Most Download
Most Cited
Total visitors:
Visitors of today:
Now online:

Most Down Articles

    Published in last 1 year | In last 2 years| In last 3 years| All| Most Downloaded in Recent Month | Most Downloaded in Recent Year|

    In last 3 years
    Please wait a minute...
    For Selected: Toggle Thumbnails
    Overview of intelligent game:enlightenment of game AI to combat deduction
    Yuxiang SUN, Yihui PENG, Bin LI, Jiawei ZHOU, Xinlei ZHANG, Xianzhong ZHOU
    Chinese Journal of Intelligent Science and Technology    2022, 4 (2): 157-173.   DOI: 10.11959/j.issn.2096-6652.202209
    Abstract1319)   HTML108)    PDF(pc) (869KB)(2543)       Save

    The field of intelligent game has gradually become one of the hotspots of AI research.A series of research breakthroughs have been made in the field of game AI and intelligent wargame in recent years.However, how to develop game AI and apply it to the actual intelligent combat deduction is still facing great difficulties.The overall progress of research in the field of intelligent games in domestic and overseas were explored, the main attribute requirements of intelligent combat deduction was tracked, and it was summarized with the latest advancements in reinforcement learning.The feasibility of developing game AI into intelligent combat deduction were comprehensively analyzed from three dimensions: mainstream research technology in the field of intelligent game, relevant intelligent decision technology and technical difficulties of combat deduction, and finally, some suggestions for the development of future intelligent combat deductiongives were given.This paper can introduce a clear development status and provide valuable research ideas for researchers in the field of intelligent game.

    Table and Figures | Reference | Related Articles | Metrics
    A survey on federated learning in crowd intelligence
    Qiang YANG, Yongxin TONG, Yansheng WANG, Lixin FAN, Wei WANG, Lei CHEN, Wei WANG, Yan KANG
    Chinese Journal of Intelligent Science and Technology    2022, 4 (1): 29-44.   DOI: 10.11959/j.issn.2096-6652.202218
    Abstract1602)   HTML212)    PDF(pc) (2877KB)(2362)       Save

    Crowd intelligence is emerging as a new artificial intelligence paradigm owing to the rapid development of the Internet.However, the data isolation and data privacy preservation problems make it difficult to share data among the crowd and to build crowd intelligent applications.Federated learning is a novel solution that aims to collaboratively build models by breaking the data barriers in crowd.Firstly, the basic ideas of federated learning and a comparison with crowd intelligence were introduced.Secondly, federated learning algorithms were divided into three categories according to the crowd organization, and further optimization techniques on privacy, accuracy and efficiency were discussed.Thirdly, federated learning operators based on linear models, tree models and neural network models were presented respectively.Finally, mainstream federated learningopensource platforms and typical applications were introduced, followed by the conclusion.

    Table and Figures | Reference | Related Articles | Metrics
    NFT: blockchain-based non-fungible token and applications
    Rui QIN, Juanjuan LI, Xiao WANG, Jing ZHU, Yong YUAN, Fei-Yue WANG
    Chinese Journal of Intelligent Science and Technology    2021, 3 (2): 234-242.   DOI: 10.11959/j.issn.2096-6652.202125
    Abstract2298)   HTML200)    PDF(pc) (871KB)(1787)       Save

    Non-fungible token (NFT) based on blockchain is a kind of digital asset ownership recorded on blockchain, which is unique, irreplaceable and indivisible.It has been widely used in collectibles, encrypted artworks and games.Firstly, the concepts, characteristics and development processes of NFT were mainly introduced, and its core elements and typical application fields were analyzes.The problems and risks faced by NFT in the aspects of property right, value, technology and supervision were also pointed out.After that, the related literatures on NFT were reviewed, and the research issues of NFT in value evaluation, transaction mode and pricing were proposed.Finally, the trend of NFT driven digital capitalization was prospected.

    Table and Figures | Reference | Related Articles | Metrics
    Artificial intelligence technologies and applications in the metaverse
    Qiang WU, Xueting JI, Linyuan LYU
    Chinese Journal of Intelligent Science and Technology    2022, 4 (3): 324-334.   DOI: 10.11959/j.issn.2096-6652.202241
    Abstract1699)   HTML322)    PDF(pc) (872KB)(1363)       Save

    Metaverse integrates and applies a variety of digital technologies, resulting in an Internet social form that integrates virtual and reality, digital and application.Artificial intelligence (AI) are systems and machine that imitate human intelligence to perform tasks and iteratively improve themselves based on the information gathered.In the process of constructing the metaverse, AI technologies not only vigorously promote the development of crucial metaverse technologies (human-computer interaction, communication, robotics, etc.) but also enables direct content creation in the metaverse, organically connecting the real and virtual worlds.By sorting out the concepts and representative technologies of the metaverse and AI, the optimization progress of AI technologies for constructing key technologies in the metaverse was introduced and the application process of AI in the metaverse was detailed.Finally, the AI technology’s development and application trends in the metaverse prospected.

    Table and Figures | Reference | Related Articles | Metrics
    A review of prediction methods for moving target trajectories
    Wen LIU, Kunlin HU, Yan LI, Zhao LIU
    Chinese Journal of Intelligent Science and Technology    2021, 3 (2): 149-160.   DOI: 10.11959/j.issn.2096-6652.202115
    Abstract917)   HTML167)    PDF(pc) (2312KB)(1321)       Save

    With the rapid emergence of mobile terminal equipment in intelligent transportation system, the deep understanding and accurate prediction of moving target trajectories are capable of reducing the traffic accident probability, and promoting the location service-based intelligent transportation applications.The trajectory prediction methods prediction methods for moving target trajectories were reviewed from the data-driven prediction methods and the behavior-driven trajectories prediction methods.Firstly, the data-driven prediction methods were reviewed, including probabilistic statistics, neural networks, deep learning, and hybrid modeling.Then, the basic conceptions of target behavior-driven trajectories prediction methods were analyzed.The corresponding dynamical modeling and intention recognition methods were reviewed.The trajectory prediction applications were briefly analyzed and reviewed, such as target trajectory reconstruction, target abnormal behavior identification, and navigation route planning.Finally, the main problems and development directions related to prediction of moving target trajectories were discussed.

