Top Read Articles

Published in last 1 year |

In last 2 years |

In last 3 years |

All

Please wait a minute...


For Selected: Download Citations EndNote Ris BibTeX Toggle Thumbnails

Select

Deep learning-based multimodal trajectory prediction methods for autonomous driving: state of the art and perspectives Jun HUANG, Yonglin TIAN, Xingyuan DAI, Xiao WANG, Zhixing PING Chinese Journal of Intelligent Science and Technology    2023, 5 (2): 180-199.   DOI: 10.11959/j.issn.2096-6652.202317 Abstract （870）   HTML （109）    PDF（pc） （6643KB）（620）       Knowledge map    Save Although deep learning methods have achieved better results than traditional trajectory prediction algorithms, there are still problems such as information loss, interaction and uncertainty difficulties in modelling, and lack of interpretability of predictions when implementing multimodal high-precision prediction for autonomous vehicles in heterogeneous, highly dynamic and complex changing environments.The newly developed Transformer's long-range modelling capability and parallel computing ability make it a great success not only in the field of natural language processing, but also in solving the above problems when extended to the task of multimodal trajectory prediction for autonomous driving.Based on this, the aim of this paper is to provide a comprehensive summary and review of past deep neural network-based approaches, in particular the Transformer-based approach.The advantages of Transformer over traditional sequential network, graphical neural network and generative model were also analyzed and classified in relation to existing challenges, simultaneously.Transformer models can be better applied to multimodal trajectory prediction tasks, and that such models have better generalisation and interpretability.Finally, the future directions of multimodal trajectory prediction were presented. Table and Figures | Reference | Related Articles | Metrics

Select

Semantic communications for future: basic principle and implementation methodology Ping ZHANG, Kai NIU, Shengshi YAO, Jincheng DAI Journal on Communications    2023, 44 (5): 1-14.   DOI: 10.11959/j.issn.1000-436x.2023079 Abstract （835）   HTML （244）    PDF（pc） （2053KB）（893）       Knowledge map    Save The basic principle of semantic communications and the associated implementation methodology were introduced.First, the systematic model of semantic communications was proposed and basic concepts and terminology were deduced by comparing the fundamental differences between classic communications and semantic communications.Thus, the technological advantages of semantic communications were concluded.Then, the development of semantic information theory was retrospected and the measurement system of semantic information was established.Furthermore, the normalized conditional complexity (NCC) was proposed to evaluate the limit of semantic compression and the property of semantic typical sequence coding was discussed so as to reveal the corresponding asymptotic performance.In addition, the semantic coding transmission methods were classified into two typical schemes, that is, direct coding and transform coding, and the basic principles of these schemes were presented.For the text, speech, and image sources, the superior performance of the semantic coding techniques were demonstrated.Finally, the difficulty and open issues of the semantic communications were further concluded and further research directions were pointed out. Table and Figures | Reference | Related Articles | Metrics

Select

AI-driven digital image art creation: methods and case analysis Changsheng WANG Chinese Journal of Intelligent Science and Technology    2023, 5 (3): 406-414.   DOI: 10.11959/j.issn.2096-6652.202333 Abstract （812）   HTML （214）    PDF（pc） （48558KB）（602）       Knowledge map    Save In recent years, the rapid advancement of artificial intelligence technology has introduced novel tools for the realm of digital image creation.The use of AI tools for digital image creation has gradually become a common practice.In this context, this paper analyzed the methods and cases of AI-driven digital image art creation through interviews, surveys, and case analyses.The survey revealed that the majority of respondents believed that AI tools had a significant impact on their creative process, especially the widespread use of direct output from artificial intelligence methods in digital image art creation.By analyzing the cases in detail, this paper revealed the typical paradigms of AI-based digital image art creation and summarized them as the “AI art creation workflow”, which included AI direct output, AI assisted drawing, and ControlNet precision drawing.These methods can effectively replace repetitive steps in digital image creation and improve image output efficiency, assist in digital image drawing and break through the conventional drawing ideas, and achieve precise and controllable expression of digital image art content. Table and Figures | Reference | Related Articles | Metrics

Select

Survey of research on multimodal semantic communication Zhijin QIN, Tantan ZHAO, Fan LI, Xiaoming TAO Journal on Communications    2023, 44 (5): 28-41.   DOI: 10.11959/j.issn.1000-436x.2023105 Abstract （787）   HTML （125）    PDF（pc） （1190KB）（1200）       Knowledge map    Save With the cross-integration of artificial intelligence and communications, technologies for processing multimodal data such as text, image, audio, and video are booming, the shared dimension of modal semantics is deeply excavated, and the characteristics of multimodal semantic information such as high abstraction, intelligence and simplicity are being fully utilized, which brings new ideas and means to semantic communications.First, the fundamental theories and classifications of semantic communication were introduced, and the research status of single-modal semantic communication was reviewed for text, image, audio, and video respectively.Then, the research status of multimodal semantic communication was reviewed, and multimodal data fusion technology and secure semantic communication were introduced.Finally, the challenges faced by multimodal semantic communication were summarized. Table and Figures | Reference | Related Articles | Metrics

Select

Secure and collaborative spectrum sensing scheme based on audit game Yuntao WANG, Zhou SU, Qichao XU, Yiliang LIU, Haixia PENG, Hao LUAN Journal on Communications    2023, 44 (12): 1-14.   DOI: 10.11959/j.issn.1000-436x.2023238 Abstract （768）   HTML （712）    PDF（pc） （920KB）（886）       Knowledge map    Save To defend against poisoning attacks and free-riding attacks conducted by malicious sensing terminals in crowd sensing-based collaborative spectrum sensing (CCSS), a novel audit game-based defense scheme was proposed, which combined the pre-deterrence and post-punishment mechanisms.Firstly, considering the audit budget constraint, a mixed-strategy audit game model under incomplete information was designed, which set a penalty strategy to deter malicious collaborators before spectrum sensing, and audited and punished them after the fusion of sensing data.Then, a lightweight audit chain model with on-chain and off-chain collaboration was designed, in which audit evidence was stored in an off-chain data warehouse and its metadata was publicly published on the blockchain.Furthermore, a distributed and intelligent audit algorithm based on reinforcement learning was devised to adaptively seek the approximate mix-strategy equilibrium of the audit game.Simulation results demonstrate that the proposed scheme can quickly obtain the stable and approximately optimal audit strategies and actively suppress the poisoning and free-riding behaviors of malicious collaborators, in comparison with conventional schemes. Table and Figures | Reference | Related Articles | Metrics

