Resource Type

Journal Article 1278

Conference Videos 115

Conference Information 31

Year

2024 7

2023 146

2022 157

2021 173

2020 127

2019 121

2018 103

2017 94

2016 53

2015 42

2014 26

2013 20

2012 19

2011 19

2010 28

2009 22

2008 23

2007 32

2006 26

2005 41

open ︾

Keywords

Machine learning 42

Deep learning 34

Artificial intelligence 25

Reinforcement learning 14

disruptive technology 11

COVID-19 10

reliability 9

Additive manufacturing 8

Safety 7

artificial intelligence 7

Sustainability 6

disruptive technologies 6

pattern recognition 6

robustness 5

strategic emerging industries 5

Big data 4

Efficacy 4

Gut microbiota 4

Multi-agent systems 4

open ︾

Search scope:

排序： Display mode:

Latent discriminative representation learning for speaker recognition Research Articles

Duolin Huang, Qirong Mao, Zhongchen Ma, Zhishen Zheng, Sidheswar Routryar, Elias-Nii-Noi Ocquaye,2211708034@stmail.ujs.edu.cn,mao_qr@ujs.edu.cn,zhongchen_ma@ujs.edu.cn,1209103822@qq.com,sidheswar69@gmail.com,eocquaye@ujs.edu.cn

Frontiers of Information Technology & Electronic Engineering 2021, Volume 22, Issue 5,   Pages 615-766 doi: 10.1631/FITEE.1900690

Abstract: Extracting discriminative speaker-specific representations from speech signals and transforming them into fixed length vectors are key steps in speaker identification and verification systems. In this study, we propose a method for . We mean that the learned representations in this study are not only discriminative but also relevant. Specifically, we introduce an additional speaker embedded lookup table to explore the relevance between different utterances from the same speaker. Moreover, a reconstruction constraint intended to learn a is introduced to make representation discriminative. Experimental results demonstrate that the proposed method outperforms state-of-the-art methods based on the Apollo dataset used in the Fearless Steps Challenge in INTERSPEECH2019 and the TIMIT dataset.

Keywords： 说话人识别；潜在可区分性表征学习；说话人嵌入查找表；线性映射矩阵    

HTML PDF Collect

Histogram equalization using a reduced feature set of background speakers’ utterances for speaker recognition Article

Myung-jae KIM, Il-ho YANG, Min-seok KIM, Ha-jin YU

Frontiers of Information Technology & Electronic Engineering 2017, Volume 18, Issue 5,   Pages 738-750 doi: 10.1631/FITEE.1500380

Abstract: We propose a method for histogram equalization using supplement sets to improve the performance of speaker recognition when the training and test utterances are very short. The supplement sets are derived using outputs of selection or clustering algorithms from the background speakers’ utterances. The proposed approach is used as a feature normalization method for building histograms when there are insufficient input utterance samples. In addition, the proposed method is used as an i-vector normalization method in an i-vector-based probabilistic linear discriminant analysis (PLDA) system, which is the current state-of-the-art for speaker verification. The ranks of sample values for histogram equalization are estimated in ascending order from both the input utterances and the supplement set. New ranks are obtained by computing the sum of different kinds of ranks. Subsequently, the proposed method determines the cumulative distribution function of the test utterance using the newly defined ranks. The proposed method is compared with conventional feature normalization methods, such as cepstral mean normalization (CMN), cepstral mean and variance normalization (MVN), histogram equalization (HEQ), and the European Telecommunications Standards Institute (ETSI) advanced front-end methods. In addition, performance is compared for a case in which the greedy selection algorithm is used with fuzzy -means and -means algorithms. The YOHO and Electronics and Telecommunications Research Institute (ETRI) databases are used in an evaluation in the feature space. The test sets are simulated by the Opus VoIP codec. We also use the 2008 National Institute of Standards and Technology (NIST) speaker recognition evaluation (SRE) corpus for the i-vector system. The results of the experimental evaluation demonstrate that the average system performance is improved when the proposed method is used, compared to the conventional feature normalization methods.

