Resource Type

Journal Article 54

Year

2024 1

2023 6

2022 4

2021 5

2019 7

2018 2

2017 5

2016 3

2015 1

2014 1

2013 2

2011 2

2010 2

2008 4

2007 1

2006 3

2004 1

2001 2

2000 2

open ︾

Keywords

Support vector regression 2

nuclear safety 2

3D face reconstruction 1

3D interpreted horizon 1

AIDS 1

Abnormal event detection network 1

Abnormal events detection 1

Antibody purification 1

Antigen-binding fragment 1

Artificial intelligence 1

Brain tumor segmentation 1

CPAL 1

Cancer 1

Cardiovascular disease 1

Cascaded regressor 1

Caustics 1

Cavitation application 1

Cavitation nuclei 1

Chemical resistant yarn 1

open ︾

Search scope:

排序： Display mode:

Received signal strength based indoor positioning algorithm using advanced clustering and kernel ridge regression Research Articles

Yanfen Le, Hena Zhang, Weibin Shi, Heng Yao,leyanfen@usst.edu.cn,hyao@usst.edu.cn

Frontiers of Information Technology & Electronic Engineering 2021, Volume 22, Issue 6,   Pages 827-838 doi: 10.1631/FITEE.2000093

Abstract: We propose a novel algorithm based on the . The proposed algorithm can be divided into three steps, an offline phase at which an (AC) strategy is used, an online phase of approximate localization at which is used, and an online phase of precise localization with . Specifically, after offline fingerprint collection and similarity measurement, we employ an AC strategy based on the -medoids clustering algorithm using additional reference points that are geographically located at the outer cluster boundary to enrich the data of each cluster. During the approximate localization, RSS measurements are compared with the cluster radio maps to determine to which cluster the target most likely belongs. Both the Euclidean distance of the RSSs and the Hamming distance of the coverage vectors between the observations and training records are explored for . Then, a kernel-based ridge regression method is used to obtain the ultimate positioning of the target. The performance of the proposed algorithm is evaluated in two typical indoor environments, and compared with those of state-of-the-art algorithms. The experimental results demonstrate the effectiveness and advantages of the proposed algorithm in terms of positioning accuracy and complexity.

Keywords： 室内定位；接收信号强度（RSS）指纹；核岭回归；簇匹配；改进型分簇    

HTML PDF Collect

Image quality assessmentmethod based on nonlinear feature extraction in kernel space Article

Yong DING,Nan LI,Yang ZHAO,Kai HUANG

Frontiers of Information Technology & Electronic Engineering 2016, Volume 17, Issue 10,   Pages 1008-1017 doi: 10.1631/FITEE.1500439

Abstract: To match human perception, extracting perceptual features effectively plays an important role in image quality assessment. In contrast to most existing methods that use linear transformations or models to represent images, we employ a complex mathematical expression of high dimensionality to reveal the statistical characteristics of the images. Furthermore, by introducing kernel methods to transform the linear problem into a nonlinear one, a full-reference image quality assessment method is proposed based on high-dimensional nonlinear feature extraction. Experiments on the LIVE, TID2008, and CSIQ databases demonstrate that nonlinear features offer competitive performance for image inherent quality representation and the proposed method achieves a promising performance that is consistent with human subjective evaluation.

Keywords： Image quality assessment     Full-reference method     Feature extraction     Kernel space     Support vector regression    

HTML PDF Collect

Expanding the Scope of Multivariate Regression Approaches in Cross-Omics Research Article

Xiaoxi Hu, Yue Ma, Yakun Xu, Peiyao Zhao, Jun Wang

Engineering 2021, Volume 7, Issue 12,   Pages 1725-1731 doi: 10.1016/j.eng.2020.05.028

Abstract:

