Resource Type

Journal Article 81

Year

2024 1

2023 11

2022 6

2021 8

2020 9

2019 7

2018 5

2017 5

2016 1

2015 6

2014 1

2010 1

2008 2

2007 2

2006 1

2005 2

2004 4

2003 1

2002 4

2000 4

open ︾

Keywords

Deep learning 3

Artificial intelligence 2

Cancer 2

Coronavirus disease 2019 2

Generative adversarial network 2

Machine learning 2

3D cell containers 1

> existence theorem 1

ACE2 1

AI-generated content 1

ANFIS 1

Accuracy analysis 1

Active learning 1

Adeno-associated virus 1

Adversarial 1

Air traffic management 1

Aircraft model 1

Allergic disease 1

Angiogenesis 1

open ︾

Search scope:

排序： Display mode:

Latent source-specific generative factor learning for monaural speech separation using weighted-factor autoencoder

Jing-jing Chen, Qi-rong Mao, You-cai Qin, Shuang-qing Qian, Zhi-shen Zheng,2221808071@stmail.ujs.edu.cn,mao_qr@ujs.edu.cn,2211908026@stmail.ujs.edu.cn,2211908025@stmail.ujs.edu.cn,3160602062@stmail.ujs.edu.cn

Frontiers of Information Technology & Electronic Engineering 2020, Volume 21, Issue 11,   Pages 1535-1670 doi: 10.1631/FITEE.2000019

Abstract: Much recent progress in monaural (MSS) has been achieved through a series of architectures based on s, which use an encoder to condense the input signal into compressed features and then feed these features into a decoder to construct a specific audio source of interest. However, these approaches can neither learn of the original input for MSS nor construct each audio source in mixed speech. In this study, we propose a novel weighted-factor (WFAE) model for MSS, which introduces a regularization loss in the objective function to isolate one source without containing other sources. By incorporating a latent attention mechanism and a supervised source constructor in the separation layer, WFAE can learn source-specific and a set of discriminative features for each source, leading to MSS performance improvement. Experiments on benchmark datasets show that our approach outperforms the existing methods. In terms of three important metrics, WFAE has great success on a relatively challenging MSS case, i.e., speaker-independent MSS.

Keywords： 语音分离；生成因子；自动编码器；深度学习    

HTML PDF Collect

Study on the Mechanism and Cause Mode of the Karst Collapse——Taking Tai’an-Laiwu for Example

Gao Zongjun

Strategic Study of CAE 2008, Volume 10, Issue 4,   Pages 38-43

Abstract:

The fearful karst collapses have been produced in succession since 1970s by the exploitation of karst water in the area of Tai'an-Laiwu, Shandong province. The limestone buried by Quaternary System grows into karst caves, and karst collapse brings enormous harm to the local society and economy development. The spatio-temporal distributing characteristics of karst collapse are summed up in detail. The geological condition, artificial function and forming mechanism of karst collapse are discussed. The cause mode of the karst collapse aiming at the existing questions is discussed and the idea for karst collapse studying in the future is given at last.

Keywords： Tai’an-Laiwu     karst collaps     spatio-temporal distributing characteristics     forming mechanism     cause mode    

HTML PDF Collect

Research progress of the cause for orange peel of aluminum alloy sheet during tensile deformation

Ma Mingtu,Yang Hongya,Wu Emei and Jin Qingsheng

Strategic Study of CAE 2014, Volume 16, Issue 1,   Pages 4-13

Abstract:

Research progresses of forming causes for orange peel during the tensile deformation of aluminum alloy sheet are reviewed. This paper first shows the surface morphology of tensile deformation of sheets with orange peel and non orange peel，sliding zone，roughness of surface，tensile fracture morphology and nano hardness measurement results and characterization. Recent research results of electron backscattered diffraction（EBSD）using the forming causes of orange peel and the texture measurement results of orange peel and non orange peel using X-ray are further introduced. According to the mentioned results，microstructure and mechanical properties，the forming causes of orange peel are analyzed further. A series of results show the appearance of orange peel surface after tensile deformation is closely related to the texture and grain orientation caused in tensile deformation. The texture generating is closely related to inhomogeneity deformation of grain. Grain size will significantly affect the inhomogeneity deformation and the formation of texture ； coarse grain is easier to cause inhomogeneity deformation，grain rotation and texture than that of fine grain，resulting in surface orange peel forming after tensile deformation. Thus，it introduces a model of surface state of the coarse grain and fine grain after the tensile deformation. It is also suggested that the formation of orange peel should be further researched and analyzed so as to perfect the quantitative description of orange peel formation.

Keywords： orange peel forming     mechanical property     tension fracture     nano hardness     EBSD     X-ray    

HTML PDF Collect

Theoretical analysis and calculation for filling factor of solar cellvarying along with illumination intensity

Ding Jinlei,ChengXiaofang,Zhai Zaiteng,Zha Jun,Mao Meiqin

Strategic Study of CAE 2007, Volume 9, Issue 6,   Pages 82-87

Abstract:

Based on the solar cell DC model and the mathematic expression of maximum power point,  the equations describing short circuit current,  open circuit voltage,  maximum power current,  voltage and filling factor varying along with the illumination intensity are deduced and calculated with two real solar cells data. The fact that short circuit current and maximum power current are proportional to the illumination intensity, and open circuit voltage and maximum power voltage are proportional to the natural logarithm of illumination intensity is certified. The relation of filling factor varying along with the illumination intensity is not a simple functional expression and effected by the solar cell model parameters is present. A simulated experiment is established to valid the theoretic analysis and calculating by Multisim.

Keywords： solar cell     illumination intensity     output characteristics     filling factor    

HTML PDF Collect

Analysis of the Quality of Daily DEM Generation with Geosynchronous InSAR Article

Zefa Yang, Qingjun Zhang, Xiaoli Ding, Wu Chen

Engineering 2020, Volume 6, Issue 8,   Pages 913-918 doi: 10.1016/j.eng.2020.07.003

Abstract:

Up-to-date digital elevation model (DEM) products are essential in many fields such as hazards mitigation and urban management. Airborne and low-earth-orbit (LEO) space-borne interferometric synthetic aperture radar (InSAR) has been proven to be a valuable tool for DEM generation. However, given the limitations of cost and satellite repeat cycles, it is difficult to generate or update DEMs very frequently (e.g., on a daily basis) for a very large area (e.g., continental scale or greater). Geosynchronous synthetic aperture radar (GEOSAR) satellites fly in geostationary earth orbits, allowing them to observe the same ground area with a very short revisit time (daily or shorter). This offers great potential for the daily DEM generation that is desirable yet thus far impossible with space-borne sensors. In this work, we systematically analyze the quality of daily GEOSAR DEM. The results indicate that the accuracy of a daily GEOSAR DEM is generally much lower than what can be achieved with typical LEO synthetic aperture radar (SAR) sensors; therefore, it is important to develop techniques to mitigate the effects of errors in GEOSAR DEM generation.

Keywords： Daily digital elevation model     Interferometric synthetic aperture radar     Geosynchronous synthetic aperture radar     Accuracy analysis    

HTML PDF Collect

SmartPaint: a co-creative drawing system based on generative adversarial networks Special Feature on Intelligent Design

Lingyun SUN, Pei CHEN, Wei XIANG, Peng CHEN, Wei-yue GAO, Ke-jun ZHANG

Frontiers of Information Technology & Electronic Engineering 2019, Volume 20, Issue 12,   Pages 1644-1656 doi: 10.1631/FITEE.1900386