    Table and Figures | Reference | Related Articles | Metrics
    Review of pedestrian trajectory prediction methods
    Linhui LI, Bin ZHOU, Weiwei REN, Jing LIAN
    Chinese Journal of Intelligent Science and Technology    2021, 3 (4): 399-411.   DOI: 10.11959/j.issn.2096-6652.202140
    Abstract1582)   HTML341)    PDF(pc) (2826KB)(1309)       Save

    With the breakthrough of deep learning technology and the proposal of large data sets, the accuracy of pedestrian trajectory prediction has become one of the research hotspots in the field of artificial intelligence.The technical classification and research status of pedestrian trajectory prediction were mainly reviewed.According to the different modeling methods, the existing methods were divided into shallow learning and deep learning based trajectory prediction algorithms, the advantages and disadvantages of representative algorithms in each type of method were analyzed and introduced.Then, the current mainstream public data sets were summarized, and the performance of mainstream trajectory prediction methods based on the data sets was compared.Finally, the challenges faced by the trajectory prediction technology and the development direction of future work were prospected.

    Table and Figures | Reference | Related Articles | Metrics
    The DAOs to AI for Science by DeSci: the state of the art and perspective
    Fei-Yue WANG, Qinghai MIAO, Junping ZHANG, Wenbo ZHENG, Wenwen DING
    Chinese Journal of Intelligent Science and Technology    2023, 5 (1): 1-6.   DOI: 10.11959/j.issn.2096-6652.202310
    Abstract817)   HTML252)    PDF(pc) (788KB)(1155)       Save

    The new wave of artificial intelligence technology represented by ChatGPT is promoting the comprehensive transformation of human society, the transformation of scientific research paradigm is accelerating, and an artificial intelligence-driven scientific research (AI for Science, AI4S) revolution is coming.The basic concepts and characteristics of AI4S were analyzed, and the development status of AI4S were briefly summarized from the perspectives of mathematics, physics, biology, and materials.Vigorously developing AI4S is of great significance to improving national competitiveness, developing social economy, and strengthening technical reserves.In order to promote the development of AI4S better, the following two points are essential: one is to change the contemporary teaching and education, and advocate AI for Education (AI4E) and Education for AI (E4AI); the other is to establish and adapt to the "new scientific research paradigm" with "new organization mode" in a "new research ecology", based on DAOs and DeSci, for open, fair and just sustainable support for AI4S.

    Reference | Related Articles | Metrics
    Artificial intelligence and deep learning methods for solving differential equations: the state of the art and prospects
    Jingwei LU, Xiang CHENG, Fei-Yue WANG
    Chinese Journal of Intelligent Science and Technology    2022, 4 (4): 461-476.   DOI: 10.11959/j.issn.2096-6652.202255
    Abstract876)   HTML118)    PDF(pc) (6809KB)(1018)       Save

    With the rapid advancement of fundamental theories and computing capacity, deep learning techniques have made impressive achievements in many fields.Differential equations, as an important tool for describing the physical world, have long been a focus of interest for researchers in various fields.Combining the two methods has gained popularity as a study issue in recent years.Since deep learning can efficiently extract features from large amounts of data and differential equations can reflect objective physical laws, the combination of the two can effectively improve the generalization ability of deep learning and enhance the interpretability of deep learning.Firstly, the problem of solving differential equations by deep learning was briefly introduced.Then, two types of deep learning methods for solving differential equations were introduced: data-driven and physical-informed methods.Furthermore, the applications of relevant deep learning-based solving methods were discussed.Meanwhile, DeDAO (differential equations DAO), a foundation model for artificial intelligence for science, was proposed to address existing challenges.Finally, conclusions of deep learning methods for solving differential equations were presented.

    Table and Figures | Reference | Related Articles | Metrics
    A survey of 3D object detection algorithms
    Zhe HUANG, Yongcai WANG, Deying LI
    Chinese Journal of Intelligent Science and Technology    2023, 5 (1): 7-31.   DOI: 10.11959/j.issn.2096-6652.202312
    Abstract1057)   HTML160)    PDF(pc) (6364KB)(944)       Save

    3D object detection is a fundamental problem in autonomous driving,virtual reality,robotics,and other applications.Its goal is to extract the most accurate 3D box characterizing interested targets from the disordered point clouds,such as the closest 3D box surrounding the pedestrians or vehicles.The target 3D box's location,size,and orientation are also output.Currently,there are two primary approaches for 3D object detection: (1) pure point cloud based 3D object detection,in which the point clouds are created by binocular vision,RGB-D camera,and lidar; (2) fusion-based 3D object detection based on the fusion of image and point cloud.The various representations of 3D point clouds were introduced.Then representative methods were introduced from three aspects: traditional machine learning techniques; non-fusion deep learning based algorithms; and multimodal fusion-based deep learning algorithms in progressive relation.The algorithms within and across each category were examined and compared,and the differences and connections between the various methods were analyzed thoroughly.Finally,remaining challenges of 3D object detection were discussed and explored.And the primary datasets and metrics used in 3D object detection studies were summarized.

    Table and Figures | Reference | Related Articles | Metrics
    A cooperative multi-agent reinforcement learning algorithm based on dynamic self-selection parameters sharing
    Han WANG, Yang YU, Yuan JIANG
    Chinese Journal of Intelligent Science and Technology    2022, 4 (1): 75-83.   DOI: 10.11959/j.issn.2096-6652.202214
    Abstract518)   HTML55)    PDF(pc) (3737KB)(866)       Save

    In multi-agent reinforcement learning, parameter sharing can effectively alleviate the inefficiency of learning caused by non-stationarity.However, maintaining the same policy forall agents during learning may have detrimental effects.To solve this problem, a new approach was introduced to give agents the ability to automatically identify agents that may benefit from parameter sharing and dynamically share parameters them during learning.Specifically, agents needed to encode empirical trajectories as implicit information that can represent their potential intentions, and selected peers to share parameters by comparing their intentions.Experiments show that the proposed method not only can improve the efficiency of parameter sharing, but also ensure the quality of policy learning in multi-agent system.