Select

Intelligent communication and networking key technologies for manned/unmanned cooperation: states-of-the-art and trends Hao YIN, Jibo WEI, Haitao ZHAO, Jiao ZHANG, Haijun WANG, Baoquan REN Journal on Communications    2024, 45 (1): 1-17.   DOI: 10.11959/j.issn.1000-436x.2024037 Abstract （701）   HTML （195）    PDF（pc） （2351KB）（1017）       Knowledge map    Save The intelligent communication and networking technologies for manned/unmanned cooperation was comprehensively surveyed.Firstly, the requirements on communication and networking were analyzed from the application scenarios of manned/unmanned cooperation.Then, in context of physical layer, link layer and network layer respectively, the key issues regarding channel modeling, waveform design, networking protocol and intelligent collaboration were analyzed.And the states-of-the-art in this research area and the characteristics of representative technologies were deeply studied.In the end, the possible development trends and promising technologies were prospected on the way to make the manned/unmanned cooperative communication and networking more intelligent, more efficient and more flexible. Table and Figures | Reference | Related Articles | Metrics

Select

Impact and countermeasures of generative AI represented by ChatGPT on the telecom industry Sihong ZHANG, Jian ZHANG Telecommunications Science    2023, 39 (5): 67-75.   DOI: 10.11959/j.issn.1000-0801.2023116 Abstract （692）   HTML （120）    PDF（pc） （1269KB）（1139）       Knowledge map    Save The release of ChatGPT, sparked a wave of generative AI, representing the arrival of the singularity moment of general artificial intelligence and highly likely restructuring the information industry ecosystem.The domestic industry has strengthened the research in the field of intelligent computing represented by ChatGPT, and operators have become the main force in the construction of computing network infrastructure, ushering in new opportunities for the development of intelligent computing.A detailed analysis of the capabilities, development status, and application prospects of generative AI were provided, and the technical elements behind generative AI, the demands for computing network resources, the impact on the communication industry, the opportunities and challenges faced by operators in the development wave of generative AI were thought about.Finally, the positioning and response strategies of operators were discussed. Table and Figures | Reference | Related Articles | Metrics

Select

Research on the development path and countermeasures of data element value Yunlong YANG, Liang ZHANG, Xulei YANG Big Data Research    2023, 9 (6): 100-109.   DOI: 10.11959/j.issn.2096-0271.2022080 Abstract （673）   HTML （106）    PDF（pc） （2022KB）（866）       Knowledge map    Save Based on the development of data element marketization at home and abroad, the development path and characteristics of data element value in foreign countries were expounded.The current situation of China's data element market in terms of transaction market and application scenarios was summarized.In view of the current development of China's data element market, combined with China's data element market environment and development characteristics, through the construction of a data element market model with Chinese characteristics, we can speed up the release of data element value. Table and Figures | Reference | Related Articles | Metrics

Select

Overview of observational data-based time series causal inference Zefan ZENG, Siya CHEN, Xi LONG, Guang JIN Big Data Research    2023, 9 (4): 139-158.   DOI: 10.11959/j.issn.2096-0271.2022059 Abstract （662）   HTML （67）    PDF（pc） （2614KB）（1491）       Knowledge map    Save With the increase of data storage and the improvement of computing power,using observational data to infer time series causality has become a novel approach.Based on the properties and research status of time series causal inference,five observational data-based methods were induced,including Granger causal analysis,information theory-based method,causal network structure learning algorithm,structural causal model-based method and method based on nonlinear state-space model.Then we briefly introduced typical applications in economics and finance,medical science and biology,earth system science and other engineering fields.Further,we compared the advantages and disadvantages and analyzed the ways for improvement of the five methods according to the focus and difficulties of time series causal inference.Finally,we looked into the future research directions. Table and Figures | Reference | Related Articles | Metrics

Select

In celebration of McCulloch-Pitts ANN model’s 80th anniversary: its origin, principle, and influence Qinghai MIAO, Yutong WANG, Yisheng LV, Xiaoxiang NA, Fei-Yue WANG Chinese Journal of Intelligent Science and Technology    2023, 5 (2): 133-142.   DOI: 10.11959/j.issn.2096-6652.202314 Abstract （543）   HTML （141）    PDF（pc） （8731KB）（502）       Knowledge map    Save In 1943, Warren McCulloch and Walter Pitts published a paper titled “A logical calculus of the ideas immanent in nervous activity”, which demonstrated that the functioning of neural networks could be described using logical calculus.This expanded the field of computational neuroscience and laid the foundation for the development of artificial neural networks.On the occasion of the 80th anniversary of the publication of the M-P paper, the intellectual origins of the M-P theory was explored, taking into account the historical context and the authors’ career trajectories.With the help of examples from the original paper, the basic principles of the M-P model were outlined, and its advantages and limitations were summarized.Furthermore, the impact of the M-P theory on the development of information science was discussed, focusing on the authors’ contributions to cybernetics, including their work on circular causality and feedback mechanisms, which provided a foundation for the development of modern artificial intelligence technologies such as parallel intelligence and large-scale models. Table and Figures | Reference | Related Articles | Metrics