Abstract: Artificial intelligence (AI) has played a significant role in imitating and producing large-scale designs such as e-commerce banners. However, it is less successful at creative and collaborative design outputs. Most humans express their ideas as rough sketches, and lack the professional skills to complete pleasing paintings. Existing AI approaches have failed to convert varied user sketches into artistically beautiful paintings while preserving their semantic concepts. To bridge this gap, we have developed SmartPaint, a co-creative drawing system based on generative adversarial networks (GANs), enabling a machine and a human being to collaborate in cartoon landscape painting. SmartPaint trains a GAN using triples of cartoon images, their corresponding semantic label maps, and edge detection maps. The machine can then simultaneously understand the cartoon style and semantics, along with the spatial relationships among the objects in the landscape images. The trained system receives a sketch as a semantic label map input, and automatically synthesizes its edge map for stable handling of varied sketches. It then outputs a creative and fine painting with the appropriate style corresponding to the human’s sketch. Experiments confirmed that the proposed SmartPaint system successfully generates high-quality cartoon paintings.

Keywords： Co-creative drawing     Deep learning     Image generation    

HTML PDF Collect

Personalized topic modeling for recommending user-generated content Article

Wei ZHANG, Jia-yu ZHUANG, Xi YONG, Jian-kou LI, Wei CHEN, Zhe-min LI

Frontiers of Information Technology & Electronic Engineering 2017, Volume 18, Issue 5,   Pages 708-718 doi: 10.1631/FITEE.1500402

Abstract: User-generated content (UGC) such as blogs and twitters are exploding in modern Internet services. In such systems, recommender systems are needed to help people filter vast amount of UGC generated by other users. However, traditional rec-ommendation models do not use user authorship of items. In this paper, we show that with this additional information, we can significantly improve the performance of recommendations. A generative model that combines hierarchical topic modeling and matrix factorization is proposed. Empirical results show that our model outperforms other state-of-the-art models, and can provide interpretable topic structures for users and items. Furthermore, since user interests can be inferred from their productions, rec-ommendations can be made for users that do not have any ratings to solve the cold-start problem.

Keywords： User-generated content (UGC)     Collaborative filtering (CF)     Matrix factorization (MF)     Hierarchical topic modeling    

HTML PDF Collect

Cantonese porcelain classification and image synthesis by ensemble learning and generative adversarial network Special Feature on Intelligent Design

Steven Szu-Chi CHEN, Hui CUI, Ming-han DU, Tie-ming FU, Xiao-hong SUN, Yi JI, Henry DUH

Frontiers of Information Technology & Electronic Engineering 2019, Volume 20, Issue 12,   Pages 1632-1643 doi: 10.1631/FITEE.1900399

Abstract: Accurate recognition of modern and traditional porcelain styles is a challenging issue in Cantonese porcelain management due to the large variety and complex elements and patterns. We propose a hybrid system with porcelain style identification and image recreation modules. In the identification module, prediction of an unknown porcelain sample is obtained by logistic regression of ensembled neural networks of top-ranked design signatures, which are obtained by discriminative analysis and transformed features in principal components. The synthesis module is developed based on a conditional generative adversarial network, which enables users to provide a designed mask with porcelain elements to generate synthesized images of Cantonese porcelain. Experimental results of 603 Cantonese porcelain images demonstrate that the proposed model outperforms other methods relative to precision, recall, area under curve of receiver operating characteristic, and confusion matrix. Case studies on image creation indicate that the proposed system has the potential to engage the community in understanding Cantonese porcelain and promote this intangible cultural heritage.

Keywords： Cantonese porcelain     Classification     Generative adversarial network     Creative arts    

HTML PDF Collect

Generative adversarial network based novelty detection usingminimized reconstruction error Article

Huan-gang WANG, Xin LI, Tao ZHANG

Frontiers of Information Technology & Electronic Engineering 2018, Volume 19, Issue 1,   Pages 116-125 doi: 10.1631/FITEE.1700786

Abstract: Generative adversarial network (GAN) is the most exciting machine learning breakthrough in recent years, and it trains the learning model by finding the Nash equilibrium of a two-player zero-sum game. GAN is composed of a generator and a discriminator, both trained with the adversarial learning mechanism. In this paper, we introduce and investigate the use of GAN for novelty detection. In training, GAN learns from ordinary data. Then, using previously unknown data, the generator and the discriminator with the designed decision boundaries can both be used to separate novel patterns from ordinary patterns. The proposed GAN-based novelty detection method demonstrates a competitive performance on the MNIST digit database and the Tennessee Eastman (TE) benchmark process compared with the PCA-based novelty detection methods using Hotelling’s and squared prediction error statistics.

