Editorial: Machine Learning and Intelligent Communications (MLICOM 2018)

Mobile Networks and Applications -     

Parallel XPath query based on cost optimization

The Journal of Supercomputing - The performance of XPath query is the key factor to the capacity of XML processing. It is an important way to improve the performance of XPath by making full use of...     

Application of intelligent real-time image processing in fitness motion detection under internet of things

The purpose is to study the applicability of digital and intelligent real-time Image Processing (IP) in fitness motion detection under the environment of the Internet of Things (IoT). Given the absence of real-time training standards and possible workout injury problems during fitness activities, an intelligent fitness real-time IP system based on Deep Learning (DL) is implemented. Specifically, the keyframes of the real-time images are collected from the fitness monitoring video, and the DL algorithm is introduced to analyze the fitness motions. Afterward, the performance of the proposed system is evaluated through simulation. Subsequently, the Noise Reduction (NR) performance of the proposed algorithm is evaluated from the Peak Signal-to-Noise Ratio (PSNR), which remains above 20 dB for seriously noisy images (with a noise density reaching up to 90%). By comparison, the PSNR of the Standard Median Filter (SMF) and Ranked-order Based Adaptive Median Filter (RAMF) algorithms are not higher than 10 dB. Meanwhile, the proposed algorithm outperforms other DL algorithms by over 2.24% with a detection accuracy of 97.80%; the proposed system can adaptively detect the fitness motion, with a transmission delay no larger than 1 s given a maximum of 750 keyframes. Therefore, the proposed DL-based intelligent fitness real-time IP algorithm has strong robustness, high detection accuracy, and excellent real-time image diagnosis and processing effect, thus providing an experimental reference for sports digitalization and intellectualization.

     

Erratum to: High-purity helical carbon nanotubes by trace-waterassisted chemical vapor deposition: Large-scale synthesis and growth mechanism

Nano Research - The first author, Fanbin Meng, and the second author, Ying Wang, contributed equally to this work was unfortunately forgotten to write on the first pages of the main text and the...     

Neural Machine Translation by Fusing Key Information of Text

When the Transformer proposed by Google in 2017, it was first used for machine translation tasks and achieved the state of the art at that time. Although the current neural machine translation model can generate high quality translation results, there are still mistranslations and omissions in the translation of key information of long sentences. On the other hand, the most important part in traditional translation tasks is the translation of key information. In the translation results, as long as the key information is translated accurately and completely, even if other parts of the results are translated incorrect, the final translation results’ quality can still be guaranteed. In order to solve the problem of mistranslation and missed translation effectively, and improve the accuracy and completeness of long sentence translation in machine translation, this paper proposes a key information fused neural machine translation model based on Transformer. The model proposed in this paper extracts the keywords of the source language text separately as the input of the encoder. After the same encoding as the source language text, it is fused with the output of the source language text encoded by the encoder, then the key information is processed and input into the decoder. With incorporating keyword information from the source language sentence, the model’s performance in the task of translating long sentences is very reliable. In order to verify the effectiveness of the method of fusion of key information proposed in this paper, a series of experiments were carried out on the verification set. The experimental results show that the Bilingual Evaluation Understudy (BLEU) score of the model proposed in this paper on the Workshop on Machine Translation (WMT) 2017 test dataset is higher than the BLEU score of Transformer proposed by Google on the WMT2017 test dataset. The experimental results show the advantages of the model proposed in this paper.     

A network-based mobility management scheme for future Internet

The current Internet was originally designed for “fixed” terminals and can hardly support mobility. It is necessary to develop new mobility management schemes for the future Internet. This paper proposes an Identifiers Separating and Mapping Scheme (ISMS), which is a candidate for the future Internet mobility management, and discusses the basic principles and detailed message flow. ISMS is a network-based mobility management scheme that takes advantage of the identity and location separation. The mobility entities in the core network are responsible for the location management. ISMS is designed to satisfy the requirements of faster handover, route optimism, advanced management, location privacy and security. The average handover delay of ISMS is on the order of milliseconds only, which is far smaller than that of Mobile IPv6. Analyses show that ISMS can reduce packet overhead on wireless channels. We build a prototype and perform some experiments. Results verify the feasibility of ISMS.     

A comparative study of two techniques for improving power‐handling capability of CMOS T/R switches

This article proposes an asymmetric topology for transmit/receive (T/R) switches and more importantly presents a comparative study of both LC‐tuned and resistive body‐floating techniques for improving the power‐handling capability of the T/R switches in the same 0.18‐μm triple‐well CMOS. It is shown from simulations and measurements that the switches adopting either technique achieve comparable performances. For instance, the switch employing the LC‐tuned body‐floating technique exhibits insertion loss of 1.5 dB, isolation of 23.5 dB, and power‐handling capability of 22.5 dBm at 5.2 GHz, whereas the switch using the resistive body‐floating technique exhibits insertion loss of 1.3 dB, isolation of 24 dB, and power‐handling capability of 22.2 dBm, respectively. Therefore, one can conclude that the asymmetric topology with the resistive body‐floating technique is more suitable for designing T/R switches for wireless local area network applications as it consumes smaller silicon area. © 2010 Wiley Periodicals, Inc. Int J RF and Microwave CAE, 2010.     

Fabrication of metallic micromirror using electroplating technology

A nickel micromirror array was designed and successfully fabricated using a thick photoresist as a sacrificial layer and as a mold for nickel electroplating. It was composed of two address electrodes, two support posts and a nickel mirror plate. The mirror plate, which is supported by two nickel posts, is overhung about 10 μm from the silicon substrate. The nickel mirror plate is actuated by an electrostatic force generated by electrostatic potential difference applied between the mirror plate and the address electrode. Optimized fabrication processes have been developed to reduce residual stress in mirror plate and prevent contact between the mirror plate and the substrate, which ensure a reasonable flat and smooth micromirror for operation at low actuation voltage.

     

Development of a web-based insulin decision aid for the elderly: usability barriers and guidelines

Universal Access in the Information Society - In recent years, researchers have attempted to shift patient decision aids (PDAs) from paper-based to web-based to increase its accessibility. Insulin...