Search | Engineering

Subscribe Submit

Home Journals Focus Achievement Fronts About Us 中文版

Resource Type

Journal Article 1900

Conference Videos 213

Conference Information 83

Conference Topics 3

Year

2024 5

2023 163

2022 230

2021 243

2020 193

2019 147

2018 131

2017 131

2016 82

2015 56

2014 38

2013 49

2012 50

2011 67

2010 80

2009 72

2008 53

2007 41

2006 32

2005 51

open ︾

Keywords

sustainable development 20

neural network 17

Machine learning 15

technology 14

Deep learning 13

key technology 12

Artificial intelligence 11

disruptive technology 11

Three Gorges Project 10

development 10

2035 9

China 8

Neural network 8

Software-defined networking (SDN) 7

construction technology 7

development trend 7

resource utilization 7

water resource 6

information technology 5

open ︾

Search scope:

排序： Display mode:

Discovering semantically related technical terms and web resources in Q&A discussions Research Articles

Junfang Jia, Valeriia Tumanian, Guoqiang Li,li.g@sjtu.edu.cn

Frontiers of Information Technology & Electronic Engineering 2021, Volume 22, Issue 7, Pages 969-985 doi: 10.1631/FITEE.2000186

Abstract: A sheer number of techniques and are available for software engineering practice and this number continues to grow. Discovering semantically similar or related and offers the opportunity to design appealing services to facilitate information retrieval and information discovery. In this study, we extract and from a community of question and answer (A) discussions and propose an approach based on a neural language model to learn the semantic representations of and in a joint low-dimensional vector space. Our approach maps and to a semantic vector space based only on the surrounding and of a technical term (or web resource) in a discussion thread, without the need for mining the text content of the discussion. We apply our approach to Stack Overflow data dump of March 2018. Through both quantitative and qualitative analyses in the clustering, search, and semantic reasoning tasks, we show that the learnt technical-term and web-resource vector representations can capture the semantic relatedness of and , and they can be exploited to support various search and semantic reasoning tasks, by means of simple -nearest neighbor search and simple algebraic operations on the learnt vector representations in the embedding space.

Keywords：技术术语；网络资源；词语嵌入；问答网站；聚类任务；推荐任务

HTML PDF Collect

Learning natural ordering of tags in domain-specific Q&A sites

Junfang Jia, Guoqiang Li,jiajunfang816@163.com,li.g@sjtu.edu.cn

Frontiers of Information Technology & Electronic Engineering 2021, Volume 22, Issue 2, Pages 141-286 doi: 10.1631/FITEE.1900645

Abstract: is a defining characteristic of Web 2.0. It allows users of social computing systems (e.g., ) to use free terms to annotate content. However, is really a free action? Existing work has shown that users can develop implicit consensus about what tags best describe the content in an online community. However, there has been no work studying the regularities in how users order tags during . In this paper, we focus on the ing of tags in domain-specific Q&A sites. We study tag sequences of millions of questions in four Q&A sites, i.e., CodeProject, SegmentFault, Biostars, and CareerCup. Our results show that users of these Q&A sites can develop implicit consensus about in which order they should assign tags to questions. We study the relationships between tags that can explain the emergence of ing of tags. Our study opens the path to improve existing tag recommendation and Q&A site navigation by leveraging the ing of tags.

Keywords： Question and answering (Q& A) sites Tagging Natural order Skip gram

HTML PDF Collect

Dynamic grouping of heterogeneous agents for exploration and strike missions Research Article

Chen CHEN, Xiaochen WU, Jie CHEN, Panos M. PARDALOS, Shuxin DING,xiaofan@bit.edu.cn,wsygdhrwxc@sina.com,pardalos@ufl.edu

Frontiers of Information Technology & Electronic Engineering 2022, Volume 23, Issue 1, Pages 86-100 doi: 10.1631/FITEE.2000352

Abstract: The ever-changing environment and complex combat missions create new demands for the formation of mission groups of unmanned combat agents. This study aims to address the problem of dynamic construction of mission groups under new requirements. Agents are heterogeneous, and a method must dynamically form new groups in circumstances where missions are constantly being explored. In our method, a strategy that combines s and response threshold models is proposed to dynamically adjust the members of the mission group and adapt to the needs of new missions. The degree of matching between the mission requirements and the group's capabilities, and the communication cost of are used as indicators to evaluate the quality of the group. The response threshold method and the ant colony algorithm are selected as the comparison algorithms in the simulations. The results show that the grouping scheme obtained by the proposed method is superior to those of the comparison methods.

Keywords： Multi-agent Dynamic missions Group formation Heuristic rule Networking overhead

HTML PDF Collect

Pattern Recognition With Fuzzy Central Clustering Algorithms

Zen Huanglin,Yuan Hui,Liu Xiaofang

Strategic Study of CAE 2004, Volume 6, Issue 11, Pages 33-37

Abstract:

Based on optimization of constrained nonlinear programming, an approach of clustering center and a fuzzy membership function of pattern classification are derived from an objective function of the constrained nonlinear programming. An unsupervised algorithm with recursive expression and a fuzzy central cluster neural network are suggested in this paper. The fuzzy central cluster neural network proposed here can realize crisp decision or fuzzy decision in pattern classification.