Keywords： Generative adversarial network (GAN)     Novelty detection     Tennessee Eastman (TE) process    

HTML PDF Collect

Comprehensive evaluation factor of optoelectronic properties for transparent conductive metallic mesh films Research Articles

Yilei Zhang, Jinxuan Cao, Zhengang Lu, Heyan Wang, Jiubin Tan,luzhengang@hit.edu.cn

Frontiers of Information Technology & Electronic Engineering 2021, Volume 22, Issue 11,   Pages 1532-1540 doi: 10.1631/FITEE.2000690

Abstract: Finding the optimal optoelectronic properties (zero-order optical transmittance, shielding effectiveness, and stray light uniformity) of is significant for its application in electromagnetic interference shielding areas. However, there are few relevant studies at present. Based on optoelectronic properties, we propose a factor , which is simple in form and can be used to evaluate the mesh with different parameters in a simple and efficient way. The effectivity of is verified by comparing the trend of values with the evaluation results of the . The evaluation factor can also be extended to evaluate the optoelectronic properties of different kinds of es, which makes it extremely favorable for design and application.

Keywords： 金属网栅；TOPSIS法；熵权法；综合评价因子；透明导电膜    

HTML PDF Collect

Learning Rat-Like Behavior for a Small-Scale Biomimetic Robot

Zihang Gao, Guanglu Jia, Hongzhao Xie, Qiang Huang, Toshio Fukuda, Qing Shi

Engineering 2022, Volume 17, Issue 10,   Pages 232-243 doi: 10.1016/j.eng.2022.05.012

Abstract:

Existing biomimetic robots can perform some basic rat-like movement primitives (MPs) and simple behavior with stiff combinations of these MPs. To mimic typical rat behavior with high similarity, we propose parameterizing the behavior using a probabilistic model and movement characteristics. First, an analysis of fifteen 10min video sequences revealed that an actual rat has six typical behaviors in the open
field, and each kind of behavior contains different bio-inspired combinations of eight MPs. We used the softmax classifier to obtain the behavior-movement hierarchical probability model. Secondly, we specified the MPs using movement parameters that are static and dynamic. We obtained the predominant values of the static and dynamic movement parameters using hierarchical clustering and fuzzy C-means
clustering, respectively. These predominant parameters were used for fitting the rat spinal joint trajectory using a second-order Fourier series, and the joint trajectory was generalized using a back propagation neural network with two hidden layers. Finally, the hierarchical probability model and the generalized joint trajectory were mapped to the robot as control policy and commands, respectively. We implemented the six typical behaviors on the robot, and the results show high similarity when compared with the behaviors of actual rats.

Keywords： Biomimetic     Bio-inspired robot     Neural network learning system     Behavior generation    

HTML PDF Collect

Prokaryotic expression and bioactivity analysis of growth hormone and insulin-like growth factor-I from Platichthys stellatus

Xu Yongjiang,Zang Kun,Liu Xuezhou,Shi Bao and Chen Shengyi

Strategic Study of CAE 2015, Volume 17, Issue 1,   Pages 67-73

Abstract:

The mature peptide domain of insulin-like growth factor-I from Platichthys stellatus were amplified with specific primers based on its cDNA sequence. Then the matured peptide fragment was subcloned into the prokaryotic expression vector pET-28a to successfully construct IGF-I/pET-28a recombinant plasmid which were highly expressed in E.coli BL21（DE3） after being induced by IPTG with special fusion polypeptides containing His6 at their N-terminus. The obtained IGF-I polypeptide expressed in form of inclusion bodies with molecular weight of 12.1 kD and maximally accounted for 39.8 % of the whole bacterial protein post 3 h induction with 0.5 mmol/L IPTG at 37 ℃. Western blotting analysis indicated fusion polypeptides had the antigenicity to His6 antibody. The inclusion bodies were denaturalized using 6 mol/L guanidine HCl， purified using Ni-NTA affinity chromatography and annealed by gradient dialysis in urea， then purified proteins with molecular weight of 12.1 kD which was obtained from IGF-I recombinant bacterium. The proliferation experiment showed recombinant IGF-I protein could significantly promote the proliferation of human embryonic kidney cells HEK293T at 0.6 μg/mL and inhibit the proliferation with 1.8 μg/mL which verified its biological activity. Therefore， the IGF-I prokaryotic expression system was successfully constructed in the present study and biologically active IGF-I fusion protein was obtained. The present results would be helpful for better understanding the roles of IGF-I in growth regulation and development of high effective additive for growth promotion of Platichthys stellatus.

Keywords： Platichthys stellatus； insulin-like growth factor-I； prokaryotic expression； bioactivity    

HTML PDF Collect

Surprising Advances in Generative Artificial Intelligence Prompt Amazement—and Worries

Dana Mackenzie

Engineering 2023, Volume 25, Issue 6,   Pages 9-11 doi: 10.1016/j.eng.2023.04.004

HTML PDF Collect

A-STC: auction-based spanning tree coverage algorithm formotion planning of cooperative robots Research Article

Guan-qiang GAO, Bin XIN

Frontiers of Information Technology & Electronic Engineering 2019, Volume 20, Issue 1,   Pages 18-31 doi: 10.1631/FITEE.1800551

Abstract:

The multi-robot coverage motion planning (MCMP) problem in which every reachable area must be covered is common in multi-robot systems. To deal with the MCMP problem, we propose an efficient, complete, and off-line algorithm, named the “auction-based spanning tree coverage (A-STC)” algorithm. First, the configuration space is divided into mega cells whose size is twice the minimum coverage range of a robot. Based on connection relationships among mega cells, a graph structure can be obtained. A robot that circumnavigates a spanning tree of the graph can generate a coverage trajectory. Then, the proposed algorithm adopts an auction mechanism to construct one spanning tree for each robot. In this mechanism, an auctioneer robot chooses a suitable vertex of the graph as an auction item from neighboring vertexes of its spanning tree by heuristic rules. A bidder robot submits a proper bid to the auctioneer according to the auction vertexes’ relationships with the spanning tree of the robot and the estimated length of its trajectory. The estimated length is calculated based on vertexes and edges in the spanning tree. The bidder with the highest bid is selected as a winner to reduce the makespan of the coverage task. After auction processes, acceptable coverage trajectories can be planned rapidly. Computational experiments validate the effectiveness of the proposed MCMP algorithm and the method for estimating trajectory lengths. The proposed algorithm is also compared with the state-of-the-art algorithms. The comparative results show that the A-STC algorithm has apparent advantages in terms of the running time and the makespan for large crowded configuration spaces.

Keywords： Coverage motion planning     Multi-robot system     Auction algorithm     Spanning tree coverage algorithm    

HTML PDF Collect

Effect of levonorgestrel intrauterine system on IGF-1 and the dependablity study of prevention pelvic inflammatory disease

Wu Xiaojie,Liu Xia,Tao Yueping,Wang Jie

Strategic Study of CAE 2015, Volume 17, Issue 6,   Pages 4-7

Abstract:

Objective: To study the effect of levonorgestrel Intrauterine System on insulin-like growth factor-l (IGF-1) and the result of levonorgestrel Intrauterine System Prevention pelvic inflammatory disease. Methods: The 450 cases of hysteroscopic resection for endometrial polyps divided to study group(198 cases) who were placed levonorgestrel Intrauterine System in uterus after hysteroscopic electroresection, and control group(252 cases) who were not placted at random. The IGF-1 expression of endometrial biopsy specimens during intraoperative and rechected after 6 months were check out by immunohis to chemistry. Patients were followed up for 2Syears to analyse the effluence of pelvic inflammatory disease. Results: All patients had successful surgery. Intraoperative specimens compared with afteroperation specimens of the IGF-1 expression, there was a significant differencesSin study group but control group. Followed up for 2 years, 14 cases has pelvic inflammatory disease in study group,39 cases has pelvic inflammatory disease in control group,there was a significant differences. The thickness of endometrium after operation is lower than before operation in study group but control group. Conclusions:It may be the mainSmechanism of Prevention pelvic inflammatory disease and inhibition endometrium that Levonorgestrel intrauterine system can prevent endometrial IGF-1 expression.

Keywords： levonorgestrel     Intrauterine system insulin-like growth factor-1     pelvic inflammatory disease    

HTML PDF Collect

Title Author Date Type Operation

Latent source-specific generative factor learning for monaural speech separation using weighted-factor autoencoder

Jing-jing Chen, Qi-rong Mao, You-cai Qin, Shuang-qing Qian, Zhi-shen Zheng,2221808071@stmail.ujs.edu.cn,mao_qr@ujs.edu.cn,2211908026@stmail.ujs.edu.cn,2211908025@stmail.ujs.edu.cn,3160602062@stmail.ujs.edu.cn

Journal Article

Study on the Mechanism and Cause Mode of the Karst Collapse——Taking Tai’an-Laiwu for Example

Gao Zongjun

Journal Article

Research progress of the cause for orange peel of aluminum alloy sheet during tensile deformation

Ma Mingtu,Yang Hongya,Wu Emei and Jin Qingsheng

Journal Article

Theoretical analysis and calculation for filling factor of solar cellvarying along with illumination intensity

Ding Jinlei,ChengXiaofang,Zhai Zaiteng,Zha Jun,Mao Meiqin

Journal Article

Analysis of the Quality of Daily DEM Generation with Geosynchronous InSAR

Zefa Yang, Qingjun Zhang, Xiaoli Ding, Wu Chen

Journal Article

SmartPaint: a co-creative drawing system based on generative adversarial networks

Lingyun SUN, Pei CHEN, Wei XIANG, Peng CHEN, Wei-yue GAO, Ke-jun ZHANG

Journal Article

Personalized topic modeling for recommending user-generated content

Wei ZHANG, Jia-yu ZHUANG, Xi YONG, Jian-kou LI, Wei CHEN, Zhe-min LI

Journal Article

Cantonese porcelain classification and image synthesis by ensemble learning and generative adversarial network

Steven Szu-Chi CHEN, Hui CUI, Ming-han DU, Tie-ming FU, Xiao-hong SUN, Yi JI, Henry DUH

Journal Article

Generative adversarial network based novelty detection usingminimized reconstruction error

Huan-gang WANG, Xin LI, Tao ZHANG

Journal Article

Comprehensive evaluation factor of optoelectronic properties for transparent conductive metallic mesh films

Yilei Zhang, Jinxuan Cao, Zhengang Lu, Heyan Wang, Jiubin Tan,luzhengang@hit.edu.cn

Journal Article

Learning Rat-Like Behavior for a Small-Scale Biomimetic Robot

Zihang Gao, Guanglu Jia, Hongzhao Xie, Qiang Huang, Toshio Fukuda, Qing Shi

Journal Article

Prokaryotic expression and bioactivity analysis of growth hormone and insulin-like growth factor-I from Platichthys stellatus

Xu Yongjiang,Zang Kun,Liu Xuezhou,Shi Bao and Chen Shengyi

Journal Article

Surprising Advances in Generative Artificial Intelligence Prompt Amazement—and Worries

Dana Mackenzie

Journal Article

A-STC: auction-based spanning tree coverage algorithm formotion planning of cooperative robots

Guan-qiang GAO, Bin XIN

Journal Article

Effect of levonorgestrel intrauterine system on IGF-1 and the dependablity study of prevention pelvic inflammatory disease

Wu Xiaojie,Liu Xia,Tao Yueping,Wang Jie

Journal Article