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|

Published in last 1 year

Please wait a minute...


For Selected: Download Citations EndNote Ris BibTeX Toggle Thumbnails

Select

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 Abstract （290）   HTML （8）    PDF（pc） （3799KB）（672）       Knowledge map    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

Select

Embodied intelligent driving: concept, methods, the state of the art and beyond Tianyu SHEN, Zhiwei LI, Lili FAN, Tingzhen ZHANG, Dandan TANG, Meihua ZHOU, Huaping LIU, Kunfeng WANG Chinese Journal of Intelligent Science and Technology    2024, 6 (1): 17-32.   DOI: 10.11959/j.issn.2096-6652.202404 Abstract （916）   HTML （134）    PDF（pc） （5059KB）（542）       Knowledge map    Save Embodied intelligence transcends the boundaries of traditional artificial intelligence by emphasizing the importance of interaction between machines and the physical world, facilitating the development of intelligent entities that combine hardware and software to learn from and adapt to their environments, thereby solving real-world problems. Inspired by this philosophy, the concept and framework of embodied intelligent driving are introduced, aiming at integrating the idea of embodied intelligence into the development and application of autonomous vehicles. Through the continuous interaction between physical agents, virtual agents, and real traffic scenes, intelligent driving systems can achieve precise perception, efficient execution, and autonomous evolution in complex scenes, enhancing the long-term adaptability of autonomous vehicles in open traffic environments. Based on the embodied intelligent driving framework, the relevant technologies are summarize and the development status and existing problems of such technologies are analyzed. Furthermore, thoughts and prospects in this field are demonstrated by exploring the important roles and application potential of virtual-real interactive data intelligence, foundation models and foundation intelligence, continuous learning and parallel intelligence. This paper is expected to promote innovative research and the application on embodied intelligent driving in a wider range of scenarios, and provide new ideas and solutions for the development of mobile robot systems such as intelligent vehicles. Table and Figures | Reference | Related Articles | Metrics

Select

Research on path planning of material transmission platform based on A* and dynamic window method Wei TANG, Xiao TAN, Yu SUN, Jiapeng YAN, Guangrui YAN Chinese Journal of Intelligent Science and Technology    2023, 5 (4): 515-524.   DOI: 10.11959/j.issn.2096-6652.202304 Abstract （189）   HTML （7）    PDF（pc） （4961KB）（538）       Knowledge map    Save Due to the problems of traditional material transfer equipment such as single working mode and inflexible adjustment of transfer path, intelligent material transfer system has gradually become a research hotspot in the field of logistics transmission. A path planning algorithm based on A* and dynamic window method was proposed for the modular material transmission platform, in order to improve its obstacle avoidance ability during the transfer process by flexibly adjusting the material transfer path. In the global path planning, the smoothness and static obstacle avoidance of the transmission path were realized by improving the A* weight function and integrating the Bezier curve and matrix interference theory. And by introducing the dynamic window method and extracting the global path key points as transition points for local path guidance of the transmission target, dynamic obstacle avoidance was realized when the path falling into local optimization was avoided. The research results showed that the path planning algorithm based on A* and dynamic window method could reduce the total global path length by 4.6% and the total path turning angle by 42.3%, while the dynamic obstacles could be effectively avoided in the local planning, which verified the rationality of the path planning algorithm. Table and Figures | Reference | Related Articles | Metrics

Select

Understanding of AI large model technology empowering the field of ships Zhaojie WANG, Lei YU, Jinhui XIONG, Huaiyu LI, Yunjun HAN, Zhen SHEN, Rui GUO, Yong ZHANG Chinese Journal of Intelligent Science and Technology    2024, 6 (1): 33-40.   DOI: 10.11959/j.issn.2096-6652.202408 Abstract （592）   HTML （77）    PDF（pc） （2187KB）（465）       Knowledge map    Save This paper summarized the focus, the development trend and the technical nature of AI large model research, analyzed the development strategy of AI at the national level, the urgent needs in the field of national defense, and the basis of applications in the field of ships. Then, from the aspects of the development of intelligent green ships, the innovation of defense equipment systems, the construction of management and control system and the transformation of knowledge-intensive industries, the broad prospect of applying AI large model technologies to the field of ships was discussed. The paper pointed out that the combination of AI large model technologies and concepts such as parallel systems, knowledge factories and digital employees can catalyze new designs, research and development and verification methods such as "AI design" + "digital factory" + "parallel verification". In addition, AI large model technology can inject intelligent and green elements into the shipping industry from aspects such as the hull design, ship construction, shipping management, energy conservation and emission reduction, can optimize ship functions, and improve efficiency, economy and environmental protection. Combined with new materials, new energy power and new information electronics and other technologies, AI large model technologies can shape the future marine defense equipment system based on new concepts and new patterns. At the same time, AI large model technologies can enable the construction of ship management and control systems, optimize planning, help scientific and technological innovation, improve management efficiency and improve the quality and efficiency of the corporations. In particular, with the establishment of knowledge factories in the field of ships, the training of digital employees, the promotion of industrial robots and the expansion of far-reaching sea fields, artificial intelligence large model technologies will be able to promote the organic combination and close collaboration of "natural persons", "robots" and "digital people" in the field of ships, and accelerate the upgrading of the ship industry to be knowledge intensive and intelligent intensive. This can transform the industrial ecology and value creation mode to be high-end, intelligent, and green, and realize a development mode that pays more attention to quality and efficiency for shipbuilding corporations. Table and Figures | Reference | Related Articles | Metrics

Select

Parallel drug systems: framework and methods based on large language models and three types of humans Fei LIN, Fei-Yue WANG, Yonglin TIAN, Xianting DING, Qinghua NI, Jing WANG, Le SHEN Chinese Journal of Intelligent Science and Technology    2024, 6 (1): 88-99.   DOI: 10.11959/j.issn.2096-6652.202409 Abstract （188）   HTML （45）    PDF（pc） （4853KB）（400）       Knowledge map    Save With the rapid development of the next generation of artificial intelligence technologies, such as the internet of things, large language models, and multimodal interactions, the traditional processes of drug research and production processing had been facing the challenges of an intelligent transition in recent years. In this context, this paper used the theory of parallel intelligence as the research philosophy and proposed a virtual-real interactive parallel drug systems, utilizing the ACP approach and large language models. It incorporated the concept of three types of beings—digital humans, robots, and natural persons—into the systems, providing a detailed discussion on the theoretical underpinnings, construction techniques, and potential application scenarios of the systems. The parallel drug systems covered the entire process of the pharmaceutical industry. For the drug development phase, it considered processes such as drug discovery, laboratory research, and clinical trials. In the production processing phase, it encompassed pharmaceutical manufacturing operations and system analysis predictions. The medical healthcare subsystem included personalized medication consultation, augmented reality drug guidance, and privacy security. The whole systems open up a digitized "drug space", aiming to establish a new paradigm for the drug systems and propel the revolution of intelligent medication. Table and Figures | Reference | Related Articles | Metrics