    Table and Figures | Reference | Related Articles | Metrics
    A survey of research on demand responsive transit and its route optimization
    Shuai FENG, Xiaoming LIU
    Chinese Journal of Intelligent Science and Technology    2021, 3 (2): 161-171.   DOI: 10.11959/j.issn.2096-6652.202116
    Abstract548)   HTML66)    PDF(pc) (1070KB)(744)       Save

    With the widespread application of new infrastructure and other technologies, demand responsive transit (DRT) is becoming the trend of urban traffic development in the future.In order to further clarify the research status of DRT at home and abroad, firstly, the classification of DRT and the operational production factors were analyzed.Secondly, the production process and operation practice of DRT mode were described.Thirdly, the DRT optimization problem was summarized and analyzed from the three dimensions including optimization objectives, constraint selection and solving algorithm, especially the meta heuristic algorithm.Finally, the prospect of DRT scenarios, model construction, algorithm solution, and the collaborative optimization were proposed.Several hotspots and possible directions of future research were suggested.

    Table and Figures | Reference | Related Articles | Metrics
    Parallel philosophy and intelligent technology: dual equations and testing systems for parallel industries and smart societies
    Fei-Yue WANG
    Chinese Journal of Intelligent Science and Technology    2021, 3 (3): 245-255.   DOI: 10.11959/j.issn.2096-6652.202126
    Abstract456)   HTML54)    PDF(pc) (4026KB)(726)       Save

    Starting from Karl Popper’s Three Worlds, the knowledge system facing three worlds and the corresponding philosophical problem were proposed.The scope of traditional philosophy from being and becoming to believing was extended, and a new parallel philosophy as the foundation for intelligent science and technology was proposed.The dual equation systems and parallel testing were introduced through ACP, and cyber-physical-social systems (CPSS).This will enable a true DAO approach for intelligent parallel industries and smart societies: trustable, reliable, usable, and effective +efficient (true), distributed + decentralized, autonomous + automated, organized + ordered (DAO), and the corresponding distributed autonomous organizations and operations (DAOs).

    Table and Figures | Reference | Related Articles | Metrics
    Knowledge graph construction for control systems in process industry
    Tianhao MOU, Shaoyuan LI
    Chinese Journal of Intelligent Science and Technology    2022, 4 (1): 129-141.   DOI: 10.11959/j.issn.2096-6652.202216
    Abstract641)   HTML94)    PDF(pc) (1908KB)(718)       Save

    Achieving intelligence in industrial control systems is a prevailing trend in recent years, with numerous new technologies and ideas prompted.Knowledge graph is a fundamental resource for artificial intelligence, and domain-specific knowledge graph construction attracts a lot of research attentions.However, knowledge graph construction for control systems is still in the early stage of exploitation.In this paper, structural characteristics and task requirements of process control systems were analyzed.Furthermore, a knowledge graph construction methodology architecture for process control systems was proposed.Firstly, a brief summary on existing related works was given.After that, the characteristics of process industry control systems were analyzed, and the corresponding knowledge graph construction principles and procedures were proposed.Cyber-physical assets management was taken as a case study for detailed explanation.Finally, a prospect for the future research directions of knowledge graph construction for process control systems was made.

    Table and Figures | Reference | Related Articles | Metrics
    Research on application of edge computing system based on KubeEdge
    Hang ZHAO, Sheng LIU, Kun LUO, Shichao CHEN, Linghui KONG, Fan JIA
    Chinese Journal of Intelligent Science and Technology    2022, 4 (1): 118-128.   DOI: 10.11959/j.issn.2096-6652.202201
    Abstract636)   HTML61)    PDF(pc) (2220KB)(677)       Save

    With the increasing development of Internet of things, traditional data processing methods based on cloud computing have shown many problems, such as high bandwidth occupation and time delay.Edge computing can be a supplement for cloud computing with the characteristics of low latency and high reliability to process data.The KubeEdge edge computing system and its application were mainly discussed and analyzed.Firstly, the system architecture, functions, and key technologies of KubeEdge were introduced.Secondly, the KubeEdge was applied to the parts assembly scenario with dual-arm cooperative robot, and the functions and performances of a cloud-edge collaboration system based on KubeEdge for the robot assembly application were analyzed and tested.The experimental results show that the system can satisfy the functional and application requirements of the scenario, which also provides basic reference and guidance for practical applications of KubeEdge.

    Table and Figures | Reference | Related Articles | Metrics
    Collective knowledge graph: meta knowledge transfer and federated graph reasoning
    Mingyang CHEN, Wen ZHANG, Xiangnan CHEN, Hongting ZHOU, Huajun CHEN
    Chinese Journal of Intelligent Science and Technology    2022, 4 (1): 55-64.   DOI: 10.11959/j.issn.2096-6652.202217
    Abstract604)   HTML66)    PDF(pc) (833KB)(647)       Save

    Collective knowledge graphs refer to knowledge graphs that are managed and maintained in a decentralized or distributed manner through group collaboration.Compared with the existing centrally managed knowledge graph, the collective knowledge graph has the characteristics of knowledge right confirmation, privacy protection, crowd sourcing incentive, and credible traceability.Tring to explore the technical challenges faced by building and applying a collective knowledge graph platform.For meta knowledge transfer, the knowledge incompleteness of a single knowledge graph by knowledge transfer among multiple knowledge graphs from different sources under a decentralized and autonomous framework was considered.The main difficulty was to enhance the respective knowledge graph representation by sharing useful knowledge with each other as much as possible while fully protecting the autonomous ownership of knowledge.For federated graph reasoning, the knowledge graph reasoning in a distributed environment under the privacy-preserving by means of the federated learning mechanism was considered.Meta knowledge transfer focused on transferring entity-independent knowledge between knowledge graphs with overlapped relation set, while federated graph reasoning aimed at learning better entity embeddings for knowledge graphs with overlapped entity set.The model design and experimental validation for each of these two problems were conducted.