Recent technological advancements and developments have led to a dramatic increase in the amount of high-dimensional data and thus have increased the demand for proper and efficient multivariate regression methods. Numerous traditional multivariate approaches such as principal component analysis have been used broadly in various research areas, including investment analysis, image identification, and population genetic structure analysis. However, these common approaches have the limitations of ignoring the correlations between responses and a low variable selection efficiency. Therefore, in this article, we introduce the reduced rank regression method and its extensions, sparse reduced rank regression and subspace assisted regression with row sparsity, which hold potential to meet the above demands and thus improve the interpretability of regression models. We conducted a simulation study to evaluate their performance and compared them with several other variable selection methods. For different application scenarios, we also provide selection suggestions based on predictive ability and variable selection accuracy. Finally, to demonstrate the practical value of these methods in the field of microbiome research, we applied our chosen method to real population-level microbiome data, the results of which validated our method. Our method extensions provide valuable guidelines for future omics research, especially with respect to multivariate regression, and could pave the way for novel discoveries in microbiome and related research fields.

Keywords： Multivariate regression methods     Reduced rank regression     Sparsity     Dimensionality reduction     Variable selection    

HTML PDF Collect

Mouse Oocyte Enucleation with Surface Tension Assisted Method

Meng Qinggang,Zhu Shien,Zeng Shenming,Zhang Zhongcheng

Strategic Study of CAE 2001, Volume 3, Issue 11,   Pages 65-69

Abstract:

In the present experiment a new simple method-Surface Tension Aided (STA)- for mouse oocyte enucleation is employed and is compared with three other ones. In method STA, the chromosome spindle was squeezed out by the surface tension of the drop edge with the help of micropipette through a slit made in advance in zona pellucida. In method A, the nucleus was aspirated out through a plat end, 25 μm micropipette via the slit. In method B, the nucleus was aspirated out through a 10μm micropipette directly. In method C, the nucleus was assumed just under the first polar body and the enucleating procedure was carried out by aspirated one third of cytoplasm beneath the polarbody. The manipulation time in method A (3 min/oocyte) was significantly longer than that in method STA (1.33min/oocyte), method B (1.30 min/oocyte) and method C (1.41 min/ oocyte) ; The cytoplasm loss in method C (28.4% ) was significantly higher than those in the other three methods. In methods STA, A and B, very small amount (approximately 5% ) of cytoplasm was lost. The accuracy rate of method C (35.3%) was significantly lower than those in the other three methods, the accuracy rate of method STA, A and B was above 95 % and there is no significant differences among these methods. Some of the cytoplasts produced by STA were used for mouse ear fibroblast cell nuclear transfer by electrofusion. Majority (76.1%) of the cell-cytoplast pairs fused to form reconstructed embryos, 85.4 % of reconstituted embryos developed to form pronuclei and 49.4% of them clove to form 2-cell embryos.

Keywords： surface tension assisted     enucleation     oocyte     mouse    

HTML PDF Collect

Development Strategy of Nuclear Safety Technology in China

Peng Shuming, Xia Jiawen, Wang Yiren, Peng Xianke, Huang Hongwen, Zheng Chun, Ding Wenjie

Strategic Study of CAE 2021, Volume 23, Issue 3,   Pages 113-119 doi: 10.15302/J-SSCAE-2021.03.017

Abstract:

Nuclear safety is a key component of the national security system, and it is the foundation and lifeline of the nuclear industry. Advanced and reliable nuclear safety technology is crucial for maintaining and improving intrinsic safety. Therefore, conducting strategic research on nuclear safety technologies is important for enhancing the nuclear industry in China. In this article, we conduct an in-depth research on China’s nuclear safety technology system using methods including academician interviews, field surveys, conference discussion, and literature review. The results show that, guiding by the overall national security and the nuclear safety concepts, China’s nuclear safety technology has made significant progress in recent years and its nuclear safety performance is good. However, China’s nuclear safety technology system still face several bottleneck problems. For example, the nuclear safety standards system needs improvement, the overall planning of nuclear safety software research and development is insufficient, and the precision and advanced nuclear safety equipment still depends on foreign countries. To continuously modernize the nuclear safety governance system and governance capacities and strengthen China’s nuclear industry, several suggestions are proposed. First, the nuclear safety standards system should be further improved. Second, independent nuclear safety software with high quality should be promoted by coordinating scientific research resources to tackle key problems. Third, government, industry, university, research, and application need to be coordinated to research and develop high-end nuclear safety equipment.