Select

Key problems and progress of pedestrian trajectory prediction methods: the state of the art and prospects Quancheng DU, Xiao WANG, Lingxi LI, Huansheng NING Chinese Journal of Intelligent Science and Technology    2023, 5 (2): 143-162.   DOI: 10.11959/j.issn.2096-6652.202315 Abstract （532）   HTML （88）    PDF（pc） （5939KB）（474）       Knowledge map    Save Pedestrian trajectory prediction aims to use observed human historical trajectories and surrounding environmental information to predict the future position of the target pedestrian, which has important application value in reducing collision risks for autonomous vehicles in social interactions.However, traditional model-driven pedestrian trajectory prediction methods are difficult to predict pedestrian trajectories in complex and highly dynamic scenes.In contrast, datadriven pedestrian trajectory prediction methods rely on large-scale datasets and can better capture and model more complex pedestrian interaction relationships, thereby achieving more accurate pedestrian trajectory prediction results, and have become a research hotspot in fields such as autonomous driving, robot navigation and video surveillance.In order to macroscopically grasp the research status and key issues of pedestrian trajectory prediction methods, We started with the classification of pedestrian trajectory prediction technology and methods.First, the research progress of existing pedestrian trajectory prediction methods were elaborated and the current key issues and challenges were summarized.Second, according to the modeling differences of pedestrian trajectory prediction models, existing methods were divided into model-driven and data-driven pedestrian trajectory prediction methods, and the advantages, disadvantages and applicable scenarios of different methods were summarized.Then, the mainstream datasets used in pedestrian trajectory prediction tasks were summarized and the performance indicators of different algoriths were compared.Finally, the future development direction of pedestrian trajectory prediction was prospected. Table and Figures | Reference | Related Articles | Metrics

Select

Survey on multi-agent reinforcement learning methods from the perspective of population Fengtao XIANG, Junren LUO, Xueqiang GU, Jiongming SU, Wanpeng ZHANG Chinese Journal of Intelligent Science and Technology    2023, 5 (3): 313-329.   DOI: 10.11959/j.issn.2096-6652.202326 Abstract （528）   HTML （68）    PDF（pc） （3737KB）（608）       Knowledge map    Save Multi-agent systems are a cutting-edge research concept in the field of distributed artificial intelligence. Traditional multi-agent reinforcement learning methods mainly focus on topics such as group behavior emergence, multi-agent cooperation and coordination, communication and communication between agents, opponent modeling and prediction. However, they still face challenges such as observable environment, non-stationary opponent strategies, high dimensionality of decision space, and difficulty in understanding credit allocation. How to design multi-agent reinforcement learning methods that meet the large number and scale of intelligent agents and adapt to multiple different application scenarios is a cutting-edge topic in this field. This article first outlined the relevant research progress of multi-agent reinforcement learning. Secondly, a comprehensive overview and induction of multi-agent learning methods with multiple types and paradigms were conducted from the perspectives of scalability and population adaptation. Four major categories of scalable learning methods were systematically sorted out, including set permutation invariance, attention, graph and network theory, and mean field theory. There were four major categories of population adaptive reinforcement learning methods: transfer learning, course learning, meta learning, and meta game, and typical application scenarios were provided. Finally, the frontier research directions were prospected from five aspects: benchmark platform development, two-layer optimization architecture, adversarial strategy learning, human-machine collaborative value alignment and adaptive game decision-making loop, providing reference for the research on relevant frontier key issues of multi-agent reinforcement learning in multimodal environments. Table and Figures | Reference | Related Articles | Metrics

Select

A measurable technical form of data is needed to include data assets in accounting statements Big Data Research    2023, 9 (6): 184-187.   DOI: 10.11959/j.issn.2096-0271.2023075 Abstract （491）   HTML （248）    PDF（pc） （1201KB）（263）       Knowledge map    Save Reference | Related Articles | Metrics

Select

Potential risks and governance strategies of artificial intelligence generated content technology Yaling LI, Yuanqi QIN, Que WEI Chinese Journal of Intelligent Science and Technology    2023, 5 (3): 415-423.   DOI: 10.11959/j.issn.2096-6652.202332 Abstract （482）   HTML （57）    PDF（pc） （2926KB）（501）       Knowledge map    Save Artificial intelligence generated content technology is reshaping the production and consumption patterns of digital content.The research was based on the basic concepts and technological development process of artificial intelligence generated content technology, focusing on exploring ethical risks and governance challenges such as privacy leakage, algorithm hegemony, digital divide, intellectual property protection and employment impact caused by artificial intelligence generated content.After reviewing the typical governance paths and experiences of developed countries abroad, this paper summarized and proposed measures and development suggestions for China to address the potential risks of AI generated content.One was to prioritize development and coordinate layout; Second was to strengthen the full factor investment in the research and development of artificial intelligence technology; Third was to improve the governance rule system of artificial intelligence technology; Fourth was to accelerate the research and development of artificial intelligence governance technology. Table and Figures | Reference | Related Articles | Metrics

Select

Construction of multi-modal social media dataset for fake news detection Guopeng GAO, Yaodong FANG, Yanfang HAN, Zhenxing QIAN, Chuan QIN Chinese Journal of Network and Information Security    2023, 9 (4): 144-154.   DOI: 10.11959/j.issn.2096-109x.2023060 Abstract （462）   HTML （46）    PDF（pc） （2309KB）（310）       Knowledge map    Save The advent of social media has brought about significant changes in people’s lives.While social media allows for easy access and sharing of news, it has also become a breeding ground for the dissemination of fake news, posing a serious threat to social security and stability.Consequently, researchers have shifted their focus towards fake news detection.Although several deep learning-based solutions have been proposed, these methods heavily rely on large amounts of supporting data.Currently, there is a scarcity of existing datasets, particularly in Chinese, and the collected news articles are often limited to the same category.To enhance the detection of fake news, a new multi-modal fake news dataset (MFND) was developed, which comprised Chinese and English news data from ten diverse categories: politics, economy, entertainment, sports, international affairs, technology, military, education, health, and social life.The word frequencies and categories of the proposed fake news dataset were analyzed and compared with existing fake news datasets in terms of number of news, news categories, modal information and news languages.The results of the comparison demonstrate that the MFND dataset excels in terms of category information and news languages.Moreover, training and validating existing typical fake news detection methods with MFND dataset, the experimental results show an improvement of approximately 10% in model performance compared to existing mainstream fake news datasets. Table and Figures | Reference | Related Articles | Metrics