Select

RAG-PHI: RAG-driven parallel human and parallel intelligence Yonglin TIAN, Xingxia WANG, Yutong WANG, Jiangong WANG, Chao GUO, Lili FAN, Tianyu SHEN, Wansen WU, Hongmei ZHANG, Zhengqiu ZHU, Fei-Yue WANG Chinese Journal of Intelligent Science and Technology    2024, 6 (1): 41-51.   DOI: 10.11959/j.issn.2096-6652.2024015 Abstract （360）   HTML （30）    PDF（pc） （5743KB）（398）       Knowledge map    Save The advancement of large models offers new perspectives and foundation intelligence for building parallel human ecosystems comprised of biological humans, digital humans, and robotic humans. However, challenges such as time-limited updates to knowledge, inadequate specialized capabilities, and risks of information privacy leakage persist in the management and control of complex systems. To tackle these issues, a retrieval-augmented generation-driven parallel human and parallel intelligence framework (RAG-PHI) is introduced. It proposes to establish an open data platform that facilitates the integration of real-time, industry-specific, and private knowledge into the parallel human system. It develops dynamic routing and retrieval for context capture and the reconfiguration of parallel human capabilities, along with introducing context-aware prompt learning to enhance cognitive and behavioral skills. Furthermore, towards the organization and management, training and evaluation, operation and production of parallel human, the structures of parallel human community, parallel human school, and parallel human factory are proposed by the RAG-PHI architecture. These are designed to foster a parallel human ecosystem powered by RAG and large foundation models, thereby enhancing productivity in the age of intelligent industries. Table and Figures | Reference | Related Articles | Metrics

Select

Digital teachers and parallel education: A paradigm shift in teaching and learning after ChatGPT Fei-Yue WANG Chinese Journal of Intelligent Science and Technology    2023, 5 (4): 454-463.   DOI: 10.11959/j.issn.2096-6652.202348 Abstract （353）   HTML （114）    PDF（pc） （2449KB）（355）       Knowledge map    Save From its historical origin to present function, education is an inspiration and integral part of our quest for artificial intelligence(AI). We must ensure that teaching and education should be positioned as the first and most important field for research and development of intelligent science and technology. Otherwise increasingly complicated AI technology would not only remain unexplainable but also become ungovernable, and be manipulated easily by some minority of our human beings to harm the majority of us. Considering the current impact to all aspects of our society at the global level by ChatGPT and likewise artificial intelligence-generated content(AIGC)/artificial general intelligence(AGI) technologies, hereby we investigate a new approach to effectively deploy intelligent technology, especially digital teachers and parallel schools, for intelligent teaching and smart education. We hope this would lead to a paradigm shift in teaching and education for the benefits of humanity, and safe, healthy, sustainable development of our shared human community. Table and Figures | Reference | Related Articles | Metrics

Select

Parallel and digital police for new norm of public safety: from parallel security to peaceful China Fei-Yue WANG Chinese Journal of Intelligent Science and Technology    2023, 5 (4): 431-435.   DOI: 10.11959/j.issn.2096-6652.202347 Abstract （204）   HTML （69）    PDF（pc） （1519KB）（304）       Knowledge map    Save Due to the impact of artificial intelligence generated content technologies such as AlphaGo and ChatGPT, the governance of intelligent science and technology becomes a significant concern all over the world. This review addressed related issues by integrating traditional public safety management with new artificial intelligence (AI) technologies and provided an alternative philosophy and approach for safety, security and sustainability in the future society of AI. Table and Figures | Reference | Related Articles | Metrics

Select

From prompt engineering to generative artificial intelligence for large models: the state of the art and perspective Jun HUANG, Fei LIN, Jing YANG, Xingxia WANG, Qinghua NI, Yutong WANG, Yonglin TIAN, Juanjuan LI, Fei-Yue WANG Chinese Journal of Intelligent Science and Technology    2024, 6 (2): 115-133.   DOI: 10.11959/j.issn.2096-6652.202424 Abstract （276）   HTML （74）    PDF（pc） （3521KB）（275）       Knowledge map    Save Large language models and vision-language models have demonstrated significant potential in various downstream applications, making it become a research hotspot. However, the issues such as hallucinations and knowledge transfer impact the performance of these models. Firstly, this paper explores the fundamental principles of prompt engineering and alignment techniques, and proposes the concept of "prescriptive", which is based on optimizing prompts and expert feedback verification and can be adjusted in real-time. This aims to further enhance the performance of large language models in cross-domain applications. Secondly, the core technologies of prompt engineering, such as the principles of multi-step reasoning for handling complex tasks, are analyzed in depth. Additionally, the development status of prompt engineering is discussed based on practical applications in various fields. Finally, this paper summarizes the challenges faced by prompt engineering and looks into its future development directions. The development of prompt engineering in theory and application, provide comprehensive solutions for improving the performance of large models in practical applications. Table and Figures | Reference | Related Articles | Metrics

Select

Intelligent blockchains and blockchain intelligence: the infrastructure intelligence for DePIN Juanjuan LI, Sangtian GUAN, Rui QIN, Jiachen HOU, Fei-Yue WANG Chinese Journal of Intelligent Science and Technology    2024, 6 (1): 5-16.   DOI: 10.11959/j.issn.2096-6652.202403 Abstract （203）   HTML （45）    PDF（pc） （1969KB）（267）       Knowledge map    Save Decentralized physical infrastructure networks (DePIN) were an indispensable cornerstone for the upcoming digital society, transforming traditional infrastructure reliant on centralized control and management into a new type of infrastructure network driven by communities and autonomous governance. The deep integration of blockchain and artificial intelligence (AI) technologies played a key role in enabling this transformation. To this end, this paper first emphasized the organic combination of "AI for blockchain (AI4B)" and "blockchain for AI (B4AI)", forming a synergistic, bidirectional closed-loop circuit to construct the truly intelligent blockchains, thereby realizing a new paradigm of blockchain intelligence. Secondly, it proposed a novel technological architecture for intelligent blockchains: on one hand, embedding intelligence into every layer of traditional blockchain architecture to cultivate the blockchain intelligence ecosystem ranging from foundational intelligence to infrastructure intelligence and then to application intelligence; on the other hand, corresponding to the actual intelligent blockchain construction, artificial intelligent blockchain were built, and through their virtual-real feedback and parallel execution, the blockchain intelligence ecosystem evolved from static rule orientation to dynamic adaptive evolution. Then, it analyzed the core intelligent attributes of blockchain intelligence from the perspectives of intelligent contracts, decentralized identity, knowledge management, and autonomous governance. Lastly, it outlined the typical application scenarios of blockchain intelligence and the key challenges faced. This paper aims to actively promote the research and development of intelligent blockchains and blockchain intelligence technologies, laying the foundation for building the core infrastructure of the future digital age. Table and Figures | Reference | Related Articles | Metrics