    Table and Figures | Reference | Related Articles | Metrics
    Research on key technologies of social computing for urban complex system
    Xiaofeng JIA, Song GAO, Xi JIANG, Hongwei QI, Xiao WANG, Jun ZHANG, Rui QIN, Liwei OUYANG
    Chinese Journal of Intelligent Science and Technology    2021, 3 (2): 228-233.   DOI: 10.11959/j.issn.2096-6652.202124
    Abstract323)   HTML29)    PDF(pc) (2948KB)(622)       Save

    Urban complex system has the characteristics of multiple scattered elements, complex multi-dimensional relationships, dynamic structural changes and high degree of social function coupling.Real-time global data perception, hierarchical decentralized collaborative scheduling and complex dynamic relationship construction are the key issues of accurate modeling and fine management of urban system.The social computing technologies based on ACP parallel intelligent method provides theoretical basis for the problems.Based on this, the large-scale, multi-modal, high-dimensional and total factor modeling of urban complex system was carried out.Based on the chain code mechanism of virtual-real dual parallel regulation, the key technologies of social computing were proposed and its system architecture was designed to realize the global chain communication and polymorphic application of urban complex system.The architecture can provide an important paradigm for the oriented distributed, intelligent and active response of complex urban management in the future.

    Table and Figures | Reference | Related Articles | Metrics
    Traffic situational awareness research and development enhanced by social media data: the state of the art and prospects
    Yuanwen CHEN, Xiao WANG, Lingxi LI, Fei-Yue WANG
    Chinese Journal of Intelligent Science and Technology    2022, 4 (1): 1-13.   DOI: 10.11959/j.issn.2096-6652.202220
    Abstract537)   HTML79)    PDF(pc) (744KB)(619)       Save

    Traffic situational awareness is an important research direction of intelligent transportation systems.Most of the existing research focused on how to use physical sensors to perceive the current traffic situation and predict the future traffic state.However, the performance of physical sensors is prone to instability or failure due to adverse weather, electromagnetic interference, energy limitation and other problems, resulting in sparse or missing collected data, which makes the perception of traffic situation lagging and inaccurate.Social media data provides a new and enhanced way of perceiving comprehensive traffic situation information in a timely manner.Facing with the current traffic situation where sudden abnormal traffic events occur frequently, social sensing and physical sensing data can complement with each other to further improve the efficiency of urban traffic management.The related work of traffic event detection and traffic state prediction enhancing based on social media data were analyzed, and how those research works provide decision support for the traffic management departments to plan and guide traffic reasonably and alleviate traffic congestion were explored.Finally, some future research directions of traffic situational awareness enhanced by social media data were proposed.

    Reference | Related Articles | Metrics
    Collective decision-making in open environment: concepts, challenges, and leading technologies
    Xueqi CHENG, Bingbing XU, Qi CAO, Shenghua LIU, Juan CHEN, Lei LIN, Huawei SHEN
    Chinese Journal of Intelligent Science and Technology    2022, 4 (1): 45-54.   DOI: 10.11959/j.issn.2096-6652.202219
    Abstract489)   HTML58)    PDF(pc) (1203KB)(606)       Save

    Research on collective decision-making is based on new decision-making theories and their methods are driven by group participation, human-computer interaction, and big data, to realize complex problem solving and intelligent decision-making in an open environment.However, the open environment is of high openness, complex interaction, and emerging behaviors, making collective decision-making face the challenges of difficult incentive mechanism design, uncontrollable decision-making individuals, diverse decision-making environments, and highly complex decosion-making information.Based on the era background of collective decision-making in an open environment, a new decision-making paradigm was proposed, its conceptual connotation, main challenges, and leading technologies for effective implementation of collective decision-making were sorted out.The successful cases of collective decision-making were analyzed, in order to support the application of new decision-making paradigms in the fields of economy, medical care, and people’s livelihood, and to promote progress and changes in the corresponding fields.

    Table and Figures | Reference | Related Articles | Metrics
    Research development on automated robotic peg-in-hole assembly
    De XU, Fangbo QIN
    Chinese Journal of Intelligent Science and Technology    2022, 4 (2): 200-211.   DOI: 10.11959/j.issn.2096-6652.202223
    Abstract472)   HTML45)    PDF(pc) (1312KB)(606)       Save

    Peg-in-hole assembly is a typical operation task in manufactory.The research of peg-in-hole assembly based on industrial robots is valuable for the application of robots in the automated assembly area.For the peg-in-hole components with high precision or complex shapes, the efficient and reliable assembly is still very challenging.The development of automated robotic peg-in-hole assembly of peg-in-hole was reviewed from the view of control.First, the process of robotic peg-in-hole assembly was introduced.Secondly, the assembly control methods based on the traditional models were described.The newly emerged intelligent assembly methods based on learning mechanism were discussed, especially the applications of imitation learning and reinforcement learning in the automated robotic assembly.The combination of the traditional methods and the artificial intelligent methods will provide new energy for the automated robotic assembly, which will be one of the important developing tendencies in future.

    Table and Figures | Reference | Related Articles | Metrics
    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
    Abstract841)   HTML101)    PDF(pc) (6643KB)(603)       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
    Overview of metro train driving technology development:from manual driving to intelligent unmanned driving
    Wenzhu LAI, Dewang CHEN, Zhenfeng HE, Xinguo DENG, CARLO Marano GIUSEPPE
    Chinese Journal of Intelligent Science and Technology    2022, 4 (3): 335-343.   DOI: 10.11959/j.issn.2096-6652.202204
    Abstract666)   HTML132)    PDF(pc) (647KB)(589)       Save

    Based on the current development status of subway train driving technology in China and abroad, the four stages of subway train driving technology development were proposed and explained as manual driving, automatic driving, unmanned driving, and intelligent unmanned driving.After summarizing the construction situation of unmanned subway trains in China, the disadvantages of the current train control methods based on neural network-based machine learning methods were addressed.Then, the basic block diagram of metro intelligent unmanned driving based on man-machine hybrid intelligence was put forward and the deep fuzzy system was introduced.A promising solution for the combination of expert experience in dealing with emergency and interpretable AI algorithms for unmanned driving system to evolve into intelligent unmanned driving was provided.

