Articles de revues : « LSGAN »

1

Nie, Jianghua, Yongsheng Xiao, Lizhen Huang et Feng Lv. « Time-Frequency Analysis and Target Recognition of HRRP Based on CN-LSGAN, STFT, and CNN ». Complexity 2021 (12 avril 2021) : 1–10. http://dx.doi.org/10.1155/2021/6664530.

Texte intégral

Résumé :

Aiming at the problem of radar target recognition of High-Resolution Range Profile (HRRP) under low signal-to-noise ratio conditions, a recognition method based on the Constrained Naive Least-Squares Generative Adversarial Network (CN-LSGAN), Short-time Fourier Transform (STFT), and Convolutional Neural Network (CNN) is proposed. Combining the Least-Squares Generative Adversarial Network (LSGAN) with the Wasserstein Generative Adversarial Network with Gradient Penalty (WGAN-GP), the CN-LSGAN is presented and applied to the HRRP denoise. The frequency domain and phase features of HRRP are gained by STFT in order to facilitate feature learning and also match the input data format of the CNN. These experimental results show that the CN-LSGAN has better data augmentation performance and can effectively avoid the model collapse compared to the generative adversarial network (GAN) and LSGAN. Also, the method has better recognition performance than the one-dimensional CNN method and the Long Short-Term Memory (LSTM) network method.

Styles APA, Harvard, Vancouver, ISO, etc.

2

Yue, Yunpeng, Hai Liu, Xu Meng, Yinguang Li et Yanliang Du. « Generation of High-Precision Ground Penetrating Radar Images Using Improved Least Square Generative Adversarial Networks ». Remote Sensing 13, n^o 22 (15 novembre 2021) : 4590. http://dx.doi.org/10.3390/rs13224590.

Texte intégral

Résumé :

Deep learning models have achieved success in image recognition and have shown great potential for interpretation of ground penetrating radar (GPR) data. However, training reliable deep learning models requires massive labeled data, which are usually not easy to obtain due to the high costs of data acquisition and field validation. This paper proposes an improved least square generative adversarial networks (LSGAN) model which employs the loss functions of LSGAN and convolutional neural networks (CNN) to generate GPR images. This model can generate high-precision GPR data to address the scarcity of labelled GPR data. We evaluate the proposed model using Frechet Inception Distance (FID) evaluation index and compare it with other existing GAN models and find it outperforms the other two models on a lower FID score. In addition, the adaptability of the LSGAN-generated images for GPR data augmentation is investigated by YOLOv4 model, which is employed to detect rebars in field GPR images. It is verified that inclusion of LSGAN-generated images in the training GPR dataset can increase the target diversity and improve the detection precision by 10%, compared with the model trained on the dataset containing 500 field GPR images.

Styles APA, Harvard, Vancouver, ISO, etc.

3

Aguirre, Nicolas, Leandro J. Cymberknop, Edith Grall-Maës, Eugenia Ipar et Ricardo L. Armentano. « Central Arterial Dynamic Evaluation from Peripheral Blood Pressure Waveforms Using CycleGAN : An In Silico Approach ». Sensors 23, n^o 3 (1 février 2023) : 1559. http://dx.doi.org/10.3390/s23031559.

Texte intégral

Résumé :

Arterial stiffness is a major condition related to many cardiovascular diseases. Traditional approaches in the assessment of arterial stiffness supported by machine learning techniques are limited to the pulse wave velocity (PWV) estimation based on pressure signals from the peripheral arteries. Nevertheless, arterial stiffness can be assessed based on the pressure–strain relationship by analyzing its hysteresis loop. In this work, the capacity of deep learning models based on generative adversarial networks (GANs) to transfer pressure signals from the peripheral arterial region to pressure and area signals located in the central arterial region is explored. The studied signals are from a public and validated virtual database. Compared to other works in which the assessment of arterial stiffness was performed via PWV, in the present work the pressure–strain hysteresis loop is reconstructed and evaluated in terms of classical machine learning metrics and clinical parameters. Least-square GAN (LSGAN) and Wasserstein GAN with gradient penalty (WGAN-GP) adversarial losses are compared, yielding better results with LSGAN. LSGAN mean ± standard deviation of error for pressure and area pulse waveforms are 0.8 ± 0.4 mmHg and 0.1 ± 0.1 cm2, respectively. Regarding the pressure–strain elastic modulus, it is achieved a mean absolute percentage error of 6.5 ± 5.1%. GAN-based deep learning models can recover the pressure–strain loop of central arteries while observing pressure signals from peripheral arteries.

Styles APA, Harvard, Vancouver, ISO, etc.

4

Dewi, Christine, Rung-Ching Chen, Yan-Ting Liu et Hui Yu. « Various Generative Adversarial Networks Model for Synthetic Prohibitory Sign Image Generation ». Applied Sciences 11, n^o 7 (24 mars 2021) : 2913. http://dx.doi.org/10.3390/app11072913.

Texte intégral

Résumé :

A synthetic image is a critical issue for computer vision. Traffic sign images synthesized from standard models are commonly used to build computer recognition algorithms for acquiring more knowledge on various and low-cost research issues. Convolutional Neural Network (CNN) achieves excellent detection and recognition of traffic signs with sufficient annotated training data. The consistency of the entire vision system is dependent on neural networks. However, locating traffic sign datasets from most countries in the world is complicated. This work uses various generative adversarial networks (GAN) models to construct intricate images, such as Least Squares Generative Adversarial Networks (LSGAN), Deep Convolutional Generative Adversarial Networks (DCGAN), and Wasserstein Generative Adversarial Networks (WGAN). This paper also discusses, in particular, the quality of the images produced by various GANs with different parameters. For processing, we use a picture with a specific number and scale. The Structural Similarity Index (SSIM) and Mean Squared Error (MSE) will be used to measure image consistency. Between the generated image and the corresponding real image, the SSIM values will be compared. As a result, the images display a strong similarity to the real image when using more training images. LSGAN outperformed other GAN models in the experiment with maximum SSIM values achieved using 200 images as inputs, 2000 epochs, and size 32 × 32.

Styles APA, Harvard, Vancouver, ISO, etc.

5

Man, Zhenlong, Jinqing Li, Xiaoqiang Di, Xu Liu, Jian Zhou, Jia Wang et Xingxu Zhang. « A novel image encryption algorithm based on least squares generative adversarial network random number generator ». Multimedia Tools and Applications 80, n^o 18 (20 mai 2021) : 27445–69. http://dx.doi.org/10.1007/s11042-021-10979-w.

Texte intégral

Résumé :

AbstractIn cryptosystems, the generation of random keys is crucial. The random number generator is required to have a sufficiently fast generation speed to ensure the size of the keyspace. At the same time, the randomness of the key is an important indicator to ensure the security of the encryption system. The chaotic random number generator has been widely used in cryptosystems due to the uncertainty, non-repeatability, and unpredictability of chaotic systems. However, chaotic systems, especially high-dimensional chaotic systems, have slow calculation speed and long iteration time. This caused a conflict between the number of random keys and the speed of generation. In this paper, we introduce the Least Squares Generative Adversarial Networks(LSGAN)into random number generation. Using LSGAN’s powerful learning ability, a novel learning random number generator is constructed. Six chaotic systems with different structures and different dimensions are used as training sets to realize the rapid and efficient generation of random numbers. Experimental results prove that the encryption key generated by this scheme can pass all randomness tests of the National Institute of Standards and Technology (NIST). Hence, our result shows that LSGAN has the potential to improve the quality of the random number generators. Finally, the results are successfully applied to the image encryption scheme based on selective scrambling and overlay diffusion, and good results are achieved.

Styles APA, Harvard, Vancouver, ISO, etc.

6

Bhatia, Himesh, William Paul, Fady Alajaji, Bahman Gharesifard et Philippe Burlina. « Least kth-Order and Rényi Generative Adversarial Networks ». Neural Computation 33, n^o 9 (19 août 2021) : 2473–510. http://dx.doi.org/10.1162/neco_a_01416.

Texte intégral

Résumé :

Abstract We investigate the use of parameterized families of information-theoretic measures to generalize the loss functions of generative adversarial networks (GANs) with the objective of improving performance. A new generator loss function, least kth-order GAN (LkGAN), is introduced, generalizing the least squares GANs (LSGANs) by using a kth-order absolute error distortion measure with k≥1 (which recovers the LSGAN loss function when k=2). It is shown that minimizing this generalized loss function under an (unconstrained) optimal discriminator is equivalent to minimizing the kth-order Pearson-Vajda divergence. Another novel GAN generator loss function is next proposed in terms of Rényi cross-entropy functionals with order α>0, α≠1. It is demonstrated that this Rényi-centric generalized loss function, which provably reduces to the original GAN loss function as α→1, preserves the equilibrium point satisfied by the original GAN based on the Jensen-Rényi divergence, a natural extension of the Jensen-Shannon divergence. Experimental results indicate that the proposed loss functions, applied to the MNIST and CelebA data sets, under both DCGAN and StyleGAN architectures, confer performance benefits by virtue of the extra degrees of freedom provided by the parameters k and α, respectively. More specifically, experiments show improvements with regard to the quality of the generated images as measured by the Fréchet inception distance score and training stability. While it was applied to GANs in this study, the proposed approach is generic and can be used in other applications of information theory to deep learning, for example, the issues of fairness or privacy in artificial intelligence.

Styles APA, Harvard, Vancouver, ISO, etc.

7

Jia-Li Li, Jia-Li Li, Xing-Guo Jiang Jia-Li Li, Li He Xing-Guo Jiang et De-Cai Li Li He. « Face Age Feature Analysis Based on Improved Conditional Adversarial Auto-encoder (I-CAAE) ». 電腦學刊 34, n^o 1 (février 2023) : 063–73. http://dx.doi.org/10.53106/199115992023023401005.

Texte intégral

Résumé :

<p>In recent years, the research of face age features has achieved rapid development driven by deep learning. The faces generated by the Conditional Adversarial Auto-encoder (CAAE) model are not only highly credible, but also closer to the target age. However, there are many problems, such as low resolution of human face image generation and poor local feature retention effect of human face features. To this end, this paper improves on the CAAE network. Firstly, referring to the LSGAN network structure, the 4 convolution layers of the encoder are added to 5 layers and the 4 convolution layers of the generator are added to 7 layers. Secondly, on the basis of the original loss function, the image gradient difference loss function is added to ensure the output face image quality. Meanwhile, the data set were preprocessed for face correction. Finally, this paper performs face similarity analysis on the Eye-key platform and contrasts the generated image quality using structural similarity and peak signal to noise ratio metrics. In addition, the generated results were tested for their robustness. The experimental results show that the average similarity of faces generated by the Improved Conditional Adversarial Auto-encoder (I-CAAE) network was increased by 3.9. And the average peak signal to noise ratio of the generated pictures was reduced by 1.8. Confirming the superiority of the proposed method.</p> <p> </p>

Styles APA, Harvard, Vancouver, ISO, etc.

8

Tataryn, T., D. Savytskii, L. Vasylechko, C. Paulmann et U. Bismayer. « Crystal and twin structure in LSGMn crystals ». Acta Crystallographica Section A Foundations of Crystallography 68, a1 (7 août 2012) : s181. http://dx.doi.org/10.1107/s0108767312096511.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

9

Liu, Jia-Bao, et Ali Zafari. « Computing Minimal Doubly Resolving Sets and the Strong Metric Dimension of the Layer Sun Graph and the Line Graph of the Layer Sun Graph ». Complexity 2020 (24 septembre 2020) : 1–8. http://dx.doi.org/10.1155/2020/6267072.

Texte intégral

Résumé :

Let G be a finite, connected graph of order of, at least, 2 with vertex set VG and edge set EG. A set S of vertices of the graph G is a doubly resolving set for G if every two distinct vertices of G are doubly resolved by some two vertices of S. The minimal doubly resolving set of vertices of graph G is a doubly resolving set with minimum cardinality and is denoted by ψG. In this paper, first, we construct a class of graphs of order 2n+Σr=1k−2nmr, denoted by LSGn,m,k, and call these graphs as the layer Sun graphs with parameters n, m, and k. Moreover, we compute minimal doubly resolving sets and the strong metric dimension of the layer Sun graph LSGn,m,k and the line graph of the layer Sun graph LSGn,m,k.

Styles APA, Harvard, Vancouver, ISO, etc.

10

Yang, Cheng-Hong, Sin-Hua Moi, Yu-Da Lin et Li-Yeh Chuang. « Genetic Algorithm Combined with a Local Search Method for Identifying Susceptibility Genes ». Journal of Artificial Intelligence and Soft Computing Research 6, n^o 3 (1 juillet 2016) : 203–12. http://dx.doi.org/10.1515/jaiscr-2016-0015.

Texte intégral

Résumé :

Abstract Detecting genetic association models between single nucleotide polymorphisms (SNPs) in various disease-related genes can help to understand susceptibility to disease. Statistical tools have been widely used to detect significant genetic association models, according to their related statistical values, including odds ratio (OR), chi-square test (χ2), p-value, etc. However, the high number of computations entailed in such operations may limit the capacity of such statistical tools to detect high-order genetic associations. In this study, we propose lsGA algorithm, a genetic algorithm based on local search method, to detect significant genetic association models amongst large numbers of SNP combinations. We used two disease models to simulate the large data sets considering the minor allele frequency (MAF), number of SNPs, and number of samples. The three-order epistasis models were evaluated by chi-square test (χ2) to evaluate the significance (P-value < 0.05). Analysis results showed that lsGA provided higher chi-square test values than that of GA. Simple linear regression indicated that lsGA provides a significant advantage over GA, providing the highest β values and significant p-value.

Styles APA, Harvard, Vancouver, ISO, etc.

11

Kabir, Homayun, Jeevan Kanesan, Ahmed Wasif Reza et Harikrishnan Ramiah. « A Mathematical Algorithm of Locomotive Source Localization Based on Hyperbolic Technique ». International Journal of Distributed Sensor Networks 2015 (2015) : 1–9. http://dx.doi.org/10.1155/2015/384180.

Texte intégral

Résumé :

Recent trend shows that sensors situated on an axis in two-dimensional scenario measuring the time difference of arrival (TDOA) and frequency difference of arrival (FDOA) of the emitting signal from a moving source can estimate the emitting signal’s position and velocity from the intersection point of hyperbola, which derives from TDOA and FDOA. However, estimating the location of an emitter based on hyperbolic measurements is a highly nonlinear problem with inconsistent data, which are created due to the measurement noise, the deviation between assumption model and actual field of the velocity, and so forth. In addition, the coefficient matrix of TDOA and FDOA equations set is singular in the linear sensor array network (LSAN). In this paper, a noniterative and simpler method is proposed to locate the instantaneous position of the moving source in LSAN by estimating the position and velocity based on TDOA and FDOA which does not have the convergence problem. In addition, the method avoids the singularity problem of LSAN by introducing the nuisance variables. The proposed method achieved the theoretical lower bound for near to far field with same and different velocity and different baseline of sensors in low to moderate noise.

Styles APA, Harvard, Vancouver, ISO, etc.

12

Stratulat, Lacramioara, Maria Geba et Daniela Salajan. « Village from Muscel by Ion Marinescu Valsan State of Conservation and the Chromatic Palette ». Revista de Chimie 69, n^o 12 (15 janvier 2019) : 3464–68. http://dx.doi.org/10.37358/rc.18.12.6770.

Texte intégral

Résumé :

Ion Marinescu V�lsan (1865 - 1936) was a Romanian painter belonging to the modern Romanian art from the beginning of the 20th century. Many of the paintings painted by him have picturesque landscapes in his native town, Malureni, Arges County. He was influencedby Nicolae Grigorescu. Village from Muscel painting, by Ion Marinescu V�lsan, was examined by several non-invasive techniques (Vis, UV &grazing light examination, IR reflectography, optical microscopy and X-rays fluorescence spectrometry) to obtain information on its chromatic palette and state of conservation. Zinc white, Lead white, Prussian blue, Cinnabar, Chrome yellow, Yellow ochre, Red ochre, Viridian and Burnt umber were used as the pigments, while the preparation layer is from Chalk, Zinc white, Lead white, identified by XRF analysis.

Styles APA, Harvard, Vancouver, ISO, etc.

13

Curr, Kenneth, Snehlata Tripathi, Johan Lennerstrand, Brendan A. Larder et Vinayaka R. Prasad. « Influence of naturally occurring insertions in the fingers subdomain of human immunodeficiency virus type 1 reverse transcriptase on polymerase fidelity and mutation frequencies in vitro ». Journal of General Virology 87, n^o 2 (1 février 2006) : 419–28. http://dx.doi.org/10.1099/vir.0.81458-0.

Texte intégral

Résumé :

The fingers subdomain of human immunodeficiency virus type 1 (HIV-1) reverse transcriptase (RT) is a hotspot for nucleoside analogue resistance mutations. Some multi-nucleoside analogue-resistant variants contain a T69S substitution along with dipeptide insertions between residues 69 and 70. This set of mutations usually co-exists with classic zidovudine-resistance mutations (e.g. M41L and T215Y) or an A62V mutation and confers resistance to multiple nucleoside analogue inhibitors. As insertions lie in the vicinity of the dNTP-binding pocket, their influence on RT fidelity was investigated. Commonly occurring insertion mutations were selected, i.e. T69S-AG, T69S-SG and T69S-SS alone, in combination with 3′-azido-2′,3′-deoxythymidine-resistance mutations M41L, L210W, R211K, L214F, T215Y (LAGAZ and LSGAZ) or with an alternate set where A62V substitution replaces M41L (VAGAZ, VSGAZ and VSSAZ). Using a lacZα gapped duplex substrate, the forward mutation frequencies of recombinant wild-type and mutant RTs bearing each of the above sets of mutations were measured. All of the mutants displayed significant decreases in mutation frequencies. Whereas the dipeptide insertions alone showed the least decrease (4·0- to 7·5-fold), the VAG series showed an intermediate reduction (5·0- to 11·4-fold) and the LAG set showed the largest reduction in mutation frequencies (15·3- and 16·3-fold for LAGAZ and LSGAZ, respectively). Single dNTP exclusion assays for mutants LSGAZ and LAGAZ confirmed their large reduction in misincorporation efficiencies. The increased in vitro fidelity was not due to excision of the incorrect nucleotide via ATP-dependent removal. There was also no direct correlation between increased fidelity and template–primer affinity, suggesting a change in the active site that is conducive to better discrimination during dNTP insertion.

Styles APA, Harvard, Vancouver, ISO, etc.

14

Ghosh, Payel, Melanie Mitchell et Judith Gold. « LSGA : combining level-sets and genetic algorithms for segmentation ». Evolutionary Intelligence 3, n^o 1 (21 février 2010) : 1–11. http://dx.doi.org/10.1007/s12065-010-0036-x.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

15

Sturesson, Lennart, et Charlotte Froese Fischer. « LSGEN - a program to generate configuration-state lists of LS-coupled basis functions ». Computer Physics Communications 74, n^o 3 (mars 1993) : 432–40. http://dx.doi.org/10.1016/0010-4655(93)90024-7.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

16

Chen, Bingzhi, Yishu Liu, Zheng Zhang, Yingjian Li, Zhao Zhang, Guangming Lu et Hongbing Yu. « Deep Active Context Estimation for Automated COVID-19 Diagnosis ». ACM Transactions on Multimedia Computing, Communications, and Applications 17, n^o 3s (31 octobre 2021) : 1–22. http://dx.doi.org/10.1145/3457124.

Texte intégral

Résumé :

Many studies on automated COVID-19 diagnosis have advanced rapidly with the increasing availability of large-scale CT annotated datasets. Inevitably, there are still a large number of unlabeled CT slices in the existing data sources since it requires considerable consuming labor efforts. Notably, cinical experience indicates that the neighboring CT slices may present similar symptoms and signs. Inspired by such wisdom, we propose DACE, a novel CNN-based deep active context estimation framework, which leverages the unlabeled neighbors to progressively learn more robust feature representations and generate a well-performed classifier for COVID-19 diagnosis. Specifically, the backbone of the proposed DACE framework is constructed by a well-designed Long-Short Hierarchical Attention Network (LSHAN), which effectively incorporates two complementary attention mechanisms, i.e., short-range channel interactions (SCI) module and long-range spatial dependencies (LSD) module, to learn the most discriminative features from CT slices. To make full use of such available data, we design an efficient context estimation criterion to carefully assign the additional labels to these neighbors. Benefiting from two complementary types of informative annotations from -nearest neighbors, i.e., the majority of high-confidence samples with pseudo labels and the minority of low-confidence samples with hand-annotated labels, the proposed LSHAN can be fine-tuned and optimized in an incremental learning manner. Extensive experiments on the Clean-CC-CCII dataset demonstrate the superior performance of our method compared with the state-of-the-art baselines.

Styles APA, Harvard, Vancouver, ISO, etc.

17

Tataryn, T., L. Vasylechko, D. Savytskii, M. Berkowski, C. Paulmann, U. Bismayer et A. Tarnavsky. « Thermal behaviour of crystal and domain structure of LSGMn-05 anode material for SOFC ». Solid State Ionics 240 (juin 2013) : 29–33. http://dx.doi.org/10.1016/j.ssi.2013.03.026.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

18

Fade, Geraldine, Fabienne Gobel, Eric Pele, Benoit Chaput, Ignacio Garrido, Vincent Pinsolle, Philippe Pelissier et Raphael Sinna. « Anatomical basis of the lateral superior gluteal artery perforator (LSGAP) flap and role in bilateral breast reconstruction ». Journal of Plastic, Reconstructive & ; Aesthetic Surgery 66, n^o 6 (juin 2013) : 756–62. http://dx.doi.org/10.1016/j.bjps.2013.02.017.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

19

Monfared, Mohammad E. Dehghan, et Fazlollah Lak. « Comparing Two MLEs of The Change Point When an lspan style=qtext-decoration:overline;qgligXl/igl/spang Control Chart Is Used ». Journal of Statistical Theory and Applications 16, n^o 2 (2017) : 209. http://dx.doi.org/10.2991/jsta.2017.16.2.6.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

20

Liu, Tao, Xiang Gao, Bei-Gang He et Jing-Kun Yu. « A Limiting Current Oxygen Sensor Based on LSGM as a Solid Electrolyte and LSGMN (N = Fe, Co) as a Dense Diffusion Barrier ». Journal of Materials Engineering and Performance 25, n^o 7 (10 juin 2016) : 2943–50. http://dx.doi.org/10.1007/s11665-016-2171-8.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

21

Sharma, Devilal. « Role of Tax Revenue to Strengthen of Pokhara Sub-Metropolitan Corporation ». Janapriya Journal of Interdisciplinary Studies 2 (17 août 2017) : 51–60. http://dx.doi.org/10.3126/jjis.v2i1.18066.

Texte intégral

Résumé :

After the restoration of the democracy in Nepal, the demand for spending up decentralization process has been gained ground. As a result of increasingly assertive role of stakeholders, the enactment of local self-governance Act (LSGA), 1999 in line with 9th plan, objective had been achieved providing the base for further promotion of decentralization framework in the country. Municipal financing is new concept in Nepal. Municipal financing indicates the study of various sources of revenue (both internal and external) and their collection, allocation, mobilization and utilization of those resource in such a manner that ultimate municipal goal can be achieved through it. For sustainable development effort conducted by local government to realized revenue and evaluation such performance was done through field surveys and on the basis of existing available data and reports. Simple tabular presentation percentage tools is used to analyzed data and found PSMC is not success to collect sufficient tax revenue as its possibilities. Janapriya Journal of Interdisciplinary Studies Vol. 2, No.1 (December 2013), page: 51-60

Styles APA, Harvard, Vancouver, ISO, etc.

22

Li, Liangyu, Su Tiexiong, Fukang Ma et Yu Pu. « Research on a small sample fault diagnosis method for a high-pressure common rail system ». Advances in Mechanical Engineering 13, n^o 9 (septembre 2021) : 168781402110461. http://dx.doi.org/10.1177/16878140211046103.

Texte intégral

Résumé :

In the fault diagnosis of high-pressure common rail diesel engines, it is often necessary to face the problem of insufficient diagnostic training samples due to the high cost of obtaining fault samples or the difficulty of obtaining fault samples, resulting in the inability to diagnose the fault state. To solve the above problem, this paper proposes a small-sample fault diagnosis method for a high-pressure common rail system using a small-sample learning method based on data augmentation and a fault diagnosis method based on a GA_BP neural network. The data synthesis of the training set using Least Squares Generative Adversarial Networks (LSGANs) improves the quality and diversity of the synthesized data. The correct diagnosis rate can reach 100% for the small sample set, and the iteration speed increases by 109% compared with the original BP neural network by initializing the BP neural network with an improved genetic algorithm. The experimental results show that the present fault diagnosis method generates higher quality and more diverse synthetic data, as well as a higher correct rate and faster iteration speed for the fault diagnosis model when solving small sample fault diagnosis problems. Additionally, the overall fault diagnosis correct rate can reach 98.3%.

Styles APA, Harvard, Vancouver, ISO, etc.

23

Newitt, David C., Ying Lu, Brian MacDonald, Sharmila Majumdar et Laurent Pothuaud. « In vivo application of 3D-line skeleton graph analysis (LSGA) technique with high-resolution magnetic resonance imaging of trabecular bone structure ». Osteoporosis International 15, n^o 5 (1 mai 2004) : 411–19. http://dx.doi.org/10.1007/s00198-003-1563-4.

Texte intégral

Styles APA, Harvard, Vancouver, ISO, etc.

24

Kwon, Moonhyuk, Connor L. Hodgins, Tegan M. Haslam, Susan A. Roth, Trinh-Don Nguyen, Edward C. Yeung et Dae-Kyun Ro. « Germacrene A Synthases for Sesquiterpene Lactone Biosynthesis Are Expressed in Vascular Parenchyma Cells Neighboring Laticifers in Lettuce ». Plants 11, n^o 9 (28 avril 2022) : 1192. http://dx.doi.org/10.3390/plants11091192.

Texte intégral

Résumé :

Sesquiterpene lactone (STL) and natural rubber (NR) are characteristic isoprenoids in lettuce (Lactuca sativa). Both STL and NR co-accumulate in laticifers, pipe-like structures located along the vasculature. NR-biosynthetic genes are exclusively expressed in laticifers, but cell-type specific expression of STL-biosynthetic genes has not been studied. Here, we examined the expression pattern of germacrene A synthase (LsGAS), which catalyzes the first step in STL biosynthesis in lettuce. Quantitative PCR and Illumina read mapping revealed that the transcripts of two GAS isoforms (LsGAS1/LsGAS2) are expressed two orders of magnitude (~100–200) higher in stems than laticifers. This result implies that the cellular site for LsGAS1/2 expression is not in laticifers. To gain more insights, promoters of LsGAS1/2 were cloned and fused to β-glucuronidase (GUS), followed by transformations of lettuce with these promoter-GUS constructs. In in situ GUS assays, the GUS expression driven by the LsGAS1/2 promoters was tightly associated with vascular bundles. High-resolution microsections showed that GUS signals are not present in laticifers but are detected in the vascular parenchyma cells neighboring the laticifers. These results suggest that expression of LsGAS1/2 occurs in the parenchyma cells neighboring laticifers, while the resulting STL metabolites accumulate in laticifers. It can be inferred that active metabolite-trafficking occurs from the parenchyma cells to laticifers in lettuce.

Styles APA, Harvard, Vancouver, ISO, etc.

25

Bhattarai, Naba Raj. « Strengths and Challenges of Federal Governance in Nepal : Re Thinking with Rural Development Approach ». Research Nepal Journal of Development Studies 3, n^o 2 (31 décembre 2020) : 38–48. http://dx.doi.org/10.3126/rnjds.v3i2.34457.

Texte intégral

Résumé :

Rural development in Nepal is a complex phenomenon. It is an interaction among economic, social, political and cultural factors. The concept of rural development is a process of wholistic development and change to improve rural livelihood. Rural development is linked with infrastructural development, commercialization of agriculture, proper utilization and of resources, food security, creating opportunities, inclusive development in the rural area and positive change in overall society. The main objective of the study is to assess the strength and challenges of federal governance in Nepal. Further, the study had reviewed the existing governance status in Nepal including Local Self Governance Act (LSGA) 1999 and its impact in the country. It aims to identify the rural development approach for the proper development of the nation with need based or right based approach. The study was conducted in the descriptive and exploratory design. The secondary data were only used in the study. The major sources of data were collected from the MoFALD, Central Library of TU, CBS, CEDA library, Nepal Rasta Bank Library, NPC, Public Information Centre, World Bank, Nepal etc. Nepal is still anxious to see and enjoy “democracy dividends” – social welfare, justice, equity, and equal access to resources and power. A reflection on the above calls to question certain issues that stands as challenge(s) to democratic governance in Nepal. These issues remain critical governance problems: leadership challenges, corruption, lack of transparency, and system of electoral reforms, rising civil strife, poverty, unemployment, lack of human security and human rights.

Styles APA, Harvard, Vancouver, ISO, etc.

26

Wang, Jianhua, Xiaolin Chang, Yixiang Wang, Ricardo J. Rodríguez et Jianan Zhang. « LSGAN-AT : enhancing malware detector robustness against adversarial examples ». Cybersecurity 4, n^o 1 (décembre 2021). http://dx.doi.org/10.1186/s42400-021-00102-9.

Texte intégral

Résumé :

AbstractAdversarial Malware Example (AME)-based adversarial training can effectively enhance the robustness of Machine Learning (ML)-based malware detectors against AME. AME quality is a key factor to the robustness enhancement. Generative Adversarial Network (GAN) is a kind of AME generation method, but the existing GAN-based AME generation methods have the issues of inadequate optimization, mode collapse and training instability. In this paper, we propose a novel approach (denote as LSGAN-AT) to enhance ML-based malware detector robustness against Adversarial Examples, which includes LSGAN module and AT module. LSGAN module can generate more effective and smoother AME by utilizing brand-new network structures and Least Square (LS) loss to optimize boundary samples. AT module makes adversarial training using AME generated by LSGAN to generate ML-based Robust Malware Detector (RMD). Extensive experiment results validate the better transferability of AME in terms of attacking 6 ML detectors and the RMD transferability in terms of resisting the MalGAN black-box attack. The results also verify the performance of the generated RMD in the recognition rate of AME.

Styles APA, Harvard, Vancouver, ISO, etc.

27

Wang, Changgang, Yu Cao, Shi Zhang et Tong Ling. « A Reconstruction Method for Missing Data in Power System Measurement Based on LSGAN ». Frontiers in Energy Research 9 (29 mars 2021). http://dx.doi.org/10.3389/fenrg.2021.651807.

Texte intégral

Résumé :

The integrity of data is an essential basis for analyzing power system operating status based on data. Improper handling of measurement sampling, information transmission, and data storage can lead to data loss, thus destroying the data integrity and hindering data mining. Traditional data imputation methods are suitable for low-latitude, low-missing-rate scenarios. In high-latitude, high-missing-rate scenarios, the applicability of traditional methods is in doubt. This paper proposes a reconstruction method for missing data in power system measurement based on LSGAN (Least Squares Generative Adversarial Networks). The method is designed to train in an unsupervized learning mode, enabling the neural network to automatically learn measurement data, power distribution patterns, and other complex correlations that are difficult to model explicitly. It then optimizes the generator parameters using the constraint relations implied by true sample data, enabling the trained Generator to generate highly accurate data to reconstruct the missing data. The proposed approach is entirely data-driven and does not involve mechanistic modeling. It can still reconstruct the missing data in the case of high latitude and high loss rate. We test the effectiveness of the proposed method by comparing three other GAN derivation methods in our experiments. The experimental results show that the proposed method is feasible and effective, and the accuracy of the reconstructed data is higher while taking into account the computational efficiency.

Styles APA, Harvard, Vancouver, ISO, etc.

28

Li, Xianghua, Cong Liu, Kun Sheng, Bo Wen, Haodong Xie, Wenxin Zhao et Qixiong Yang. « A Multi-Level Investment Demand Assessment Model for Renewable-Dominated Power System Planning ». Frontiers in Energy Research 9 (10 janvier 2022). http://dx.doi.org/10.3389/fenrg.2021.807590.

Texte intégral

Résumé :

To achieve the goal of carbon peak and carbon neutrality, the integration of diversified renewable energy will be the principal feature of the planning framework of the smart grid, and the planning direction and focus of power systems would shift to the network transmittability and flexibility enhancement. This paper presents an infrastructure investment demand assessment model based on multi-level analysis method for the renewable-dominated power system planning. First, for the load side, the composite capacity ratio is used to assess the capacity demand of power transformation infrastructure for satisfying the load growth. Then, the renewable energy permeability is adopted as the basis to assess the extensional transmittability capacity for the integration of high renewables. Furthermore, the capacity demand of flexible transmission lines for power grid flexibility enhancement is also estimated. Finally, the amount of unit investment for source-network-load infrastructure capacities can be predicted based on the least square generation adjunctive network and support vector machine (LSGAN-SVM) algorithm. The performance of the proposed model has been tested and benchmarked on a practical-sized power system to verify its effectiveness and feasibility.

Styles APA, Harvard, Vancouver, ISO, etc.

29

Sun, Shimin, Guihua Li, Renwei Ding, Lihong Zhao, Yujie Zhang, Shuo Zhao, Jinwei Zhang et Junlin Ye. « Seismic random noise suppression using improved CycleGAN ». Frontiers in Earth Science 11 (24 janvier 2023). http://dx.doi.org/10.3389/feart.2023.1102656.

Texte intégral

Résumé :

Random noise adversely affects the signal-to-noise ratio of complex seismic signals in complex surface conditions and media. The primary challenges related to processing seismic data have always been reducing the random noise and increasing the signal-to-noise ratio. In this study, we propose an improved cycle-consistent generative adversarial network (CycleGAN) seismic random noise suppression method. First, the generator replaces the original cycle-consistent generative adversarial network generator network structure with the Unet structure combined with the Resnet structure in order to increase the diversity of seismic data feature extraction and decrease the loss of seismic data details. Second, in order to improve the network’s stability, the feature extraction effect, the event texture preservation effect, and the signal-to-noise ratio, the Least Square GAN (LSGAN) square difference loss is used in place of the conventional generative adversarial network cross-entropy loss. The feasibility of the proposed method was confirmed using model and real seismic data, both of which demonstrated that the improved cycle-consistent generative adversarial network method effectively suppressed random noise in seismic data. In addition, the denoising effect was superior to both the widely used FX deconvolution denoising method and original cycle-consistent generative adversarial network denoising method.

Styles APA, Harvard, Vancouver, ISO, etc.

30

Bagla, Sandeep, Rachel Piechowiak, Abin Sajan, Julie Orlando, A. Diego Hipolito Canario et Ari Isaacson. « Angiographic Analysis of the Anatomical Variants in Genicular Artery Embolization ». Journal of Clinical Interventional Radiology ISVIR, 29 avril 2021. http://dx.doi.org/10.1055/s-0041-1729464.

Texte intégral

Résumé :

Abstract Purpose: Genicular artery embolization (GAE) has been proposed as a novel technique to treat painful synovitis related to osteoarthritis. An in-depth understanding of the genicular arterial anatomy is crucial to achieve technical success and avoid nontarget-related complications. Given the lack of previous angiographic description, the present study analyzes genicular arterial anatomy and proposes an angiographic classification system. Materials and Methods: Angiographic findings from 41 GAEs performed during two US clinical trials from January 2017 to July 2019 were reviewed to analyze the anatomical details of the following vessels: descending genicular artery (DGA), medial superior genicular artery (MSGA), medial inferior genicular artery (MIGA), lateral superior genicular artery (LSGA), lateral inferior genicular artery (LIGA), and anterior tibial recurrent artery (ATRA). The diameter, angle of origin, and anastomotic pathways were recorded for each vessel. The branching patterns were classified as: medially, M1 (3/3 arteries present) vs M2 (2/3 arteries present); and laterally, L1 (3/3 arteries present) vs L2 (2/3 arteries present). Results: A total of 91 genicular arteries were embolized: DGA (26.4%), MIGA (23.1%), MSGA (22.0%), LIGA (14.3%), and LSGA/ATRA (14.3%). The branching patterns were: medially = M1, 74.4% (n = 29), M2, 25.6% (n = 10); and laterally = L1, 94.9% (n = 37), L2, 5.1% (n = 2). A common origin for MSGA and LSGA was noted in 11 patients (28.2%). A direct DGA origin from the popliteal artery was reported in three patients (7.7%, n = 3). Conclusions: A thorough understanding of the geniculate arterial anatomy is important for maximizing postprocedural pain reduction while minimizing complications, procedure time, and radiation exposure during GAE.

Styles APA, Harvard, Vancouver, ISO, etc.

31

Long, N. J., H. L. Tuller, Lower Hurt et New Zealand. « Mixed Ionic-Electronic Conduction in N1 Doped Lanthanum Gallate Perovskites ». MRS Proceedings 496 (1997). http://dx.doi.org/10.1557/proc-496-129.

Texte intégral

Résumé :

ABSTRACTLanthanum gallate is a promising material for “monolithic” fuel cells or oxygen pumps, i.e. one in which the electrolyte and electrodes are formed from a common phase. We have investigated La1−xSrxGa1–yNiyO3 (LSGNx-y) with x=0.1 and y=0.2 and 0.5 as a potential cathode material for such an electrochemical device. The σ(PO2,T) for LSGN10–20 points to a p-type electronic conductivity at high PO2 and predominantly ionic conductivity at low PO2. LSGN10–50 has an electronic conductivity suitable for SOFC applications of approximately 50 S/cm in air at high temperature. AC impedance spectroscopy on an electron blocking cell of the form M/LSG/LSGN/LSG/M was used to isolate the ionic conductivity in the LSGN10–20 material. The ionic conductivity was found to have a similar magnitude and activation energy to that of undoped LSG material with σi= 0.12 S/cm at 800°C and EA= 1.0 ± 0.1 eV. Thermal expansion measurements on the LSGN materials were characterized as a function of temperature and dopant level and were found to match that of the electrolyte under opeating conditions.

Styles APA, Harvard, Vancouver, ISO, etc.

32

Shao, Hao, Lunwen Wang, Hui Liu et Rangang Zhu. « A link prediction method for MANETs based on fast spatio-temporal feature extraction and LSGANs ». Scientific Reports 12, n^o 1 (7 octobre 2022). http://dx.doi.org/10.1038/s41598-022-20981-3.

Texte intégral

Résumé :

AbstractLink prediction aims to learn meaningful features from networks to predict the possibility of topology. Most of the existing research on temporal link prediction is mainly aimed at networks with slow topology changes. They ignore the information of topology interval and link duration. This paper proposes a link prediction model named FastSTLSG. It can automatically analyze the features of the topology in a unified framework to effectively capture the spatio-temporal correlation of Mobile Ad Hoc Networks. First, we regard the changing topology as a chaotic system, transform it into a series of static snapshots based on the autocorrelation function; Next, the fast graph convolutional network efficiently analyses the topological relationships between nodes and reduces the computational complexity by importance sampling. Then, the gate recurrent unit captures the temporal correlation between snapshots. Finally, the fully connected layer reconstructs the topological structure. In addition, we take full advantage of least squares generative adversarial networks to further improve the performance of generator to obtain high-quality link prediction results. Extensive experiments on different datasets show that our FastSTLSG model obtains higher prediction accuracy compared with existing baseline models.

Styles APA, Harvard, Vancouver, ISO, etc.

33

Jaishi, M., R. Allen et L. Sahi. « Challenges and issues of decentralized agriculture service at the VDC level : experiences from Okhaldhunga District ». Journal of the Institute of Agriculture and Animal Science, 10 août 2018, 79–90. http://dx.doi.org/10.3126/jiaas.v33i0.20689.

Texte intégral

Résumé :

Decentralized management of natural resources has the potential to solve the twin problems of Nepalese society which are poverty and poor governance. An important focus of the Local Self Government Act (LSGA) of 1999 is to develop a local self-governance system and local leadership through which local bodies (LBs) make decisions on matters affecting their daily needs and livelihoods. Through the capacity building of local bodies, there is an ample opportunity to boost effective decentralized agriculture service provision at the VDC level. The objective of this paper is to provide basic understanding of the challenge and issues felt during implementation of VDC-level decentralization in the agricultural sector. A review of documents describing extension reforms and experiences was conducted in support of this study. Experience to date shows a great willingness of rural people to take responsibility for local development and to receive appropriate training to improve their management capability. LBs and development partners can assist in capacity building and further strengthen such local bodies to mitigate weaknesses. However, there remain challenges and issues to provide effective agricultural services in enhancing the livelihoods of the poor and to the promotion of more market-led production system.Journal of the Institute of Agriculture and Animal Science. Vol. 33-34, 2015, Page: 79-90

Styles APA, Harvard, Vancouver, ISO, etc.

34

Zhang, Weixin, Junqi Guo, Zheng Wang, Yanwei Li, Xiangfeng Meng, Yu Shen et Weifeng Liu. « Improved production of germacrene A, a direct precursor of ß-elemene, in engineered Saccharomyces cerevisiae by expressing a cyanobacterial germacrene A synthase ». Microbial Cell Factories 20, n^o 1 (7 janvier 2021). http://dx.doi.org/10.1186/s12934-020-01500-3.

Texte intégral

Résumé :

Abstract Background The sesquiterpene germacrene A is a direct precursor of ß-elemene that is a major component of the Chinese medicinal herb Curcuma wenyujin with prominent antitumor activity. The microbial platform for germacrene A production was previously established in Saccharomyces cerevisiae using the germacrene A synthase (LTC2) of Lactuca sativa. Results We evaluated the performance of LTC2 (LsGAS) as well as nine other identified or putative germacrene A synthases from different sources for the production of germacrene A. AvGAS, a synthase of Anabaena variabilis, was found to be the most efficient in germacrene A production in yeast. AvGAS expression alone in S. cerevisiae CEN.PK2-1D already resulted in a substantial production of germacrene A while LTC2 expression did not. Further metabolic engineering the yeast using known strategies including overexpression of tHMGR1 and repression of squalene synthesis pathway led to an 11-fold increase in germacrene A production. Site-directed mutagenesis of AvGAS revealed that while changes of several residues located within the active site cavity severely compromised germacrene A production, substitution of Phe23 located on the lateral surface with tryptophan or valine led to a 35.2% and 21.8% increase in germacrene A production, respectively. Finally, the highest production titer of germacrene A reached 309.8 mg/L in shake-flask batch culture. Conclusions Our study highlights the potential of applying bacterial sesquiterpene synthases with improved performance by mutagenesis engineering in producing germacrene A.

Styles APA, Harvard, Vancouver, ISO, etc.

Articles de revues sur le sujet « LSGAN »

Créez une référence correcte selon les styles APA, MLA, Chicago, Harvard et plusieurs autres