一种面向临床领域时序知识图谱的链接预测模型

知识图谱(knowledge graph)链接预测可以解决知识图谱中缺失信息的发现和还原,是目前知识图谱领域的研究热点.传统的知识图谱链接预测方法大多面向静态的数据,并不适用于具有动态变化特性的时序知识图谱.时序知识图谱广泛存在于不同领域中,以临床医学领域为例,糖尿病作为一种典型的慢性病,其病程是一个疾病缓慢发展演化的过程.因此,在临床医学时序知识图谱上进行临床意义的链接预测,比如预测糖尿病的并发症,则需要考虑糖尿病病程发展随时间变化的时序特性,这也为传统的知识图谱链接预测方法带来巨大挑战.为此,结合临床医学事实知识的时序特性,提出一种基于LSTM序列增量学习的临床领域时序知识图谱链接预测模型.该模型结合LSTM长短期记忆单元递归神经网络在序列学习上的优势,通过构建基于LSTM的序列增量学习层,以端到端的方式提取时序知识图谱中的三元组时序特征,从而实现对时序知识图谱的链接预测.通过在糖尿病时序知识图谱上的实验,验证了模型的高效性、可用性及稳定性.

Phishing detection method based on URL features

In order to effectively detect malicious phishing behaviors, a phishing detection method based on the uniform resource locator （URL） features is proposed. First, the method compares the phishing URLs with legal ones to extract the features of phishing URLs. Then a machine learning algorithm is applied to obtain the URL classification model from the sample data set training. In order to adapt to the change of a phishing URL, the classification model should be constantly updated according to the new samples. So, an incremental learning algorithm based on the feedback of the original sample data set is designed. The experiments verify that the combination of the URL features extracted in this paper and the support vector machine （SVM） classification algorithm can achieve a high phishing detection accuracy, and the incremental learning algorithm is also effective.

Human tracking in camera network with non-overlapping FOVs

An adaptive human tracking method across spatially separated surveillance cameras with non-overlapping fields of views （FOVs） is proposed. The method relies on the two cues of the human appearance model and spatio-temporal information between cameras. For the human appearance model, an HSV color histogram is extracted from different human body parts （head, torso, and legs）, then a weighted algorithm is used to compute the similarity distance of two people. Finally, a similarity sorting algorithm with two thresholds is exploited to find the correspondence. The spatio- temporal information is established in the learning phase and is updated incrementally according to the latest correspondence. The experimental results prove that the proposed human tracking method is effective without requiring camera calibration and it becomes more accurate over time as new observations are accumulated.

Incremental semi-supervised learning for intelligent seismic facies identification

Intelligent seismic facies identification based on deep learning can alleviate the time-consuming and labor-intensive problem of manual interpretation,which has been widely applied.Supervised learning can realize facies identification with high efficiency and accuracy;however,it depends on the usage of a large amount of well-labeled data.To solve this issue,we propose herein an incremental semi-supervised method for intelligent facies identification.Our method considers the continuity of the lateral variation of strata and uses cosine similarity to quantify the similarity of the seismic data feature domain.The maximum-diff erence sample in the neighborhood of the currently used training data is then found to reasonably expand the training sets.This process continuously increases the amount of training data and learns its distribution.We integrate old knowledge while absorbing new ones to realize incremental semi-supervised learning and achieve the purpose of evolving the network models.In this work,accuracy and confusion matrix are employed to jointly control the predicted results of the model from both overall and partial aspects.The obtained values are then applied to a three-dimensional(3D)real dataset and used to quantitatively evaluate the results.Using unlabeled data,our proposed method acquires more accurate and stable testing results compared to conventional supervised learning algorithms that only use well-labeled data.A considerable improvement for small-sample categories is also observed.Using less than 1%of the training data,the proposed method can achieve an average accuracy of over 95%on the 3D dataset.In contrast,the conventional supervised learning algorithm achieved only approximately 85%.

Incremental learning of the triangular membership functions based on single-pass FCM and CHC genetic model

In order to improve the efficiency of learning the triangular membership functions( TMFs) for mining fuzzy association rule( FAR) in dynamic database,a single-pass fuzzy c means( SPFCM)algorithm is combined with the real-coded CHC genetic model to incrementally learn the TMFs. The cluster centers resulting from SPFCM are regarded as the midpoint of TMFs. The population of CHC is generated randomly according to the cluster center and constraint conditions among TMFs. Then a new population for incremental learning is composed of the excellent chromosomes stored in the first genetic process and the chromosomes generated based on the cluster center adjusted by SPFCM. The experiments on real datasets show that the number of generations converging to the solution of the proposed approach is less than that of the existing batch learning approach. The quality of TMFs generated by the approach is comparable to that of the batch learning approach. Compared with the existing incremental learning strategy,the proposed approach is superior in terms of the quality of TMFs and time cost.

DETERMINE OPTIMUM NUMBER OF COMPACT OVERLAPPED CLUSTERS USING FRLVQ TECHNIQUE

A method, named XHJ-method, is proposed in this letter to determine the number of clusters of a data set, which incorporates with the Fuzzy Reinforced Learning Vector Quantization (FRLVQ) technique. The simulation results show that this new method works well for the traditional iris data and an artificial data set, which contains un-equally sized and spaced clusters.

Effect of MgO and SiO_2 on surface tension of fluoride containing slag

Surface tensions of slag addition Mg O and Si O2 based on conventional 70%CaF 2-30%Al2O3 and 60%Ca F2-20%Ca O-20%Al2O3(mass fraction) at 1300 °C, 1400 °C and 1500 °C were investigated. Influence mechanism of Mg O and Si O2 on slag surface tension was also analyzed. Results indicate that surface tension decreases with the increase of Mg O content in the case of the Mg O content(mass fraction) less than 8%, however, when Mg O content(mass fraction) is from 8% to 30%, surface tension increases with the increase of Mg O content. When Si O2 content(mass fraction) is from 2% to 8%, surface tension decreases with the increase of Si O2 content. Additionally, the relationship between surface tension and optical basicity is a monotonically increasing linear function. Research findings can provide important reference for slag design and the study of slag-metal interfacial tension.

Prediction for Geometric Characteristics of Single Track of Deposition Layer and Surface Roughness in Thin Wire-Based Metal Additive Manufacturing Process

Machine learning prediction models for thin wire-based metal additive manufacturing(MAM)process were proposed,aiming at the complex relationship between the process parameters and the geometric characteristics of single track of the deposition layer and surface roughness.The effects of laser power,wire feeding speed and scanning speed on the width and height of the single track and surface roughness were experimentally studied.The results show that laser power has a significant impact on the width of the single track but little effect on the height.As the wire feeding speed increases,the width and height of the single track increase,especially the height.The faster the scanning speed,the smaller the width of the single track,while the height does not change much.Then,support vector regression(SVR)and artificial neural network(ANN)regression methods were employed to set up prediction models.The SVR and ANN regression models perform well in predicting the width,with a smaller root mean square error and a higher correlation coefficient R2.Compared with the ANN model,the SVR model performs better both in predicting geometric characteristics of single track and surface roughness.Multi-layer thin-walled parts were manufactured to verify the accuracy of the models.

Response of Plant Community Carbon and Nitrogen Stoichiometry to Experimental Warming on the Qinghai-Tibet Plateau

Low temperature is an important limiting factor for alpine ecosystems on the Tibetan Plateau. This study is based on data from on-site experimental warming platforms(open top chambers, OTC) at three elevations(4300 m, 4500 m, 4700 m) on the Qinghai-Tibet Plateau. The carbon and nitrogen stoichiometry characteristics of plant communities, both above-ground and below-ground, were observed in three alpine meadow ecosystems in August and September of 2011 and August of 2012. Experimental warming significantly increased above-ground nitrogen content by 21.4% in September 2011 at 4500 m, and reduced above-ground carbon content by 3.9% in August 2012 at 4300 m. Experimental warming significantly increased below-ground carbon content by 5.5% in August 2011 at 4500 m, and the below-ground ratio of carbon to nitrogen by 28.0% in September 2011 at 4300 m, but reduced below-ground nitrogen content by 15.7% in September 2011 at 4700 m, below-ground carbon content by 34.3% in August 2012 at 4700 m, and the below-ground ratio of carbon to nitrogen by 37.9% in August 2012 at 4700 m. Experimental warming had no significant effect on the characteristics of community carbon and nitrogen stoichiometry under other conditions. Therefore, experimental warming had inconsistent effects on the carbon and nitrogen stoichiometry of plant communities at different elevations and during different months. Soil ammonium nitrogen and nitrate nitrogen content were the main factors affecting plant community carbon and nitrogen stoichiometry.

Augmentation Quotients for Complex Representation Rings of Generalized Quaternion Groups

Abstract Denote by Qm the generalized quaternion group of order 4m. Let R（Qm） be its complex representation ring, and △（Qm） its augmentation ideal. In this paper, the author gives an explicit Z-basis for the △n（Qm） mid determines the isomorphism class of the n-th augmentation quotient for each positive integer n.

Gain characteristics of a dual-pump fiber optical parametric amplifier with Raman effect

We investigate the pump-depleted model of a dual-pump fiber optical parametric amplifier(FOPA) with Raman effect.As bandwidth increases,the gain profile of the distorted FOPA would be impacted seriously.Under the widebands,especially when the pump separation is large,zero dispersion wavelength(ZDW) fluctuation is another factor which can not be neglected.Numerical simulations with these comprehensive factors are mainly analyzed to obtain their influence on gain characteristics.Saturated gain spectrum is also discussed in detail.

Intrinsically reinforced silks obtained by incorporation of graphene quantum dots into silkworms

Silkworm silks have been widely used in a variety of fields due to their sensuousness, luster and excellent mechanical properties. Researchers have paid special attention in improving the mechanical properties of silks. In this work,Bombyx mori larval silkworms are injected with graphene quantum dots(GQDs) through a vascular injection to enhance mechanical properties of the silkworm silks. The GQDs can be incorporated into the silkworm silk gland easily due to hemolymph circulation and influence the spinning process of silkworm. The breaking strength, elongation at break and toughness modulus of the silks increase by 2.74, 1.33 and 3.62 times, respectively, by injecting per individual with 0.6 μg GQDs. Wide-angle X-ray scattering indicates that the size ofβ-sheet nanocrystals in GQDs-silks is smaller than that in control-silks. Infrared spectra suggest that GQDs confine the conformation transition of silk fibroin to β-sheet from random coil/α-helix, and the change of the size and content of β-sheet may be the reason for the improvement of the mechanical properties. The toxicity and safety limit of GQDs incorporated into each silkworm is also evaluated, and the results show that the upmost dose of GQDs per silkworm is30.0 μg. The successful obtainment of reinforced silks by in vivo uptake of GQDs provides a promising route to produce high-strength silks.

Biological reaction signal enhancement in porous silicon Bragg mirror based on quantum dots fluorescence

In this paper, we mainly study the preparation of an optical biosensor based on porous silicon(PSi) Bragg mirror and its feasibility for biological detection. The quantum dot(QD) labeled biotin was pipetted onto streptavidin functionalized PSi Bragg mirror samples, the affinity reaction between QD labeled biotin and streptavidin in PSi occurred, so the QDs were indirectly connected to the PSi. The fluorescence of QD enhanced the signal of biological reactions in PSi. The performance of the sensor is verified by detecting the fluorescence of the QD in PSi. Due to the fluorescence intensity of the QDs can be enhanced by PSi Bragg mirror, the sensitivity of the PSi optical biosensor will be improved.

Analysis on spectral gain characteristics of PPMgLN based quasi-phase-matching optical parametric amplification

A deep understanding of the spectral gain characteristics of optical parametric oscillators (OPOs) and optical parametric amplifiers (OPAs) is important for a highly efficient optical parametric conversion. We numerically calculated the spectral gain characteristics of a quasi-phase-matching (QPM) parametric conversion process using the periodically poled 6% (mol/mol) MgO doped LiNbO3 (PPMgLN) as the nonlinear crystal. In the simulation we utilized the approach of a transformative matrix of the periodically poled nonlinear medium, which results from the small-signal approximation of three-wave mixed nonlinear equations. Numerical simulation results show that: (1) The full width at half maximum (FWHM) of the spectral gain of the parametric process becomes wider with the increase of parametric wavelength and reaches the maximum at degeneration; (2) The gain coefficient decreases gradually with the increase of parametric wavelength; (3) The spectral gain bandwidth decreases correspondingly with the increase of the nonlinear material length; (4) There exists an optimal parametric wavelength band, which is most suitable for the high gain parametric conversion when pumped by a laser source with a wide wavelength band, such as the high power fiber laser.

Direct measurement of the Raman enhancement factor of rhodamine 6G on graphene under resonant excitation

Graphene substrates have recently been found to generate Raman enhancement. Systematic studies using different Raman probes have been implemented, but one of the most commonly used Raman probes, rhodamine 6G （R6G）, has yielded controversial results for the enhancement effect on graphene. Indeed, the Raman enhancement factor of R6G induced by graphene has never been measured directly under resonant excitation because of the presence of intense fluorescence backgrounds. In this study, a polarization-difference technique is used to suppress the fluorescence background by subtracting two spectra collected using different excitation laser polarizations. As a result, enhancement factors are obtained ranging between 1.7 and 5.6 for the four Raman modes of R6G at 611, 1,183, 1,361, and 1,647 cm-~ under resonant excitation by a 514.5 nm laser. By comparing these results with the results obtained under non-resonant excitation （632.8 nm） and pre-resonant excitation （593 nm）, the enhancement can be attributed to static chemical enhancement （CHEM） and tuning of the molecular resonance. Density functional theory simulations reveal that the orbital energies and densities for R6G are modified bv ~raphene dots.

Experimental warming shifts coupling of carbon and nitrogen cycles in an alpine meadow

Aims Terrestrial ecosystem carbon(C)uptake is remarkably regulated by nitrogen(N)availability in the soil.However,the coupling of C and N cycles,as reflected by C:N ratios in different components,has not been well explored in response to climate change.Methods Here,we applied a data assimilation approach to assimilate 14 datasets collected from a warming experiment in an alpine meadow in China into a grassland ecosystem model.We attempted to evaluate how experimental warming affects C and N coupling as indicated by constrained parameters under ambient and warming treatments separately.Important Findings The results showed that warming increased soil N availability with decreased C:N ratio in soil labile C pool,leading to an increase in N uptake by plants.Nonetheless,C input to leaf increased more than N,leading to an increase and a decrease in the C:N ratio in leaf and root,respectively.Litter C:N ratio was decreased due to the increased N immobilization under high soil N availability or warming-accelerated decomposition of litter mass.Warming also increased C:N ratio of slow soil organic matter pool,suggesting a greater soil C sequestration potential.As most models usually use a fixed C:N ratio across different environments,the divergent shifts of C:N ratios under climate warming detected in this study could provide a useful benchmark for model parameterization and benefit models to predict C-N coupled responses to future climate change.