Juha T. Tanttu

Wavelets in recognition of bird sounds

This paper presents a novel method to recognize inharmonic and transient bird sounds efficiently. The recognition algorithm consists of feature extraction using wavelet decomposition and recognition using either supervised or unsupervised classifier. The proposed method was tested on sounds of eight bird species of which five species have inharmonic sounds and three reference species have harmonic sounds. Inharmonic sounds are not well matched to the conventional spectral analysis methods, because the spectral domain does not include any visible trajectories that computer can track and identify. Thus, the wavelet analysis was selected due to its ability to preserve both frequency and temporal information, and its ability to analyze signals which contain discontinuities and sharp spikes. The shift invariant feature vectors calculated from the wavelet coefficients were used as inputs of two neural networks: the unsupervised self-organizing map (SOM) and the supervised multilayer perceptron (MLP). The results were encouraging: the SOM network recognized 78% and the MLP network 96% of the test sounds correctly.

A Comparative Study of Some Multivariable PI Controller Tuning Methods

Abstract In this paper four different multivariable PI controller tuning methods are compared. Multivariable PI controller is designed using all four methods for a two input two ouput state state space model. The resulted designs are then compared using frequency domain performance and robustness criteria and time domain simulations

Hammerstein model for speech coding

A nonlinear Hammerstein model is proposed for coding speech signals. Using Tsays nonlinearity test, we first show that the great majority of speech frames contain nonlinearities (over 80% in our test data) when using 20-millisecond speech frames. Frame length correlates with the level of nonlinearity: the longer the frames the higher the percentage of nonlinear frames. Motivated by this result, we present a nonlinear structure using a frame-by-frame adaptive identification of the Hammerstein model parameters for speech coding. Finally, the proposed structure is compared with the LPC coding scheme for three phonemes /a/, /s/, and /k/ by calculating the Akaike information criterion of the corresponding residual signals. The tests show clearly that the residual of the nonlinear model presented in this paper contains significantly less information compared to that of the LPC scheme. The presented method is a potential tool to shape the residual signal in an encode-efficient form in speech coding.

AUTOMATIC FEATURE EXTRACTION AND CLASSIFICATION OF CROSSBILL (LOXIA SPP.) FLIGHT CALLS

ABSTRACT In this paper a new method for the automatic classification of bird sounds is presented. Our method is based on acoustic parameters (features) taken from the first harmonic component computed from the sound spectrogram. The features are based on a line segment approximation of the first harmonic component. The final feature vectors, consisting of 16 real numbers, are then classified using a self-organizing map (SOM) neural network. Flight calls of four crossbill species (Loxia spp.) are used as a test example. In the first phase, an unsupervised network was trained and tested using common crossbill L. curvirostra flight calls recorded mainly in the Netherlands. The network was tested using two-barred L. leucoptera, Scottish L. scotica and parrot L. pytyopsittacus crossbill flight calls in the second phase. Finally, the results were validated applying the same network to flight calls of common crossbills and parrot crossbills recorded in Finland. The method automatically separated common crossbill flight calls from those of parrot crossbills. The classification accuracy of the Dutch recordings was 58% in the first phase and 54% in the second phase. The Finnish recordings were classified with 54% accuracy.

Experimental Comparison of Self-Tuning Controller Methods in Multivariable Case

Abstract This paper describes an application of multivariable self-tuning controllers to a computer-controlled, laboratory-scaled concentration-flow process. A minimum variance self-tuning controller, which is modified to take into account constant reference signals, and a newly developed selftuning controller, which is derived by penalizing also the control signal in the cost, are evaluated using both simulated and experimental results.

A distributed parameter system simulator

A simple and easy-to-use computer simulator (TDP) t for distrib uted parameter systems is presented. The simulator is based on commercially available TWODEPEP (a partial differential equa tion solver), to which measurement and control software mod ules have been added. The possibility to speed up computation with an attached processor is discussed. Finally, two simulation examples are presented.

IR-based method for copper electrolysis short circuit detection

In the copper electrorefining process short-circuits between the anodes and cathodes are harmful. They cause decreasing production rate and poor cathode copper quality. Short- circuits should be detected and eliminated as soon as possible. Manual inspection methods often take a lot of time and excessive walking on the electrodes can not be avoided. For these reasons there is a lot of interest to develop short-circuit detection and quality control. In this paper an IR based method for short circuit detection is presented. In the case of the short-circuited anode and cathode pair especially cathode bar becomes significantly warmer than bar in the normal condition. Using IR camera mounted on a moving crane these hot spots among the electrodes were easily detected. IR imaging was tested in the harsh conditions of the refinery hall with various crane speeds. Image processing is a tool to interpret the obtained IR images. In this paper an algorithm for searching the locations of the short-circuits in the electrolytic cell using imaging results as test material is proposed. The basic idea of the developed algorithm is first to search and calculate necessary edges and initial lines of the electrolytic cell. The second step is to determine the exact position of each cathode plate in the cell so that using thresholding the location of the short-circuited cathode can be determined. IR imaging combined with image processing has proven to be a superior method for predictive maintenance and process control compared to manual ones in the copper electrorefining process. It also makes it possible to collect valuable information for the quality control purposes.

IR-based system for short-circuit detection during copper electrorefining process

In this paper an infrared system for short-circuit detection in the copper electrorefining process is presented. The system consists of an IR-camera, a computer, radiomodems and software including the developed algorithm to process a thermal image. The basic component of the proposed system is an infrared camera mounted in an air-conditioned protection unit on a moving crane. The video output of the infrared camera is connected to the input of a framegrabber card in a computer. The framegrabber card with software captures a thermal image of the electrolytic cell, then processes it to locate the hot spots (short-circuits in a cell). The inspection results are transferred directly by radio link to the control room to be printed and further processed. The system presented in this paper is a prototype that has been tested for several months. The test results indicate that strong short-circuits can be detected with the proposed system as reliably as with a currently used manual method (gaussmeter). The advantages of the proposed system are easier and faster measurements (all cathodes in a cell can be measured remotely at the same time) and possibility to gather new process information.

Modelling and simulation of a copper electrolysis cell group

Abstract The energy consumption of the copper electrolysis process is relatively high. Electrical disturbances – like contact failures and short circuits – even increase the energy consumption and also reduce the quality of copper produced. To better understand and improve the process, a computationally feasible and reliable model of copper electrolysis cell group is of great importance. In this paper a multiphysical FEM model of copper electrolysis cell group is presented. A number of simplifications are proposed to make the model computationally feasible.

An Expert System for the Multivariable Controller Design

Abstract In this paper a software package for the design of centralized and decentralized multivariable controllers is represented. The software package consists of numerical calculation programs and an expert system. The paper first describes the different subtasks of the multivariable controller design. Next a short descriptions of the design and analysis methods included in the software package is given. The description of the implementation of the expert system finishes the paper.