Mahdi Esfahanian

Using local binary patterns as features for classification of dolphin calls

An image processing technique called Local Binary Patterns (LBP) has been explored for its ability to generate feature vectors for dolphin vocalization classification. The LBP operator eliminates the need for contour tracing, denoising, and other prior processing. In an experimental study of classifying dolphin whistle types, the performance of the LBP operation was compared with that of the popular contour-based Time-Frequency Parameters (TFP) approach. The preliminary experimental results illustrate that the LBP method produces more consistent classifier accuracy of dolphin whistle calls even when the contour shapes are complex and populated with impulsive clicks and anthropogenic harmonics.

Optimal operation of a multi-source microgrid to achieve cost and emission targets

This paper presents a new approach for the optimization of photovoltaic-wind hybrid systems with battery storage to meet the load requirements. In this study, a 24-hour ahead energy management for a microgrid is utilized. The objectives aim at raising efficiency of energy utilization, minimizing operational cost and reducing environmental effects of energy usage. Also a demand response (DR) program is considered as one of the cost-effective energy alternatives. Based on the prediction of available energy from the PV and wind generators, battery storage availability, load prediction, micro gas turbine (μGT) and main grid emission characteristics, a central energy management system calculates a day-ahead plan of power references for the gas turbine, power purchased from the grid, power sold to the grid, status of the battery and controllable loads. A multi-objective optimization is implemented in order to minimize the energy cost and greenhouse gas emissions.

Comparison of two methods for detection of North Atlantic Right Whale upcalls

In this paper, a study is carried out for detecting North Atlantic Right Whale upcalls with measurements from passive acoustic monitoring devices. Preprocessed spectrograms of upcalls are subjected to two different tasks, one of which is based on extraction of time-frequency features from upcall contours, and the other that employs a Local Binary Pattern operator to extract salient texture features of the upcalls. Then several classifiers are used to evaluate the effectiveness of both the contour-based and texture-based features for upcall detection. Detection results reveal that popular classifiers such as Linear Discriminant Analysis, Support Vector Machine, and TreeBagger can achieve high detection rates. Furthermore, using LBP features for call detection shows improved accuracy of about 3% to 4% over time-frequency features when an identical classifier is used.

A new approach for classification of dolphin whistles

This paper presents a novel approach to categorize dolphin whistles into various types. Most accurate methods to identify dolphin whistles are tedious and not robust, especially in the presence of ocean noise. One of the biggest challenges of dolphin whistle extraction is the coexistence of short-time duration wide-band echo clicks with the whistles. In this research a subspace of select orientation parameters of the 2-D Gabor wavelet frames is utilized to enhance or suppress signals by their orientation. The result is a Gabor image that contains a noise free grayscale representation of the fundamental dolphin whistle which is resampled and fed into the Sparse Representation Classifier. The classifier uses the l1-norm to select a match. Experimental studies conducted demonstrate: (a) a robust technique based on the Gabor wavelet filters in extracting reliable call patterns, and (b) the superior performance of Sparse Representation Classifier for identifying dolphin whistles by their call type.

Sparse representation for classification of dolphin whistles by type

A compressive-sensing approach called Sparse Representation Classifier (SRC) is applied to the classification of bottlenose dolphin whistles by type. The SRC algorithm constructs a dictionary of whistles from the collection of training whistles. In the classification phase, an unknown whistle is represented sparsely by a linear combination of the training whistles and then the call class can be determined with an l1-norm optimization procedure. Experimental studies conducted in this research reveal the advantages and limitations of the proposed method against some existing techniques such as K-Nearest Neighbors and Support Vector Machines in distinguishing different vocalizations.

Sparse representation classification of dolphin whistles using local binary patterns

A sparse representation classifier (SRC) has been adapted and applied to spectrograms to identify bottlenose dolphin whistles by their types. The classifier that relies on near completeness of the training features renders their choice no longer crucial as long as criteria are met to assure signal sparsity. Signal sparsity is ensured via the employment of a robust, effective, and computationally simple local binary patterns (LBP) operator that eliminates the need for costly denoising and contour tracking operations. The performance of the proposed method is compared to classifier-feature combinations of the K-nearest neighbor (KNN) and support vector machine (SVM) classifiers, and feature vectors of time-frequency contour parameters, Fourier descriptors, and raw data. The experimental results demonstrate superior accuracy and robustness of the proposed method to classify dolphin whistles into distinct call types. The method can be generalized to all narrowband signals with time varying spectra.

A new method for detection of North Atlantic right whale up-calls

A study of detecting North Atlantic Right Whale (NARW) up-calls has been conducted with measurements from passive acoustic monitoring devices. Denoising and normalization algorithms are applied to remove local variance and narrowband noise in order to isolate the NARW up-calls in spectrograms. The resulting spectrograms, after binarization, are treated with a region detection procedure called the Moor-Neighbor algorithm to find continuous objects that are candidates of up-call contours. After selected properties of each detected object are computed, they are compared with a pair of low and high empirical thresholds to estimate the probability of the detected object being an up-call; therefore, those objects that are determined with certainty to be non up-calls are discarded. The final stage in the proposed call detection method is to separate true up-calls from the rest of potential up-calls with classifiers such as linear discriminate analysis (LDA), Naive Bayes, and decision tree. Experimental results u...