检索结果-内蒙古大学图书馆

21st IEEE International Conference on Computer Applications, ICCA 2024

作者： San, Win Pa Pa Zaw, Sai Maung Maung University of Computer Studies Mandalay Image and Signal Processing Lab Mandalay Myanmar University of Computer Studies Mandalay Faculty of Computer Systems and Technology Mandalay Myanmar

ISBN: (纸本)9789998601673

Nowadays, with aging of the human society, the 'ratio of family care givers and elderly' is not equivalent and cannot give enough caring to the elderly in some countries. Therefore, automatic health monitoring system for elderly draws the interests of many researchers and become as special issue. In the implementation of elderly people monitoring system, the detection of fall events plays as an important role because the fall is the common cause which is very risky and threaten the health of elderly. The aim of this research is to implement the vision-based fall detection system which is important for health monitoring of elderly by applying the computer vision and deep learning technology. Most of the traditional vision-based fall detection systems which based on the height, width of human posture, fail to detect the fall events from different camera viewpoints. In this research, to accurately detect the fall from different camera viewpoint, the features fusion approach is applied over the deep learning model. In the implementation of the system, firstly, the human silhouette image is created by using the background subtraction. After that, the human silhouette image which have been extracted from two consecutive frames are fused as a single image called Silhouette History image (SHI). Then, the SHI results are used as shape feature. On the other hand, the motion features called Dense Optical Flow (DOF) is extracted over the two consecutive video frames and fuse SHI and DOF as a single input image. Then, the results of features fusion are feed as input for pretrained Convolution Neural Network (CNN) for extracting the deep CNN features. Finally, the Recurrent Neural Network (RNN) called Long-Short-Term-Memory (LSTM) is trained over those CNN features for recognizing the sequence of fall event. The experiments are performed using the publicly available dataset of UP-fall detection dataset for evaluating and confirming the effectiveness of the proposed method. © 2024

关键词： Fall detection

来源：评论

学校读者我要写书评

暂无评论

Knowledge-guided EEG Representation Learning 46

Knowledge-guided EEG Representation Learning

引用

46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2024

作者： Kommineni, Aditya Avramidis, Kleanthis Leahy, Richard Narayanan, Shrikanth University of Southern California Signal Analysis and Interpretation Lab Los AngelesCA90089 United States University of Southern California Signal and Image Processing Institute Los AngelesCA90089 United States

ISBN: (纸本)9798350371499

Self-supervised learning has produced impressive results in multimedia domains of audio, vision and speech. This paradigm is equally, if not more, relevant for the domain of biosignals, owing to the scarcity of labelled data in such scenarios. The ability to leverage large-scale unlabelled data to learn robust representations could help improve the performance of numerous inference tasks on biosignals. Given the inherent domain differences between multimedia modalities and biosignals, the established objectives for self-supervised learning may not translate well to this domain. Hence, there is an unmet need to adapt these methods to biosignal analysis. In this work we propose a self-supervised model for EEG, which provides robust performance and remarkable parameter efficiency by using state space-based deep learning architecture. We also propose a novel knowledge-guided pre-training objective that accounts for the idiosyncrasies of the EEG signal. The results indicate improved embedding representation learning and downstream performance compared to prior works on exemplary tasks. Also, the proposed objective significantly reduces the amount of pre-training data required to obtain performance equivalent to prior works. © 2024 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

EEG signal analysis based on time-variant coupled network Lattice model

EEG signal analysis based on time-variant coupled network La...

引用

ICBPE 2006 - 2006 International Conference on Biomedical and Pharmaceutical Engineering

作者： Minfen, Shen Guoliang, Chang Shuwang, Wang Beadle, Patch J. Key Lab. of Digital Signal and Image Processing of Guangdong Province Shantou University Shantou China School of System Engineering Portsmouth University Portsmouth United Kingdom

ISBN: (纸本)8190426249

Brain electrical activity is widely accepted as the typical non-stationary signal. In addition, there exist more evidences that both EEG and ERP signals are chaotic signal produced by the nonlinear dynamics system. To investigate the time-varying nonlinear dynamics of the ERP under specified cognitive tasks, a novel model based on the time-variant coupled map lattice system is proposed for this purpose. The time-variant largest Lyapunov exponent (LLE) is also defined as the quantitative parameters to reveal the global characters of system and discover new information. Several simulations and real ERP signals under different fixed location cue were examined in terms of LLE spectra for studying the signal's dynamic complexity. The experimental results show that the brain chaos changes with time under different attention tasks of the information processing. The influence of the LLE with the scopes size of cues mainly occurs in P2 period. No simple linearly relationship between the scopes of cues and the influence of complexity is found. © 2006 Research Publishing Services.