    Table and Figures | Reference | Related Articles | Metrics
    Parallel museums: intelligent management and control of museum operations in the new era
    Chunfa WANG, Fei-Yue WANG, Yue LU, Huabiao LI, Chao GUO
    Chinese Journal of Intelligent Science and Technology    2021, 3 (2): 125-136.   DOI: 10.11959/j.issn.2096-6652.202113
    Abstract375)   HTML35)    PDF(pc) (7292KB)(581)       Save

    The development of society and the growth of public cultural needs bring new challenges to the operations and management of museums in the new era.Considering the current state of the museum management and its challenges in exhibition, education, and safety, the parallel museums framework as a new solution to the museum management was proposed, and technical reference for constructing intelligent museum was proposed.The parallel museums framework was the application of ACP theory in museum operations and management, descriptive intelligence was used to construct a virtual museum, predictive intelligence was used to do large-scale computational experiments in the virtual museum, and prescriptive intelligence and parallel execution were used to control the real museum.

    Table and Figures | Reference | Related Articles | Metrics
    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
    Abstract518)   HTML66)    PDF(pc) (3737KB)(573)       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
    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
    Abstract773)   HTML207)    PDF(pc) (48558KB)(573)       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
    Research on metro train driverless system based on man-machine hybrid intelligence
    Benzun HUANG, Dewang CHEN, Zhenfeng HE, Xinguo DENG, Marano GIUSEPPECARLO
    Chinese Journal of Intelligent Science and Technology    2022, 4 (4): 584-591.   DOI: 10.11959/j.issn.2096-6652.202205
    Abstract213)   HTML37)    PDF(pc) (3698KB)(569)       Save

    Based on the development status of subway train driving technology at home and abroad, the necessity of subway train intelligent driving development and research was expounded.In view of the poor interpretability of machine learning algorithms used in current unmanned driving, with an introduction of fuzzy system, a metro train unmanned driving system based on man-machine hybrid intelligence was proposed, which realized man-machine hybrid intelligence in two ways.The subway train driverless system combined with cognitive system was explored, which a future-oriented solution for the realization of strong artificial intelligence subway train driverless system in the real sense was provided.

    Table and Figures | Reference | Related Articles | Metrics
    Diffusion Model and Artificial Intelligence Generated Content
    Chinese Journal of Intelligent Science and Technology    2023, 5 (3): 378-379.   DOI: 10.11959/j.issn.2096-6652.202334-1
    Abstract131)   HTML38)    PDF(pc) (2154KB)(551)       Save
    Reference | Related Articles | Metrics
    Information security of the industrial control system for rail:analysis and prospect
    Yidong LI, Zikai ZHANG, Hairong DONG, Honglei ZHANG, Haoyu CHEN, Yushan HAN
    Chinese Journal of Intelligent Science and Technology    2021, 3 (2): 139-148.   DOI: 10.11959/j.issn.2096-6652.202114
    Abstract299)   HTML35)    PDF(pc) (3168KB)(545)       Save

    As one of the important national infrastructures, more and more attentions are attracted by the industrial control system for rail (ICS-R), with the rapid development of information technology and the increasingly severe network situation.The system composition of ICS-R was analyzed, the types of security threats faced by the ICS-R were summarized and analyzed, the practical cases of threat propagation were given, and the information security threat trend of ICS-R was analyzed considering the development trend of technology.Finally, several development suggestions were prospected as promising techniques.

    Table and Figures | Reference | Related Articles | Metrics
    A survey on applications of ontology knowledge representation in robotics
    Yueguang GE, Shaolin ZHANG, Yinghao CAI, Tao LU, Dayong WEN, Haitao WANG, Shuo WANG
    Chinese Journal of Intelligent Science and Technology    2022, 4 (2): 212-222.   DOI: 10.11959/j.issn.2096-6652.202224
    Abstract276)   HTML44)    PDF(pc) (1371KB)(540)       Save

    The technology about knowledge representation plays an increasingly important role in the autonomous operation of robots facing the complex and unstructured working environment.Knowledge representation focuses on the model of knowledge symbols and how to realize knowledge processing through reasoning procedures automatically.The robot knowledge representation framework and the latest application progress based on ontology representation and reasoning were reviewed.The technical background, realization methods of knowledge representation and reasoning, and recent research progress in the robotics field were summarized from deterministic knowledge and uncertain knowledge.And the future research direction of knowledge-enabled robots was predicted.

    Table and Figures | Reference | Related Articles | Metrics
    A deep learning short-term traffic flow prediction method considering spatial-temporal association
    Yang ZHANG, Yue HU, Dongrong XIN
    Chinese Journal of Intelligent Science and Technology    2021, 3 (2): 172-178.   DOI: 10.11959/j.issn.2096-6652.202117
    Abstract172)   HTML22)    PDF(pc) (3982KB)(535)       Save

    The short-term traffic flow prediction is too dependent on the time correlation characteristics, which due to the problems that the correlation factors of the spatial correlation characteristics are too complicated and difficult to quantify.In response to this defect, a deep learning short-term traffic flow prediction method considering spatial-temporal association was proposed.Firstly, by constructing a spatial association measurement function that simultaneously considers distance, flow similarity, and speed similarity, the spatial correlation between the target road segment and the surrounding associated road segments was quantified and predicted.Then, a convolutional neural network model with long short-term memory neurons embedded was constructed.The long short-term memory neurons were used to extract the temporal correlation characteristics between the data, and the spatial correlation metric and the convolution transmission of traffic data were used to extract the spatial correlation characteristics between the data, so as to realize the traffic flow prediction considering the spatial-temporal association.The experimental results show that the proposed method can adapt to short-term forecasting under different traffic flow characteristics such as weekdays and weekends, and the prediction accuracy is better than that of the classical methods.In weekdays and weekends, the forecast bias are 10.45% and 12.35% respectively.

    Table and Figures | Reference | Related Articles | Metrics
    Exploration of the continual learning ability that supports the application ecological evolution of the large-scale pretraining Peng Cheng series open source models
    Yue YU, Xin LIU, Fangqing JIANG, Han ZHANG, Hui WANG, Wei ZENG
    Chinese Journal of Intelligent Science and Technology    2022, 4 (1): 97-108.   DOI: 10.11959/j.issn.2096-6652.202212
    Abstract400)   HTML59)    PDF(pc) (3005KB)(518)       Save

    Large-scale pre-training models have achieved great success in the field of natural language processing by using large-scale corpora and pre-training tasks.With the gradual development of large models, the continual learning ability of large models has become a new research focus.The continual learning technology of the Peng Cheng series large models, the exploration of practice and the still facing challenges were mainly introduced, including the Peng Cheng series continual learning technology through task expansion, data increment and knowledge reasoning, Peng Cheng PANGU multi-task continual learning and the practical exploration of the continual learning ability of the Peng Cheng TONGYAN open source large model, the vocabulary update, semantic mapping and knowledge conflicts that the large model faces in the process of continual learning.