Select

A survey on application of block chain in next generation intelligent manufacturing Zhiwei LIN, Songchuan ZHANG, Chengji WANG, Yiwei ZHOU Chinese Journal of Intelligent Science and Technology    2023, 5 (2): 200-211.   DOI: 10.11959/j.issn.2096-6652.202248 Abstract （460）   HTML （67）    PDF（pc） （13396KB）（478）       Knowledge map    Save In the process of promoting digital transformation of Chinese manufacturing enterprises, block chain technology has attracted extensive attention of researchers.The overall research progress domestically and abroad in the field of block chain technology was concluded.The recent researches on block chain technology in manufacturing process of food and military products, cloud manufacturing and other fields were summarized.The future path of combining block chain technology with intelligent manufacturing was predicted from 4 aspects: storage problem, scalability problem, computational power waste problem, security and privacy problem, aiming to provide valuable research ideas for further researchers. Table and Figures | Reference | Related Articles | Metrics

Select

Digital transformation service platform:enhancing enterprise competitiveness in a new competitive situation Yazhen YE, Yangyong ZHU Big Data Research    2023, 9 (3): 3-14.   DOI: 10.11959/j.issn.2096-0271.2023029 Abstract （455）   HTML （199）    PDF（pc） （1743KB）（486）       Knowledge map    Save With the improvement of data abilities and the development of emerging technologies, there are profound changes occurring in economic patterns and competitive structure of industries.In order to better respond to future opportunities and challenges, and to improve competitiveness of enterprises in new situations, it is necessary to understand and master the knowledge of digital transformation.The new competitive situation was discussed in which traditional enterprises would gradually be replaced by digital-transformed ones, digital transformation was differentiated from digitalization.Main challenges facing traditional enterprises while undergoing digital transformation were pinpointed, which were the lack of funds, talents, data and consciousness.A digital transformation service platform oriented to new competitive situation was proposed, which provided a feasible solution to enhancing enterprise competitiveness and conducting digital transformation. Table and Figures | Reference | Related Articles | Metrics

Select

Digital transformation in higher education:a systematic review Haihong QIAN, Maoyi WANG, Yun XIONG Big Data Research    2023, 9 (3): 56-70.   DOI: 10.11959/j.issn.2096-0271.2023032 Abstract （450）   HTML （98）    PDF（pc） （3934KB）（542）       Knowledge map    Save Promoting digital transformation becomes the key to achieving high-quality development of education.Based on the survey of the current situation of education digitalization, the essence, development, and related techniques of education digitalization transformation were analyzed.The challenges faced by the digital transformation of higher education in China were analyzed and suggestions on education and management from the perspectives of data, technology, and talent were presented.The results to explore solution on the digital transformation of higher education can provide reference to promote the digitalization of education. Table and Figures | Reference | Related Articles | Metrics

Select

A survey of deep learning-based MRI stroke lesion segmentation methods Weiyi YU, Tao CHEN, Junping ZHANG, Hongming SHAN Chinese Journal of Intelligent Science and Technology    2023, 5 (3): 293-312.   DOI: 10.11959/j.issn.2096-6652.202328 Abstract （450）   HTML （103）    PDF（pc） （23370KB）（374）       Knowledge map    Save Automatic stroke lesion segmentation has become a research hotspot in recent years.In order to comprehensively review current progress of deep learning-based MRI stroke lesion segmentation methods, start with the clinical problems of stroke treatment, we further elaborate the research background and challenges of deep learning-based lesion segmentation, and introduce common public datasets (ISLES and ATLAS) for stroke lesion segmentation.Then, we focus on the innovation and progress of deep learning-based stroke lesion segmentation methods, and summarize the research progress from three perspectives: network structure, training strategy, and loss function, and compare the advantages and disadvantages of various methods.Finally, we discusse the difficulties and challenges in this research and its future development trend. Table and Figures | Reference | Related Articles | Metrics

Select

Data augmentation method based on diffusion model for domain generalization Yujun TONG, Heqing WANG, Yueheng LUO, Wenxin NING, Mandan GUAN, Wenqing YU, Keyan HUANG, Jiaxun ZHANG, Zhanyu MA Chinese Journal of Intelligent Science and Technology    2023, 5 (3): 380-388.   DOI: 10.11959/j.issn.2096-6652.202334 Abstract （418）   HTML （38）    PDF（pc） （7426KB）（282）       Knowledge map    Save Domain generalization is an important and challenging problem in computer vision, arising from the distribution shift of real-world data.In practical applications, it is common to encounter training and testing data from different domains, and the difference in data distribution can lead to performance degradation during testing.In this paper, we propose a domain generalization method based on latent space data augmentation.Unlike traditional image-level data augmentation approaches, the method introduces a diffusion model in the latent space to achieve fine control and diversity generation of features, thereby achieving feature level data augmentation and enhancing the model's generalization ability in the target domain.Specifically, the classifier-based implicit diffusion model, trained within the latent space, can conditionally generate accurate and rich source domain features.It leverages efficient sampling techniques to expedite the generation of augmented features.Experimental results show that the method has achieved significant performance improvement in various domain generalization tasks, and has good effectiveness and robustness in real scenarios.The key innovation of this paper lies in shifting data augmentation to the latent space level and introducing the diffusion model for augmentation, providing a novel approach to address the domain generalization problem. Table and Figures | Reference | Related Articles | Metrics

