Authentication email has already been sent, please check your email box: and activate it as soon as possible.
You can login to My Profile and manage your email alerts.
If you haven’t received the email, please:
|
|
There are 6 papers published in subject: > since this site started. |
Results per page: |
Select Subject |
Select/Unselect all | For Selected Papers |
Saved Papers
Please enter a name for this paper to be shown in your personalized Saved Papers list
|
1. FFT Parallel processing method based on ASIP | |||
Tian Run,Man Yi | |||
Electrics, Communication and Autocontrol Technology 28 February 2023 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:With the research and development of various types of application-specific instruction-set processor (ASIP), the algorithm library based on single-core general processor can not make full use of the structural characteristics and special instruction set of ASIP. In order to improve the computing performance of ASIP, it is usually necessary to design a special algorithm library. Based on a special processor for 5G small base station wireless communication, this paper optimizes the general FFT algorithm. In this paper, data reordering is added to the Cooley-Tukey algorithm to ensure the natural order of input and output data and increase the data-level parallelism in the algorithm. The optimized algorithm is implemented on the simulator of the dedicated processor using the dedicated instruction set. The experimental results show that the proposed method achieves a high speedup in the dedicated processor. | |||
TO cite this article:Tian Run,Man Yi. FFT Parallel processing method based on ASIP[OL].[28 February 2023] http://en.paper.edu.cn/en_releasepaper/content/4759324 |
2. Complex Dynamic Hand Gesture Auto-Detection and Recognition with WiFi Signal Based on CNN | |||
Xu Pan,Ting Jiang,Xudong Li,Xue Ding | |||
Electrics, Communication and Autocontrol Technology 20 February 2019 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:WiFi signal has been proven it can be used for dynamic hand gesture recognition, which is expected to provide a novel way for human-computer interaction (HCI). Traditional methods for dynamic hand gesture recognition with WiFi can just recognize simple gestures like up and down movement, left and right movement. Besides, the detection and segmentation algorithms for the gestures are performed in offline data. In this paper, a complete dynamic hand gesture automatic detection and recognition framework is proposed by using the instantaneous received signal strength (IRSS) extracted from multiple independent WiFi nodes. We analyzed that the starting and ending points of the gesture waveform segments are not absolutely accurate no matter by manual segmentation or the proposed auto-segmentation algorithm. Therefore, we designed a recognition module based on convolutional neural network (CNN) to effectively eliminate the errors caused by segmentation phase to improve the recognition accuracy of the system. In the experimental phase, we can adjust the parameters to balance gesture detection accuracy and recognition accuracy. The system can achieve 88.98% recognition accuracy with 87.88% detection accuracy or 94.79% recognition accuracy with 72.12% detection accuracy. | |||
TO cite this article:Xu Pan,Ting Jiang,Xudong Li, et al. Complex Dynamic Hand Gesture Auto-Detection and Recognition with WiFi Signal Based on CNN[OL].[20 February 2019] http://en.paper.edu.cn/en_releasepaper/content/4747306 |
3. A Multi-stage Encoding Scheme for Multiple Audio Objects Using Compressed Sensing | |||
Yang Ziyu,Jia Maoshen,Wang Wenbei,Zhang Jiaming | |||
Electrics, Communication and Autocontrol Technology 16 October 2015 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:Object-based audio techniques have become common as they provide the flexibility for personalized rendering. In this work, a multi-stage encoding scheme for multiple audio objects is proposed. The scheme is based on intra-object sparsity. In the encoding phase, the dominant time-frequency (TF) instants of all active object signals are extracted and divided into several stages to form the multi-stage observation signals for transmission. In the decoding phase, the preserved TF instants are recovered via the Compressed Sensing (CS) technique, and further used for reconstructing the audio objects. The evaluations validated that the proposed encoding scheme can achieve scalable transmission while maintaining the perceptual quality of each audio object. | |||
TO cite this article:Yang Ziyu,Jia Maoshen,Wang Wenbei, et al. A Multi-stage Encoding Scheme for Multiple Audio Objects Using Compressed Sensing[J]. |
4. Failure Detection and Validation of Multifunctional Self-validating Sensor Using WRVM Predictor | |||
SHEN Zhengguang,SONG Kai,WANG Qi | |||
Electrics, Communication and Autocontrol Technology 19 January 2012 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:A novel multifunctional self-validating sensor functional model is proposed for evaluation, improvement, and forecast of measurement value reliability. This paper presents a detailed introduction of main content--self-validating function, especially the quantitative health evaluation and remaining using life forecasting. As a fundamental self-validating function, a novel strategy based on relevance vector machine (RVM) coupled with wavelet analysis is proposed for failure detection, isolation, and recovery (FDIR) of multifunctional self-validating sensor. It centers on the working principle and on-line updating algorithm of WRVM predictor. The proposed WRVM predictor can also distinguish the fault free signal with sudden change from the failure signal and it is updated online for pursuit of signal change. A multifunctional self-validating sensor experimental system is designed to evaluate the performance of novel strategy. Results demonstrate that the proposed methodology provides a good solution to the FDIR of multifunctional self-validating sensor. | |||
TO cite this article:SHEN Zhengguang,SONG Kai,WANG Qi. Failure Detection and Validation of Multifunctional Self-validating Sensor Using WRVM Predictor[OL].[19 January 2012] http://en.paper.edu.cn/en_releasepaper/content/4463224 |
5. Audio Content Classification by Using Spectral Features | |||
Qian Xueming ,Liu Guizhong,Wang Huan ,Li Zhi ,Nan Nan,Wang Zhe ,Sun Li | |||
Electrics, Communication and Autocontrol Technology 10 February 2009 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:Audio information play important role in speaker identification and semantic based video content analysis, indexing and retrieval. Sometimes, audio clues are dominant in determining the story unit types. In this paper, a new temporal spectral feature including the proposed spectral histogram is integrated for audio content classification. By analysis the temporal spectral distribution, we adaptively determine the effective feature vectors for audio content discrimination. Finally, several one class support vector machine (SVM) are used to classify each audio clip into following five types: silence, pure music, pure speech, speech with noise background (Speech+Noise), and speech with music background (Speech+Music). Experimental results show the effectiveness of the proposed methods. | |||
TO cite this article:Qian Xueming ,Liu Guizhong,Wang Huan , et al. Audio Content Classification by Using Spectral Features[OL].[10 February 2009] http://en.paper.edu.cn/en_releasepaper/content/28696 |
6. Using another feature selection algorithm for POS Tagging based on Maximum Entropy Principle | |||
Yao Ning | |||
Electrics, Communication and Autocontrol Technology 09 November 2007 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:Maximum Entropy model is widely used in natural language processing in many fields, this paper uses Maximum Entropy model to build a part-of-speech tagging system based on the special needs. Because of the huge difference of grammar and structure between Chinese and English, this paper focuses on feature selection’s influence on the premise that its feature template is selected. And we use a feature selection algorithm-iteration, modification, and cutting (IMC) applied to Maximum Entropy model. The experiment shows that we can gain a better result through appropriate feature selection methods. | |||
TO cite this article:Yao Ning. Using another feature selection algorithm for POS Tagging based on Maximum Entropy Principle[OL].[ 9 November 2007] http://en.paper.edu.cn/en_releasepaper/content/16257 |
Select/Unselect all | For Selected Papers |
Saved Papers
Please enter a name for this paper to be shown in your personalized Saved Papers list
|
Results per page: |
About Sciencepaper Online | Privacy Policy | Terms & Conditions | Contact Us
© 2003-2012 Sciencepaper Online. unless otherwise stated