关键词： Dynamics

来源：评论

学校读者我要写书评

暂无评论

Automated Classification of Segmented Cancerous Cells in Multispectral images

引用

Journal of Life Sciences 2013年第4期7卷 358-362页

作者： Alaa Hilal Jamal Charara Ali Al Houseini Walid Hassan Mohamad Nassreddine Signal and Image Processing Lab Faculty of Sciences I Lebanese University Beirut Lebanon

Automatic reading procedures in colon cells biopsies allow a faster and precise reading of microscopic biopsies. These procedures implement automatic image segmentation in order to classify cell types as cancerous or noncancerous. The authors have developed a new approach aiming to detect colon cancer cells derived from the ＂Snake＂ method but using a progressive division of the dimensions of the image to achieve rapid segmentation. The aim of the present paper was to classify different cancerous cell types based on nine morphological parameters and on probabilistic neural network. Three types of cells were used to assess the efficiency of our classifications models, including BH （Benign Hyperplasia）, IN （Intraepithelial Neoplasia） that is a precursor state for cancer, and Ca （Carcinoma） that corresponds to abnormal tissue proliferation （cancer）. Results showed that among the nine parameters used to classify cells, only three morphologic parameters （area, Xor convex and solidity） were found to be effective in distinguishing the three types of cells. In addition, classification of unknown cells was possible using this method.

关键词： Multispectral image classification morphologic parameters probabilistic neural network.

来源：评论

学校读者我要写书评

暂无评论

Isolated word, speaker dependent recognition under the presence of noise, based on an audio retrieval algorithm

Isolated word, speaker dependent recognition under the prese...

引用

Conference Record of the Thirty-Eighth Asilomar Conference on signals, Systems and Computers

作者： Vasiloglou, Nikolaos Schafer, Ronald W. Hans, Mat C. Georgia Institute of Technology Center for Signal and Image Processing Atlanta GA 30332 Hewlett-Packard Laboratories Mobile and Media Systems Lab. Palo Alto CA 94304

With rapidly increasing storage and computational capacity, a common PC can store and index hundreds of hours of speech. This suggests that new approaches based on database techniques might be useful in speech recognition and speech indexing. This paper presents a first step in such a direction. The algorithm developed relies on an indexed single-speaker database. The database consists of spoken utterances transcribed into text. The waveforms of these utterances are converted off-line to binary symbols called fingerprints through a nonlinear frequency-domain transform. The fingerprints are associated with the transcribed text. Given the fingerprint of a new waveform, the best word match from the database can be retrieved. A 3255 word database is used as a test bed. All the words from this database are mixed with white noise and time-scale modified to provide test data. The database is queried with the fingerprint of the test words and the best match is retrieved. The results of the experiments conducted are promising, showing a 99.5% recognition rate for a 20dB signal to Noise Ratio (SNR). © 2004 IEEE.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Fast generation of LULC maps for temporal studies in North-Western Africa

Fast generation of LULC maps for temporal studies in North-W...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： P. del Aguila F. Calderero F. Marqués J. Marcello F. Eugenio KTH Signal Processing Lab Image Processing Group UPF Image Processing Group UPC ULPGC Institute for Oceanography and Global Change

This paper provides an objective evaluation of six supervised classification techniques and three state of the art features, with the objective of obtaining a single combination of them that provides both robustness and objective performance improvements. As a conclusion, a simple procedure for obtaining LULC maps with four targeted classes is proposed.

关键词： Remote sensing Satellites Support vector machines Earth Databases Robustness Entropy

来源：评论

学校读者我要写书评

暂无评论

A visual complexity-sensitive DWT ordering scheme for hiding data in images

引用

Research Journal of Applied Sciences, Engineering and Technology 2014年第16期7卷 3286-3297页

作者： Iliyasu, Abdullah M. Al-Asmari, Awad Kh. Salama, Ahmed S. Al-Qodah, Mohammed A. Abd Elwahab, Mohamed A. Le, Phuc Q. Salman Bin Abdulaziz University Al Kharj Saudi Arabia Department of Computational Intelligence and Systems Science Tokyo Institute of Technology Japan Image and Signal Processing Lab King Saud University Saudi Arabia

A scheme is proposed to hide data in images based on a prioritized ordering of the content of the host (or cover) image. A watermark embedding process uses the watermark strength to determine the ordering of the 16 regions resulting from the second level Discrete Wavelet Transform (DWT) decomposed content of the host image. To determine the best ordering for hiding the data, various types of image of varying content and, hence, visual complexity were considered, analyzed and ranked in terms of their ability to withstand changes that do not imperil the visual quality (PSNR) of their watermarked versions depending on which an N×N-sized watermark stream is hidden in the 8 highest ranked sub-bands of the host image. From this perspective, an ordering for images classified as simple, normal and complex images was used to determine a generalized ordering of the DWT decomposed sub-bands of the image. The generalized ordering presented here ascertains that the content of the image and its visual complexity had little effect on an earlier proposed prioritized ordering of the DWT Sub-bands. To validate the veracity of the ordering scheme, 1000 images from the Corel 1000A database, their visual complexity and features were taken into account. The results confirmed that high embedding capacity, appreciable visual quality of watermarked images and complete recovery hidden data are realizable based on the ordering scheme proposed in this study. © Maxwell Scientific Organization, 2014.