Select

Industrial digital transformation:research onfault diagnosis methods Biao YANG, Yun XIONG, Ling FU, Weifeng XU, Jing LI Big Data Research    2024, 10 (1): 110-126.   DOI: 10.11959/j.issn.2096-0271.2023041 Abstract （416）   HTML （65）    PDF（pc） （3317KB）（315）       Knowledge map    Save Industrial digitalization is an important way for industrial transformation and upgrading of China's industry, and digital transformation has become an important trend in the development of China's industry.The reliability and stability of industrial systems play an important role in the high quality and sustainable development of industrial production.Failures affect the operation of industrial systems and even cause major safety accidents and economic losses.To deal with this problem, fault diagnosis technology has emerged and gradually developed.Efficient and high-quality fault diagnosis digital technology has become a key technology for industrial digital transformation.The research progress of digital methods of fault diagnosis in industry were analyzed.According to the development characteristics, three stages were divided, including domain experience-led modeling methods, data-driven digital methods combining with domain experience, and data-driven digital methods combining with interpretability.Focus on the basic ideas and characteristics of the methods in each stage, the future research directions were discussed, and the references were provided for promoting industrial digital transformation. Table and Figures | Reference | Related Articles | Metrics

Select

Generative AI empowered metaverse organisms: prospects and challenges Hao WANG, Yushan PAN, Yi PAN Big Data Research    2023, 9 (3): 85-96.   DOI: 10.11959/j.issn.2096-0271.2023033 Abstract （411）   HTML （102）    PDF（pc） （2778KB）（473）       Knowledge map    Save The metaverse has been discussed in fields such as medicine, manufacturing, finance, education, and public services, but the application scenarios based on virtual reality have not truly achieved the ＆quot;real-virtual-real＆quot; loop interaction method.Its interaction mode has also not truly given the digital world the same consciousness and perception as the physical world.Taking medicine as a case study, the prospective applications and challenges of generative artificial intelligence models in metaverse organisms were explored, including digitizing biological cells, and building connections between digitized cells and digital neurons, in order to promote metaverse life forms to have perception and biochemical reactions consistent with the physical world, thereby empowering the development of the medical field.In response to the current advantages and disadvantages of the metaverse and generative artificial intelligence models, the clever design of human-machine collaboration mechanisms was discussed to promote conscious interaction between humans and metaverse organisms in medicine. Table and Figures | Reference | Related Articles | Metrics

Select

Data valuation approach and application in view of data full lifecycle Dongqing LI, Yinxiao LIU, Lei DENG, Mingyang LI Big Data Research    2023, 9 (3): 39-55.   DOI: 10.11959/j.issn.2096-0271.2023044 Abstract （403）   HTML （90）    PDF（pc） （3924KB）（556）       Knowledge map    Save Data asset valuation is the foundation of modern data asset management, operation, and data circulation.Based on the theory of the data full lifecycle, starting from first principles, single data asset table was evaluated by assessing their cost, data management, and data application value.Using technologies such as data warehousing and graph algorithms, the cost value of a single data asset table was accurately calculated by using a layer-by-layer allocation method and inheriting the lineage path.Then, the non-economic factor weight of data asset was obtained by using the analytic hierarchy process, and the value of data asset was obtained through a ladder evaluation.Finally, verifies the rationality and feasibility of the new method was verified through an example. Table and Figures | Reference | Related Articles | Metrics

Select

Application Status and Analysis of Starlink Constellation Yu WANG, Qing LI, Kejun LI, Changlin JIANG, Ye WANG, Yong JIANG, Mingwei XU Space-Integrated-Ground Information Networks    2023, 4 (2): 93-102.   DOI: 10.11959/j.issn.2096-8930.2023023 Abstract （399）   HTML （74）    PDF（pc） （6589KB）（530）       Knowledge map    Save Starlink, asatellite broadband constellation operated by SpaceX, is currently the most influential and promising LEO broadband satellite constellation.With the expansion of the constellation deployment, its high-frequency launch and batch deployment of satellites, provision of diversified satellite broadband services, rapid growth of global user terminals, as well as potential support and capability enhancing for military are manifesting gradually.Firstiy, the current status of Starlink's on-orbit operations were analyzed, and its internet services with other satellite broadband service providers was compared.Then, the application characteristics and technical challenges of Starlink's inter-satellite laser links were focused on, and Starlink's military application progress and the evolution trend were discussed.Finally, the comprehensive application advantages Starlink offers, and technical challenges faced by Starlink were summarized, which could served as a stepping stone for the design of our country's satellite network.Overall, the construction and application of a mega LEO constellation like Starlink involves the chain integration of a series of component, ranging from satellite design and industrialized production, satellite launch facilities, constellation operation and maintenance, satellite networking, toglobal ground station supporting, rather than just the satellite platforms. Table and Figures | Reference | Related Articles | Metrics

Select

Research on LEO Satellite Network Routing Security Wenhao XUE, Tian PAN, Chengcheng LU, Fan YANG, Tao HUANG, Yunjie LIU Space-Integrated-Ground Information Networks    2023, 4 (2): 13-23.   DOI: 10.11959/j.issn.2096-8930.2023015 Abstract （395）   HTML （86）    PDF（pc） （6824KB）（363）       Knowledge map    Save The design of secure mechanisms and failure recovery mechanisms for inter-satellite routing has become pivotal in maintaining dependable communication within the LEO satellite network.To address the potential security threats faced by satellite networks, the impact of different routing attack behaviors on a typical inter-satellite routing protocol was analyzed and differentiated packet security authentication mechanisms and link failure recovery mechanisms were designed.Additionally, a satellite network emulation platform based on virtualization technology was constructed, enabled the verification of the effectiveness of the designed inter-satellite routing security mechanisms through the emulation of various routing attack scenarios.Furthermore, performance metrics such as CPU utilization and packet processing time were also evaluated before and after the introduction of security mechanisms.Experimental results demonstrated that the proposed inter-satellite routing security mechanism effectively mitigated multiple security threats in the space network environment while reduced communication latency caused by sudden link failures, thereby ensured secure and reliable communication within the LEO satellite network. Table and Figures | Reference | Related Articles | Metrics

