Search | Engineering

Subscribe Submit

Home Journals Focus Achievement Fronts About Us 中文版

Resource Type

Journal Article 62

Year

2023 4

2022 5

2021 15

2020 6

2019 4

2018 1

2017 5

2016 1

2013 2

2012 2

2011 2

2009 1

2008 2

2007 2

2006 2

2005 1

2004 1

2003 3

2002 1

2000 1

open ︾

Keywords

Artificial intelligence 2

Deep learning 2

Event-triggered control 2

Synthesis reasoning 2

diagnosis 2

emergency management 2

Abnormal event detection network 1

Abnormal events detection 1

Abstract thinking 1

Abstraction 1

Adaptive control law 1

Adaptive network fuzzy inference system 1

Additive white Gaussian noise 1

Age of information (AoI) 1

Artificial general intelligence 1

Automatic generation control (AGC) 1

Autonomous navigation 1

Big Data Knowledge Engineering 1

Big data 1

open ︾

Search scope:

排序： Display mode:

Characters of topological relations and its applications in spatial reasoning

Li Chengming and Liu Xiaoli

Strategic Study of CAE 2013, Volume 15, Issue 5, Pages 14-19

Abstract:

In the paper,the formal representation of topological relationships are proposed according to our early research results, and the characters are also introduced. Based on these characters, the results for com-posite topological relations are introduced. At last, the applications in spatial reasoning are proposed.

Keywords： topological relationship composite of topological relations spatial reasoning algbra reasoning logical reasoning

HTML PDF Collect

A survey of script learning Review

Yi Han, Linbo Qiao, Jianming Zheng, Hefeng Wu, Dongsheng Li, Xiangke Liao,hanyi12@nudt.edu.cn,qiao.linbo@nudt.edu.cn,zhengjianming12@nudt.edu.cn,wuhefeng@mail.sysu.edu.cn,dsli@nudt.edu.cn,xkliao@nudt.edu.cn

Frontiers of Information Technology & Electronic Engineering 2021, Volume 22, Issue 3, Pages 287-436 doi: 10.1631/FITEE.2000347

Abstract: Script is the structured knowledge representation of prototypical real-life event sequences. Learning the commonsense knowledge inside the script can be helpful for machines in understanding natural language and drawing commonsensible inferences. is an interesting and promising research direction, in which a trained system can process narrative texts to capture script knowledge and draw inferences. However, there are currently no survey articles on , so we are providing this comprehensive survey to deeply investigate the standard framework and the major research topics on . This research field contains three main topics: event representations, models, and evaluation approaches. For each topic, we systematically summarize and categorize the existing systems, and carefully analyze and compare the advantages and disadvantages of the representative systems. We also discuss the current state of the research and possible future directions.

Keywords：脚本学习；自然语言处理；常识知识建模；事件推理

HTML PDF Collect

Peacetime and Epidemic Combination Medical Materials Reserve System for Public Health Emergencies

Cai Jianping, Wang Jing

Strategic Study of CAE 2022, Volume 24, Issue 6, Pages 107-115 doi: 10.15302/J-SSCAE-2022.07.005

Abstract:

Establishing a medical materials reserve system that integrates normal time with emergencies is crucial for promoting the medical materials support ability and improving the emergency management system in China in case of public health emergencies. This study summarizes the development status of China's medical materials reserve system and analyzes its problems from three aspects: institutional development, supply capacity, and coordination mechanism. Moreover, it expounds on the necessity and urgency for building a medical materials reserve system that integrates normal time and emergencies and proposes a construction plan from three aspects: basic concept, framework, and operation mechanism. Furthermore, we suggest that China should improve its medical materials reserve policies and institutions, optimize the medical materials reserve system, perfect the operation mechanism, and establish a medical materials reserve information sharing platform.

Keywords： public health emergencies medical materials reserve system normal time and emergency combination basic framework operation mechanism

HTML PDF Collect

Application of Uncertainty Reasoning Theory to Satellite Fault Detection and Diagnosis

Yang Tianshe,Li Huaizu,Cao Yuping

Strategic Study of CAE 2003, Volume 5, Issue 2, Pages 68-74

Abstract:

Generally, reasoning theory can be divided into certainty reasoning theory and uncertainty reasoning theory. Traditionally, certainty reasoning theory is used to detect and diagnose satellite faults. However, in practice, it is difficult to detect and diagnose some satellite faults automatically only by use of certainty reasoning theory. The reason is that detection and diagnosis of these faults requires reasonable reasoning and fault-tolerant capability, but certainty reasoning theory can not realize the capability. Fortunately, uncertainty reasoning theory can meet this requirement. Now, it is attracting attention of many researchers and practitioners in the space field all over the world that uncertainty reasoning theory is applied to detect and diagnose the satellite faults which can not be handled properly by certainty reasoning theory. Uncertainty reasoning theory includes several kinds of theories, such as inclusion degree theory, rough set theory, evidence reasoning theory, probabilistic reasoning theory, fuzzy reasoning theory, and so on. This paper introduces three new methods to detect and diagnose the satellite faults, in which inclusion degree theory, rough set theory and evidence reasoning theory of the uncertainty reasoning theory are used respectively.

Keywords： satellite fault detection diagnosis uncertainty reasoning theory

HTML PDF Collect

Causal Inference Review

Kun Kuang, Lian Li, Zhi Geng, Lei Xu, Kun Zhang, Beishui Liao, Huaxin Huang, Peng Ding, Wang Miao, Zhichao Jiang

Engineering 2020, Volume 6, Issue 3, Pages 253-263 doi: 10.1016/j.eng.2019.08.016

Abstract:

Causal inference is a powerful modeling tool for explanatory analysis, which might enable current machine learning to become explainable. How to marry causal inference with machine learning to develop eXplainable Artificial Intelligence (XAI) algorithms is one of key steps towards to the artificial intelligence 2.0. With the aim of bringing knowledge of causal inference to scholars of machine learning
and artificial intelligence, we invited researchers working on causal inference to write this survey from different aspects of causal inference. This survey includes the following sections: "Estimating average treatment effect: A brief review and beyond" from Dr. Kun Kuang, "Attribution problems in counterfactual inference" from Prof. Lian Li, "The Yule-Simpson paradox and the surrogate paradox" from Prof. Zhi Geng, "Causal potential theory" from Prof. Lei Xu, "Discovering causal information from observational data" from Prof. Kun Zhang, "Formal argumentation in causal reasoning and explanation" from Profs. Beishui Liao and Huaxin Huang, "Causal inference with complex experiments" from Prof. Peng Ding, "Instrumental variables and negative controls for observational studies" from Prof. Wang Miao, and "Causal inference with interference" from Dr. Zhichao Jiang.

Keywords： Causal inference Instructive variables Negative control Causal reasoning and explanation Causal discovery Counter factual inference Treatment effect estimation

HTML PDF Collect

Progress in Neural NLP: Modeling, Learning, and Reasoning Review

Ming Zhou, Nan Duan, Shujie Liu, Heung-Yeung Shum

Engineering 2020, Volume 6, Issue 3, Pages 275-290 doi: 10.1016/j.eng.2019.12.014

Abstract:

Natural language processing (NLP) is a subfield of artificial intelligence (AI) that focuses on enabling computers to understand and process human languages. In the last five years, we have witnessed the rapid development of NLP in tasks such as machine translation, question-answering, and machine reading comprehension based on deep learning and an enormous volume of annotated and unannotated data. In this paper, we will review the latest progress in the neural network-based NLP framework (neural NLP) from three perspectives: modeling, learning, and reasoning. In the modeling section, we will describe several fundamental neural network-based modeling paradigms, such as word embedding, sentence embedding, and sequence-to-sequence modeling, which are widely used in modern NLP engines. In the learning section, we will introduce widely used learning methods for NLP models, including supervised, semi-supervised, and unsupervised learning; multitask learning; transfer learning; and active learning. We view reasoning as a new and exciting direction for neural NLP, but it has yet to be well addressed. In the reasoning section, we will review reasoning mechanisms, including the knowledge, existing non-neural inference methods, and new neural inference methods. We emphasize the importance of reasoning in this paper because it is important for building interpretable and knowledge-driven neural NLP models to handle complex tasks. At the end of this paper, we will briefly outline our thoughts on the future directions of neural NLP.

Keywords： Natural language processing Deep learning Modeling learning and Reasoning

HTML PDF Collect

Mathematical Reasoning Challenges Artificial Intelligence

Sean O’Neill

Engineering 2019, Volume 5, Issue 5, Pages 817-818 doi: 10.1016/j.eng.2019.08.009

HTML PDF Collect

An ANFIS-based Approach for Predicting MiningInduced Surface Subsidence

Ding Dexin,Zhang Zhijun,Bi Zhongwei

Strategic Study of CAE 2007, Volume 9, Issue 1, Pages 33-39

Abstract:

Current approaches for predicting mining induced surface subsidence have a drawback in common that they predict the subsidence only on the basis of a physical or mechanical approach irrespective of the practical examples in engineering practice in mining induced surface subsidence.However,these experiences created in engineering practice are of great value and full use should be made of them to establish an approach for predicting mining induced surface subsidence.Therefore,this paper accumulated a lot of practical examples of mining induced surface subsidence,integrated these examples by using adaptive neuro-fuzzy inference system (ANFIS)and established an ANFIS-based approach for predicting mining induced surface subsidence.The approach was further tested by using practical examples of mining induced surface subsidence.The results show that the approach can converge quickly,fit the data in very good agreement and make generalization prediction with high accuracy.

Keywords： underground mining mining induced surface subsidence adaptive neuro唱fuzzy inferencesystem

HTML PDF Collect

A New Evolution-reasoning Method in Conceptual Design Based on Extension Theory

Hao Yanwei,Liu Haisheng,Zhang Guoxian

Strategic Study of CAE 2003, Volume 5, Issue 5, Pages 63-69

Abstract:

After existing study methods are analyzed, a new researching model for conceptual design based on extension and genetic algorithms was presented. The inner-model and outer-model of product project were set up with matter elements. In genetic algorithms the coding for individual, the means for cross-over and mutation were all founded based on the inner-model. The fitness function was set up combined with relationship function. The technique solves the innovative and incompatible problems in conceptual design. The feasibility of the new researching model is testified by three conceptual design examples for retarder.

Keywords： conceptual design matter elements transform genetic algorithms evolution reasoning extension appraisal

HTML PDF Collect

Visual commonsense reasoning with directional visual connections Research Articles

Yahong Han, Aming Wu, Linchao Zhu, Yi Yang,yahong@tju.edu.cn

Frontiers of Information Technology & Electronic Engineering 2021, Volume 22, Issue 5, Pages 615-766 doi: 10.1631/FITEE.2000722

Abstract: To boost research into cognition-level visual understanding, i.e., making an accurate inference based on a thorough understanding of visual details, (VCR) has been proposed. Compared with traditional visual question answering which requires models to select correct answers, VCR requires models to select not only the correct answers, but also the correct rationales. Recent research into human cognition has indicated that brain function or cognition can be considered as a global and dynamic integration of local neuron connectivity, which is helpful in solving specific cognition tasks. Inspired by this idea, we propose a to achieve VCR by dynamically reorganizing the that is contextualized using the meaning of questions and answers and leveraging the directional information to enhance the reasoning ability. Specifically, we first develop a GraphVLAD module to capture to fully model visual content correlations. Then, a contextualization process is proposed to fuse sentence representations with visual neuron representations. Finally, based on the output of , we propose to infer answers and rationales, which includes a ReasonVLAD module. Experimental results on the VCR dataset and visualization analysis demonstrate the effectiveness of our method.

Keywords：视觉常识推理；有向连接网络；视觉神经元连接；情景化连接；有向连接

HTML PDF Collect

AED-Net: An Abnormal Event Detection Network Article

Tian Wang, Zichen Miao, Yuxin Chen, Yi Zhou, Guangcun Shan, Hichem Snoussi

Engineering 2019, Volume 5, Issue 5, Pages 930-939 doi: 10.1016/j.eng.2019.02.008

Abstract:

It has long been a challenging task to detect an anomaly in a crowded scene. In this paper, a self-supervised framework called the abnormal event detection network (AED-Net), which is composed of a principal component analysis network (PCAnet) and kernel principal component analysis (kPCA), is proposed to address this problem. Using surveillance video sequences of different scenes as raw data, the PCAnet is trained to extract high-level semantics of the crowd's situation. Next, kPCA, a one-class classifier, is trained to identify anomalies within the scene. In contrast to some prevailing deep learning methods, this framework is completely self-supervised because it utilizes only video sequences of a normal situation. Experiments in global and local abnormal event detection are carried out on Monitoring Human Activity dataset from University of Minnesota (UMN dataset) and Anomaly Detection dataset from University of California, San Diego (UCSD dataset), and competitive results that yield a better equal error rate (EER) and area under curve (AUC) than other state-of-the-art methods are observed. Furthermore, by adding a local response normalization (LRN) layer, we propose an improvement to the original AED-Net. The results demonstrate that this proposed version performs better by promoting the framework's generalization capacity.

Keywords： Abnormal events detection Abnormal event detection network Principal component analysis network Kernel principal component analysis

HTML PDF Collect

Study of Dynamic Fuzzy Inference Mechanism of Fault Diagnosis Expert System for Production Line

Tan Li,Liu Jin,Mei Liting

Strategic Study of CAE 2005, Volume 7, Issue 6, Pages 57-60

Abstract:

Developing fault diagnosis expert system for production line, the principle and method of structuring fuzzy inference engine are presented in this paper. Moreover, the idea of dynamic fuzzy relation with real time is introduced. And, it is illustrated that this idea is realized by defining a dynamic membership function changing with non-fault-time.

Keywords： fault diagnosis expert system fuzzy inference

HTML PDF Collect

Environmental and Dynamic Conditions for the Occurrence of Persistent Haze Events in North China

Yihui Ding,Ping Wu,Yanju Liu,Yafang Song

Engineering 2017, Volume 3, Issue 2, Pages 266-271 doi: 10.1016/J.ENG.2017.01.009

Abstract:

This paper presents a concise summary of recent studies on the long-term variations of haze in North China and on the environmental and dynamic conditions for severe persistent haze events. Results indicate that haze days have an obviously rising trend over the past 50 years in North China. The occurrence frequency of persistent haze events has a similar rising trend due to the continuous rise of winter temperatures, decrease of surface wind speeds, and aggravation of atmospheric stability. In North China, when severe persistent haze events occur, anomalous southwesterly winds prevail in the lower troposphere, providing sufficient moisture for the formation of haze. Moreover, North China is mainly controlled by a deep downdraft in the mid-lower troposphere, which contributes to reducing the thickness of the planetary boundary layer, obviously reducing the atmospheric capacity for pollutants. This atmospheric circulation and sinking motion provide favorable conditions for the formation and maintenance of haze in North China.

Keywords： North China Persistent haze events Environmental conditions Dynamic conditions

HTML PDF Collect

Study and implementation of claim decision support system for large water transfer project

Wang Wei

Strategic Study of CAE 2011, Volume 13, Issue 12, Pages 108-112

Abstract:

Considering the shortage of the experience and expert in construction claim of large water transfer project, case-based reasoning (CBR) and rule-based reasoning (RBR) in artificial intelligence are used in claim management. The knowledge-based claim decision support system is designed and implemented, in which the previous cases of hydraulic engineering claims are stored structurally. The system is used for the construction management of a trans-basin water transfer project.

Keywords： water transfer project claim management case-based reasoning (CBR) rule-based reasoning (RBR) decision support system

HTML PDF Collect

Adaptive network fuzzy inference system based navigation controller for mobile robot Research Article

Panati SUBBASH, Kil To CHONG

Frontiers of Information Technology & Electronic Engineering 2019, Volume 20, Issue 2, Pages 141-151 doi: 10.1631/FITEE.1700206

Abstract:

Autonomous navigation of a mobile robot in an unknown environment with highly cluttered obstacles is a fundamental issue in mobile robotics research. We propose an adaptive network fuzzy inference system (ANFIS) based navigation controller for a differential drive mobile robot in an unknown environment with cluttered obstacles. Ultrasonic sensors are used to capture the environmental information around the mobile robot. A training data set required to train the ANFIS controller has been obtained by designing a fuzzy logic based navigation controller. Additive white Gaussian noise has been added to the sensor readings and fed to the trained ANFIS controller during mobile robot navigation, to account for the effect of environmental noise on sensor readings. The robustness of the proposed navigation controller has been evaluated by navigating the mobile robot in three different environments. The performance of the proposed controller has been verified by comparing the travelled path length/efficiency and bending energy obtained by the proposed method with reference mobile robot navigation controllers, such as neural network, fuzzy logic, and ANFIS. Simulation results presented in this paper show that the proposed controller has better performance compared with reference controllers and can successfully navigate in different environments without any collision with obstacles.

Keywords： Adaptive network fuzzy inference system Additive white Gaussian noise Autonomous navigation Mobile robot