Learning a Deep Predictive Coding Network for a Semi-Supervised 3D-Hand Pose Estimation

In this paper we present a CNN based approach for a real time 3D-hand pose estimation from the depth sequence. Prior discriminative approaches have achieved remarkable success but are facing two main challenges: Firstly, the methods are fully supervised hence require large numbers of annotated training data to extract the dynamic information from a hand representation. Secondly, unreliable hand detectors based on strong assumptions or a weak detector which often fail in several situations like complex environment and multiple hands. In contrast to these methods, this paper presents an approach that can be considered as semi-supervised by performing predictive coding of image sequences of hand poses in order to capture latent features underlying a given image without supervision. The hand is modelled using a novel latent tree dependency model (LDTM) which transforms internal joint location to an explicit representation. Then the modeled hand topology is integrated with the pose estimator using data dependent method to jointly learn latent variables of the posterior pose appearance and the pose configuration respectively. Finally, an unsupervised error term which is a part of the recurrent architecture ensures smooth estimations of the final pose. Experiments on three challenging public datasets, ICVL, MSRA, and NYU demonstrate the significant performance of the proposed method which is comparable or better than state-of-the-art approaches.      

Fault detection and diagnostic method of diesel engine by combining rule-based algorithm and BNs/BPNNs

The stable operation of diesel engine is critical to the normal production of the industry, and the prevention, monitoring, and identification of faults are of great significance. At present, the fault research on diesel engines still has some defects, such as only few types of faults diagnosis are identified, the accuracy of fault diagnosis is still low, and fault identification is located at a fixed speed. A novel fault detection and diagnostic method of diesel engine by combining rule-based algorithm and Bayesian networks (BNs) or Back Propagation neural networks (BPNNs) is proposed. The signals are processed by wavelet threshold denoising and ensemble empirical mode decomposition. The signal-sensitive feature values are extracted from the decomposed intrinsic mode function. Seven faults are roughly identified using rule-based algorithm and finely identified using BNs or BPNNs. Results show the proposed fault diagnosis method has a good diagnostic performance for a wide range of rotation speeds when the training data for BNs and BPNNs are from fixed speeds. In addition, the influences of the layers of decomposed signals, sensor noise and external excitation interference on the fault diagnostic performance are also researched.     

基于人工神经网络的柴油机失火故障诊断

车载诊断系统在诊断失火故障时,采用基于曲轴段角加速度和阈值规则相结合的方法,该方法在内燃机高速轻载运行时诊断单缸完全失火工况存在一定的局限性。通过对比分析失火和正常工况下曲轴瞬时转速的幅频和相频特征,提取不同谐次的幅值和相位信息,结合人工神经网络作为故障模式识别工具,得到了一种改善方法。通过台架实验,对此改善方法进行了单缸完全失火、两缸完全失火和单缸一定程度失火的故障诊断测试。结果表明,在实验条件下该方法可以有效识别不同的失火模式,并可在单缸失火模式下实现失火程度判别。同时,该方法通过少量工况数据训练神经网络,即可实现一定转速范围内的失火诊断,可行性强,可用于发动机失火故障在线诊断。     

A survey of 5G technologies: regulatory,standardization and industrial perspectives

In recent years, there have been significant developments in the research on 5th Generation (5G) networks. Several enabling technologies are being explored for the 5G mobile system era. The aim is to evolve a cellular network that is intrinsically flexible and remarkably pushes forward the limits of legacy mobile systems across all dimensions of performance metrics. All the stakeholders, such as regulatory bodies, standardization authorities, industrial fora, mobile operators and vendors, must work in unison to bring 5G to fruition. In this paper, we aggregate the 5G-related information coming from the various stakeholders, in order to i) have a comprehensive overview of 5G and ii) to provide a survey of the envisioned 5G technologies; their development thus far from the perspective of those stakeholders will open up new frontiers of services and applications for next-generation wireless networks.     

Convolutional and generative adversarial neural networks in manufacturing

Manufacturing is undergoing transformation driven by the developments in process technology, information technology, and data science. A future manufacturing enterprise will be highly digital. This will create opportunities for machine learning algorithms to generate predictive models across the enterprise in the spirit of the digital twin concept. Convolutional and generative adversarial neural networks have received some attention of the manufacturing research community. Representative research and applications of the two machine learning concepts in manufacturing are presented. Advantages and limitations of each neural network are discussed. The paper might be helpful in identifying research gaps, inspire machine learning research in new manufacturing domains, contribute to the development of successful neural network architectures, and getting deeper insights into the manufacturing data.     

自主机器人多智能体软件架构及伴随行为机制

自主机器人是一类由计算机软件控制的信息物理系统，如何支持该类机器人在开放环境下的有效和协调运行是自主机器人控制软件（CSAR：Control Software of Autonomous Robot）研究与实践面临的一项重要挑战.本文基于组织理论的思想，采用Structure-in-5的组织架构模式，提出了基于多智能体的CSAR的软件架构MaRSA（Multi-agent Robotic Software Architecture），通过独立抽象CSAR的行为规划、分发、执行等软构件并显式加强这些构件间的交互，从而为自主机器人行为的有效规划和协调实施奠定架构基础；提出了基于MaRSA架构的伴随行为机制，从因果性、时序性和按需性三个方面建立了机器人观察行为和任务行为间的伴随关系，并基于分步规划和动态决策的思想设计并实现了伴随行为的自主决策算法DAAB（Decision Algorithm of Accompanying Behaviors）.论文分别在仿真环境和实际机器人环境下设计了对比性实验，结果表明，与主流的反应式行为决策算法和BDI式概率决策算法相比较，基于MaRSA和伴随行为机制的DAAB算法所生成的伴随行为规划在开放环境下具有可行性和更高效的执行效率.     

Regulatory and ownership determinants of unbundling regime choice for European electricity transmission utilities

One of the fundamental provisions of the European electricity directives is the so-called unbundling of structures and functions. Vertical disintegration with Full Unbundling (ownership unbundling or independent system operation) is considered an important step toward electricity market restructuring. While Full Unbundling (FU) models appear to be the most prevalent, several European countries adhered solely to less stringent forms of unbundling. Using a dataset of the 35 major electricity transmission utilities in Europe, this study provides an econometric analysis to understand the individual effect of regulation and ownership structure on the decision to adopt more stringent unbundling regimes. The overall results show that incentive-based or hybrid regulatory schemes and private ownership, are associated with a higher probability that a country will opt for FU.     

Image Super-Resolution Based on Generative Adversarial Networks: A Brief Review

Single image super resolution (SISR) is an important research content in the field of computer vision and image processing. With the rapid development of deep neural networks, different image super-resolution models have emerged. Compared to some traditional SISR methods, deep learning-based methods can complete the superresolution tasks through a single image. In addition, compared with the SISR methods using traditional convolutional neural networks, SISR based on generative adversarial networks (GAN) has achieved the most advanced visual performance. In this review, we first explore the challenges faced by SISR and introduce some common datasets and evaluation metrics. Then, we review the improved network structures and loss functions of GAN-based perceptual SISR. Subsequently, the advantages and disadvantages of different networks are analyzed by multiple comparative experiments. Finally, we summarize the paper and look forward to the future development trends of GAN-based perceptual SISR.     

A Novel Method of Heart Failure Prediction Based on DPCNNXGBOOST Model

The occurrence of perioperative heart failure will affect the quality of medical services and threaten the safety of patients. Existing methods depend on the judgment of doctors, the results are affected by many factors such as doctors’ knowledge and experience. The accuracy is difficult to guarantee and has a serious lag. In this paper, a mixture prediction model is proposed for perioperative adverse events of heart failure, which combined with the advantages of the Deep Pyramid Convolutional Neural Networks (DPCNN) and Extreme Gradient Boosting (XGBOOST). The DPCNN was used to automatically extract features from patient’s diagnostic texts, and the text features were integrated with the preoperative examination and intraoperative monitoring values of patients, then the XGBOOST algorithm was used to construct the prediction model of heart failure. An experimental comparison was conducted on the model based on the data of patients with heart failure in southwest hospital from 2014 to 2018. The results showed that the DPCNN-XGBOOST model improved the predictive sensitivity of the model by 3% and 31% compared with the text-based DPCNN Model and the numeric-based XGBOOST Model.