Select

GenFedRL: a general federated reinforcement learning framework for deep reinforcement learning agents Biao JIN, Yikang LI, Zhiqiang YAO, Yulin CHEN, Jinbo XIONG Journal on Communications    2023, 44 (6): 183-197.   DOI: 10.11959/j.issn.1000-436x.2023122 Abstract （383）   HTML （65）    PDF（pc） （1359KB）（407）       Knowledge map    Save To solve the problem that intelligent devices equipped with deep reinforcement learning agents lack effective security data sharing mechanisms in the intelligent Internet of things, a general federated reinforcement learning (GenFedRL) framework was proposed for deep reinforcement learning agents.The joint training through model-sharing technology was realized by GenFedRL without the need to share the local private data of deep reinforcement learning agents.Each agent device’s data and computing resources could be effectively used without disclosing the privacy of its private data.To cope with the complexity of the real communication environment and meet the need to accelerate the training speed, a model-sharing mechanism based on synchronization and parallel was designed for GenFedRL.Combined with the model structure characteristics of common deep reinforcement learning algorithms, general federated reinforcement learning algorithm suitable for single network structure and multi-network structure was designed based on the FedAvg algorithm, respectively.Then, the model sharing mechanism among agents with the same network structure was implemented to protect the private data of various agents better.Simulation experiments show that common deep reinforcement learning algorithms still perform well in GenFedRL even in the harsh communication environment where most data nodes cannot participate in training. Table and Figures | Reference | Related Articles | Metrics

Select

Survey on adversarial attacks and defenses for object detection Xinxin WANG, Jing CHEN, Kun HE, Zijun ZHANG, Ruiying DU, Qiao LI, Jisi SHE Journal on Communications    2023, 44 (11): 260-277.   DOI: 10.11959/j.issn.1000-436x.2023223 Abstract （380）   HTML （107）    PDF（pc） （2195KB）（364）       Knowledge map    Save In response to recent developments in adversarial attacks and defenses for object detection, relevant terms and concepts associated with object detection and adversarial learning were first introduced.Subsequently, according to the evolution process of the methods, a comprehensive retrospective analysis was conducted on the research achievements in the realm of adversarial attacks and defense methods for object detection.Particularly, attack methods and defense strategies were categorized based on the attacker knowledge and the deep learning lifecycle.Furthermore, an in-depth analysis and discussion of the characteristics and relationships among different approaches were provided.Lastly, considering the strengths and limitations of existing research, the imminent challenges and directions were summarized for further exploration in adversarial attack and defense of object detection. Table and Figures | Reference | Related Articles | Metrics

Select

Byzantine-robust federated learning over Non-IID data Xindi MA, Qinghua LI, Qi JIANG, Zhuo MA, Sheng GAO, Youliang TIAN, Jianfeng MA Journal on Communications    2023, 44 (6): 138-153.   DOI: 10.11959/j.issn.1000-436x.2023115 Abstract （367）   HTML （83）    PDF（pc） （2173KB）（732）       Knowledge map    Save The malicious attacks of Byzantine nodes in federated learning was studied over the non-independent and identically distributed dataset , and a privacy protection robust gradient aggregation algorithm was proposed.A reference gradient was designed to identify “poor quality” shared gradients in model training, and the influence of heterogeneity data on Byzantine node recognition was reduced by reputation evaluation.Meanwhile, the combination of homomorphic encryption and random noise obfuscation technology was introduced to protect user privacy in the process of model training and Byzantine node recognition.Finally, through the evaluation over the real-world datasets, the simulation results show that the proposed algorithm can accurately and efficiently identify Byzantine attack nodes while protecting user privacy and has good convergence and robustness. Table and Figures | Reference | Related Articles | Metrics

Select

Membership inference attack and defense method in federated learning based on GAN Jiale ZHANG, Chengcheng ZHU, Xiaobing SUN, Bing CHEN Journal on Communications    2023, 44 (5): 193-205.   DOI: 10.11959/j.issn.1000-436x.2023094 Abstract （362）   HTML （73）    PDF（pc） （3691KB）（319）       Knowledge map    Save Aiming at the problem that the federated learning system was extremely vulnerable to membership inference attacks initiated by malicious parties in the prediction stage, and the existing defense methods were difficult to achieve a balance between privacy protection and model loss.Membership inference attacks and their defense methods were explored in the context of federated learning.Firstly, two membership inference attack methods called class-level attack and user-level attack based on generative adversarial network (GAN) were proposed, where the former was aimed at leaking the training data privacy of all participants, while the latter could specify a specific participant.In addition, a membership inference defense method in federated learning based on adversarial sample (DefMIA) was further proposed, which could effectively defend against membership inference attacks by designing adversarial sample noise addition methods for global model parameters while ensuring the accuracy of federated learning.The experimental results show that class-level and user-level membership inference attack can achieve over 90% attack accuracy in federated learning, while after using the DefMIA method, their attack accuracy is significantly reduced, approaching random guessing (50%). Table and Figures | Reference | Related Articles | Metrics

Select

Big data and computing models Guojie LI Big Data Research    2024, 10 (1): 9-16.   DOI: 10.11959/j.issn.2096-0271.2024017 Abstract （360）   HTML （183）    PDF（pc） （1457KB）（416）       Knowledge map    Save At present, artificial intelligence continues to heat up.Large language models have attracted much attention and set off a wave of enthusiasm around the world.The success of artificial intelligence is not essentially a ＆quot;miracle＆quot; of large computing power, but a change in computing models.Firstly, this paper affirms the fundamental role of data in AI, and points out that synthetic data will be the main source of data in the future.Then, this paper reviews the development of computing models, highlights the historic competition between neural network models and Turing models.We points out that the important hallmark of large language models is the emergence of intelligence in machines, emphasizes that the essence of large language models is ＆quot;compression＆quot;, and analyzes the reasons for the ＆quot;illusion＆quot; of large language models.Finally, we call on the scientific community to attach importance to large scientific models in ＆quot;AI for research(AI4R)＆quot;. Reference | Related Articles | Metrics

