Classification and regression models of audio and vibration signals for machine state monitoring in precision machining systems

We present a data-driven method for monitoring machine status in manufacturing processes. Audio and vibration data from precision machining are used for inference in two operating scenarios: (a) variable machine health states (anomaly detection); and (b) settings of machine operation (state estimation). Audio and vibration signals are first processed through Fast Fourier Transform and Principal Component Analysis to extract transformed and informative features. These features are then used in the training of classification and regression models for machine state monitoring. Specifically, three classifiers (K-nearest neighbors, convolutional neural networks and support vector machines) and two regressors (support vector regression and neural network regression) were explored, in terms of their accuracy in machine state prediction. It is shown that the audio and vibration signals are sufficiently rich in information about the machine that 100% state classification accuracy could be accomplished. Data fusion was also explored, showing overall superior accuracy of data-driven regression models.     

Graph-based video fingerprinting using double optimal projection

A double optimal projection method that involves projections for intra-cluster and inter-cluster dimensionality reduction are proposed for video fingerprinting. The video is initially set as a graph with frames as its vertices in a high-dimensional space. A similarity measure that can compute the weights of the edges is then proposed. Subsequently, the video frames are partitioned into different clusters based on the graph model. Double optimal projection is used to explore the optimal mapping points in a low-dimensional space to reduce the video dimensions. The statistics and geometrical fingerprints are generated to determine whether a query video is copied from one of the videos in the database. During matching, the video can be roughly matched by utilizing the statistics fingerprint. Further matching is thereafter performed in the corresponding group using geometrical fingerprints. Experimental results show the good performance of the proposed video fingerprinting method in robustness and discrimination.     

Review of pulsed thermal NDT: Physical principles,theory and data processing

This paper summarizes the basics of pulsed thermal nondestructive testing (TNDT) including theoretical solutions, data processing algorithms and practical implementation. Typical defects are discussed along with 1D analytical and multi-dimensional numerical solutions. Special emphasis is focused on defect characterization by the use of inverse solutions. A list of TNDT terms is provided. Applications of active TNDT, mainly in the aerospace industry, are discussed briefly, and some trends in the further development of this technique are described.     

Optimised phase compositions and improved microwave dielectric properties based on calcium tin silicates

The Ca_(1+2y)Sn_(1-x)Si_(1+y)O_(5-2x+4y) low-permittivity microwave dielectric ceramics were prepared through solid-state reaction at 1350–1450 °C for 5 h. The relations between microwave dielectric properties and phase compositions for non-stoichiometric Ca_(1+2y)Sn_(1-x)Si_(1+y)O_(5-2x+4y) ceramics have been investigated. A single CaSnSiO₅ phase with abnormally positive temperature coefficient of resonant frequency (τ_f = + 62.5 ppm/°C) was synthesised at 1450 °C. This composition was an effective τ_f compensator of CaSiO₃ and Ca₃SnSi₂O₉ phases with typically negative τ_f value. The CaSiO₃ second phase was related to the Sn deficiency in the CaSn_(1-x)SiO_(5-2x) (0 < x < 1.0) composition, whereas the Ca₃SnSi₂O₉ second phase was obtained by controlling the Ca:Sn:Si ratios on the basis of the Ca_(1+2y)SnSi_(1+y)O_(5+4y) (0 < y < 1.0) composition. A promising low-permittivity millimetre-wave ceramic with most excellent microwave dielectric properties (ε_r = 10.2, Q×f = 81,000 GHz and τ_f = −4.8 ppm/°C) was produced from the Ca_(1+2y)SnSi_(1+y)O_(5+4y) (y = 0.4) ceramic.     

基于深度学习的视频跟踪研究进展综述

近年来深度学习迅猛发展，颠覆了语音识别、图像分类、文本理解等领域的算法设计思路。深度学习因其具备强大的特征提取能力，在图像识别领域的成绩尤为突出。然而深度学习与视频监控领域的结合并不多，由于深度模型具有多层网络结构，算法复杂度大，训练和更新模型时比较耗时，很难满足实时性要求。回顾了深度学习的发展史，介绍了最近10年来国内外深度学习主要模型，论述了基于深度学习的目标跟踪算法，指出了各算法的优缺点，最后对当前该领域存在的问题和发展前景进行了总结和展望。     

An efficient video summarization for surveillance system using normalized k-means and quick sort method

There has been a vast augmentation in quantity of Video Content (VC) generated amid the last some years. The Video Summarization (VS) approach is introduced for managing the VC. Prevailing VS techniques have endeavored to render the VS but the systems have Execution Time (ET) as well as condensing the video's content in domain specific manner. To triumph over such disadvantages, this paper proposed efficient VS for surveillance system using normalized k-means along with quick sort method. The proposed technique comprises eight stages, like split video into frames, pre-sampling, provide ID number, feature extraction, Feature Selection (FS), clustering, extract frames, video summary. Initially, the video frames are pre-sampled utilizing the proposed Three Step Cross Searching Algorithm (TSCS) technique. Then, give the ID number for every frame. Next, the features are extracted as of the frames. Then, the necessary features are selected using Entropy based Spider Monkey Algorithms (ESMA). In next stage, the features are grouped using Normalized K-Means (N-Kmeans) algorithm for identifying best candidate frames. Then select the minimum distance value based cluster set is the Key Frame (KF) selection. At last, the video is orderly summarized using quick sort method. Finally, in experimental evaluation the proposed work is compared with the prevailing methods. The proposed VS gave better outcome than the existing approaches.     

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.     

Zinc doped Fe2O3 for boosting Electrocatalytic Nitrogen Fixation to ammonia under mild conditions

Artificial nitrogen fixation is emerging as a promising approach for synthesis of ammonia at mild conditions. Inspired by biological nitrogen fixation based on bacteria containing iron, zinc doped Fe₂O₃ nanoparticles are proposed as an efficient and earth abundant electrocatalyst for converting N₂ to NH₃. In neutral media, it achieves a maximum Faradaic efficiency (FE) of 10.4% and a large NH₃ yield rate of 15.1 μg h^?1 mg^?1_cat. at ?0.5 V vs. reversible hydrogen electrode. This catalyst also exhibits excellent selectivity and stability. Theoretical calculations suggest the reaction follows the associative enzymatic mechanism and it has a barrier of as low as 0.68 eV.     

Enhanced transduction coefficient in piezoelectric PZT ceramics by mixing powders calcined at different temperatures

Large transduction coefficient ($d_{33}\times g_{33}$) is difficult to obtain in piezoelectric ceramics because these two parameters show opposite trends with compositional modifications. Herein, the Pb(Zr_0.53Ti_0.47)O₃ ceramic powders were calcinated under different temperatures (A:830 °C, B:860 °C, and C:890 °C), and then mixed together according to different weight ratios (1A:1B:1C, 1A:2B:1C, 1A:2B:3C and 3A:2B:1C) for ceramics preparation. Both d₃₃ and g₃₃ are improved successfully, and the transduction coefficient with the weight ratio of 1A:2B:3C reaches up to 17,500 × 10⁻¹⁵ m²/N, which is 60 % higher than that with the powders calcinated under 830 °C, and at least twice those of commercial PZT-4, PZT-5A and PZT-8 ceramics. The improved transduction coefficient is owing to the enhanced piezoelectric constant and spontaneous polarization resulted from the increased grain size, relative density and the fraction of tetragonal phase. These results indicate that this is a simple but effective way to tailor the transduction coefficient in piezoelectric ceramics.