Dimension Reduction of Speech Emotion Feature Based on Weighted Linear Discriminant Analysis

Jingjing Yuan,Li Chen,Taiting Fan,Jian Jia 보안공학연구지원센터 2015 International Journal of Signal Processing, Image Vol.8 No.11

Feature dimension reduction is important for speech emotion recognition. The classical linear discriminant analysis has been used widely in this field, but the best projection separating class from others can’t be obtained with the linear discriminant analysis method due to outlier class. To approach this problem, a novel distance weighted function based on the linear discriminant analysis is introduced, which can improve the separability of sample data and has low computational complexity. In order to evaluate the proposed algorithm’s performance, some experiments are performed on two speech databases: UCI and CASIA. Experimental results on the UCI database demonstrate that the presented algorithm has a better performance. Experimental results on CASIA show that the proposed algorithm yields an average accuracy of 88.78% in the classification of four emotions, revealing that it is a better choice as feature dimension reduction for emotion classification than the traditional algorithms.

Phosphorylation of Silk Fibroin via Maillard Reaction and Its Behavior of Biomimetic Mineralization

Jingjing Yuan,Qian Zhou,Ping Wang,Chao Deng,Jiugang Yuan,Qiang Wang 한국섬유공학회 2019 Fibers and polymers Vol.20 No.8

Silk fibroin (SF) has the characteristics of non-toxicity, good biocompatibility and low immunogenicity, andexhibits many potential applications in biomaterial fields. In the present work, chemical phosphorylation of SF was carriedout via the Maillard reaction using D-glucose-6-phosphate (GP), aiming at increasing the number of binding-sites forcalcium ion and promoting the biomimetic mineralization of SF films. Changes in the molecular weight of SF before andafter GP grafting were analyzed by SDS-PAGE and SEC chromatogram. Structures, morphologies, and elementalcompositions for the fibroin-based films before and after mineralization were evaluated by the means of EDS, SEM, FTIR,and XRD. The results indicated that GP was successfully grafted onto SF surfaces, companying with a slight decrease in themolecular weight. Biomimetic mineralization led to a noticeable deposition of hydroxyapatite (HAp) on the film of SF-g-GP, and higher contents of calcium and phosphorous were detected on the mineralized material, revealing thatphosphorylation promoted the mineralization processing. Meanwhile, biocompatibility of the obtained SF-g-GP/HAp wasabove the acceptable level according to ISO 10993-5-2009. The present work provides an alternative to prepare the fibroinbasedbone repair materials.

Power Quality Warning of High-Speed Rail Based on Multi-Features Similarity

Jingjing Bai,Wei Gu,Xiaodong Yuan,Qun Li,Bing Chen,Xuchong Wang 대한전기학회 2015 Journal of Electrical Engineering & Technology Vol.10 No.1

As one type of power quality (PQ) disturbance sources, high-speed rail (HSR) can have major impacts on the power supply grid. Providing timely and accurate warning information for PQ problems of HSR is important for the safe and stable operation of traction power supply systems and the power supply grid. This study proposes a novel warning approach to identify PQ problems and provide warning prompts based on the monitored data of HSR. To embody the displacement and status change of monitored data, multi-features of different sliding windows are computed. To reflect the relative importance degree of these features in the overall evaluation, an analytic hierarchy process (AHP) is used to analyse the weights of multi-features. Finally, a multi-features similarity algorithm is applied to analyse the difference between monitored data and the reference data of HSR, and PQ warning results based on dynamic thresholds can be analysed to quantify its severity. Cases studies demonstrate that the proposed approach is effective and feasible, and it has now been applied to an actual PQ monitoring platform.

Power Quality Warning of High-Speed Rail Based on Multi-Features Similarity

Bai, Jingjing,Gu, Wei,Yuan, Xiaodong,Li, Qun,Chen, Bing,Wang, Xuchong The Korean Institute of Electrical Engineers 2015 Journal of Electrical Engineering & Technology Vol.10 No.1

As one type of power quality (PQ) disturbance sources, high-speed rail (HSR) can have major impacts on the power supply grid. Providing timely and accurate warning information for PQ problems of HSR is important for the safe and stable operation of traction power supply systems and the power supply grid. This study proposes a novel warning approach to identify PQ problems and provide warning prompts based on the monitored data of HSR. To embody the displacement and status change of monitored data, multi-features of different sliding windows are computed. To reflect the relative importance degree of these features in the overall evaluation, an analytic hierarchy process (AHP) is used to analyse the weights of multi-features. Finally, a multi-features similarity algorithm is applied to analyse the difference between monitored data and the reference data of HSR, and PQ warning results based on dynamic thresholds can be analysed to quantify its severity. Cases studies demonstrate that the proposed approach is effective and feasible, and it has now been applied to an actual PQ monitoring platform.

Empirical Analysis of User Interaction Behavior in Microblogging

WeiGuo Yuan,Yun Liu,JingJing Yang 한국산학기술학회 2012 SmartCR Vol.2 No.3

Patterns of user interaction behavior in online social networks have attracted increasing academic interest, since the quantitative understanding of user behavior is helpful to uncover the origins of many socioeconomic phenomena. In order to gain insights into user interaction behavior characteristics in microblogging, we have crawled Sina Microblog data and obtained user profiles and statuses. Six features of users are studied in our experiments, which are followers and friends, statuses and favorites, retweets and comments. Empirical analysis reveals some common statistical features of user behavior in microblogging. First, all of these properties follow different power-law distributions. Especially, followers and statuses exhibit a double-power-law distribution and friends follow a specific interval power law distribution. Second, there exists a strong positive correlation between statuses and followers, retweets and comments, but the relation between followers and friends is weak. What"s more, there exists a moderate correlation between the number of friends and statuses, retweets and followers, and comments and followers. Third, only a small number of statuses have extreme dissemination and concern. From a quantitative view, the result shows that the strong effect of celebrity cannot be ignored in Sina Microblogs. We believe this paper has added rich empirical materials to our knowledge and understanding of user behavior in microblogging.