关键词： Data hiding Discrete wavelet transform (DWT) image processing Information security Visual complexity Watermarking

来源：评论

学校读者我要写书评

暂无评论

Modelling of random extra pulses during quasi-closed glottal cycle phases 10

Modelling of random extra pulses during quasi-closed glottal...

引用

10th International Workshop on Models and Analysis of Vocal Emissions for Biomedical Applications, MAVEBA 2017

作者： Aichinger, P. Roesner, I. Schoentgen, J. Pernkopf, F. Department of Otorhinolaryngology Division of Phoniatrics-Logopedics Medical University of Vienna Austria F.N.R.S. Université Libre de Bruxelles Laboratories of Image Signal Processing and Acoustics Faculty of Applied Sciences Brussels Belgium Signal Processing and Speech Communication Lab Graz University of Technology Austria

ISBN: (纸本)9788864536064

The presence of random extra pulses during quasi-closed glottal cycle phases may constitute a distinct voice quality type relevant to the clinical care of disordered voices. In this paper, we propose for this voice type a glottal area waveform model that includes automatic parameter estimation. The model involves (1) extraction of the fundamental frequency, (2) estimation of the cyclic pulse times, heights and shapes, (3) Fourier synthesis of a cyclic pulse train model, (4) closed phases estimation via fitting an inverted parabola to the averaged pulse shape, (5) estimation of the random extra pulses’ positions and shapes, and (6) pulse shape filtering based synthesis of the random extra pulses. For a typical voice sample, the root mean square error energy level of the purely cyclic model = -13.2 dB, which improves by 1.5 dB when extra pulses are added to the model. © Models and Analysis of Vocal Emissions for Biomedical Applications, MAVEBA *** right reserved.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

image fusion algorithm based on features motivated multi-channel pulse coupled neural networks

Image fusion algorithm based on features motivated multi-cha...

引用

2nd International Conference on Bioinformatics and Biomedical Engineering, iCBBE 2008

作者： Qu, Xiaobo Yan, Jingwen Dept. of Communication Engineering Xiamen University Fujian 361005 China Key Lab. of Digital Signal and Image Processing of Guangdong Province Shantou University Guangdong 515063 China

ISBN: (纸本)9781424417483

Pulse coupled neural networks (PCNN) is a mammal visual cortex-inspired artificial neural networks. Owing to the coupling links in neurons, PCNN is successful to utilize the local information, thus it has been successfully employed in image fusion. However, in traditional PCNN for image fusion, value of per pixel is used to motivate per neuron. In this paper, image feature of per pixel, e.g. gradient and local energy, is used to motivate per neuron and generate firing maps. Each firing map is corresponding to one type feature. Furthermore, a new multichannel PCNN is presented to combine these firing maps via a weighting function which measures the contribution of these features to the fused image quality. Finally, pixels with maximum firing times, when firing times of source images are compared, are selected as the pixels of the fused image. Experimental results demonstrate that the proposed algorithm outperforms Waveletbased and Wavelet-PCNN-based fusion algorithms. © 2008 IEEE.

关键词： image fusion

来源：评论

学校读者我要写书评

暂无评论

Vehicle tracking using image processing techniques

引用

4th International Conference on Rough Sets and Current Trends in Computing, RSCTC 2004

作者： Rhee, Seung Hak Han, Seungjo Kim, Pan koo Ahmad, Muhammad Bilal Park, Jong An College of Electronics and Information Engineering Chosun University Gwangju Korea Republic of Signal and Image Processing Lab Dept. of Mechatronics Kwangju Institute of Science and Technology Gwangju Korea Republic of

ISBN: (纸本)3540221174

A real time vehicle tracking in image sequences is presented. The moving vehicles are segmented by the method of differential image followed by the process of morphological dilation. The vehicles are recognized and tracked using statistical moments. The straight lines in the moving vehicles are found with the help of Radon transform. The direction of the moving object is calculated from the orientation of the straight lines in the direction of the principal axes of the moving objects. The direction of the moving object and the displacement of the object in the image sequence are used to calculate the velocity of the moving objects. © Springer-Verlag Berlin Heidelberg 2004.

关键词： Vehicles

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：