Agglomerative hierarchical clustering (AHC) has been widely used in speaker diarization systems to classify speech segments in a given data source by speaker identity, but is known to be not robust to data source vari...
详细信息
ISBN:
(纸本)9781424417452
Agglomerative hierarchical clustering (AHC) has been widely used in speaker diarization systems to classify speech segments in a given data source by speaker identity, but is known to be not robust to data source variation. In this paper, we identify one of the key potential sources of this variability that negatively affects clustering error rate (CER), namely short speech segments, and propose three solutions to tackle this issue. Through experiments on various meeting conversation excerpts, the proposed methods are shown to outperform simple AHC in terms of relative CER improvements in the range of 17-32%.
With the popularity of MPEG-4 and MPEG-7 standards, video object (VO) segmentation becomes a very challenging research area in video applications. We present a novel method for semi-automatic object segmentation for a...
详细信息
ISBN:
(纸本)0780356101
With the popularity of MPEG-4 and MPEG-7 standards, video object (VO) segmentation becomes a very challenging research area in video applications. We present a novel method for semi-automatic object segmentation for a video sequence. The proposed approach starts with a rough user input VO definition. It then combines each frame's region segmentation and motion estimation results to construct the objects of interest for temporal tracking this object along the time. An active contour model based algorithm is employed to further fine-tune the object's contour so as to extract accurate object boundary. Some experimental results and future research directions are also discussed.
To address the problem of unsupervised outlier detection in wireless sensor networks, we develop an algorithm that (1) is flexible with respect to the outlier definition, (2) works in-network with a communication load...
详细信息
To address the problem of unsupervised outlier detection in wireless sensor networks, we develop an algorithm that (1) is flexible with respect to the outlier definition, (2) works in-network with a communication load proportional to the outcome, and (3) reveals its outcome to all sensors. We examine the algorithm’s performance using simulation with real sensor data streams. Our results demonstrate that the algorithm is accurate and imposes a reasonable communication load and level of power consumption.
This study addresses the problem of detecting change points in streaming data. Herein, we focus on detecting changes with low complexity and high accuracy to manage large-volume, high-velocity data. To this end, we pr...
详细信息
This study addresses the problem of detecting change points in streaming data. Herein, we focus on detecting changes with low complexity and high accuracy to manage large-volume, high-velocity data. To this end, we propose a novel method of detecting changes via data compression, by introducing minimum description length (MDL) change statistics to an adaptive windowing regime. The time complexity of the resulting algorithm, Sequential Compression with Adaptive Windowing (SCAW), is optimal except for a logarithmic factor, and is theoretically justified through exponential upper bounds on error probabilities. Moreover, SCAW can be used to detect arbitrary types of changes by choosing an appropriate compressor. We also introduce the notion of asymptotic reliability as a criterion of change point detectionalgorithms, and determine SCAW's parameter using this criterion. Finally, we demonstrate the effectiveness of the proposed method in experiments using synthetic and real-world data from markets and industrial machinery.
We present the design of readout electronics for an Electrolyte Insulator Semiconductor capacitor (EISCAP) sensor. The sensor detects the presence of bioanalytes by sensing the change in the pH of the electrolyte. Our...
详细信息
We present the design of readout electronics for an Electrolyte Insulator Semiconductor capacitor (EISCAP) sensor. The sensor detects the presence of bioanalytes by sensing the change in the pH of the electrolyte. Our technique uses an EISCAP relaxation oscillator embedded in a successive approximation analog-to-digital conversion algorithm to give a digital readout of the pH of the test solution. A microcontroller based pH readout instrument, incorporating calibration to account for sensor variations, is described. Experimental results that demonstrate the efficacy of our techniques are given.
Wireless Sensor networks (WSN) are prone to cause failures due to the constraining factors of energy, memory and communication capability. This paper describes an efficient faulty detection and recovery mechanism for ...
详细信息
ISBN:
(纸本)9781424440085
Wireless Sensor networks (WSN) are prone to cause failures due to the constraining factors of energy, memory and communication capability. This paper describes an efficient faulty detection and recovery mechanism for ZigBee network which is an industrial standard widely adopted for WSN. We propose a localized tree based method for detecting faults due to energy exhaustion of nodes and repair them after node failure. We design three types of failure mechanisms depending on the type of node in the tree network of ZigBee. In order to avoid much more exchange message and reduce the collision of re-joining network, we take an ¿elected new parent¿ strategy from the disconnected children, and make the disconnected node re-join network together with as many descendant nodes as possible. Simulation results show that our proposed method consumes less energy than the original ZigBee network, and prolong the lifetime of network efficiently.
Traffic queuing and delay can't be detected accurately by traditional loop detection due to technical limit. In recent years, video technology has been applied to the traffic control detection, which has a greater...
详细信息
Traffic queuing and delay can't be detected accurately by traditional loop detection due to technical limit. In recent years, video technology has been applied to the traffic control detection, which has a greater deal of information and larger detection area, and therefore, it will bring revolutionary change to the traffic control algorithm. This paper provides discussions on the characteristics of vehicle arrival in urban arterial based on video traffic detection, and puts forward the pattern recognition approach of the traffic queuing arrival and calculation method of the related parameters, which can offer the reliable basis for the generation of traffic control scheme. Furthermore, the feasibility of this method is illustrated by example analysis.
We propose a skin detection algorithmic system for a consequent video sequence which is fast, reliable and applicable. We adopted YCbCr color space, which is competitive in extracting the skin region from digital tele...
详细信息
ISBN:
(纸本)0780386396
We propose a skin detection algorithmic system for a consequent video sequence which is fast, reliable and applicable. We adopted YCbCr color space, which is competitive in extracting the skin region from digital television (DTV) related images. Based on a Gaussian color probability density, and the assumption that the color is homogeneous in a continuous scene, we adopted a face detection method to extract the skin space locus from one scene to another scene so that adequate skin space is renewed by face detection. We target this algorithm for DTV applications. As speed of the algorithm is crucial in a real time system, we adopted motion estimation (ME) to find the exact frames which need the skin space to be updated due to scene change or skin color change. The core of this work is a practical adaptive skin space search algorithm, meanwhile reducing distortion from various image sources. Our adaptive skin locus update (ASLU) algorithm shows outstanding result comparing to static skin region detectionalgorithms.
暂无评论