중·한 원소스 멀티테리토리(One Source Multi- Territory) 모식 영화에 대한 현지화 원소의 차이 연구 - 과 을 중심으로 -

Yin Jun,Yuan Jingzhuo,Cheng Jingjing 한중경제문화학회 2020 한중경제문화연구 Vol.15 No.-

EMI Modeling and Experiment of a GaN Based LLC Half-Bridge Converter

Mofan Tian,Yuan Hao,Kangping Wang,Yang Xuan,Lang Huang,Jingjing Sun,Xu Yang 전력전자학회 2015 ICPE(ISPE)논문집 Vol.2015 No.6

This paper focuses on the electromagnetic interference (EMI) research and analysis of the MHz switching frequency GaN MOSFET based on the LLC resonant DC-DC converter. In this paper, first, the CM coupling paths are studied to get simplified models. Then the impact of the parasitic capacitors (both the capacitors to the ground and the capacitors in the devices) on the CM current are analyzed. Finally the high frequency model is derived from the work above. Moreover this paper makes the comparison between normal Si MOSFET and GaNbased MOSFET behavior in EMI. The modeling result proves that GaN MOSFET has a worse behavior on EMI test. An experiment layout which is aimed at minimizing the irrelevant factors is designed and the experiment result proves the accuracy of the modeling.

Energy-efficient Relay MAC with Dynamic Power Control in Wireless Body Area Networks

( Xuelian Cai ),( Jingjing Yuan ),( Xiaoming Yuan ),( Wu Zhu ),( Jiandong Li ),( Changle Li ),( Sana Ullah ) 한국인터넷정보학회 2013 KSII Transactions on Internet and Information Syst Vol.7 No.7

Wireless body area network (WBAN) is an emerging short-range wireless communication network with sensor nodes located on, in or around the human body for healthcare, entertainment and ubiquitous computing. In WBANs, energy is severely constrained which is the prime consideration in the medium access control (MAC) protocol design. In this paper, we propose a novel MAC protocol named Energy-efficient Relay MAC with dynamic Power Control (ERPC-MAC) to save energy consumption. Without relying on the additional devices, ERPC-MAC employs relaying nodes to provide relay service for nodes which consume energy fast. Accordingly the superframe adjustment is performed and then the network topology can be smoothly switched from single-hop to multi-hop. Moreover, for further energy saving and reliability improvement, the dynamic power control is introduced to adjust the power level whenever a node transmits its packets to the coordinator or the relaying node. To the best of the authors` knowledge, this is the first effort to integrate relay, topology adjustment and power control to improve the network performance in a WBAN. Comprehensive simulations are conducted to evaluate the performance. The results show that the ERPC-MAC is more superior to the existing standard and significantly prolongs the network lifetime.

Power Quality Early Warning Based on Anomaly Detection

Wei Gu,Jingjing Bai,Xiaodong Yuan,Shuai Zhang,Yuankai Wang 대한전기학회 2014 Journal of Electrical Engineering & Technology Vol.9 No.4

Different power quality (PQ) disturbance sources can have major impacts on the power supply grid. This study proposes, for the first time, an early warning approach to identifying PQ problems and providing early warning prompts based on the monitored data of PQ disturbance sources. To establish a steady-state power quality early warning index system, the characteristics of PQ disturbance sources are analyzed and summed up. The higher order statistics anomaly detection (HOSAD) algorithm, based on skewness and kurtosis, and hierarchical power quality early warning flow, were then used to mine limit-exceeding and abnormal data and analyze their severity. Cases studies show that the proposed approach is effective and feasible, and that it is possible to provide timely power quality early warnings for limit-exceeding and abnormal data.

Preparation of Non-Planar-Ring Epoxy Thermosets Combining Ultra-Strong Shape Memory Effects and High Performance

Qiong Li,Songqi Ma,Jingjing Wei,Sheng Wang,Xiwei Xu,Kaifeng Huang,Binbo Wang,Wangchao Yuan,Jin Zhu 한국고분자학회 2020 Macromolecular Research Vol.28 No.5

Non-planar-ring epoxies together with non-planar-ring hardeners could achieve thermosets combining ultra-high shape recovery speed and excellent thermal properties. High shape recovery speed reflected high efficiency, and could decrease the energy consumption and the harmful effect of external stimuli on the materials, while it often conflicts with the thermal properties of shape memory polymers. In this paper, for the first time, epoxy resins with the super-short shape recovery time within 3 s were developed from non-planar-ring epoxies and hardeners, and their glass transition temperature (T g) were ~127 °C much higher than their benzene ring analogues. The effects of non-planar-ring structures of the epoxies and hardeners on the curing behavior, thermal properties as well as the shape memory properties of the thermosets were systematically investigated; the structure-property relationships were disclosed with the help of computational simulation of structure parameters and ESP maps. The faster shape recovery speed of the non-planar-ring epoxy thermosets is from their higher molecular mobility contributed by the conformational transition of non-planar-rings as well as their higher recovery force compared with benzene ring analogs. Their higher T gs are from the steric hindrance by the larger molecular volume of the non-planar-rings than benzene ring. This work will provide an effective method to produce shape memory polymers with excellent shape memory effects and high performance.