    Table and Figures | Reference | Related Articles | Metrics
    Machine Learning Methods in AI 3.0
    Chinese Journal of Intelligent Science and Technology    2022, 4 (4): 542-543.   DOI: 10.11959/j.issn.2096-6652.202240-1
    Abstract271)   HTML86)    PDF(pc) (745KB)(513)       Save
    Reference | Related Articles | Metrics
    Research on anti-spoofing method of face recognition based on semi-supervised learning
    Li LI, Weiliang ZENG, Yonghui HUANG, Weijun SUN
    Chinese Journal of Intelligent Science and Technology    2021, 3 (3): 370-380.   DOI: 10.11959/j.issn.2096-6652.202138
    Abstract335)   HTML45)    PDF(pc) (2002KB)(492)       Save

    It is a long-term challenge to identify the real and fake faces in the images.When the synthetic fake faces are very realistic, it is difficult for machines and even naked eyes to distinguish the real and fake ones.The supervised anti-spoofing method often requires a large number of labeled samples for a good performance.An anti-spoofing method of face recognition based on semi-supervised learning was proposed to reduce the dependence on massive labeled samples.The method adopted an image inpainting model to learn the data distribution of face images.During the training process, a few labeled samples periodically provided supervised signals to train the classifier to distinguish real faces from fake ones.The proposed method could be used for face anti-spoofing in different scenario, such as faces captured by cameras or generated by generative adversarial net.Accordingly, it was evaluated on the NUAA and RMFD datasets.Experiment results show that the proposed method can keep the quality of restored images, and achieve desirable classification accuracy.With a few labeled samples, the proposed method outperforms Improved-GAN and common semi-supervised methods, and surpasses supervised learning method based on support vector machine and convolutional neural network.

    Table and Figures | Reference | Related Articles | Metrics
    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
    Abstract521)   HTML136)    PDF(pc) (8731KB)(486)       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
    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
    Abstract472)   HTML57)    PDF(pc) (2926KB)(483)       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
    Abnormal cell segmentation for lung pathological image based on denseblock and attention mechanism
    Wencheng CUI, Keli WANG, Hong SHAO
    Chinese Journal of Intelligent Science and Technology    2023, 5 (4): 525-534.   DOI: 10.11959/j.issn.2096-6652.202210
    Abstract242)   HTML3)    PDF(pc) (3799KB)(482)       Save

    Aiming at the problems of unbalanced brightness of lung cell images and achieving accurate segmentation of abnormal cell contour difficultly, an abnormal cell segmentation model based on U-Net was proposed, which combined the dense connection mechanism and attention mechanism. Firstly, U-Net with encoder-decoder structure was used to segment abnormal cells. Secondly, the dense block was introduced into U-Net to improve the propagation ability between features and extract more characteristic information of abnormal cells. Finally, the attention mechanism was used to increase the weight of abnormal cell regions and reduce the interference of the imbalance of brightness to the model. The experimental results show that the IoU value and Dice similarity coefficient achieved by this method are 0.6928 and 0.8060, respectively. Compared with other models, this proposed method is able to segment low-contrast regions and abnormal cells with diverse shapes.

    Table and Figures | Reference | Related Articles | Metrics
    Research on the manipulator intelligent trajectory planning method based on the improved TD3 algorithm
    Qiang ZHANG, Wen WEN, Xiaodong ZHOU, Weihui LIU, Xiaoyu CHU
    Chinese Journal of Intelligent Science and Technology    2022, 4 (2): 223-232.   DOI: 10.11959/j.issn.2096-6652.202225
    Abstract339)   HTML33)    PDF(pc) (3862KB)(477)       Save

    An intelligent trajectory planning and obstacle avoidance method based on the improved twin delayed deep deterministic policy gradient algorithm (TD3) was proposed to solve the trajectory planning problem for a 4-DOF manipulator mounted on a satellite.The training strategy had 2 periods.In the pre-training stage, the target position was always guided combining with the output of the strategy network to optimize the trajectory.After the pre-training, the algorithm can autonomously output the velocity trajectory while the initial position and the target were specified randomly in the joint space of the manipulator.This target-guided mechanism decreased the unnecessary explorations and improved the learning efficiency in high dimensional action space.In the second training stage, a collision-free safety reference trajectory was firstly obtained by demonstration, and then this trajectory was constantly learned during the training process until the final output trajectory has the ability to avoid obstacles.

    Table and Figures | Reference | Related Articles | Metrics
    A review of continual learning for robotics
    Chao ZHAO, Jie XU, Xingyu CHEN, Kuizhi MEI, Xuguang LAN
    Chinese Journal of Intelligent Science and Technology    2022, 4 (3): 308-323.   DOI: 10.11959/j.issn.2096-6652.202235
    Abstract567)   HTML116)    PDF(pc) (1356KB)(474)       Save

    One of the limitations of robotics is that it is difficult for robots to adapt to fickle tasks.A robot will inevitably forget the knowledge from old environments or tasks when facing new environments or tasks.In order to summarize research in continual learning for robotics, firstly, the framework and evaluation protocols in continual learning were introduced.And then necessity and challenge of continual learning in the robotics were expounded.The research for continual learning was also summarized.Finally, the prospect of continual learning was predicted and some valuable research directions were put forward.

    Table and Figures | Reference | Related Articles | Metrics
    Plant leaf detection technology based on multi-scale CNN feature fusion
    Ying LI, Long CHEN, Zhaohong HUANG, Yang SUN, Guorong CAI
    Chinese Journal of Intelligent Science and Technology    2021, 3 (3): 304-311.   DOI: 10.11959/j.issn.2096-6652.202131
    Abstract253)   HTML28)    PDF(pc) (2235KB)(473)       Save

    Plant leaf detection is one of the essential aspects of the scientific plant breeding and precision agriculture process.The traditional practice of plant leaf detection requires professional knowledge of the operators, high labor costs, and long time-consuming cycles.The plant leaf detection technology based on multi-scale CNN feature fusion (MCFF) was proposed.Starting from the needs of deep learning technology assisted plant cultivation, a MCFF was used to detect leaf count for three different types and resolutions of rosette model plants, arabidopsisthaliana, and tobacco.Compared with the other three algorithms, the MCFF has a higher detection accuracy with an average detection rate of mAP 0.662, a highly competitive performance (AP = 0.946) has been achieved for each indicator close to the practical level.