Keywords： Speaker recognition     Histogram equalization     i-vector    

HTML PDF Collect

A new score normalizaion algorithm based on EMD-Tnorm for speaker verification

Li Yanping,Ding Hui,Tang Zhenmin

Strategic Study of CAE 2010, Volume 12, Issue 2,   Pages 95-100

Abstract:

In this paper, the verification system from two aspects was improved. On one hand, we extended MixMax model that the EMD (earth mover's distance) can be applied, which can remove the disturbance of noise; on the other hand, we improved the Tnorm score normalization method based on the EMD. Experimental results show that this method can compensate the speaker-dependent and test-dependent variability, also show a stable performance improvement by decreasing the FA and FR.

Keywords： speaker verification     robustness     earth mover’s distance     MixMax model    

HTML PDF Collect

Personalizing a Service Robot by Learning Human Habits from Behavioral Footprints Article

Kun Li, Max Q.-H. Meng

Engineering 2015, Volume 1, Issue 1,   Pages 79-84 doi: 10.15302/J-ENG-2015024

Abstract:

For a domestic personal robot, personalized services are as important as predesigned tasks, because the robot needs to adjust the home state based on the operator's habits. An operator's habits are composed of cues, behaviors, and rewards. This article introduces behavioral footprints to describe the operator's behaviors in a house, and applies the inverse reinforcement learning technique to extract the operator's habits, represented by a reward function. We implemented the proposed approach with a mobile robot on indoor temperature adjustment, and compared this approach with a baseline method that recorded all the cues and behaviors of the operator. The result shows that the proposed approach allows the robot to reveal the operator's habits accurately and adjust the environment state accordingly.

Keywords： personalized robot     habit learning     behavioral footprints    

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

Passive millimeter-wave target recognition based on Laplacian eigenmaps

Luo Lei,Li Yuehua,Luan Yinghong

Strategic Study of CAE 2010, Volume 12, Issue 3,   Pages 77-81

Abstract:

Aiming at the disadvantages of feature extraction and selection in the traditional method for passive millimeter-wave (MMW) metal target recognition, the existence and characteristics of low dimensional manifold of the short-time Fourier spectrum of metal target echo signal are explored using manifold learning algorithm, Laplacian eigenmaps. Target classification is performed through comparing the similarity of the test samples and the positive class in terms of the low dimensional manifold. The experiments show that the method gets higher recognition rate than other linear and kernel-based nonlinear dimensionality reduction algorithm, and is robust to data aliasing.

Keywords： manifold learning     Laplacian eigenmaps     nonlinear dimensionality reduction     low dimensional manifold     MMW    

HTML PDF Collect

Visual interpretability for deep learning: a survey Review

Quan-shi ZHANG, Song-chun ZHU

Frontiers of Information Technology & Electronic Engineering 2018, Volume 19, Issue 1,   Pages 27-39 doi: 10.1631/FITEE.1700808

Abstract: This paper reviews recent studies in understanding neural-network representations and learning neural networks with interpretable/disentangled middle-layer representations. Although deep neural networks have exhibited superior performance in various tasks, interpretability is always Achilles’ heel of deep neural networks. At present, deep neural networks obtain high discrimination power at the cost of a low interpretability of their black-box representations. We believe that high model interpretability may help people break several bottlenecks of deep learning, e.g., learning from a few annotations, learning via human–computer communications at the semantic level, and semantically debugging network representations. We focus on convolutional neural networks (CNNs), and revisit the visualization of CNN representations, methods of diagnosing representations of pre-trained CNNs, approaches for disentangling pre-trained CNN representations, learning of CNNs with disentangled representations, and middle-to-end learning based on model interpretability. Finally, we discuss prospective trends in explainable artificial intelligence.