Select

Endogenous Security for the Space-Integrated-Ground Information Network in 6G Xinsheng JI, Kaizhi HUANG, Jiangxing WU, Yajun CHEN, Wei YOU Space-Integrated-Ground Information Networks    2023, 4 (2): 2-12.   DOI: 10.11959/j.issn.2096-8930.2023014 Abstract （357）   HTML （90）    PDF（pc） （6020KB）（338）       Knowledge map    Save The space-integrated-ground information network in 6G is facing security challenges due to its characteristics, such as the high exposure of the network, high-speed movement of nodes, limited computing resources.Moreover, new security issues are certainly introduced in the development of new architectures, new applications, new technologies and so on.It is urgent to propose new universal security theories to overcome safety and security threats by the integrated solutions.For this purpose, this paper first expounded the cyberspace endogenous security and proposed its endogenous security architecture.Then, under the guidance of the cyberspace endogenous security theory, the relevant security theory and practice norms were respectively discussed for onboard systems, 6G ground mobile networks, and satellite-ground links.Finally, the authentication and encryption mechanism of the communication and security integration from the aspects of security authentication and high security communication encryption, and the integration of traditional security technology and endogenous security were analyzed. Table and Figures | Reference | Related Articles | Metrics

Select

Future of AI painting from a legal perspective: the balance between freedom and control Yinyuan MA Chinese Journal of Intelligent Science and Technology    2023, 5 (3): 424-430.   DOI: 10.11959/j.issn.2096-6652.202331 Abstract （356）   HTML （204）    PDF（pc） （1501KB）（206）       Knowledge map    Save AI painting, as a representative of the new Internet technology, has a free environment consistent with the development of the early Internet.However, the free sharing of public resources is not eternal.The conflict between old system and new will inevitably brings many problems in the application of the existing laws.China’s existing laws and regulations for network service providers responsibility than the outside to be more perfect, again forced to increase the service provider or to serve the interests of the users responsibility will lead to imbalance, and there is no necessity for reference.Under the existing legal framework, the use of special legislation and industry autonomy to reinforce the power limits of the dominant player is enough, and the future of AI painting needs to always pay attention to the value of balance. Reference | Related Articles | Metrics

Select

A survey of federated learning for 6G networks Guanglei GENG, Bo GAO, Ke XIONG, Pingyi FAN, Yang LU, Yuwei WANG Chinese Journal on Internet of Things    2023, 7 (2): 50-66.   DOI: 10.11959/j.issn.2096-3750.2023.00323 Abstract （350）   HTML （60）    PDF（pc） （6843KB）（247）       Knowledge map    Save It is an important feature of the 6G that how to realize everything interconnection through large-scale complex heterogeneous networks based on native artificial intelligence (AI).Thanks to the distinct machine learning architecture of data processing locally, federated learning (FL) is regarded as one of the promising solutions to incorporate distributed AI in 6G scenarios, and has become a critical research direction of 6G.Therefore, the necessity of introducing distributed AI into the future 6G especially for internet of things (IoT) scenarios was analyzed.And then, the potentials of FL in meeting the 6G requirements were discussed, and the state-of-the-arts of FL related technologies such as architecture design, resource utilization, data transmission, privacy protection, and service provided for 6G were investigated.Finally, several key technical challenges and potential valuable research directions for FL-empowered 6G were put forward. Table and Figures | Reference | Related Articles | Metrics

Select

Risks and countermeasures of artificial intelligence generated content technology in content security governance Zhe QIAO Telecommunications Science    2023, 39 (10): 136-146.   DOI: 10.11959/j.issn.1000-0801.2023190 Abstract （344）   HTML （60）    PDF（pc） （1074KB）（470）       Knowledge map    Save Recently, artificial intelligence generated content (AIGC) technology has achieved various disruptive results and has become a new trend in AI research and application, driving AI into a new era.Firstly, the development status of AIGC technology was analyzed, focusing on generative models such as generative adversarial networks and diffusion models, as well as multimodal technologies, and surveying and elaborating on the existing technological capabilities for text, speech, image and video generation.Then, the risks brought by AIGC technology in the field of content security governance were focused and analyzed, including fake information, content infringement, network and software supply chain security, data leakage and other aspects.Finally, in view of the above security risks, counter strategies were proposed from the technical, application and regulatory levels, respectively. Table and Figures | Reference | Related Articles | Metrics

Select

Research on new frameworks and key technologies for intelligent emergency command communication networks Li WANG, Aiguo FEI, Ping ZHANG, Lianming XU Journal on Communications    2023, 44 (6): 1-11.   DOI: 10.11959/j.issn.1000-436x.2023112 Abstract （339）   HTML （100）    PDF（pc） （2103KB）（869）       Knowledge map    Save The new generation of emergency command communication network is the basic means and important support for enhancing China’s emergency response capabilities such as national natural disasters and accidents, and is a key component of establishing a scientific emergency management technology system.Focusing on the requirements of communication, navigating, and sensing capabilities in “intelligent emergency”, a theoretical method and framework for intelligent emergency command and communication networks was proposed, which was introduced from three aspects in terms of network deployment, resource allocation, and assisted decision-making.The difficulties and technical ideas of multi-objective dynamic network deployment for communication, navigating, and sensing, multi-dimension efficient resource allocation for communication, computation, and caching, and multi-level decision-making and intelligent enhancement with cloud-edge-terminal collaboration were analyzed and discussed.It provides theoretical methods and key technical supports for building a new generation of emergency command and communication network in China. Table and Figures | Reference | Related Articles | Metrics