Keywords： fuzzy sets central cluster pattern recognition neural network

HTML PDF Collect

Three New Missions Head for Mars

Mitch Leslie

Engineering 2020, Volume 6, Issue 12, Pages 1336-1338 doi: 10.1016/j.eng.2020.10.007

HTML PDF Collect

TIE algorithm: a layer over clustering-based taxonomy generation for handling evolving data None

Rabia IRFAN, Sharifullah KHAN, Kashif RAJPOOT, Ali Mustafa QAMAR

Frontiers of Information Technology & Electronic Engineering 2018, Volume 19, Issue 6, Pages 763-782 doi: 10.1631/FITEE.1700517

Abstract: Taxonomy is generated to effectively organize and access large volume of data. A taxonomy is a way of representing concepts that exist in data. It needs to continuously evolve to reflect changes in data. Existing automatic taxonomy generation techniques do not handle the evolution of data; therefore, the generated taxonomies do not truly represent the data. The evolution of data can be handled by either regenerating taxonomy from scratch, or allowing taxonomy to incrementally evolve whenever changes occur in the data. The former approach is not economical in terms of time and resources. A taxonomy incremental evolution (TIE) algorithm, as proposed, is a novel attempt to handle the data that evolve in time. It serves as a layer over an existing clustering-based taxonomy generation technique and allows an existing taxonomy to incrementally evolve. The algorithm was evaluated in research articles selected from the computing domain. It was found that the taxonomy using the algorithm that evolved with data needed considerably shorter time, and had better quality per unit time as compared to the taxonomy regenerated from scratch.

Keywords： Taxonomy Clustering algorithms Information science Knowledge management Machine learning

HTML PDF Collect

An anchor-based spectral clustering method None

Qin ZHANG, Guo-qiang ZHONG, Jun-yu DONG

Frontiers of Information Technology & Electronic Engineering 2018, Volume 19, Issue 11, Pages 1385-1396 doi: 10.1631/FITEE.1700262

Abstract:

Spectral clustering is one of the most popular and important clustering methods in pattern recognition, machine learning, and data mining. However, its high computational complexity limits it in applications involving truly large-scale datasets. For a clustering problem with n samples, it needs to compute the eigenvectors of the graph Laplacian with O(n³) time complexity. To address this problem, we propose a novel method called anchor-based spectral clustering (ASC) by employing anchor points of data. Specifically, m (m<<n) anchor points are selected from the dataset, which can basically maintain the intrinsic (manifold) structure of the original data. Then a mapping matrix between the original data and the anchors is constructed. More importantly, it is proved that this data-anchor mapping matrix essentially preserves the clustering structure of the data. Based on this mapping matrix, it is easy to approximate the spectral embedding of the original data. The proposed method scales linearly relative to the size of the data but with low degradation of the clustering performance. The proposed method, ASC, is compared to the classical spectral clustering and two state-of-the-art accelerating methods, i.e., power iteration clustering and landmark-based spectral clustering, on 10 real-world applications under three evaluation metrics. Experimental results show that ASC is consistently faster than the classical spectral clustering with comparable clustering performance, and at least comparable with or better than the state-of-the-art methods on both effectiveness and efficiency.

Keywords： Clustering Spectral clustering Graph Laplacian Anchors

HTML PDF Collect

Task planning in robotics: an empirical comparison of PDDL-and ASP-based systems Special Feature on Intelligent Robats

Yu-qian JIANG, Shi-qi ZHANG, Piyush KHANDELWAL, Peter STONE

Frontiers of Information Technology & Electronic Engineering 2019, Volume 20, Issue 3, Pages 363-373 doi: 10.1631/FITEE.1800514

Abstract:

Robots need task planning algorithms to sequence actions toward accomplishing goals that are impossible through individual actions. Off-the-shelf task planners can be used by intelligent robotics practitioners to solve a variety of planning problems. However, many different planners exist, each with different strengths and weaknesses, and there are no general rules for which planner would be best to apply to a given problem. In this study, we empirically compare the performance of state-of-the-art planners that use either the planning domain description language (PDDL) or answer set programming (ASP) as the underlying action language. PDDL is designed for task planning, and PDDL-based planners are widely used for a variety of planning problems. ASP is designed for knowledge-intensive reasoning, but can also be used to solve task planning problems. Given domain encodings that are as similar as possible, we find that PDDL-based planners perform better on problems with longer solutions, and ASP-based planners are better on tasks with a large number of objects or tasks in which complex reasoning is required to reason about action preconditions and effects. The resulting analysis can inform selection among general-purpose planning systems for particular robot task planning domains.

