Nrityabodha: Towards understanding Indian classical dance using a deep learning approach

Indian classical dance has existed since over 5000 years and is widely practised and performed all over the world. However, the semantic meaning of the dance gestures and body postures as well as the intricate steps accompanied by music and recital of poems is only understood fully by the connoisseur. The common masses who watch a concert rarely appreciate or understand the ideas conveyed by the dancer. Can machine learning algorithms aid a novice to understand the semantic intricacies being expertly conveyed by the dancer? In this work, we aim to address this highly challenging problem and propose deep learning based algorithms to identify body postures and hand gestures in order to comprehend the intended meaning of the dance performance. Specifically, we propose a convolutional neural network and validate its performance on standard datasets for poses and hand gestures as well as on constrained and real-world datasets of classical dance. We use transfer learning to show that the pre-trained deep networks can reduce the time taken during training and also improve accuracy. Interestingly, we show with experiments performed using Kinect in constrained laboratory settings and data from Youtube that it is possible to identify body poses and hand gestures of the performer to understand the semantic meaning of the enacted dance piece.     

关于极限理论的学习经验

分析极限理论在数学分析学习中的重要性，介绍学习极限理论的三点经验与体会，即充分理解基本内容；加强基本功训练；试着多问自己一些问题，学会举出各种各样的例子。     

Historical data learning based dynamic LSP routing for overlay IP/MPLS over WDM networks

Overlay IP/MPLS over WDM network is a promising network architecture starting to gain wide deployments recently. A desirable feature of such a network is to achieve efficient routing with limited information exchanges between the IP/MPLS and the WDM layers. This paper studies dynamic label switched path (LSP) routing in the overlay IP/MPLS over WDM networks. To enhance network performance while maintaining its simplicity, we propose to learn from the historical data of lightpath setup costs maintained by the IP-layer integrated service provider (ISP) when making routing decisions. Using a novel historical data learning scheme for logical link cost estimation, we develop a new dynamic LSP routing method named Existing Link First (ELF) algorithm. Simulation results show that the proposed algorithm significantly outperforms the existing ones under different traffic loads, with either limited or unlimited numbers of optical ports. Effects of the number of candidate routes, add/drop ratio and the amount of historical data are also evaluated.     

Extreme learning machine approach for sensorless wind speed estimation

Precise predictions of wind speed play important role in determining the feasibility of harnessing wind energy. In fact, reliable wind predictions offer secure and minimal economic risk situation to operators and investors. This paper presents a new model based upon extreme learning machine (ELM) for sensor-less estimation of wind speed based on wind turbine parameters. The inputs for estimating the wind speed are wind turbine power coefficient, blade pitch angle, and rotational speed. In order to validate authors compared prediction of ELM model with the predictions with genetic programming (GP), artificial neural network (ANN) and support vector machine with radial basis kernel function (SVM-RBF). This investigation analyzed the reliability of these computational models using the simulation results and three statistical tests. The three statistical tests includes the Pearson correlation coefficient, coefficient of determination and root-mean-square error. Finally, this study compared predicted wind speeds from each method against actual measurement data. Simulation results, clearly demonstrate that ELM can be utilized effectively in applications of sensor-less wind speed predictions. Concisely, the survey results show that the proposed ELM model is suitable and precise for sensor-less wind speed predictions and has much higher performance than the other approaches examined in this study.     

An improved ensemble learning machine for biological activity prediction of tyrosine kinase inhibitors

Boosting is one of the most important strategies in ensemble learning because of its ability to improve the stability and performance of weak learners. It is nonparametric, multivariate, fast and interpretable but is not robust against outliers. To enhance its prediction accuracy as well as immunize it against outliers, a modified version of a boosting algorithm (AdaBoost R2) was developed and called AdaBoost R3. In the sampling step, extremum samples were added to the boosting set. In the robustness step, a modified Huber loss function was applied to overcome the outlier problem. In the output step, a deterministic threshold was used to guarantee that bad predictions do not participate in the final output. The performance of the modified algorithm was investigated with two anticancer data sets of tyrosine kinase inhibitors, and the mechanism of inhibition was studied using the relative weighted variable importance procedure. Investigating the effect of base learner's strength reveals that boosting is only successful using the classification and regression tree method (a weak to moderate learner) and does not have a significant effect using the radial basis functions partial least square method (a strong base learners). Copyright © 2015 John Wiley & Sons, Ltd.     

基于微信公众平台的外语微学习资源设计与应用研究

针对微信使用群体的普及,本文提出在构建外语学习资源信息管理系统的基础上,搭建一个用于学生校园学习的微信服务账号,从而通过该微信服务账号实现学生对学习资源的利用,更好的促进语言能力的提升。本文借助Web服务器、Java技术、数据库、XML解析技术等系统进行开发,并对其实现进行详细的阐述,从而实现信息化技术与教学方式的创新,具有很大的推广和应用价值。     

基于智能手机的移动学习系统开发技术研究

移动学习逐步成为成人远程教育重要的学习方式,本文针对开发基于智能手机的移动学习系统,在探讨移动学习及其网络架构的基础上,采用实例分析法,对现阶段开发移动学习系统的各种技术进行了分析,重点剖析了现阶段开发移动学习系统的开发模式及其技术架构的实现。这些技术和方法,对技术人员进行移动学习系统的开发具有指导和借鉴意义。     

一种基于峭度累积量比例微分控制的盲源分离学习率

自然梯度算法由于良好的分离性能在盲源分离中占有重要的地位,但该算法基于固定步长时,无法很好兼顾收敛速度和稳态误差。本文借鉴自动化控制的PID （Proportion Integration Differentiation ）算法,提出一种与分离状态紧密结合的变步长学习率算法。由于完成分离的信号峭度累积量是一个固有值,分离过程的信号峭度累积量与固有值将有一个不断减小的误差值。该算法以指数函数值来体现该误差值。再利用该误差构成比例微分的变步长算法,其中的步长初始值就相当于控制误差的比例值,而误差的微分项则得到加速的调整值。该算法仿真实验结果与固定步长自然梯度盲源分离算法的仿真实验结果对比：对应于初始步长的一个最大值和一个最小值,该算法的两次迭代次数均低于采用固定步长算法的迭代次数,并且对于不同类型信号在两次迭代次数间的差值约10～40次,而两种算法的稳态误差是相同的。     

结合特征学习的粒子群求解极小碰集方法

基于模型诊断中的极小碰集问题是人工智能领域的一个重要课题,现实中很多实际问题都可以转化为极小碰集问题,如老师与课程问题,极小覆盖集问题等.通过对极小碰集问题特征的研究,本文结合粒子群优化求解极小碰集的算法提出了一个新的算法,来指导极小碰集的求解:引入学习机制,减少极小碰集求解中对无解空间的搜索;加入翻转策略,来加速极小碰集有解空间中的求解.实验结果表明本文提出的算法在求解极小碰集问题上的效率有明显提高.     

一种新型的在瑞利信道下盲检测器设计

针对采用卡尔曼滤波或线性预测方案进行信号检测时,需要已知信道模型参数或预先估计信道参数这一局限性问题,提出一种新型的瑞利信道下的盲检测器。盲检测器通过设计粒子学习算法,能够在未知的信道衰落模型参数和噪声模型参数条件下检测信号。为了提升检测器的性能,采用信号延迟判决技术。仿真结果表明,盲检测器性能优异,已接近在已知信道模型参数下检测器的性能。该盲检测器易于并行设计实现,具有很高的实用价值。