Papers by Keyword: Acoustic Source Localization

Abstract: To realize accurate acoustic source localization with variable power in noisy environments, a novel acoustic source localization method with variable power based on LSSVR regression learning (ALVP-LRL) was proposed. The ratio values of any two adjacent nodes’ theoretical measurements of acoustic energy comprise feature vector, which has stable mapping relationship to source’s coordinates. LSSVR was applied to build regression models approximately reflecting that mapping relationship. By inputting feature vector constructed by real measurements into the regression models, the models’ outputs were then regarded as the estimated coordinates. Experiments were performed in 121 test locations. As SNR level reduced, amount of test locations where location errors were less than 2 meters by ALVP-LRL method changed from 77 to 54, while that amount by MLE method rapidly decreased from 121 to 11. It shows ALVP-LRL method preliminarily achieves certain effects and has more significant advantages on lower SNR occasions.

Abstract: The traditional acoustic source is sensitive to time. A novel sound source location method using linear intersection spacing multi-sensors array is provided in this paper. Each array is composed of three spaced nodes, and least squares method is used to calculate the final position according to ternary array results. Multi-arrays method is more robust than the ternary one, and much wider scope is covered. Location scope extends from 120m to 800m when the relative positioning error is 10%. A multi-array group based on linear intersection sound source localization method is provided in this paper too. Experiment results show that the proposed method has higher precision on angle locating than distance locating.

Abstract: To solve the problem of acoustic source localization in wireless sensor networks (WSN) under interference of environmental noise, a novel acoustic source localization method in WSN based on Least Square Support Vector Regression (LSSVR) modeling (ASL-LRM) was proposed. The ideal measured values of acoustic sensors were used to compose feature vector at first. Then LSSVR models were built by LSSVR modeling on the mapping relation between feature vector and acoustic source coordinate. The acoustic source was then located by inputting feature vector composed of real measured values of the sensors into LSSVR models. The modeling parameters optimization method based on localization effect in sample locations was also discussed. Experiments were performed in 100 test locations. RMSE values by ASL-LRM method in 72-76 test locations were less than MLE method and reduced by 60%-74% at most. In lower signal-to-noise ratio case, there were 87 test locations where RMSE values by ASL-LRM method were less than 2 meters, while there were only 12 test locations by MLE method. It shows ASL-LRM method achieves better localization effects in a large part of the region surrounded by sensor nodes. It especially has advantage on the occasions like lower signal-to-noise ratio or high precision localization.

Abstract: Wireless Sensor Networks (WSNs) enable susceptible sensing of the environment, offering unprecedented opportunities for observing the physical world. Acoustic source localization is an interesting topic with many possible application areas, such as intruder detection, sniper localization, automatic tracking of speakers and so on. Many existing algorithms are on the premise that the exact coordinates of sensor nodes are already known. In this paper, we propose a vector-based advanced TDoA algorithm that would calibrate the coordinate of the acoustic source by the non-prepositioned nodes. In the meanwhile, the portable sensor nodes would adjust themselves through the feedback of the estimated positions as well. Finally, we show that the proposed mechanism has high accuracy through experiments.