Keywords： nuclear safety technology     standards system     nuclear safety software     nuclear safety equipment    

HTML PDF Collect

Interactive image segmentation with a regression based ensemble learning paradigm Article

Jin ZHANG, Zhao-hui TANG, Wei-hua GUI, Qing CHEN, Jin-ping LIU

Frontiers of Information Technology & Electronic Engineering 2017, Volume 18, Issue 7,   Pages 1002-1020 doi: 10.1631/FITEE.1601401

Abstract: To achieve fine segmentation of complex natural images, people often resort to an interactive segmentation paradigm, since fully automatic methods often fail to obtain a result consistent with the ground truth. However, when the foreground and background share some similar areas in color, the fine segmentation result of conventional interactive methods usually relies on the increase of manual labels. This paper presents a novel interactive image segmentation method via a regression-based ensemble model with semi-supervised learning. The task is formulated as a non-linear problem integrating two complementary spline regressors and strengthening the robustness of each regressor via semi-supervised learning. First, two spline regressors with a complementary nature are constructed based on multivariate adaptive regression splines (MARS) and smooth thin plate spline regression (TPSR). Then, a regressor boosting method based on a clustering hypothesis and semi-supervised learning is proposed to assist the training of MARS and TPSR by using the region segmentation information contained in unlabeled pixels. Next, a support vector regression (SVR) based decision fusion model is adopted to integrate the results of MARS and TPSR. Finally, the GraphCut is introduced and combined with the SVR ensemble results to achieve image segmentation. Extensive experimental results on benchmark datasets of BSDS500 and Pascal VOC have demonstrated the effectiveness of our method, and the com-parison with experiment results has validated that the proposed method is comparable with the state-of-the-art methods for in-teractive natural image segmentation.

Keywords： Interactive image segmentation     Multivariate adaptive regression splines (MARS)     Ensemble learning     Thin-plate spline regression (TPSR)     Semi-supervised learning     Support vector regression (SVR)    

HTML PDF Collect

Fastigial Nucleus Electrical Stimulation and Central Neurogenic Neuroprotection

Dong Weiwei

Strategic Study of CAE 2001, Volume 3, Issue 11,   Pages 32-38

Abstract:

Brian can protect itself from ischemia and/or hypoxia by two distinct mechanisms which probably involve two separate systems of neurons in the CNS. The first ome mediates a reflex neurogenic neuroprotection, which is associated with oxygen-sensitive sympathoexcitatory reticulospinal neurons of rostral ventrolateral medula oblongata. It can be excited within seconds by reduction in blood flow or oxygen and initiate an oxygen conserving reflex. The second is conditioned central neurogenic neuroprotection, which is represented in intrinsic neurons in cerebellar fastigial nucleus. It can be initiated by electrical excitation of intrinsic neurons of fastigial nucleus and afford a persisting for almost two weeks neuroprotection. This mode of neuroprotection is not restricted to focal ischmia,it also protects the brain against global ischemia and excitotoxic cell injury. The ne-oruprotective mechanism of the system is associated with reduced excitability of cortical neurons, inhibition of the onset of necrosis and apoptosis of ischemic neurons, reduced expression of many detrimental factors including Caspase-3 and NF-kappaB, and reduced immunoreactivity of cerebral microvessels. Fastigial neucleus stimulation can also promote the recovery of neurological deficits and can somewhat improve the cognitive function. Some prelimilary observations of clinical application of fastigial nucleus electrical stimulation on protecting neurons from ischemic injury and treating patients with stroke are presented. Recommendations of further research on fastigial nucleus stimulation before its broad clinical practice are provided.

Keywords： neuroprotection     conditioned     fastigial neucleus     stimulation     cerebral ischemia    

HTML PDF Collect

The realization of automatic positioning of crane in high precise in the storehouse for nuclear waste

Luan Xiuchun,Han Weishi,Wang Junling,Yang Aiguang

Strategic Study of CAE 2010, Volume 12, Issue 3,   Pages 45-50

Abstract:

This paper sets forth the realization of automatic positioning of crane in high precise in the storehouse for nuclear waste, including the hardware configuration and software configuration of the control system, the control logic, the program structure and the the function curve of frequency control, and the results of field test are given.