    Table and Figures | Reference | Related Articles | Metrics
    Curriculum design for artificial intelligence and quantitative trading
    Junhuan ZHANG, Zhengyi ZHU, Kewei CAI
    Chinese Journal of Intelligent Science and Technology    2023, 5 (1): 104-112.   DOI: 10.11959/j.issn.2096-6652.202311
    Abstract391)   HTML53)    PDF(pc) (840KB)(472)       Save

    With the development of computer technology, especially the development of artificial intelligence, big data technology and blockchain technology, the transaction mode of traditional economic society and financial market has been changed.Quantitative trading is an important emerging trading mode in the contemporary financial market.To meet the social demand for quantitative trading talents, it is particularly important to explore a reasonable course system of AI and quantitative trading.Firstly, the recent development of quantitative trading and the application of AI in quantitative trading were analyzed.Then, the current situations and problems of the quantitative trading course were summarized.Finally, according to the problems, the suggestions on the course design for AI and quantitative trading were put forward in four aspects, which included teaching content system, teaching practice simulation platform, teacher training, and multi-channel practice platform.

    Table and Figures | Reference | Related Articles | Metrics
    Parallel port: new formation and system architecture of port industry Internet of minds in smart and green era
    Yuzhen WU, Jun ZHANG, Tianlu GAO, Yujian SUN, Jinxu LIU
    Chinese Journal of Intelligent Science and Technology    2021, 3 (2): 218-227.   DOI: 10.11959/j.issn.2096-6652.202123
    Abstract193)   HTML18)    PDF(pc) (2625KB)(465)       Save

    The background, demand, new formation, system architecture, and platform technology of port industry in smart and green era were analyzed.Firstly, the background and demand of port industry in smart and green era were introduced.Then the new formation and system architecture of parallel port industry were demonstrated.Next, the novel platform technology of port industry in smart and green era was discussed, including the Internet of minds, knowledge automation, hybrid-augmented intelligence and so on.Finally, an application case study of parallel systems in smart and green port was presented, i.e., port ship management system.

    Table and Figures | Reference | Related Articles | Metrics
    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
    Abstract454)   HTML61)    PDF(pc) (13396KB)(463)       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
    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
    Abstract519)   HTML87)    PDF(pc) (5939KB)(460)       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
    Theoretical framework of brain modelling and highlighted problems
    Dongwei HU, Xiaolu FENG
    Chinese Journal of Intelligent Science and Technology    2021, 3 (4): 412-434.   DOI: 10.11959/j.issn.2096-6652.202141
    Abstract334)   HTML33)    PDF(pc) (2928KB)(449)       Save

    Understanding how the brain works is an important way to constructing the final artificial general intelligence.Building models, and testing the correctness of these models play a pivotal role on understanding how the brain works.Firstly, the experimental techniques and mathematical modelling methods for the study of brain were reviewed, and then the block diagram model and theoretical framework were shown, with an emphasis on reinforcement learning.Finally, some highlighted problems in this area, and the relation with closely related disciplines were addressed.

    Table and Figures | Reference | Related Articles | Metrics
    Short-term traffic state reasoning and precise prediction in urban networks
    Yuanqi QIN, Qingyuan JI, Jun GE, Xingyuan DAI, Yuanyuan CHEN, Xiao WANG
    Chinese Journal of Intelligent Science and Technology    2022, 4 (3): 380-395.   DOI: 10.11959/j.issn.2096-6652.202233
    Abstract321)   HTML40)    PDF(pc) (1718KB)(444)       Save

    The structure of urban traffic network has a significant impact on the formation and spatio-temporal pattern propagation of traffic congestions.However, in studies based on traditional traffic models or deep learning models, the generation of traffic mode can only be described indirectly by traffic indicators, without considering the traffic network feature.This makes it very difficult to accurately describe the propagation dynamics both in temporal and spatial dimensions and lacks specificity.To tackle the above-mentioned problems, a novel traffic state prediction approach based on traffic pattern reasoning (TP2) framework was proposed.The framework modeled congestion propagation as a dynamically evolving temporal knowledge graph (TKG), and applied an inferencing framework (TPP-TKG) that was based on a novel aggregator called RGraAN.TPP-TKG captured the spatial-temporal propagation pattern of traffic congestion, and combined related road links to a given link, and constructed correlated sub region of the traffic network.Then a traffic state predicting based on graph neural network was employed to predict short-term speed evolution of road links in this sub region.Comparing to the state-of-the-art benchmark models, TP2 achieves 1% ~ 2% higher accuracy.

    Table and Figures | Reference | Related Articles | Metrics
    Application of intelligent optimization algorithms in supply chain network
    Xin ZHANG, Zhihui ZHAN
    Chinese Journal of Intelligent Science and Technology    2022, 4 (2): 174-183.   DOI: 10.11959/j.issn.2096-6652.202202
    Abstract364)   HTML60)    PDF(pc) (1042KB)(443)       Save

    Supply chain network connects members by the relationship of demand and supply and facilitates the coordination and cooperation among these members, which is particularly important in the global competition environment.The optimization and improvement of supply chain network can reduce the operating cost of enterprises, increase the income of enterprises and the customer satisfaction, and then improve the competitiveness of enterprises.Firstly, the optimization problems of supply chain network were analyzed, and these problems from several different aspects were classified, such as modeling characteristics, decision variable types, and scene features, so as to introduce the optimization problems in the existing research of supply chain network more clearly.Then, three frequently used intelligent optimization algorithms and their applications in supply chain network optimization were introduced and analyzed, such as genetic algorithm, ant colony optimization algorithm and particle swarm optimization algorithm.Finally, the future research of the optimization of supply chain network was prospected.