Keywords： Task planning Robotics Planning domain description language (PDDL) Answer set programming (ASP)

HTML PDF Collect

A Hierarchical-Based Initialization Method for K-Means Algorithm

Tang Jiubin,Lu Jianfeng,Tang Zhenmin, Yang Jingyu

Strategic Study of CAE 2007, Volume 9, Issue 11, Pages 74-79

Abstract:

K-means algorithm is one of common clustering algorithms, but the cluster center initialization is a hard problem. In this paper, a hierarchical-based initialization approach is proposed for K-Means algorithm. The general clustering problem is treated as weighted clustering problem, the original data is sampled level by level to reduce the data amount. Then clustering is carried out at each level by top-down. The initial center of each level is mapped from the clustering center of upper level and this procedure is repeated until the original data level is reached. As a result, the initial center for the original data is obtained. Both the experimental results on simulated data and real data show that the proposed method has high converging speed, high quality of clustering and is insensitive to noise, which is superior to some existing clustering algorithms.

Keywords： hierarchical technique initial cluster centers weighted data K-means clustering

HTML PDF Collect

Mars Helicopter Exceeds Expectations

Mitch Leslie

Engineering 2021, Volume 7, Issue 11, Pages 1511-1512 doi: 10.1016/j.eng.2021.09.003

HTML PDF Collect

A New Model Using Multiple Feature Clustering and Neural Networks for Forecasting Hourly PM_2.5 Concentrations, and Its Applications in China Article

Hui Liu, Zhihao Long, Zhu Duan, Huipeng Shi

Engineering 2020, Volume 6, Issue 8, Pages 944-956 doi: 10.1016/j.eng.2020.05.009

Abstract:

Particulate matter with an aerodynamic diameter no greater than 2.5 μm (PM_2.5) concentration forecasting is desirable for air pollution early warning. This study proposes an improved hybrid model, named multi-feature clustering decomposition (MCD)–echo state network (ESN)–particle swarm optimization (PSO), for multi-step PM_2.5 concentration forecasting. The proposed model includes decomposition and optimized forecasting components. In the decomposition component, an MCD method consisting of rough sets attribute reduction (RSAR), k-means clustering (KC), and the empirical wavelet transform (EWT) is proposed for feature selection and data classification. Within the MCD, the RSAR algorithm is adopted to select significant air pollutant variables, which are then clustered by the KC algorithm. The clustered results of the PM_2.5 concentration series are decomposed into several sublayers by the EWT algorithm. In the optimized forecasting component, an ESN-based predictor is built for each decomposed sublayer to complete the multi-step forecasting computation. The PSO algorithm is utilized to optimize the initial parameters of the ESN-based predictor. Real PM_2.5 concentration data from four cities located in different zones in China are utilized to verify the effectiveness of the proposed model. The experimental results indicate that the proposed forecasting model is suitable for the multi-step high-precision forecasting of PM_2.5 concentrations and has better performance than the benchmark models.

Keywords： PM_2.52.5浓度预测 PM_2.52.5浓度聚类经验小波分解多步预测

HTML PDF Collect

The research of grey clustering decision of assembly sequence based on petri net

Mo Qian,Luo Yi

Strategic Study of CAE 2008, Volume 10, Issue 11, Pages 65-68

Abstract:

This paper establishes assembly model according to the intuitionistic graphics mode characteristics of petri net, and gets feasible assembly sequence according to the principle of petri net. Most of factors influencing assembly sequence are certainly qualitative, fuzzy, non-numerical, assembly sequence is regarded as a gray system, and grey clustering decision method is adopted to evaluate feasible assembly sequence. This paper analyzes the gray classification of the influence factor and studies grey clustering decision method steps. The analysis of example indicates this method can evaluate correctly the feasible assembly sequences according to the principle of petri net and obtain decision vector.

Keywords： assembly sequence petri net grey clustering decision method

HTML PDF Collect

Asteroid Missions Begin to Pay Off

Chris Palmer

Engineering 2021, Volume 7, Issue 4, Pages 418-420 doi: 10.1016/j.eng.2021.03.005

HTML PDF Collect

Study of Bus Management of Airborne Electromechanical System

Wang Zhanlin,Qiu Lihua

Strategic Study of CAE 2001, Volume 3, Issue 6, Pages 48-52

Abstract:

There are many electromechanical systems in various vehicles. They are managed in a separate subsystem way. This paper proposes the integrated management scheme which can, by means of the data bus, make the management of subsystem have the abilities of redundancy and tolerance failure, besides accomplishing its own independent functions. The paper emphatically introduces how to realize the integrated management by simulation platform and gives the structures of hardware and software of platform, as well as the strategies of task distribution and scheduling.

Keywords： distributed multiprocessor simulation platform tasks distribution task scheduling redundancy

HTML PDF Collect

Storage hierarchy oriented DPM policy based on task information

Huang Shaomin,Qi Longning,Yang Jun,Hu Chen

Strategic Study of CAE 2010, Volume 12, Issue 2, Pages 83-89

Abstract:

Storage hierarchy oriented DPM, which uses buffer to prolong idle time, can achieve lower power than traditional DPM policies. The paper proposes task information based (TIB) policy for storage hierarchy oriented DPM. TIB subdivides the data access mode of tasks and introduces them into policy by modifying access interface to make prefetching and replacement algorithm more energy aware.

Keywords： data buffer task information DPM prefetching policy