Keywords： nuclear waste     crane     automatic control     positioning    

HTML PDF Collect

On 3Dface reconstruction via cascaded regression in shape space Article

Feng LIU, Dan ZENG, Jing LI, Qi-jun ZHAO

Frontiers of Information Technology & Electronic Engineering 2017, Volume 18, Issue 12,   Pages 1978-1990 doi: 10.1631/FITEE.1700253

Abstract: Cascaded regression has been recently applied to reconstruct 3D faces from single 2D images directly in shape space, and has achieved state-of-the-art performance. We investigate thoroughly such cascaded regression based 3D face reconstruction approaches from four perspectives that are not well been studied: (1) the impact of the number of 2D landmarks; (2) the impact of the number of 3D vertices; (3) the way of using standalone automated landmark detection methods; (4) the convergence property. To answer these questions, a simplified cascaded regression based 3D face reconstruction method is devised. This can be integrated with standalone automated landmark detection methods and reconstruct 3D face shapes that have the same pose and expression as the input face images, rather than normalized pose and expression. An effective training method is also proposed by disturbing the automatically detected landmarks. Comprehensive evaluation experiments have been carried out to compare to other 3D face reconstruction methods. The results not only deepen the understanding of cascaded regression based 3D face reconstruction approaches, but also prove the effectiveness of the proposed method.

Keywords： 3D face reconstruction     Cascaded regressor     Shape space     Real-time    

HTML PDF Collect

Unsupervised feature selection via joint local learning and group sparse regression Regular Papers

Yue WU, Can WANG, Yue-qing ZHANG, Jia-jun BU

Frontiers of Information Technology & Electronic Engineering 2019, Volume 20, Issue 4,   Pages 538-553 doi: 10.1631/FITEE.1700804

Abstract:

Feature selection has attracted a great deal of interest over the past decades. By selecting meaningful feature subsets, the performance of learning algorithms can be effectively improved. Because label information is expensive to obtain, unsupervised feature selection methods are more widely used than the supervised ones. The key to unsupervised feature selection is to find features that effectively reflect the underlying data distribution. However, due to the inevitable redundancies and noise in a dataset, the intrinsic data distribution is not best revealed when using all features. To address this issue, we propose a novel unsupervised feature selection algorithm via joint local learning and group sparse regression (JLLGSR). JLLGSR incorporates local learning based clustering with group sparsity regularized regression in a single formulation, and seeks features that respect both the manifold structure and group sparse structure in the data space. An iterative optimization method is developed in which the weights finally converge on the important features and the selected features are able to improve the clustering results. Experiments on multiple real-world datasets (images, voices, and web pages) demonstrate the effectiveness of JLLGSR.

Keywords： Unsupervised     Local learning     Group sparse regression     Feature selection    

HTML PDF Collect

The role of fusion-fission hybrid reactor in development of China nuclear energy resources

Liu Cheng’an,Shi Xueming

Strategic Study of CAE 2011, Volume 13, Issue 3,   Pages 24-28

Abstract:

The strategic position of the nuclear energy in the development of China energy resources and the important role of the fusion-fission hybrid reactors in the sustained development of nuclear energy resources are analyzed. The hybrid reactor with ITER fusion device as driving reactor core which could be realized in near future and water-cooled natural uranium fission system as blanked is discussed. With hybrid reactor the 1 GWe net electrical power output and yearly fissile fuel production 1 656 kg that could meet need of 2.68 PWR(pressurized water reactors)for fissile fuel could be attained. A rough economic estimation predict that capital cost of hybrid reactor is 1.67 times as large as capital cost of same power PWR without including the cost of nuclear fuel; the electrical cost of combined system of hybrid reactor and PWR is 1.18 times of electrical cost of same power PWR. Considering cost of fissile fuel that PWR consume, the electricity cost of combined system of hybrid reactor and PWR could be competitive with PWR electricity cost.