Select

Research on the internal logic and solution of the “Channel Computing Resources from the East to the West” project Nannan TONG, Dong CHEN, Huiying LI, Honglin ZHU Big Data Research    2023, 9 (5): 9-19.   DOI: 10.11959/j.issn.2096-0271.2023055 Abstract （339）   HTML （134）    PDF（pc） （1659KB）（542）       Knowledge map    Save The ＆quot;Channel Computing Resources from the East to the West＆quot; project is a major strategic project to build a balance of computing resources and on-demand scheduling in China's territorial space.Since the full launch of the Chinese＆quot;Channel Computing Resources from the East to the West＆quot; project construction, a series of problems have been exposed on many different fields, such as the supply side, demand side, energy side, technology side, and mechanism side.It is urgent to re-analyze and define the internal logic of the ＆quot;Channel Computing Resources from the East to the West＆quot;project from a theoretical level.The internal logic of ＆quot;Channel Computing Resources from the East to the West＆quot;, that is, the infrastructure of Chinese computing, was analyzed from different perspectives such as economic form, technological trend, technological competition, and cost-benefit.It also proposed to build a new type of infrastructure for the Chinese national computing network, called computing NET, and build a national computing NET construction path from the aspects of policy layout, network direct connection, technical support, and mechanism innovation. Table and Figures | Reference | Related Articles | Metrics

Select

Survey on model inversion attack and defense in federated learning Dong WANG, Qianqian QIN, Kaitian GUO, Rongke LIU, Weipeng YAN, Yizhi REN, Qingcai LUO, Yanzhao SHEN Journal on Communications    2023, 44 (11): 94-109.   DOI: 10.11959/j.issn.1000-436x.2023209 Abstract （337）   HTML （59）    PDF（pc） （4179KB）（405）       Knowledge map    Save As a distributed machine learning technology, federated learning can solve the problem of data islands.However, because machine learning models will unconsciously remember training data, model parameters and global models uploaded by participants will suffer various privacy attacks.A systematic summary of existing attack methods was conducted for model inversion attacks in privacy attacks.Firstly, the theoretical framework of model inversion attack was summarized and analyzed in detail.Then, existing attack methods from the perspective of threat models were summarized, analyzed and compared.Then, the defense strategies of different technology types were summarized and compared.Finally, the commonly used evaluation criteria and datasets were summarized for inversion attack of existing models, and the main challenges and future research directions were summarized for inversion attack of models. Table and Figures | Reference | Related Articles | Metrics

Select

Channel-space endogenous anti-jamming method based on multi-reconfigurable intelligent surface Yonggang ZHU, Yifu SUN, Fuqiang YAO, Cheng LI, Wenlong GUO, Kang AN Journal on Communications    2023, 44 (10): 13-22.   DOI: 10.11959/j.issn.1000-436x.2023207 Abstract （335）   HTML （120）    PDF（pc） （1679KB）（405）       Knowledge map    Save In view of the concern that the traditional anti-jamming method based on jamming recognition is challenging to defend against both the unknown and the intelligent jamming attacks, a dynamic, heterogeneous, and redundant channel-space anti-jamming technique was proposed by adopting multiple reconfigurable intelligent surface (RIS), which facilitated the exploitation of channels’ resources for combating with the unknown jamming attacks.To elaborate, a channel-space endogenous anti-jamming method was proposed by leveraging the optimization of both the RIS’ coefficients and the multiple RIS’ on-off status.Firstly, after decoupling the tightly coupled variables, the optimal closed-form solutions of transmit precoder, RIS’ coefficients, and receive decoder could be derived under the alternative optimization framework.Then, the greedy algorithm was adopted to optimize the multiple RIS’ on-off status for obtaining better anti-jamming communications, and the convergence and the computation complexity of the proposed method was analyzed.Theoretical analysis and simulation results show that the proposed method can effectively defend against the uncertain jamming attacks. Table and Figures | Reference | Related Articles | Metrics

Select

An algorithm for joint optimization of dynamic routing and scheduling in time-sensitive networking Yang ZHOU, Honglong CHEN, Lei ZHANG Chinese Journal on Internet of Things    2023, 7 (4): 52-62.   DOI: 10.11959/j.issn.2096-3750.2023.00318 Abstract （334）   HTML （30）    PDF（pc） （1460KB）（533）       Knowledge map    Save Time-sensitive networking (TSN) is a set of protocols developed by the IEEE TSN task group, aiming at achieving deterministic communications over Ethernet.As the implementation method of TSN traffic scheduling is not specified in the protocols, the routing and scheduling algorithm for TSN remains an open issue.The joint optimization problem of routing and scheduling in TSN for industrial applications was modeled, and then an online heuristic algorithm was proposed to deliver the routing and scheduling solution for dynamic traffics.The routing path was determined by optimizing both the transmission delay and network load factors, and the scheduling time was quickly conducted by twice clipping operations.Finally, a simulated TSN testbed was developed with NeSTiNg framework based on OMNeT.The simulation results show that the execution time of the proposed algorithm outperforms the baseline algorithms even with large scale of network size and network traffics.It shows that the proposed algorithm guarantees the real-time performance even in dynamically changing networks. Table and Figures | Reference | Related Articles | Metrics

Select

End-to-end scene text detection and recognition algorithm based on Transformer decoders Jinzhi ZHENG, Ruyi JI, Libo ZHANG, Chen ZHAO Journal on Communications    2023, 44 (5): 64-78.   DOI: 10.11959/j.issn.1000-436x.2023070 Abstract （334）   HTML （77）    PDF（pc） （5030KB）（378）       Knowledge map    Save Aiming at the detection and recognition task of arbitrary shape text in scene, a novelty scene text detection and recognition algorithm which could be trained by end-to-end algorithm was proposed.Firstly, the detection branch of text aware module based on segmentation idea was introduced to detect scene text from visual features extracted by convolutional network.Then, a recognition branch based on Transformer vision module and Transformer language module encoded the text features of the detection results.Finally, the text features encoded by the fusion gate in the recognition branch were fused to output the scene text.The experimental results on the three benchmark datasets of Total-Text, ICDAR2013 and ICDAR2015 show that the proposed algorithm has excellent performance in recall, precision, F-score, and has certain advantages in efficiency. Table and Figures | Reference | Related Articles | Metrics