Keywords： Artificial intelligence     Deep learning     Interpretable model    

HTML PDF Collect

Brain–Computer Interface Speaks up

Chris Palmer

Engineering 2022, Volume 9, Issue 2,   Pages 3-5 doi: 10.1016/j.eng.2021.12.004

HTML PDF Collect

Selective and Independent Control of Microrobots in a Magnetic Field: A Review Review

Min Wang, Tianyi Wu, Rui Liu, Zhuoran Zhang, Jun Liu

Engineering 2023, Volume 24, Issue 5,   Pages 21-38 doi: 10.1016/j.eng.2023.02.011

Abstract:

Due to the unique advantages of untethered connections and a high level of safety, magnetic actuation is a commonly used technique in microrobotics for propelling microswimmers, manipulating fluidics, and navigating medical devices. However, the microrobots or actuated targets are exposed to identical and homogeneous driving magnetic fields, which makes it challenging to selectively control a single robot or a specific group among multiple targets. This paper reviews recent advances in selective and independent control for multi-microrobot or multi-joint microrobot systems driven by magnetic fields. These selective and independent control approaches decode the global magnetic field into specific configurations for the individualized actuation of multiple microrobots. The methods include applying distinct properties for each microrobot or creating heterogeneous magnetic fields at different locations. Independent control of the selected targets enables the effective cooperation of multiple microrobots to accomplish more complicated operations. In this review, we provide a unique perspective to explain how to manipulate individual microrobots to achieve a high level of group intelligence on a small scale, which could help accelerate the translational development of microrobotic technology for real-life applications.

Keywords： Microrobot     Magnetic microrobot     Independent control     Selective control     Microrobotic manipulation    

HTML PDF Collect

A chaotic coverage path planner for the mobilerobot based on the Chebyshev map for special missions Article

Cai-hong LI, Yong SONG, Feng-ying WANG, Zhi-qiang WANG, Yi-bin LI

Frontiers of Information Technology & Electronic Engineering 2017, Volume 18, Issue 9,   Pages 1305-1319 doi: 10.1631/FITEE.1601253

Abstract: We introduce a novel strategy of designing a chaotic coveragepath planner for the mobile robot based on the Chebyshev map for achievingspecial missions. The designed chaotic path planner consists of atwo-dimensional Chebyshev map which is constructed by two one-dimensionalChebyshev maps. The performance of the time sequences which are generatedby the planner is improved by arcsine transformation to enhance thechaotic characteristics and uniform distribution. Then the coveragerate and randomness for achieving the special missions of the robotare enhanced. The chaotic Chebyshev system is mapped into the feasibleregion of the robot workplace by affine transformation. Then a universalalgorithm of coverage path planning is designed for environments withobstacles. Simulation results show that the constructed chaotic pathplanner can avoid detection of the obstacles and the workplace boundaries,and runs safely in the feasible areas. The designed strategy is ableto satisfy the requirements of randomness, coverage, and high efficiencyfor special missions.

Keywords： Mobile robot     Chebyshev map     Chaotic     Affine transformation     Coverage path planning    

HTML PDF Collect

Learning embeddings of a heterogeneous behavior network for potential behavior prediction Article

Yue-yang WANG, Wei-hao JIANG, Shi-liang PU, Yue-ting ZHUANG

Frontiers of Information Technology & Electronic Engineering 2020, Volume 21, Issue 3,   Pages 422-435 doi: 10.1631/FITEE.1800493

Abstract: Potential behavior prediction involves understanding the latent human behavior of specific groups, andcan assist organizations in making strategic decisions. Progress in information technology has made it possible to acquire more and more data about human behavior. In this paper, we examine behavior data obtained in realworld scenarios as an information network composed of two types of objects (humans and actions) associated with various attributes and three types of relationships (human-human, human-action, and action-action), which we call the heterogeneous behavior network (HBN). To exploit the abundance and heterogeneity of the HBN, we propose a novel network embedding method, human-action-attribute-aware heterogeneous network embedding (a4HNE), which jointly considers structural proximity, attribute resemblance, and heterogeneity fusion. Experiments on two real-world datasets show that this approach outperforms other similar methods on various heterogeneous information network mining tasks for potential behavior prediction.