Keywords： hybrid reactor     fusion reactor core     fission blanked     fissile nucleus     fissionable nucleus    

HTML PDF Collect

Considerations on Innovation in the Development of Nuclear Agricultural Sciences

Wang Zhidong,Gao Meixu

Strategic Study of CAE 2008, Volume 10, Issue 1,   Pages 86-90

Abstract:

The development status and existing problems in the field of nuclear agricultural sciences (NAS) are reviewed .Including the application of nuclear technology in mutation breeding by irradiation, isotopic technique application, food irradiation and sterile insect technique, etc. China has made great achievements in the research and application of nuclear technique in agriculture from 1950s to 1990s. Due to lack of enough financial support to the basic research and reformation of science & research system in China, the development of NAS now meets its tough time. Through analyzing the difference and reasons of NAS development between China and the USA, it is recognized that the innovation in research and scientific system is important for promoting the development speed and research level of NAS.

Keywords： nuclear agricultural sciences     mutation breeding     isotope application     food irradiation     sterile insect technique     basic theory research     innovations in research and scientific system    

HTML PDF Collect

Frequency-hopping transmitter fingerprint feature recognition with kernel projection and joint representation Research Articles

Ping SUI, Ying GUO, Kun-feng ZHANG, Hong-guang LI

Frontiers of Information Technology & Electronic Engineering 2019, Volume 20, Issue 8,   Pages 1133-1146 doi: 10.1631/FITEE.1800025

Abstract: Frequency-hopping (FH) is one of the commonly used spread spectrum techniques that finds wide applications in communications and radar systems because of its inherent capability of low interception, good confidentiality, and strong antiinterference. However, non-cooperation FH transmitter classification is a significant and challenging issue for FH transmitter fingerprint feature recognition, since it not only is sensitive to noise but also has non-linear, non-Gaussian, and non-stability characteristics, which make it difficult to guarantee the classification in the original signal space. Some existing classifiers, such as the sparse representation classifier (SRC), generally use an individual representation rather than all the samples to classify the test data, which over-emphasizes sparsity but ignores the collaborative relationship among the given set of samples. To address these problems, we propose a novel classifier, called the kernel joint representation classifier (KJRC), for FH transmitter fingerprint feature recognition, by integrating kernel projection, collaborative feature representation, and classifier learning into a joint framework. Extensive experiments on real-world FH signals demonstrate the effectiveness of the proposed method in comparison with several state-of-the-art recognition methods.

Keywords： Frequency-hopping     Fingerprint feature     Kernel function     Joint representation     Transmitter recognition    

HTML PDF Collect

An artificial intelligence based method for evaluating power grid node importance using network embedding and support vector regression Research Papers

Hui-fang WANG, Chen-yu ZHANG, Dong-yang LIN, Ben-teng HE

Frontiers of Information Technology & Electronic Engineering 2019, Volume 20, Issue 6,   Pages 816-828 doi: 10.1631/FITEE.1800146

Abstract:

The identification of important nodes in a power grid has considerable benefits for safety. Power networks vary in many aspects, such as scale and structure. An index system can hardly cover all the information in various situations. Therefore, the efficiency of traditional methods using an index system is case-dependent and not universal. To solve this problem, an artificial intelligence based method is proposed for evaluating power grid node importance. First, using a network embedding approach, a feature extraction method is designed for power grid nodes, considering their structural and electrical information. Then, for a specific power network, steady-state and node fault transient simulations under various operation modes are performed to establish the sample set. The sample set can reflect the relationship between the node features and the corresponding importance. Finally, a support vector regression model is trained based on the optimized sample set for the later online use of importance evaluation. A case study demonstrates that the proposed method can effectively evaluate node importance for a power grid based on the information learned from the samples. Compared with traditional methods using an index system, the proposed method can avoid some possible bias. In addition, a particular sample set for each specific power network can be established under this artificial intelligence based framework, meeting the demand of universality.

