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
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
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
Keywords: Speaker recognition Histogram equalization i-vector
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
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
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
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
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
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
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
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
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
Keywords: Artificial intelligence Deep learning Interpretable model
Brain–Computer Interface Speaks up
Chris Palmer
Engineering 2022, Volume 9, Issue 2, Pages 3-5 doi: 10.1016/j.eng.2021.12.004
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
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
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
Keywords: Mobile robot Chebyshev map Chaotic Affine transformation Coverage path planning
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
Keywords: Network embedding Representation learning Human behavior Social networks Heterogeneous information network Attribute
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
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
Analysis of Plates and Shells and Its Application
Liu Renhuai
Strategic Study of CAE 2000, Volume 2, Issue 11, Pages 60-67
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
Development of the Nuclear Power Human Factors Engineering Field
Yang Mengzhuo
Strategic Study of CAE 2002, Volume 4, Issue 8, Pages 12-19
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
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
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
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
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