Keywords： Network embedding     Representation learning     Human behavior     Social networks     Heterogeneous information network     Attribute    

HTML PDF Collect

KeJia: towards an autonomous service robotwith tolerance of unexpected environmental changes Special Feature on Intelligent Robats

Wei SHUAI, Xiao-ping CHEN

Frontiers of Information Technology & Electronic Engineering 2019, Volume 20, Issue 3,   Pages 307-317 doi: 10.1631/FITEE.1900096

Abstract:

KeJia is a domestic service robot, consisting of a mobile base, an arm, two cameras, and a set of software components for perception, manipulation, natural language understanding, motion and task planning, and decision making. With on-line running of these functions, a robot can adapt to dynamic environments which may have unexpected changes. In this paper, we propose a novel hierarchical method which combines motion planning with a neural network, so that the robot can tolerate errors from sensors, wear of parts, and human disturbances during motion execution. We evaluate our work on KeJia that cooks popcorn using a microwave oven, where humans try to disturb KeJia during the operation.

Keywords： Robot     Task planning     Manipulation    

HTML PDF Collect

Analysis of Plates and Shells and Its Application

Liu Renhuai

Strategic Study of CAE 2000, Volume 2, Issue 11,   Pages 60-67

Abstract:

Plates and shells are excellent structural elements. Analys of plates and shells is an important branch in modern solid mechanics. It plays a guiding role in many fields because of its wide application to almost all the engineering design, especially to astronautics, aeronautics, marine, machinery, petrochemical industry, architecture, water conservancy, power, instruments and transportation. Analysis of plates and shells originates from the 18th century with the development of industry. In the 20th century , the rocketing development of industry greatly stimulated the development and application of this subject. Now, the classical linear theory of thin plates and shells has matured and already been playing a decisive role in many engineering designs. However, there are still many problems left to be solved in the fields on nonlinear theory of thin plates and shells, and linear theory of thick plates and shells. Based on introduction of the history of development of this subject, this paper gives a brief account of the exploration the author did in nearly forty years, which has been well applied to engineering problems, in the areas of nonlinear bending, stability and vibration of thin plates and shells such as corrugated plates and shells, one-layer plates and shells, bimetallic shallow shells of revolution, latticed shallow shells, sandwich plates and shells, and laminated composite plates and shells. The paper also gives an introduction of the author's work on the linear bending of both thick and thin plates and shells.

Keywords： thin plates and shells     thick plates and shells     nonlinear problem     linear problem     bending     stability     vibration    

HTML PDF Collect

Development of the Nuclear Power Human Factors Engineering Field

Yang Mengzhuo

Strategic Study of CAE 2002, Volume 4, Issue 8,   Pages 12-19

Abstract:

The nuclear power human factors engineering is one of the components of nuclear engineering technology. It is a new engineering technology field that researches human - machine interaction and leads the human characteristics into the design of nuclear power technology to obtain safe and effective equipment and systems. The forming, progress and developments of this field are discussed combining the developing way in China. Meanwhile ,the integrated classification theory for human reliability and other research results completed by the author are expounded in this thesis.

Keywords： nuclear power human factors engineering     control room system     human reliability     integrated classification theory    

HTML PDF Collect

State-of-the-Art Review of High-Throughput Statistical Spatial-Mapping Characterization Technology and Its Applications Review

Haizhou Wang, Lei Zhao, Yunhai Jia, Dongling Li, Lixia Yang, Yuhua Lu, Guang Feng, Weihao Wan

Engineering 2020, Volume 6, Issue 6,   Pages 621-636 doi: 10.1016/j.eng.2020.05.005

Abstract:

Macroscopic materials are heterogeneous, multi-elementary, and complex. No material is homogeneous or isotropic at a certain small scale. Parts of the material that differ from one another can be termed ‘‘natural chips.” At different spots on the material, the composition, structure, and properties vary slightly, and the combination of these slight differences establishes the overall material performance. This article presents a state-of-the-art review of research and applications of high-throughput statistical spatialmapping characterization technology based on the intrinsic heterogeneity within materials. Highthroughput statistical spatial-mapping uses a series of rapid characterization techniques for analysis from the macroscopic to the microscopic scale. Datasets of composition, structure, and properties at each location are obtained rapidly for practical sample sizes. Accurate positional coordinate information and references to a point-to-point correspondence are used to set up a database that contains spatialmapping lattices. Based on material research and development design requirements, dataset spatialmapping within required target intervals is selected from the database. Statistical analysis can be used to select a suitable design that better meets the targeted requirements. After repeated verification, genetic units that reflect the material properties are determined. By optimizing process parameters, the assembly of these genetic unit(s) is verified at the mesoscale, and quantitative correlations are established between the microscale, mesoscale, macroscale, practical sample, across-the-scale span composition, structure, and properties. The high-throughput statistical spatial-mapping characterization technology has been applied to numerous material systems, such as steels, superalloys, galvanization, and ferrosilicon alloys. This approach has guided the composition and the process optimization of various materials.

Keywords： Material heterogeneity     High-throughput characterization     Statistical spatial-mapping     Original-position statistical-distribution analysis    

HTML PDF Collect

Title Author Date Type Operation

Latent discriminative representation learning for speaker recognition

Duolin Huang, Qirong Mao, Zhongchen Ma, Zhishen Zheng, Sidheswar Routryar, Elias-Nii-Noi Ocquaye,2211708034@stmail.ujs.edu.cn,mao_qr@ujs.edu.cn,zhongchen_ma@ujs.edu.cn,1209103822@qq.com,sidheswar69@gmail.com,eocquaye@ujs.edu.cn

Journal Article

Histogram equalization using a reduced feature set of background speakers’ utterances for speaker recognition

Myung-jae KIM, Il-ho YANG, Min-seok KIM, Ha-jin YU

Journal Article

A new score normalizaion algorithm based on EMD-Tnorm for speaker verification

Li Yanping,Ding Hui,Tang Zhenmin

Journal Article

Personalizing a Service Robot by Learning Human Habits from Behavioral Footprints

Kun Li, Max Q.-H. Meng

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

Passive millimeter-wave target recognition based on Laplacian eigenmaps

Luo Lei,Li Yuehua,Luan Yinghong

Journal Article

Visual interpretability for deep learning: a survey

Quan-shi ZHANG, Song-chun ZHU

Journal Article

Brain–Computer Interface Speaks up

Chris Palmer

Journal Article

Selective and Independent Control of Microrobots in a Magnetic Field: A Review

Min Wang, Tianyi Wu, Rui Liu, Zhuoran Zhang, Jun Liu

Journal Article

A chaotic coverage path planner for the mobilerobot based on the Chebyshev map for special missions

Cai-hong LI, Yong SONG, Feng-ying WANG, Zhi-qiang WANG, Yi-bin LI

Journal Article

Learning embeddings of a heterogeneous behavior network for potential behavior prediction

Yue-yang WANG, Wei-hao JIANG, Shi-liang PU, Yue-ting ZHUANG

Journal Article

KeJia: towards an autonomous service robotwith tolerance of unexpected environmental changes

Wei SHUAI, Xiao-ping CHEN

Journal Article

Analysis of Plates and Shells and Its Application

Liu Renhuai

Journal Article

Development of the Nuclear Power Human Factors Engineering Field

Yang Mengzhuo

Journal Article

State-of-the-Art Review of High-Throughput Statistical Spatial-Mapping Characterization Technology and Its Applications

Haizhou Wang, Lei Zhao, Yunhai Jia, Dongling Li, Lixia Yang, Yuhua Lu, Guang Feng, Weihao Wan

Journal Article