Keywords： Power grid     Artificial intelligence     Node importance     Text-associated DeepWalk     Network embedding     Support vector regression    

HTML PDF Collect

Stochastic extra-gradient based alternating direction methods for graph-guided regularizedminimization None

Qiang LAN, Lin-bo QIAO, Yi-jie WANG

Frontiers of Information Technology & Electronic Engineering 2018, Volume 19, Issue 6,   Pages 755-762 doi: 10.1631/FITEE.1601771

Abstract: In this study, we propose and compare stochastic variants of the extra-gradient alternating direction method, named the stochastic extra-gradient alternating direction method with Lagrangian function (SEGL) and the stochastic extra-gradient alternating direction method with augmented Lagrangian function (SEGAL), to minimize the graph-guided optimization problems, which are composited with two convex objective functions in large scale. A number of important applications in machine learning follow the graph-guided optimization formulation, such as linear regression, logistic regression, Lasso, structured extensions of Lasso, and structured regularized logistic regression. We conduct experiments on fused logistic regression and graph-guided regularized regression. Experimental results on several genres of datasets demonstrate that the proposed algorithm outperforms other competing algorithms, and SEGAL has better performance than SEGL in practical use.

Keywords： Stochastic optimization     Graph-guided minimization     Extra-gradient method     Fused logistic regression     Graph-guided regularized logistic regression    

HTML PDF Collect

Title Author Date Type Operation

Received signal strength based indoor positioning algorithm using advanced clustering and kernel ridge regression

Yanfen Le, Hena Zhang, Weibin Shi, Heng Yao,leyanfen@usst.edu.cn,hyao@usst.edu.cn

Journal Article

Image quality assessmentmethod based on nonlinear feature extraction in kernel space

Yong DING,Nan LI,Yang ZHAO,Kai HUANG

Journal Article

Expanding the Scope of Multivariate Regression Approaches in Cross-Omics Research

Xiaoxi Hu, Yue Ma, Yakun Xu, Peiyao Zhao, Jun Wang

Journal Article

Mouse Oocyte Enucleation with Surface Tension Assisted Method

Meng Qinggang,Zhu Shien,Zeng Shenming,Zhang Zhongcheng

Journal Article

Development Strategy of Nuclear Safety Technology in China

Peng Shuming, Xia Jiawen, Wang Yiren, Peng Xianke, Huang Hongwen, Zheng Chun, Ding Wenjie

Journal Article

Interactive image segmentation with a regression based ensemble learning paradigm

Jin ZHANG, Zhao-hui TANG, Wei-hua GUI, Qing CHEN, Jin-ping LIU

Journal Article

Fastigial Nucleus Electrical Stimulation and Central Neurogenic Neuroprotection

Dong Weiwei

Journal Article

The realization of automatic positioning of crane in high precise in the storehouse for nuclear waste

Luan Xiuchun,Han Weishi,Wang Junling,Yang Aiguang

Journal Article

On 3Dface reconstruction via cascaded regression in shape space

Feng LIU, Dan ZENG, Jing LI, Qi-jun ZHAO

Journal Article

Unsupervised feature selection via joint local learning and group sparse regression

Yue WU, Can WANG, Yue-qing ZHANG, Jia-jun BU

Journal Article

The role of fusion-fission hybrid reactor in development of China nuclear energy resources

Liu Cheng’an,Shi Xueming

Journal Article

Considerations on Innovation in the Development of Nuclear Agricultural Sciences

Wang Zhidong,Gao Meixu

Journal Article

Frequency-hopping transmitter fingerprint feature recognition with kernel projection and joint representation

Ping SUI, Ying GUO, Kun-feng ZHANG, Hong-guang LI

Journal Article

An artificial intelligence based method for evaluating power grid node importance using network embedding and support vector regression

Hui-fang WANG, Chen-yu ZHANG, Dong-yang LIN, Ben-teng HE

Journal Article

Stochastic extra-gradient based alternating direction methods for graph-guided regularizedminimization

Qiang LAN, Lin-bo QIAO, Yi-jie WANG

Journal Article