024-11044-2","url":null,"abstract":"<div><p>The emergence of deep learning has yielded noteworthy advancements in time series forecasting (TSF). Transformer architectures have witnessed broad utilization and adoption in TSF tasks. Transformers have proven to be the most successful solution to extract the semantic correlations among the elements within a long sequence. Various variants have enabled Transformer architecture to effectively handle long-term time series forecasting (LTSF) tasks. In this article, we first present a comprehensive overview of Transformer architectures and their subsequent enhancements developed to address various LTSF tasks. Then, we summarize the publicly available LTSF datasets and relevant evaluation metrics. Furthermore, we provide valuable insights into the best practices and techniques for effectively training Transformers in the context of time-series analysis. Lastly, we propose potential research directions in this rapidly evolving field.</p></div>","PeriodicalId":8449,"journal":{"name":"Artificial Intelligence Review","volume":"58 3","pages":""},"PeriodicalIF":10.7,"publicationDate":"2025-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10462-024-11044-2.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142925692","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"QSHO: Quantum spotted hyena optimizer for global optimization","authors":"Tapas Si,&nbsp;Péricles B. C. Miranda,&nbsp;Utpal Nandi,&nbsp;Nanda Dulal Jana,&nbsp;Ujjwal Maulik,&nbsp;Saurav Mallik,&nbsp;Mohd Asif Shah","doi":"10.1007/s10462-024-11072-y","DOIUrl":"10.1007/s10462-024-11072-y","url":null,"abstract":"<div><p>Spotted Hyena Optimizer (SHO) is a population-based metaheuristic algorithm inspired by the spotted hyenas’ social behavior, and it has been developed to solve global optimization problems. SHO has shown superior performance over its competitive metaheuristic algorithms in solving benchmark function optimization and engineering design problems. However, it suffers from getting stuck in local optima due to its lack of exploration while solving multi-modal optimization problems. This article proposes an improved SHO, quantum SHO (QSHO), inspired by quantum computing. The QSHO implements a quantum computing mechanism to promote its exploration ability. The novel method is tested on well-known IEEE CEC2013 and IEEE CEC2017 benchmark suits with 30 and 50 dimensions and four real-world engineering optimization problems. The results of QSHO are compared with that of Classical SHO, improved SHO (ISHO), Modified SHO (MSHO), Oppositional SHO with mutation operator (OBL-MO-SHO), SHO with space transformation search (STS-SHO), Quantum Salp Swarm Algorithm (QSSA), and Chimp Optimization Algorithm (ChOA). The results are analyzed using the Wilcoxon Signed Rank Test (WSRT) and Friedman Test. The empirical results show that QSHO statistically outperforms other compared algorithms for benchmark problem suits with 30 and 50 dimensions. According to Friedman Test statistics, the QSHO algorithm ranked first and second in solving CEC2013 30D and 50D, respectively, whereas it ranked first in both solving CEC2017 30D and 50D. In addition, we have assessed the QSHO in four real-world engineering optimization problems, and the QSHO statistically outperforms the competitive algorithms.</p></div>","PeriodicalId":8449,"journal":{"name":"Artificial Intelligence Review","volume":"58 3","pages":""},"PeriodicalIF":10.7,"publicationDate":"2025-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10462-024-11072-y.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142925657","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Adversarial regularize graph variational autoencoder based on encoder optimization strategy","authors":"Jin Dai,&nbsp;Yanhui Peng,&nbsp;Guoyin Wang,&nbsp;Feng Hu","doi":"10.1007/s10462-024-11068-8","DOIUrl":"10.1007/s10462-024-11068-8","url":null,"abstract":"<div><p>Graph variational autoencoders (VAEs) have been widely used to address the representation problem of graph nodes. However, most existing graph VAEs focus on minimizing reconstruction loss and overlook the uncertainty in the latent distribution and the issue of posterior collapse during training. An Adversarial Regularize Graph Variational Autoencoder Based on Encoder Optimization Strategy (MCM-ARVGE) is proposed from the perspective of network structure and loss function. MCM-ARVGE introduces a Multi-dimensional Cloud Generator (MCG) that transforms the traditional encoder, expanding the Gaussian distribution into a Gaussian cloud distribution. Furthermore, MCM-ARVGE employs the idea of adversarial regularization to train the Gaussian cloud distribution, reducing the randomness of the Gaussian cloud distribution. Finally, based on the Gaussian cloud distribution, an effective uncertainty similarity measurement method for cloud distributions is introduced to address the problem of posterior collapse. Experimental results validate the universality and effectiveness of MCM-ARVGE, as it outperforms the baseline model in graph embedding tasks.</p></div>","PeriodicalId":8449,"journal":{"name":"Artificial Intelligence Review","volume":"58 3","pages":""},"PeriodicalIF":10.7,"publicationDate":"2025-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10462-024-11068-8.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142925658","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}