模式识别与人工智能
Home      About Journal      Editorial Board      Instructions      Ethics Statement      Contact Us                   中文
Pattern Recognition and Artificial Intelligence
22 Judgement and Disposal of Academic Misconduct Article
22 Copyright Transfer Agreement
22 Proof of Confidentiality
22 Requirements for Electronic Version
More....
22 Chinese Association of Automation
22 National ResearchCenter for Intelligent Computing System
22 Institute of Intelligent Machines,Chinese Academy of Sciences
More....
 
 
2024 Vol.37 Issue.2, Published 2024-02-25

Researches and Applications    Surveys and Reviews   
   
Surveys and Reviews
95 Overview of NSFC Project Application and Funding Status of Artificial Intelligence Field(F06) in 2023
XIE Guo, WANG Le, SONG Heping, XIAO Bin, LIAO Qing, WANG Zhiheng, WU Guozheng
This paper presents a statistical analysis of the application and funding status of some projects in the two program series of "Talent" and "Research" under the National Natural Science Foundation(NSFC) in the field of artificial intelligence(application code F06) for the year 2023. The application code, the distribution of the supporting institutions and their trends over the past five years are analyzed. Additionally, the evaluation status of the field categorized by scientific problem attributes is introduced, as well as the relevant evaluation principles and measures in this field. Finally, the paper concludes with a summary and outlook, aiming at providing the reference for the relevant researchers to learn the research hotspots and future directions of this field.
2024 Vol. 37 (2): 95-105 [Abstract] ( 626 ) [HTML 1KB] [ PDF 939KB] ( 1116 )
106 A Review of Knowledge Space Theory
LI Jinhai, ZHANG Rui, ZHI Huilai, SUN Wen

Knowledge space theory is a scientific method for studying educational principles, and it yields a series of research findings. This paper is intended to comprehensively review the research efforts on knowledge space theory. Firstly, the methods and principles of constructing knowledge structures are elaborated, the research contents related to the wellgradedness are introduced, and their importance to the study of knowledge space theory is underscored. The related work of surmise relation is summarized, as well as the research methods between problems and between items. Then, research progress of competence-based knowledge space theory is delineated from three aspects: skill maps, skill functions and competence-performance approaches. Furthermore, the researches combinating knowledge space theory with probability models and granular computing are outlined, including the application of knowledge space theory in assisted learning and adaptive testing. Finally, the key scientific issues are explored in the above research fields and some preliminary research ideas are provided, providing beneficial references for subsequent studies in this field.

2024 Vol. 37 (2): 106-127 [Abstract] ( 360 ) [HTML 1KB] [ PDF 1044KB] ( 794 )
128 Review of Deep Learning-Based Video Anomaly Detection
JI Genlin, QI Xiaosha, WANG Jiaqi
The study of video anomaly detection involves the methods such as probabilistic statistics, machine learning and deep learning. The purpose of this paper is to synthesize the research results of the author's group and other advanced researches with a focus on deep learning-based video anomaly detection methods, comprehensively discussing the background, challenges and solutions in this field. Most relevant papers in the field are synthesized and systematically analyzed to provide the scholars with a fundamental understanding of the current research progress. The deep learning-based video anomaly detection methods are classified and analyzed. The network model selection for different methods is summarized. The commonly used datasets and performance evaluation indexes are introduced in detail. The advantages of various methods are highlighted by the performance comparison, and the future research directions and application scenarios in the field of video anomaly detection are deeply explored and forecasted.
2024 Vol. 37 (2): 128-143 [Abstract] ( 820 ) [HTML 1KB] [ PDF 1466KB] ( 1211 )
144 Intelligent Analysis of Childhood Epileptic Syndrome: Overview and Prospect
ZHENG Runze, FENG Yuanmeng, HU Dinghan, JIANG Tiejia, GAO Feng, CAO Jiuwen

The intelligent analysis of childhood epileptic syndrome refers to the research which aims at addressing clinical and prognostic management issues by data-driven methods such as statistical analysis and machine learning to explore clinically effective biomarkers and construct corresponding expert systems. Firstly, the definition, seizure types and classification of childhood epileptic syndrome are briefly introduced. Then, the advantages and disadvantages of the framework and typical methods of the intelligent analysis of childhood epileptic syndrome based on scalp electroencephalogram are reviewed, including data collection and preprocessing, feature extraction, decision-making systems, and expert systems. Specifically, the expert systems are divided into specific waveform detection systems, diagnostic classification systems, seizure detection systems, seizure prediction systems and quantitative assessment systems with a comprehensive summary and theoretical explanation. Finally, with the consideration of the limitations and challenges of the existing research in the field of intelligent analysis of childhood epileptic syndrome, future research directions are proposed to advance the study of intelligent analysis systems for childhood epileptic syndrome and alleviate the negative impact of the disease.

2024 Vol. 37 (2): 144-161 [Abstract] ( 287 ) [HTML 1KB] [ PDF 2821KB] ( 787 )
Researches and Applications
162 Model for Small Object Detection in Aerial Photography Based on Low Dimensional Image Feature Fusion
CAI Fenghuang, ZHANG Jiaxiang, HUANG Jie
To address the challenges of significant changes in the field of view and complex spatiotemporal information in unmanned aerial vehicle aerial image target detection, a model for small object detection in aerial photography based on low dimensional image feature fusion is presented grounded on the YOLOv5(you only look once version 5) architecture. Coordinate attention is introduced to improve the inverted residuals of MobileNetV3, thereby increasing the spatial dimension information of images while reducing parameters of the model. The YOLOv5 feature pyramid network structure is improved to incorporate feature images from shallow networks. The ability of the model to represent low-dimensional effective information of images is enhanced, and consequently the detection accuracy of the proposed model for small objects is improved. To reduce the impact of complex background in the image, the parameter-free average attention module is introduced to focus on both spatial attention and channel attention. VariFocal Loss is adopted to reduce the weight proportion of negative samples in the training process. Experiments on VisDrone dataset demonstrate the effectiveness of the proposed model. The detection accuracy is effectively improved while the model complexity is significantly reduced.
2024 Vol. 37 (2): 162-171 [Abstract] ( 423 ) [HTML 1KB] [ PDF 2828KB] ( 924 )
172 Quantum Interference Based Duet-Feature Text Representation Model
GAO Hui, ZHANG Peng, ZHANG Jing
In the field of information retrieval, quantum interference theory is applied to the study of core issues such as document relevance and order effects, aiming at modeling quantum-like interference phenomena caused by user cognition. Based on the language understanding task, the mathematical tools of quantum theory are utilized to analyze the semantic evolution phenomenon in the semantic combination process. A quantum interference based duet-feature text representation model(QDTM) is proposed. The reduced density matrix is taken as the core component of language representation to effectively model semantic interference information at the dimension-level. On this basis, a model structure is constructed to capture global and local feature information, meeting the semantic feature requirements of different granularities in the language understanding process. Experiments on text classification datasets and question and answering datasets show that QDTM outperforms quantum-inspired language models and neural network text matching models.
2024 Vol. 37 (2): 172-180 [Abstract] ( 230 ) [HTML 1KB] [ PDF 647KB] ( 802 )
181 BERT and CNN-Based Deleterious Splicing Mutation Prediction Method
SONG Chengcheng, ZHAO Yiran, LI Xiaoyan, XIA Junfeng
A key challenge in genetic diagnosis is the assessment of pathogenic genetic mutations related to splicing. Existing predictive tools for pathogenic splicing mutations are mostly based on traditional machine learning methods, heavily relying on manually extracted splicing features. Thereby the predictive performance is limited, especially for non-canonical splicing mutation producing poor performance. Therefore, a bidirectional encoder representations from transformers(BERT) and convolutional neural network(CNN)-based deleterious splicing mutation prediction method(BCsplice) is proposed. The BERT module in BCsplice comprehensively extracts contextual information of sequences. While combined with CNN that extracts local features, BERT module can adequately learn the semantic information of sequences and predict the pathogenicity of splicing mutations. The impact of non-canonical splicing mutations often relies more on deep semantic information of sequence context. By combining and extracting the multi-level semantic information of BERT through CNN, rich information representations can be obtained, aiding in the identification of non-canonical splicing mutations. Comparative experiments demonstrate the superior performance of BCsplice, especially exhibiting certain performance advantages in non-canonical splicing regions, and it contributes to the identification of pathogenic splicing mutations and clinical genetic diagnosis.
2024 Vol. 37 (2): 181-190 [Abstract] ( 344 ) [HTML 1KB] [ PDF 819KB] ( 720 )
模式识别与人工智能
 

Supervised by
China Association for Science and Technology
Sponsored by
Chinese Association of Automation
NationalResearchCenter for Intelligent Computing System
Institute of Intelligent Machines, Chinese Academy of Sciences
Published by
Science Press
 
Copyright © 2010 Editorial Office of Pattern Recognition and Artificial Intelligence
Address: No.350 Shushanhu Road, Hefei, Anhui Province, P.R. China Tel: 0551-65591176 Fax:0551-65591176 Email: bjb@iim.ac.cn
Supported by Beijing Magtech  Email:support@magtech.com.cn