Select

Online multi-stage Colonel Blotto game solving method for resource allocation under contested condition Shaofei CHEN, Mingwo ZOU, Xiaolong SU, Junren LUO, Junqiao FENG Chinese Journal of Intelligent Science and Technology    2023, 5 (4): 464-476.   DOI: 10.11959/j.issn.2096-6652.202341 Abstract （256）   HTML （19）    PDF（pc） （1475KB）（260）       Knowledge map    Save The allocation of combat resources on the future battlefield is a multi-stage confrontation problem with total resource budget constraints, which is characterized by high complexity of environment, dynamic uncertainty, and strong game confrontation. Based on the Blotto game model, the research firstly modelled the resource allocation problem in the multi-stage confrontation scenario as a two-level online Blotto game, then transformed the original problem into an online shortest path problem on a directed acyclic graph to realize the intuitive formulation of the resource allocation problem. The resource allocation problem was analyzed and solved by referring to the Lagrange game. In addition, the LagrangeBwK-Exp3-G algorithm was proposed to minimize the high probability regret of the resource allocation problem under the condition of multi-stage antagonism, and the high-probability regret bound of the algorithm on the time range T was obtained by mathematical derivation. Finally, a multi-channel power allocation experiment of satellite communication under the condition of multi-stage confrontation was designed to verify the good performance of LagrangeBwK-Exp3-G algorithm. Table and Figures | Reference | Related Articles | Metrics

Select

Research on 6G network scenario cognition based on knowledge graph Zhuoqiao ZHAO, Nan CHENG, Jie CHEN, Fangjiong CHEN, Changle LI Chinese Journal of Intelligent Science and Technology    2023, 5 (4): 494-504.   DOI: 10.11959/j.issn.2096-6652.202339 Abstract （309）   HTML （27）    PDF（pc） （3502KB）（252）       Knowledge map    Save The 6G network covers the entire space, air, ground, and sea. For diversified and personalized scenarios, the 6G network needs to provide customized services, that is, on-demand services. In order to realize on-demand services in all domains and scenarios, accurate, real-time, and intelligent cognition of the characteristics of the scenarios is an important prerequisite. How to enable the network to autonomously and intelligently recognize different scenarios and services, convert them into scenario-specific network key performance indicator (KPI), and further efficiently schedule network resources is a key problem that urgently needs to be solved. This paper applies the knowledge graph to the cognitive recognition of network scenarios, forms a standardized description of 6G network scenarios, and builds a knowledge graph based on the 6G scenario ontology. At the same time, a scene cognition reasoning method based on knowledge graph embedding is proposed, which realizes the embedding learning of graph nodes and relationships and reasons about scene feature nodes, achieving high accuracy. The method proposed in this paper helps to realize the autonomous control of the service life cycle of scene awareness, cognition, and on-demand services in the 6G full-scenario network, and has important innovation and guiding significance for improving the autonomy and intelligence of the next-generation network. Table and Figures | Reference | Related Articles | Metrics

Select

Vehicle detection and recognition algorithm based on function improvement of YOLOv3 Huajie SONG, Lei ZHOU Chinese Journal of Intelligent Science and Technology    2023, 5 (4): 535-542.   DOI: 10.11959/j.issn.2096-6652.202301 Abstract （157）   HTML （21）    PDF（pc） （3831KB）（211）       Knowledge map    Save YOLOv3 algorithm is characterized by high detection accuracy and high speed in the aspect of target detection and recognition. It is outstanding among similar algorithms, but there are still obvious problems. The loss operation of the wide and high part of the loss function of this algorithm is not obvious to the distinction between the big target and the small target, which leads to the problem that the loss calculation is not accurate enough and the prediction box size of the small target is not accurate. In view of this defect, the loss function of YOLOv3 algorithm was improved, the wide-height coordinate error was modified into the form of proportion, the non-maximum suppression method of the original model was improved and the overlap threshold was changed from the fixed value to the form of attenuation function. Finally, the model was applied to vehicle detection. The experimental results showed that the improved model improved the accuracy rate, recall rate and F1 value to different degrees while basically not affecting the vehicle detection speed, making the overall performance of the model better than the original YOLOv3 model. Table and Figures | Reference | Related Articles | Metrics

Select

Optimization of hospital operation based on parallel healthcare systems Xinzhao XIE, Yi YU, Ziyi WU, Kexin WANG, Xinyi LYU, Jing WANG, Yutong WANG, Yilun LIN, Fei-Yue WANG, Yan CHEN Chinese Journal of Intelligent Science and Technology    2024, 6 (1): 52-63.   DOI: 10.11959/j.issn.2096-6652.202406 Abstract （125）   HTML （23）    PDF（pc） （4201KB）（204）       Knowledge map    Save In the wave of digitization, the introduction of digital and parallel intelligence technologies was crucial to responding to the imbalance in the allocation of medical resources and the need for optimization of hospital management. Parallel healthcare systems can fully leverage the value of data with the help of artificial intelligence methods and optimize the solution through the interaction between reality and virtuality. The system comprised the distributed and trustworthy database, medicine-oriented operating system, medicine-oriented scenario system, and medicine-oriented large models, which enhanced data empowerment through data collection and circulation, thus facilitating trans-dimensional optimization of hospital operations. To better demonstrate the value of data in hospital operations, a method to quantify the value of data was proposed based on parallel healthcare systems and demonstrated with the help of a numerical experiment. The experimental results showed that parallel healthcare systems can effectively improve the hospital's social benefit by 47.45%, economic benefit by 13.82%, and operational efficiency by 21.90%, providing a global vision for decision-makers. Table and Figures | Reference | Related Articles | Metrics

Select

Parallel theaters: human-machine collaborative creation and intelligent management for theatrical art Qinghua NI, Chao GUO, Fei-Yue WANG Chinese Journal of Intelligent Science and Technology    2023, 5 (4): 436-445.   DOI: 10.11959/j.issn.2096-6652.202344 Abstract （226）   HTML （73）    PDF（pc） （2259KB）（203）       Knowledge map    Save Given the limitations of traditional theater production processes, which heavily rely on expert experience and manual labor, the theater industry faces a pressing demand for a transition from a paradigm primarily rooted in individual expertise and traditional competencies to one that harnesses intelligent technology and data-driven approaches. This transition aims to enhance production and operational efficiency while elevating artistic expression to address the diverse preferences of audiences more effectively. Within this context, this paper proposes the concept of "parallel theaters", specifically designed to facilitate collaborative human-machine creativity and intelligent management across the entire theater workflow. By establishing a comprehensive theater model, creating a computational experimentation platform for theatrical art and enabling a virtual-to-real feedback loop, the "parallel theaters" contributes to the intelligent and automated design and execution of critical theater production and management aspects, such as script writing, stage design, performance coordination, audience engagement and marketing. In addition, the paper explores the potential cross-disciplinary applications of "parallel theaters" in education and psychotherapy, analyzing its ability to foster the integration of the theater industry with other fields, thereby expanding the influence of the performing arts. As an avant-garde model for theater creation and management, "parallel theaters" opens new avenues for the industry in the intelligence era, promising enhanced efficiency, enriched artistic expression and a more diverse audience engagement. Table and Figures | Reference | Related Articles | Metrics

Select

Parallel financial budgeting: deep integration and intelligent services for complex business and finance Huaning CUI, Fei-Yue WANG, Juanjuan LI, Rui QIN, Ge WANG, Xiaolong LIANG, Jiachen HOU, Sangtian GUAN Chinese Journal of Intelligent Science and Technology    2023, 5 (4): 446-453.   DOI: 10.11959/j.issn.2096-6652.202346 Abstract （179）   HTML （24）    PDF（pc） （2000KB）（194）       Knowledge map    Save Financial budget management is an integral part of corporate governance, critically important for managing, controlling, coordinating and assessing internal resources. However, many enterprises still face challenges in financial budgeting, including unscientific target setting, slow execution control and ineffective budget outcome prediction. Although the advancement of digital and intelligent technologies offers strong support for mitigating these issues, it fail to address them fundamentally. Parallel intelligence theory, by creating artificial systems parallel to the real one and leveraging their virtual-real feedback and parallel execution, can realize description, prediction and prescription of financial budgeting, thereby enhancing the scientific accuracy of budget targets, the controllability of the budget process and the reliability of budget outcomes. This paper combined parallel intelligence theory with financial budgeting to propose a new paradigm of parallel financial budgeting. It provided a viable technological framework and theoretical guidance for the deep integration of business and finance as well as intelligent services supported by it in complex environments, fostering intelligent transformation and innovation in corporate financial budget management. The paper delineated the concept of parallel financial budgeting, presented its fundamental framework, and discussed its key characteristics and supporting technologies. Table and Figures | Reference | Related Articles | Metrics

Select

Parallel tourism:foundation intelligence driven smart trip services Tengchao ZHANG, Yonglin TIAN, Fei LIN, Qinghua NI, Ping SONG, Xingyuan DAI, Juanjuan LI, Naiqi WU, Dinglie LI, Fei-Yue WANG Chinese Journal of Intelligent Science and Technology    2024, 6 (2): 164-178.   DOI: 10.11959/j.issn.2096-6652.202420 Abstract （82）   HTML （11）    PDF（pc） （5139KB）（166）       Knowledge map    Save Tourism, as an activity that satisfies people's desire for diverse life experiences and knowledge, has had profound impacts on the economy, culture, and other fields. However, with the rapid development of technologies, such as the Internet of Things and multimodal large language models, traditional tourism is unable to meet the demand for intelligent and personalized travel experiences. To address this, this paper proposes an interactive personalized tourism service system based on the concept of parallel intelligence, utilizing the ACP approach and multimodal large language models. The system constructs a comprehensive tourism model and leverages retrieval-augmented generation and multi-agent collaboration systems to create a new paradigm for personalized tourism services. Additionally, this paper explores the application ecosystem of parallel tourism, expanding the tourism ecosystem from four aspects: clothing, food, accommodation and transportation. This paper analyzes the integration of other industries with personalized tourism services. Parallel tourism is poised to bring new possibilities for the development of the tourism service industry. Table and Figures | Reference | Related Articles | Metrics

Select

Knowledge making in education Chinese Journal of Intelligent Science and Technology    2024, 6 (1): 1-1.   Abstract （82）   HTML （37）    PDF（pc） （510KB）（157）       Knowledge map    Save Reference | Related Articles | Metrics

Select

Visual SLAM based on semantic information and geometric constraints in dynamic environment Jiaming LI, Mingyang XIE, Min ZHANG, Congqing WANG Chinese Journal of Intelligent Science and Technology    2023, 5 (4): 477-485.   DOI: 10.11959/j.issn.2096-6652.202342 Abstract （185）   HTML （16）    PDF（pc） （3289KB）（142）       Knowledge map    Save Most existing visual SLAM systems assume that the external environment is static, ignoring the influence of dynamic objects on the SLAM system. This assumption largely affects the accuracy and robustness of autonomous navigation. To address this issue, a dynamic SLAM system was proposed, which combined semantic information based on object detection and geometric information from multi-view geometry constraints by defining and discriminating the dynamic feature points in the system based on the moving probability. Experiment results on the public TUM dataset and our robot in real environment showed that, when comparing with ORB-SLAM2, the absolute trajectory error could be reduced larger than 94%, and the average relative position and attitude errors were reduced at least 41% and 40%, respectively, in high dynamic environments. It means that the proposed SLAM system effectively removes dynamic feature points, thus improving the localization accuracy and robustness of the visual SLAM system within high dynamic environments. Table and Figures | Reference | Related Articles | Metrics

Select

Point cloud registration method based on principal component analysis and feature map matching Weibin ZHENG, Guofu LIAN, Xueming ZHANG, Fang GUO Chinese Journal of Intelligent Science and Technology    2023, 5 (4): 543-552.   DOI: 10.11959/j.issn.2096-6652.202340 Abstract （259）   HTML （16）    PDF（pc） （5997KB）（136）       Knowledge map    Save Due to varying degrees of overlap in point cloud models, point cloud registration is prone to problems, such as feature matching errors and high difficulty in registration. Therefore, a point cloud registration method based on principal component analysis and feature map matching is proposed. Before registration, the principal component analysis method with spindle correction was used to adjust the initial pose, then the K-dimensional tree was established to search the overlapping area. Secondly, the fast point feature histograms features of the sampling points were calculated according to the overlapping area of the two-point cloud, and the point cloud feature graph matching and trimmed iterative closest point (TrICP) fine registration were performed. Registration experiments were carried out according to the existing datasets and the actual scanning model. The experimental results show that the method has good stability and higher accuracy, and the accuracy can be improved by more than 25% compared with other algorithms. Table and Figures | Reference | Related Articles | Metrics

Select

Attitude tracking control for quadrotor UAVs based on extremum seeking Dali GUO, Zhongyuan ZHAO, Zijuan LUO Chinese Journal of Intelligent Science and Technology    2023, 5 (4): 486-493.   DOI: 10.11959/j.issn.2096-6652.202337 Abstract （208）   HTML （14）    PDF（pc） （1672KB）（130）       Knowledge map    Save A robust control method based on extremum seeking is proposed for the attitude tracking problem of quadrotor UAV with uncertainty. Firstly, a nonlinear attitude model of a four rotor UAV was established, and considering the uncertainty of model parameters, a robust controller was designed to ensure the dynamic boundedness of tracking errors. Secondly, a learning-based controller was designed by combining a robust controller with a model-free learning algorithm, which automatically and iteratively adjusted the feedback gain of the robust controller and optimized the expected performance cost function online. Finally, numerical simulations were performed using MATLAB, which demonstrated a reduction of 0.246 in the steady-state tracking error of the proposed control method compared to the classical robust control method. This result confirms the robustness and superiority of the proposed method. Table and Figures | Reference | Related Articles | Metrics

Select

Preface to the book "Knowledge system and curriculum setting for undergraduate program of artificial intelligence" Chinese Journal of Intelligent Science and Technology    2024, 6 (1): 2-4.   Abstract （91）   HTML （28）    PDF（pc） （1803KB）（114）       Knowledge map    Save Table and Figures | Reference | Related Articles | Metrics

Select

Intelligent art factory: achieving creative automation through parallel art agents Chao GUO, Xingyuan DAI, Weilong LIAO, Jueyu QI, Yue LU, Qinghua NI, Lin WANG, Fei-Yue WANG Chinese Journal of Intelligent Science and Technology    2024, 6 (2): 179-188.   DOI: 10.11959/j.issn.2096-6652.202421 Abstract （87）   HTML （16）    PDF（pc） （2748KB）（113）       Knowledge map    Save In recent years, multimodal content generation models have rapidly evolved, significantly improving the efficiency of creative workers. However, existing methods still require expertise and cannot realize the automation of the whole creation process, making it difficult to widely serve the public. This paper proposes the concept and architecture of intelligent art factory, based on advanced foundation models and AI agent systems. Creative production oriented agents and digital teams, in conjunction with the basic workflow, functions, and methods of the intelligent art factory are established. The creative process automation and creative knowledge automation are achieved through collaboration among biological humans, digital humans, and robots in cyber-physical-social spaces. The intelligent art factory seeks to further liberate the creativity of the public. Table and Figures | Reference | Related Articles | Metrics

Select

Three-dimensional trajectory generation method for mobile phone dispensing Yang LIU, Jinlong SHI, Qiang QIAN, Zhen OU, Suqin BAI Chinese Journal of Intelligent Science and Technology    2024, 6 (1): 100-110.   DOI: 10.11959/j.issn.2096-6652.202407 Abstract （86）   HTML （7）    PDF（pc） （4009KB）（111）       Knowledge map    Save Due to the potential issue of non-rigid deformations in the manufacturing process of mobile phone frames, most existing dispensing automation methods struggled to acquire accurate dispensing positions. For this purpose, an innovative approach of dispensing trajectory generation was proposed, which addressed the limitations associated with previous methods. Firstly, the phone frames were scanned using a 3D laser profiler, then a point cloud registration algorithm based on the pose graph was introduced to reconstruct the point clouds of frames. The template-based approach was employed, and the dispensing trajectory for template was manually annotated. Subsequently, the template was aligned with the target by a non-rigid registration algorithm based on the deformation graph, thereby the transformed trajectory was obtained. Furthermore, a trajectory refinement strategy was presented to generate the robust, accurate dispensing trajectory of the target. Extensive experiments demonstrate that the errors of the generated dispensing trajectories were consistently below 0.01 mm, and the speed can meet the real-time requirement of practical applications. Table and Figures | Reference | Related Articles | Metrics

Select

Parallel music: human-machine hybrid music creation and performance in the era of large models Qinghua NI, Yue LU, Fei LIN, Jun HUANG, Yijin WANG, Weihua LIN, Fei-Yue WANG Chinese Journal of Intelligent Science and Technology    2024, 6 (2): 150-163.   DOI: 10.11959/j.issn.2096-6652.202423 Abstract （77）   HTML （19）    PDF（pc） （5515KB）（108）       Knowledge map    Save As foundational models in specialized fields like sound art have rapidly advanced, the convergence of artificial intelligence with music creation and performance has become increasingly pronounced. A novel framework for music creation and performance called the parallel music system was proposed. Grounded in parallel systems theory and the artificial system, computational experiments, parallel execution (ACP) approach, this system stimulates the real-world music creation and performance environments to build highly authentic virtual scenarios. It facilitates real-time, seamless interactions between the virtual and real music systems and outlines the technological strategies for music creation and performance in the era of large models, incorporating a hybrid team of humans, digital beings, and robots. Additionally, the theoretical framework of parallel music and its critical technologies are discussed, the innovative contributions and potential in the modern music field are evaluated, the applications in scenarios like music generation and music therapy are examined. The objective is to harness the emerging AI technologies of the large model era to enhance traditional paths in music creation, drive technological advancements in music performance, unlock the creative potential of musicians, and offer fresh perspectives and inspirations for music creation and performance in the new era. Table and Figures | Reference | Related Articles | Metrics

Select

Federated services: smart service paradigm based on distributed data co-governance Xiaofeng JIA, Rui QIN, Shouwen WANG, Hongwei QI, Fei-Yue WANG, Juanjuan LI, Min ZHANG, Xiaolong LIANG Chinese Journal of Intelligent Science and Technology    2024, 6 (2): 210-219.   DOI: 10.11959/j.issn.2096-6652.202416 Abstract （53）   HTML （8）    PDF（pc） （3131KB）（107）       Knowledge map    Save The acceleration of digital transformation has made data a core element driving technological innovation and economic growth. However, the widespread phenomenon of data island severely hinders data circulation and collaboration across different fields and organizations, making it difficult for data supply to meet the diverse needs of users, thus creating a dilemma in matching data supply and demand. Serving as the core link in the federated ecology and an important window for external empowerment, federated services provide an innovative solution for data circulation and utilization under the principle of distributed data co-governance, thereby enabling the intelligent matching of supply and demand. Firstly, this paper delves into the pivotal role of federated services within the federated ecology, and examines the relationship between federated services and federated ecology's key components. Secondly, it presents a five-layer basic framework of federated services and discusses its core advantages. On this basis, the paper proposes the key supporting technologies for federated services, including blockchain and decentralized autonomous organizations and operations, large language models and scenario engineering, distributed computing and edge computing, as well as encryption technology and privacy computing. Finally, taking the supply-demand matching problem of data and scenarios as a case study, the paper illustrates how federated services achieve intelligent matching of demand and supply. The federated services proposed in this paper holds significant implications for constructing a smart service paradigm based on distributed data co-governance. Table and Figures | Reference | Related Articles | Metrics

Select

Research on the explainability of vertical federated learning models based on human-in-the-loop Xiaohuan LI, Junbai ZHENG, Jiawen KANG, Jin YE, Qian CHEN Chinese Journal of Intelligent Science and Technology    2024, 6 (1): 64-75.   DOI: 10.11959/j.issn.2096-6652.202345 Abstract （128）   HTML （13）    PDF（pc） （3438KB）（99）       Knowledge map    Save Vertical federated learning (VFL) is commonly used for cross-domain data sharing in high-risk scenarios. Users need to understand and trust model decisions to promote the application of models. Existing research primarily focuses on the trade-off between explainability and privacy within VFL, and fails to fully meet the needs of users for establishing trust and fine-tuning models. To address these issues, we proposed an explainable vertical federated learning method based on human-in-the-loop (XVFL-HITL), which incorporated user feedback into the VFL's Shapley value-based explainability approach through a distributed HITL structure, using the knowledge of all VFL participants to correct training data and enhance model performance. Furthermore, considering privacy concerns, this paper employed the additive principle of Shapley values to integrate the feature contribution values of all entities other than the target participant into an aggregated measure, which effectively protected the feature privacy of each participant. Experimental results indicated that on benchmark data, the explainability results of XVFL-HITL were effective and could well protect the feature privacy of user. Additionally, compared to VFL-Random and VFL-Shapley, the model accuracy of XVFL-HITL improved by approximately 14% and 11%, respectively. Table and Figures | Reference | Related Articles | Metrics

Select

Diagnostic of breast tumors based on improved EfficientNet Zhenqi FANG, Xue LI, Hong MO Chinese Journal of Intelligent Science and Technology    2023, 5 (4): 505-514.   DOI: 10.11959/j.issn.2096-6652.202343 Abstract （141）   HTML （11）    PDF（pc） （5348KB）（91）       Knowledge map    Save Breast tumors adversely affect the holistic well-being of women. Histopathological images are a critical substantiation for doctors to diagnose breast tumor types. The structure of various types of tumor cells exhibits significant correlations, thereby posing challenges to the diagnosis using conventional methods. In this work, the enhanced EfficientNet was employed for the diagnosis of breast tumors, which enabled the network model to learn the features of the disease automatically and improve the accuracy of the diagnosis of breast tumor types. Firstly, the convolutional block attention module was used to extract effective features. Secondly, the group convolution and channel shuffle operations were introduced to improve the feature representation ability of the model. Thirdly, the Hard-Swish activation function was applied to improve the convergence speed of the model. Finally, Experiments showed that the improved EfficientNet network achieved 98.4% accuracy in eight classifications on the BreakHis dataset, which was expected to act a decision aid tool in breast tumor diagnostic research. Table and Figures | Reference | Related Articles | Metrics

Select

Multimodal individual emotion recognition with joint labeling based on integrated learning and clustering Shanjun KE, Chengyang NIE, Yumiao WANG, Bangsheng HE Chinese Journal of Intelligent Science and Technology    2024, 6 (1): 76-87.   DOI: 10.11959/j.issn.2096-6652.202401 Abstract （137）   HTML （21）    PDF（pc） （5075KB）（91）       Knowledge map    Save To address the low recognition accuracy of generic emotion recognition models when faced with different individuals, a multimodal individual emotion recognition technique based on joint labelling with integrated learning and clustering was proposed. The method first trained a generic emotion recognition model based on a public dataset, then anallysed the distributional differences between the data in the public dataset and the unlabelled data of individuals, and established a cross-domain model for predicting and labelling pseudo-labels of individual data. At the same time, the individual data were weighted clustered and labelled with cluster labels, and the cluster labels were used to jointly label with pseudo-labels, and high confidence samples were screened to further train the generic model to obtain a personalized emotion recognition model. Using this method to annotate these data with the experimentally collected data of 3 emotions from 3 subjects, the final optimized personalized model achieved an average recognition accuracy of more than 80% for the 3 emotions, which was at least a 35% improvement compared to the original generic model. Table and Figures | Reference | Related Articles | Metrics

Select

UAVAI-YOLO: dense small target detection algorithm based on UAV aerial images Zhiqian HE, Lijie CAO Chinese Journal of Intelligent Science and Technology    2024, 6 (2): 262-271.   DOI: 10.11959/j.issn.2096-6652.202422 Abstract （98）   HTML （20）    PDF（pc） （5142KB）（73）       Knowledge map    Save An improved UAVAI-YOLO model was proposed to address the problem of poor target detection in UAV aerial images. Firstly, in order to obtain richer semantic information for the model, the original convolution of the C2f module of the original backbone part was replaced with the improved DCN convolution. Secondly, in order to increase the P2 feature layer without increasing the number of model parameters, the Conv_C module was proposed to downscale the output channel of the backbone network, and at the same time, because of avoiding the loss of semantic information due to channel downsizing, the original convolution of the C2f module in the neck part was replaced by the improved ODConv dynamic convolution. Then, the BIFPN module was introduced to make full use of the contextual semantic information. Finally, Wise-IoU was used to replace the original loss function to improve the accuracy of the model target detection frame. Experimental results on the publicly available VisDrone2019 dataset and UAVDT dataset showed that the UAVAI-YOLO model improves 4.4% and 1.1% compared to the original YOLOv8n model mAP0.5, respectively, high detectability accuracy compared to other mainstream object detection models. Table and Figures | Reference | Related Articles | Metrics

Select

Reward shaping based reinforcement learning for intelligent missile penetration attack strategy planning Junren LUO, Guo LIU, Jiongming SU, Wanpeng ZHANG, Jing CHEN Chinese Journal of Intelligent Science and Technology    2024, 6 (2): 189-200.   DOI: 10.11959/j.issn.2096-6652.202411 Abstract （64）   HTML （11）    PDF（pc） （3089KB）（57）       Knowledge map    Save Facing the future requirements of distributed warfare at sea, the strategic planning of missile penetration is firstly analyzed based on the background of intelligent missile salvo penetration against surface ships in distributed warfare scenario. Secondly, a strategic planning method of intelligent missile penetration based on reward-shaping reinforcement learning is designed by using multi-class reward function. Then, the operation scenario of the missile penetration ship is constructed on the Mozi joint operation simulation system. The comparison experiment shows that the success rate of the intelligent missile penetration attack controlled by the model learned by the reward molding method is 79%, which verifies the effectiveness of the reward-based reinforcement learning method. Finally, after action review, it is found that there are emerging four kinds of penetration strategies of intelligent missiles in the reward shaping experiment, including concentrated and roundabout attack, scattered penetration multi-direction attack, group delay attack and cruise detection guide attack. Table and Figures | Reference | Related Articles | Metrics

Select

Knowledge is far more than true belief in vision Wenbo ZHENG, Fei-Yue WANG Chinese Journal of Intelligent Science and Technology    2024, 6 (2): 111-114.   DOI: 10.11959/j.issn.2096-6652.202418 Abstract （60）   HTML （18）    PDF（pc） （1670KB）（53）       Knowledge map    Save Computational knowledge vision is emphasized as a novel perspective or field in this paper. Computational knowledge vision injects a priori knowledge into a visual perception model so that the model gains comprehension, which enables the model to learn and reason effectively to a certain extent like an ordinary adult. Computational knowledge vision not only provides a "bridge" between human priori knowledge and perceptual visual machines, but also systematically adapts to different levels of visual tasks on this "bridge". In addition, this paper proposes the visual hierarchy and its connection to knowledge, stating that knowledge is a justified true belief. Finally, our recent work is summarized and a new direction is proposed, which suggests that knowledge is also a thought framework in vision. Table and Figures | Reference | Related Articles | Metrics

Select

Research on OAC model for quantitative trading of digital currency Bo XU, Yijun HE, Xiangxia LI Chinese Journal of Intelligent Science and Technology    2024, 6 (2): 220-231.   DOI: 10.11959/j.issn.2096-6652.202402 Abstract （95）   HTML （32）    PDF（pc） （4090KB）（49）       Knowledge map    Save In response to the challenges encountered in quantitative trading of digital currencies, characterized by the presence of a multitude of intricate factors and a high-dimensional factor state space, an enhanced optimistic actor-critic(OAC) model, referred to as OAC_LSTM_ATT, had been proposed. This model incorporated long short-term memory (LSTM) and a multi-head attention mechanism to optimize the network architecture of OAC, thereby augmenting its capacity for modeling time-series data and generalization. Through this integration, the intelligent agent operating in the quantitative trading environment was capable of making more adaptable and precise trading decisions, consequently elevating the quality and efficacy of trading strategies. Experimental findings revealed that, in the Bitcoin market, the cumulative return achieved was 16.36%, with a maximum drawdown of 9.08%, a Sharpe ratio of 0.014, and a volatility of 13.09%. Corresponding metrics in the Ethereum market amounted to 16.30%, 8.56%, 0.014, and 13.42%. When compared to models such as PPO, LSTM_PPO, A2C, OAC_LSTM_ATT demonstrates superior performance in terms of both effectiveness and stability, thereby offering valuable insights for the development of quantitative trading strategies. Table and Figures | Reference | Related Articles | Metrics

Select

AI agent-driven intelligent management and control of parallel museums Yue LU, Chao GUO, Qinghua NI, Huabiao LI, Chunfa WANG, Fei-Yue WANG Chinese Journal of Intelligent Science and Technology    2024, 6 (2): 134-149.   DOI: 10.11959/j.issn.2096-6652.202415 Abstract （59）   HTML （8）    PDF（pc） （7083KB）（49）       Knowledge map    Save Museums are responsible for the preservation, research and dissemination of vast cultural heritage. With the rapid development of artificial intelligence technology, society's demand for the intelligence level of museums is increasing. General artificial intelligence represented by large language models and artificial intelligence agents has achieved milestone progress, providing new technological support for the construction of museums in the new era. The artificial intelligence agent-driven human-machine hybrid museum management architecture was proposed based on parallel intelligence and parallel museum systems, thereby further leveraging the framework of parallel interaction and parallel execution of parallel museums. The system architecture and key technologies of intelligent agent-driven parallel museums were elaborated. Parallel execution and interaction optimization between artificial museums and real museums were realized by building a production factory and operation platform for intelligent agents based on artificial systems, using computational experiments to model museums and train intelligent agents, and constructing a human-machine hybrid intelligent agent team composed of biological workers, digital workers, and robotic workers. Finally, typical cases of intelligent agent-driven parallel museums were introduced. Table and Figures | Reference | Related Articles | Metrics

Select

Intelligent testing method for railway CTC interface data based on fuzzy natural language processing Yuantao JIAO, Runmei LI, Jian WANG Chinese Journal of Intelligent Science and Technology    2024, 6 (2): 201-209.   DOI: 10.11959/j.issn.2096-6652.202419 Abstract （58）   HTML （15）    PDF（pc） （3716KB）（42）       Knowledge map    Save Fuzzy natural language processing applies fuzzy theoretical knowledge to the task of natural language processing (NLP). With the continuous development of large language model and artificial intelligence, research on text data continues to deepen. As a large and complex system, the interface data between various subsystems and server software are stored and transmitted in log text format. Due to its large number of texts and miscellaneous text types, a fuzzy NLP method was proposed to solve the problem of manual testing the interface data of centralized traffic control (CTC) system. The fuzzy C-means (FCM) clustering algorithm divided the log text into different label categories, which was used as the label input for named entity recognition in NLP tasks, and BERT was introduced on the traditional BiLSTM-CRF model for text encoding, which understood the relationship between texts more accurately and improved the accuracy of text recognition. An intelligent verification tool for log-text interface testing of railway CTC system was presented based on an improved training model, which enhanced the current manual testing process of CTC system, assisted testing staff in verifying the interface testing, and increased the level of intelligence and automation in testing work. Table and Figures | Reference | Related Articles | Metrics

Select

Neural architecture search for 3D model classification based on adaptive smoothness strategy Peng ZHOU, Jun YANG Chinese Journal of Intelligent Science and Technology    2024, 6 (2): 272-280.   DOI: 10.11959/j.issn.2096-6652.202417 Abstract （32）   HTML （8）    PDF（pc） （3972KB）（42）       Knowledge map    Save Aiming at the problem of poor generalization ability in hand-crafted architectures that overly rely on expert experience, a neural network architecture search method with an adaptive smoothness strategy was proposed. Firstly, an improved candidate operation selection strategy and a continuous relaxation method were used to convert discrete search space into continuous space, and a weight-sharing mechanism was employed to enhance search efficiency. Secondly, a regularization operation with an adaptive smoothness strategy was added to the loss function, whose smoothness degree was controlled by a temperature parameter. Finally, the loss function was calculated using an exponential normalization method to avoid loss value overflow. Experimental results on 3D point cloud datasets and protein-protein interaction datasets showed that the proposed method achieved higher classification accuracy and more stable performance under the same training samples and iterations. Table and Figures | Reference | Related Articles | Metrics

Select

Spatiotemporal prediction of nitrogen dioxide concentration: an interval type-2 intuitionistic fuzzy neural network approach Liang ZHAO, Mengwei LI, Yuqing ZHENG, Beibei CUI, Xianchao ZHU Chinese Journal of Intelligent Science and Technology    2024, 6 (2): 253-261.   DOI: 10.11959/j.issn.2096-6652.202425 Abstract （39）   HTML （12）    PDF（pc） （2130KB）（35）       Knowledge map    Save The concentration of nitrogen dioxide (NO2) in the air significantly affects environmental protection and public health. Current methods for NO2 concentration prediction lack sufficient characterization of spatiotemporal correlations. Therefore, this study proposes a novel approach using interval type-2 intuitionistic fuzzy neural networks (IT2IFNNs) for spatiotemporal prediction of NO2 concentrations. Firstly, the framework of IT2IFNNs is elucidated, incorporating variable coefficient weighting for its membership and non-membership outputs, and employing a random vector functional-link neural network (RVFLNN) as the rule consequent. Secondly, a hierarchical clustering algorithm is employed to determine the fuzzy rule base and optimize the output weight values of the network consequents using least squares estimation. Finally, numerical validation is conducted using real NO2 concentration data collected in Beijing from January to March 2018. Experimental results demonstrate that compared to existing methods, the proposed approach achieves superior prediction accuracy and efficiency in both short-term and long-term spatiotemporal prediction tasks. Table and Figures | Reference | Related Articles | Metrics

Select

Low scaling factor Seam Carving tamper detection algorithm with hybrid attention Jie ZHAO, Haochan CHANG, Bin WU Chinese Journal of Intelligent Science and Technology    2024, 6 (2): 244-252.   DOI: 10.11959/j.issn.2096-6652.202414 Abstract （27）   HTML （0）    PDF（pc） （3451KB）（29）       Knowledge map    Save The existing seam carving tamper detection algorithms have the problems of low detection accuracy and weak robustness for the case of low scaling factor. A seam carving tamper detection algorithm integrated with hybrid attention mechanism is proposed. Firstly, BayarConv2D constrained convolution is used to preprocess the image, fully learn the noise characteristics of the image, and fuse the features with RGB image through matrix multiplication. Then, ResNet is used as the backbone network for feature learning, and the residual propagation and residual feedback mechanisms are introduced to highlight the operation traces of seam carving. Finally, the hybrid attention mechanism is used to simultaneously extract the features between adjacent locations and channels to better capture the global features, and then input them into the full connection layer to achieve classification. The experimental results show that on the BOSSBase1.01 dataset, when the scaling factor is 1% and 9%, the detection accuracy of the proposed method reaches 89.48% and 97.94% respectively, which is better than existing mainstream methods. At the same time, it has lower computational complexity and better robustness, and can resist JPEG compression attacks. Table and Figures | Reference | Related Articles | Metrics

Select

A predictive model of cognitive impairment in Parkinson's disease based on multivariate logistic regression Mengru BA, Xiaohong YIN, Shaoyuan LI Chinese Journal of Intelligent Science and Technology    2024, 6 (2): 232-243.   DOI: 10.11959/j.issn.2096-6652.202413 Abstract （31）   HTML （7）    PDF（pc） （4504KB）（29）       Knowledge map    Save Parkinson's disease (PD) patients were often accompanied by cognitive impairment, which seriously affected the quality of life, so the over-prediction of cognitive impairment in Parkinson's disease was crucial for clinical diagnosis and intervention. However, Parkinson's disease was affected by the coupling of multivariate factors, such as age, gender, and disease duration, which made the overprediction of cognitive impairment a serious challenge. Aiming at the multivariate coupling characteristics of cognitive impairment in Parkinson's disease, in this study, multivariate logistic regression was used to construct a novel column-linear graphical model aiming at over-predicting the risk of cognitive impairment (CI) in Parkinson's disease patients. First, the least absolute shrinkage and selection operator (LASSO) algorithm was applied to analyze the risk factors that may affect the cognitive ability of patients, and the clinical variables with high correlation were screened out. Second, multivariate logistic regression was used to analyze the correlation between variables and construct a visualized novel column-line diagram model to achieve the risk over prediction of cognitive impairment in Parkinson's disease. Finally, the results of model performance evaluation show that the novel cognitive impairment prediction model proposed in this paper has good accuracy, consistency and clinical practicability, which can significantly improve the diagnostic efficiency of clinicians; in addition, the model also realizes the visual comparison and analysis of the number and distribution of patients with different values of the same predictor, which can assist clinicians in formulating personalized healthcare management and consulting programs according to the individual risk of each patient, and help to start the intervention and treatment of the patients at an early stage, and it has a certain clinical diagnostic value. Table and Figures | Reference | Related Articles | Metrics