    Table and Figures | Reference | Related Articles | Metrics
    Parallel reasoning: a virtual-real interactive knowledge collaboration framework based on ACP approach
    Xiao WANG, Linyao YANG, Bin HU, Jiachen HOU
    Chinese Journal of Intelligent Science and Technology    2023, 5 (1): 69-82.   DOI: 10.11959/j.issn.2096-6652.202254
    Abstract200)   HTML16)    PDF(pc) (1141KB)(440)       Save

    Knowledge graph represents empirical knowledge based on structured triples, which can effectively describe the semantic relationships between real-world entities.Knowledge graph has become a critical standard technology of the new generation of artificial intelligence.The development, typical applications of multi-source knowledge graphs, and problems of knowledge collaboration were summarized.A multi-source knowledge graph collaboration framework based on ACP approach, i.e., parallel reasoning, was proposed, which realized the extraction, fusion, completion, and unbiased application of multi-source heterogeneous knowledge based on artificial systems, computational experiments, and parallel execution.In the end, simulation experiments were conducted on power grid dispatching to evaluate the effectiveness of parallel learning for solving the management and control problems of complex systems.

    Table and Figures | Reference | Related Articles | Metrics
    Key technologies and applications of intelligent guiding robots for epidemic prevention
    Teng WANG, Jing PAN, Lu DONG, Changyin SUN
    Chinese Journal of Intelligent Science and Technology    2021, 3 (2): 187-194.   DOI: 10.11959/j.issn.2096-6652.202119
    Abstract429)   HTML56)    PDF(pc) (2537KB)(438)       Save

    During the period of epidemic prevention, intelligent robots play a significant role in the fields of medical treatment, inspection and distribution, making more people realize the importance of robots in solving public health and safety problems.Focusing on the intelligent guiding robots, the key technologies and research status of the intelligent guiding robots were discussed, including robot disinfection, face recognition, speech interaction, autonomous localization, path planning.Then, taking TMiRob intelligent guiding robot as an example to discuss how these key technologies were implemented in reality.Finally, the challenges and development trends of intelligent guiding robots were presented.

    Table and Figures | Reference | Related Articles | Metrics
    Classification method of dermoscopic image based on hierarchical convolution neural network
    Hong SHAO, Mingkun ZHANG, Wencheng CUI
    Chinese Journal of Intelligent Science and Technology    2021, 3 (4): 474-481.   DOI: 10.11959/j.issn.2096-6652.202147
    Abstract162)   HTML21)    PDF(pc) (1079KB)(434)       Save

    In order to solve the problem of insufficient number of dermoscopic image and the imbalance of image data among various diseases, a classification method of dermoscopic image based on class weighted cross entropy loss function and hierarchical convolution neural network was proposed.Firstly, the dermoscopic image was processed by color constancy to eliminate the ambient light noise.Then, the hierarchical convolution neural network based on ResNet 50 was constructed, and the two classification and multi classification convolution neural network models were constructed respectively, and the class weighted cross entropy loss function was set according to the quantitative characteristics of the dermatoscopic image.The experimental results show that the method achieves good classification effect, and the classification accuracy reaches 85.94%.Compared with the improved classification model ResNet 50, the test accuracy is improved by 5.752%.

    Table and Figures | Reference | Related Articles | Metrics
    3D convolution-based image sequence feature extraction and self-attention for license plate recognition method
    Ganxiong ZENG, Xiao KE
    Chinese Journal of Intelligent Science and Technology    2021, 3 (3): 268-279.   DOI: 10.11959/j.issn.2096-6652.202128
    Abstract251)   HTML23)    PDF(pc) (10995KB)(433)       Save

    In recent years, neural networks based on self-attentive mechanism have been widely used in computer vision tasks.As the intelligent transportation system is widely used, the task difficulty of license plate recognition is increasing and the need for correct recognition is getting more pressing in the face of complex and changing traffic scenes.Therefore, a rectification-free license plate recognition method T-LPR based on self-attention was proposed.Firstly, the images were sliced and sequenced, and 3D convolution was used for feature extraction of the sliced sequences to obtain a sequence of image embedding vectors.Secondly, the sequence of embedding vectors was fed into an encoder based on Transformer Encoder, which learned the relationship between the individual embedding vectors and outputs the final encoding result.Finally, the final encoding result was classified by a classifier.Experimental results on several public datasets show that T-LPR proposed is very effective for recognizing license plates in all kinds of difficult scenarios.

    Table and Figures | Reference | Related Articles | Metrics
    Graph-regularized Bayesian broad learning system
    Junwei DUAN, Lincan XU, Yujuan QUAN, Long CHEN, C.L.Philip CHEN
    Chinese Journal of Intelligent Science and Technology    2022, 4 (1): 109-117.   DOI: 10.11959/j.issn.2096-6652.202203
    Abstract303)   HTML27)    PDF(pc) (1571KB)(431)       Save

    As a feed forward neural network, broad learning system (BLS) has attracted much attention because of its high accuracy, fast training speed, and the ability to effectively replace deep learning methods.However, it is sensitive to the number of feature nodes and the pseudo-inverse method is likely to result in the problem of over fitting for BLS model.To address the above issues, Bayesian inference and graph regularization was introduced in to the BLS model.By introducing the prior knowledge for Bayesian learning, the sparsity of the weights and the stability of the model could be effectively improved; while the graph information mining from the data could be fully considered to improve the generalization ability of the model by regularization.The UCI and NORB dataset were adopted for evaluating the performance of the proposed model.The experiment results demonstrated that the proposed graph-regularized Bayesian broad learning system model can further improve the accuracy of classification and has better stability.

    Table and Figures | Reference | Related Articles | Metrics
Copyright Information
Authorized by: China Association for Science and Technology
Sponsored by: China Institute of Communications
Posts and Telecom Press Co., Ltd.
Publisher: Beijing Xintong Media Co., Ltd.
Editor-in-Chief: Chen Shanzhi
Editorial Director: Wu Nada
Address: F8, You Dian Publisher Building, No.11, Chengshousi Road, Fengtai District, Beijing, China
Postal Code: 100078
Tel: 010-81055306
Mailing Code: 2-397
ISSN 1000-0801
CN 11-2103/TN
Total visitors:
Visitors of today:
Now online: