Resource Type

Journal Article 242

Year

2023 46

2022 42

2021 35

2020 31

2019 26

2018 19

2017 18

2016 7

2015 1

2011 1

2010 1

2009 1

2008 2

2007 3

2006 1

2005 2

2004 1

2003 1

2002 2

2001 2

open ︾

Keywords

Machine learning 42

Deep learning 34

Artificial intelligence 14

Reinforcement learning 14

Active learning 4

Bayesian optimization 3

Big data 3

Data-driven 3

Adaptive dynamic programming 2

Additive manufacturing 2

Attention 2

Autonomous driving 2

Autonomous learning 2

COVID-19 2

Classification 2

Computer vision 2

Feature learning 2

Materials design 2

Representation learning 2

open ︾

Search scope:

排序： Display mode:

Video summarization with a graph convolutional attention network Research Articles

Ping Li, Chao Tang, Xianghua Xu,patriclouis.lee@gmail.com

Frontiers of Information Technology & Electronic Engineering 2021, Volume 22, Issue 6,   Pages 902-913 doi: 10.1631/FITEE.2000429

Abstract: has established itself as a fundamental technique for generating compact and concise video, which alleviates managing and browsing large-scale video data. Existing methods fail to fully consider the local and global relations among frames of video, leading to a deteriorated summarization performance. To address the above problem, we propose a graph convolutional attention network (GCAN) for . GCAN consists of two parts, embedding learning and , where embedding learning includes the temporal branch and graph branch. In particular, GCAN uses dilated temporal convolution to model local cues and temporal self-attention to exploit global cues for video frames. It learns graph embedding via a multi-layer to reveal the intrinsic structure of frame samples. The part combines the output streams from the temporal branch and graph branch to create the context-aware representation of frames, on which the importance scores are evaluated for selecting representative frames to generate video summary. Experiments are carried out on two benchmark databases, SumMe and TVSum, showing that the proposed GCAN approach enjoys superior performance compared to several state-of-the-art alternatives in three evaluation settings.

Keywords： 时序学习；自注意力机制；图卷积网络；上下文融合；视频摘要    

HTML PDF Collect

High-emitter identification for heavy-duty vehicles by temporal optimization LSTMand an adaptive dynamic threshold Research Article

Zhenyi XU, Renjun WANG, Yang CAO, Yu KANG

Frontiers of Information Technology & Electronic Engineering 2023, Volume 24, Issue 11,   Pages 1633-1646 doi: 10.1631/FITEE.2300005

Abstract: Heavy-duty diesel vehicles are important sources of urban nitrogen oxides (NO) in actual applications for environmental compliance, emitting more than 80% of NO and more than 90% of particulate matter (PM) in total vehicle emissions. The detection and control of heavy-duty diesel emissions are critical for protecting public health. Currently, vehicles on the road must be regularly tested, every six months or once a year, to filter out high-emission mobile sources at vehicle inspection stations. However, it is difficult to effectively screen high-emission vehicles in time with a long interval between annual inspections, and the fixed threshold cannot adapt to the dynamic changes of vehicle driving conditions. An is installed inside the vehicle and can record the vehicle’s emission data in real time. In this paper, we propose a long short-term memory (LSTM) and adaptive approach to identify heavy-duty high-emitters by using OBD data, which can continuously track and record the emission status in real time. First, a LSTM emission prediction model is established to solve the attention bias discrepancy problem on time steps that is caused by the large number of OBD data streams in practice. Then, the concentration prediction error sequence is detected and distinguished from the anomalous emission contexts using flexible criteria, calculated by an adaptive with changing driving conditions. Finally, a similarity metric strategy for the time series is introduced to correct some pseudo anomalous results. Experiments on three real OBD time-series emission datasets demonstrate that our method can achieve high accuracy anomalous emission identification.

Keywords： High-emitter identification     Temporal optimization     On-board diagnostic device (OBD)     Dynamic threshold    

HTML PDF Collect

Evolutionary Immune Mechanism and Its Application on Temporal Sequential Pattern Mining

Yang Bingru,Qin Yiqing,Song Zefeng

Strategic Study of CAE 2008, Volume 10, Issue 4,   Pages 84-89

Abstract:

A new approach to solve the problem of dynamic data mining is presented. Firstly a new concept of dynamic mining process is proposed. Next the evolutionary immune mechanism in KDD is illustrated, based on a comparison between the dynamic mining process and biological immune process.Additionally how to apply the approach to temporal sequential pattern mining and evaluate the experimental results are described. Finally the work and present proposals for future work are concluded.

Keywords： dynamic data mining     immune algorithm     dynamic mining process     evolutionary immune mechanism     temporal sequential pattern mining    

HTML PDF Collect

Structure Transformation of Irregular Information for Time-sequence and Elaborate Analysis of Evolution

Ouyang Shoucheng,Zhang Kui,Hao Liping,Zhou Lirong

Strategic Study of CAE 2005, Volume 7, Issue 4,   Pages 36-41

Abstract:

In this paper, the automatic meteorological recorders of time —sequence are transformed into structure information on the basis that time doesn't own dimension of matter. The results show that the irregular information of automatic meteorological recorders may be used in careful forecasting of rain storm, which will provide a technique for evolutional irregular information over a wide range. So, the meteorology should be of evolutional science, or in other words, taking it as a branch of the inertia system of I. Newton is open to question.

Keywords： information of time-sequence     elaborate technique     irregular structure     phase space of orientation     evolution    

HTML PDF Collect

The Time Sequence Data Mining Techniques Based on Grey System Theory

Liu Bin,Liu Sifeng,Dang Yaoguo

Strategic Study of CAE 2003, Volume 5, Issue 9,   Pages 32-35

Abstract:

This paper expatiates the thoughts of data mining with embedded knowledge and the techniques status quo of data mining. Based on the thoughts and the grey system (GS) theory, it proposes the GS-based data mining method set (GDMS) for time sequence first. Then this paper introduces the idiographic arithmetic withGM(1,1) as an example. Last, it forecasts the total homes connecting with Internet in Shanghai in M02—2005 by the arithmetic.

Keywords： grey system theories     embedded knowledge     time sequeke data mining     GDMS     forecast    

HTML PDF Collect

Temporality-enhanced knowledgememory network for factoid question answering Article

Xin-yu DUAN, Si-liang TANG, Sheng-yu ZHANG, Yin ZHANG, Zhou ZHAO, Jian-ru XUE, Yue-ting ZHUANG, Fei WU

Frontiers of Information Technology & Electronic Engineering 2018, Volume 19, Issue 1,   Pages 104-115 doi: 10.1631/FITEE.1700788

Abstract: Question answering is an important problem that aims to deliver specific answers to questions posed by humans in natural language. How to efficiently identify the exact answer with respect to a given question has become an active line of research. Previous approaches in factoid question answering tasks typically focus on modeling the semantic relevance or syntactic relationship between a given question and its corresponding answer. Most of these models suffer when a question contains very little content that is indicative of the answer. In this paper, we devise an architecture named the temporality-enhanced knowledge memory network (TE-KMN) and apply the model to a factoid question answering dataset from a trivia competition called quiz bowl. Unlike most of the existing approaches, our model encodes not only the content of questions and answers, but also the temporal cues in a sequence of ordered sentences which gradually remark the answer. Moreover, our model collaboratively uses external knowledge for a better understanding of a given question. The experimental results demonstrate that our method achieves better performance than several state-of-the-art methods.

Keywords： Question answering     Knowledge memory     Temporality interaction    

HTML PDF Collect

Federated unsupervised representation learning Research Article

Fengda ZHANG, Kun KUANG, Long CHEN, Zhaoyang YOU, Tao SHEN, Jun XIAO, Yin ZHANG, Chao WU, Fei WU, Yueting ZHUANG, Xiaolin LI,fdzhang@zju.edu.cn,kunkuang@zju.edu.cn

Frontiers of Information Technology & Electronic Engineering 2023, Volume 24, Issue 8,   Pages 1181-1193 doi: 10.1631/FITEE.2200268

Abstract: To leverage the enormous amount of unlabeled data on distributed edge devices, we formulate a new problem in called federated unsupervised (FURL) to learn a common representation model without supervision while preserving data privacy. FURL poses two new challenges: (1) data distribution shift (non-independent and identically distributed, non-IID) among clients would make local models focus on different categories, leading to the inconsistency of representation spaces; (2) without unified information among the clients in FURL, the representations across clients would be misaligned. To address these challenges, we propose the federated contrastive averaging with dictionary and alignment (FedCA) algorithm. FedCA is composed of two key modules: a dictionary module to aggregate the representations of samples from each client which can be shared with all clients for consistency of representation space and an alignment module to align the representation of each client on a base model trained on public data. We adopt the contrastive approach for local model training. Through extensive experiments with three evaluation protocols in IID and non-IID settings, we demonstrate that FedCA outperforms all baselines with significant margins.

Keywords： Federated learning     Unsupervised learning     Representation learning     Contrastive learning    

HTML PDF Collect

Learning to select pseudo labels: a semi-supervised method for named entity recognition Research Articles

Zhen-zhen Li, Da-wei Feng, Dong-sheng Li, Xi-cheng Lu,lizhenzhen14@nudt.edu.cn,davyfeng.c@gmail.com,dsli@nudt.edu.cn,xclu@nudt.edu.cn

Frontiers of Information Technology & Electronic Engineering 2020, Volume 21, Issue 6,   Pages 809-962 doi: 10.1631/FITEE.1800743

Abstract: models have achieved state-of-the-art performance in (NER); the good performance, however, relies heavily on substantial amounts of labeled data. In some specific areas such as medical, financial, and military domains, labeled data is very scarce, while is readily available. Previous studies have used to enrich word representations, but a large amount of entity information in is neglected, which may be beneficial to the NER task. In this study, we propose a for NER tasks, which learns to create high-quality labeled data by applying a pre-trained module to filter out erroneous pseudo labels. Pseudo labels are automatically generated for and used as if they were true labels. Our semi-supervised framework includes three steps: constructing an optimal single neural model for a specific NER task, learning a module that evaluates pseudo labels, and creating new labeled data and improving the NER model iteratively. Experimental results on two English NER tasks and one Chinese clinical NER task demonstrate that our method further improves the performance of the best single neural model. Even when we use only pre-trained static word embeddings and do not rely on any external knowledge, our method achieves comparable performance to those state-of-the-art models on the CoNLL-2003 and OntoNotes 5.0 English NER tasks.

Keywords： 命名实体识别；无标注数据；深度学习；半监督学习方法    

HTML PDF Collect

New directions for artificial intelligence: human, machine, biological, and quantum intelligence Comment

Li WEIGANG,Liriam Michi ENAMOTO,Denise Leyi LI,Geraldo Pereira ROCHA FILHO

Frontiers of Information Technology & Electronic Engineering 2022, Volume 23, Issue 6,   Pages 984-990 doi: 10.1631/FITEE.2100227

Abstract:

This comment reviews the “once learning” mechanism (OLM) that was proposed byWeigang (1998), the subsequent success of “one-shot learning” in object categories (Li FF et al., 2003), and “you only look once” (YOLO) in objective detection (Redmon et al., 2016). Upon analyzing the current state of research in artificial intelligence (AI), we propose to divide AI into the following basic theory categories: artificial human intelligence (AHI), artificial machine intelligence (AMI), artificial biological intelligence (ABI), and artificial quantum intelligence (AQI). These can also be considered as the main directions of research and development (R&D) within AI, and distinguished by the following classification standards and methods: (1) human-, machine-, biological-, and quantum-oriented AI R&D; (2) information input processed by dimensionality increase or reduction; (3) the use of one/a few or a large number of samples for knowledge learning.

Keywords： 人工智能；机器学习；一次性学习；一瞥学习；量子计算    

HTML PDF Collect

Two-level hierarchical feature learning for image classification Article

Guang-hui SONG,Xiao-gang JIN,Gen-lang CHEN,Yan NIE

Frontiers of Information Technology & Electronic Engineering 2016, Volume 17, Issue 9,   Pages 897-906 doi: 10.1631/FITEE.1500346

Abstract: In some image classification tasks, similarities among different categories are different and the samples are usually misclassified as highly similar categories. To distinguish highly similar categories, more specific features are required so that the classifier can improve the classification performance. In this paper, we propose a novel two-level hierarchical feature learning framework based on the deep convolutional neural network (CNN), which is simple and effective. First, the deep feature extractors of different levels are trained using the transfer learning method that fine-tunes the pre-trained deep CNN model toward the new target dataset. Second, the general feature extracted from all the categories and the specific feature extracted from highly similar categories are fused into a feature vector. Then the final feature representation is fed into a linear classifier. Finally, experiments using the Caltech-256, Oxford Flower-102, and Tasmania Coral Point Count (CPC) datasets demonstrate that the expression ability of the deep features resulting from two-level hierarchical feature learning is powerful. Our proposed method effectively increases the classification accuracy in comparison with flat multiple classification methods.

Keywords： Transfer learning     Feature learning     Deep convolutional neural network     Hierarchical classification     Spectral clustering    

HTML PDF Collect

Non-IID Recommender Systems: A Review and Framework of Recommendation Paradigm Shifting Artical

Longbing Cao

Engineering 2016, Volume 2, Issue 2,   Pages 212-224 doi: 10.1016/J.ENG.2016.02.013

Abstract:

While recommendation plays an increasingly critical role in our living, study, work, and entertainment, the recommendations we receive are often for irrelevant, duplicate, or uninteresting products and services. A critical reason for such bad recommendations lies in the intrinsic assumption that recommended users and items are independent and identically distributed (IID) in existing theories and systems. Another phenomenon is that, while tremendous efforts have been made to model specific aspects of users or items, the overall user and item characteristics and their non-IIDness have been overlooked. In this paper, the non-IID nature and characteristics of recommendation are discussed, followed by the non-IID theoretical framework in order to build a deep and comprehensive understanding of the intrinsic nature of recommendation problems, from the perspective of both couplings and heterogeneity. This non-IID recommendation research triggers the paradigm shift from IID to non-IID recommendation research and can hopefully deliver informed, relevant, personalized, and actionable recommendations. It creates exciting new directions and fundamental solutions to address various complexities including cold-start, sparse data-based, cross-domain, group-based, and shilling attack-related issues.

Keywords： Independent and identically distributed (IID)     Non-IID     Heterogeneity     Coupling relationship     Coupling learning     Relational learning     IIDness learning     Non-IIDness learning     Recommender system     Recommendation     Non-IID recommendation    

HTML PDF Collect

A review of computer graphics approaches to urban modeling from a machine learning perspective Review Article

Tian Feng, Feiyi Fan, Tomasz Bednarz,t.feng@latrobe.edu.au

Frontiers of Information Technology & Electronic Engineering 2021, Volume 22, Issue 7,   Pages 915-925 doi: 10.1631/FITEE.2000141

Abstract: facilitates the generation of virtual environments for various scenarios about cities. It requires expertise and consideration, and therefore consumes massive time and computation resources. Nevertheless, related tasks sometimes result in dissatisfaction or even failure. These challenges have received significant attention from researchers in the area of . Meanwhile, the burgeoning development of artificial intelligence motivates people to exploit , and hence improves the conventional solutions. In this paper, we present a review of approaches to in using in the literature published between 2010 and 2019. This serves as an overview of the current state of research on from a perspective.

Keywords： 城市建模；计算机图形学；机器学习；深度学习    

HTML PDF Collect

Learning Curve and Its Application in Production Operation al Research

Chen Zhixiang

Strategic Study of CAE 2007, Volume 9, Issue 7,   Pages 82-88

Abstract:

Learning curve is one character function that improves output by the experience accumulation of producer. Learning curve can be used to establish scientific cost plan, improve shop flow scheduling, labor quota and plan, quality, and so on. This paper reviews the research literatures, introduces different forms of learning curve, analyzes their characters, and discusses the future directions of application of learning curve.

Keywords： learning curve     operational management     behaviors research    

HTML PDF Collect

Predictions of Additive Manufacturing Process Parameters and Molten Pool Dimensions with a Physics-Informed Deep Learning Model Article

Mingzhi Zhao, Huiliang Wei, Yiming Mao, Changdong Zhang, Tingting Liu, Wenhe Liao

Engineering 2023, Volume 23, Issue 4,   Pages 181-195 doi: 10.1016/j.eng.2022.09.015

Abstract:

Molten pool characteristics have a significant effect on printing quality in laser powder bed fusion (PBF), and quantitative predictions of printing parameters and molten pool dimensions are critical to the intelligent control of the complex processes in PBF. Thus far, bidirectional predictions of printing parameters and molten pool dimensions have been challenging due to the highly nonlinear correlations involved. To
address this issue, we integrate an experiment on molten pool characteristics, a mechanistic model, and deep learning to achieve both forward and inverse predictions of key parameters and molten pool characteristics during laser PBF. The experiment provides fundamental data, the mechanistic model significantly augments the dataset, and the multilayer perceptron (MLP) deep learning model predicts the molten pool dimensions and process parameters based on the dataset built from the experiment and the mechanistic model. The results show that bidirectional predictions of the molten pool dimensions and process parameters can be realized, with the highest prediction accuracies approaching 99.9% and mean prediction accuracies of over 90.0%. Moreover, the prediction accuracy of the MLP model is closely related to the characteristics of the dataset—that is, the learnability of the dataset has a crucial impact on the prediction accuracy. The highest prediction accuracy is 97.3% with enhancement of the dataset via the mechanistic model, while the highest prediction accuracy is 68.3% when using only the experimental dataset. The prediction accuracy of the MLP model largely depends on the quality of the dataset as well. The research results demonstrate that bidirectional predictions of complex correlations using MLP are feasible for laser PBF, and offer a novel and useful framework for the determination of process conditions and outcomes for intelligent additive manufacturing.

 

Keywords： Additive manufacturing     Molten pool     Model     Deep learning     Learnability    

HTML PDF Collect

Communicative Learning: A Unified Learning Formalism Review

Luyao Yuan, Song-Chun Zhu

Engineering 2023, Volume 25, Issue 6,   Pages 77-100 doi: 10.1016/j.eng.2022.10.017

Abstract:

In this article, we propose a communicative learning (CL) formalism that unifies existing machine learning paradigms, such as passive learning, active learning, algorithmic teaching, and so forth, and facilitates the development of new learning methods. Arising from human cooperative communication, this formalism poses learning as a communicative process and combines pedagogy with the burgeoning field of machine learning. The pedagogical insight facilitates the adoption of alternative information sources in machine learning besides randomly sampled data, such as intentional messages given by a helpful teacher. More specifically, in CL, a teacher and a student exchange information with each other collaboratively to transmit and acquire certain knowledge. Each agent has a mind, which includes the agent's knowledge, utility, and mental dynamics. To establish effective communication, each agent also needs an estimation of its partner's mind. We define expressive mental representations and learning formulation sufficient for such recursive modeling, which endows CL with human-comparable learning efficiency. We demonstrate the application of CL to several prototypical collaboration tasks and illustrate that this formalism allows learning protocols to go beyond Shannon's communication limit. Finally, we present our contribution to the foundations of learning by putting forth hierarchies in learning and defining the halting problem of learning.

Keywords： Artificial intelligencehine     Cooperative communication     Machine learning     Pedagogy     Theory of mind    

HTML PDF Collect

Title Author Date Type Operation

Video summarization with a graph convolutional attention network

Ping Li, Chao Tang, Xianghua Xu,patriclouis.lee@gmail.com

Journal Article

High-emitter identification for heavy-duty vehicles by temporal optimization LSTMand an adaptive dynamic threshold

Zhenyi XU, Renjun WANG, Yang CAO, Yu KANG

Journal Article

Evolutionary Immune Mechanism and Its Application on Temporal Sequential Pattern Mining

Yang Bingru,Qin Yiqing,Song Zefeng

Journal Article

Structure Transformation of Irregular Information for Time-sequence and Elaborate Analysis of Evolution

Ouyang Shoucheng,Zhang Kui,Hao Liping,Zhou Lirong

Journal Article

The Time Sequence Data Mining Techniques Based on Grey System Theory

Liu Bin,Liu Sifeng,Dang Yaoguo

Journal Article

Temporality-enhanced knowledgememory network for factoid question answering

Xin-yu DUAN, Si-liang TANG, Sheng-yu ZHANG, Yin ZHANG, Zhou ZHAO, Jian-ru XUE, Yue-ting ZHUANG, Fei WU

Journal Article

Federated unsupervised representation learning

Fengda ZHANG, Kun KUANG, Long CHEN, Zhaoyang YOU, Tao SHEN, Jun XIAO, Yin ZHANG, Chao WU, Fei WU, Yueting ZHUANG, Xiaolin LI,fdzhang@zju.edu.cn,kunkuang@zju.edu.cn

Journal Article

Learning to select pseudo labels: a semi-supervised method for named entity recognition

Zhen-zhen Li, Da-wei Feng, Dong-sheng Li, Xi-cheng Lu,lizhenzhen14@nudt.edu.cn,davyfeng.c@gmail.com,dsli@nudt.edu.cn,xclu@nudt.edu.cn

Journal Article

New directions for artificial intelligence: human, machine, biological, and quantum intelligence

Li WEIGANG,Liriam Michi ENAMOTO,Denise Leyi LI,Geraldo Pereira ROCHA FILHO

Journal Article

Two-level hierarchical feature learning for image classification

Guang-hui SONG,Xiao-gang JIN,Gen-lang CHEN,Yan NIE

Journal Article

Non-IID Recommender Systems: A Review and Framework of Recommendation Paradigm Shifting

Longbing Cao

Journal Article

A review of computer graphics approaches to urban modeling from a machine learning perspective

Tian Feng, Feiyi Fan, Tomasz Bednarz,t.feng@latrobe.edu.au

Journal Article

Learning Curve and Its Application in Production Operation al Research

Chen Zhixiang

Journal Article

Predictions of Additive Manufacturing Process Parameters and Molten Pool Dimensions with a Physics-Informed Deep Learning Model

Mingzhi Zhao, Huiliang Wei, Yiming Mao, Changdong Zhang, Tingting Liu, Wenhe Liao

Journal Article

Communicative Learning: A Unified Learning Formalism

Luyao Yuan, Song-Chun Zhu

Journal Article