Browsing by Author "Onaran, İbrahim"

Now showing 1 - 12 of 12

Open Access
Baseline regularized sparse spatial filters
(IEEE, 2013) Onaran, İbrahim; Ince, N.F.; Cetin, A. Enis
The common spatial pattern (CSP) method has large number of applications in brain machine interfaces (BMI) to extract features from the multichannel neural activity through a set of linear spatial projections. These spatial projections minimize the Rayleigh quotient (RQ) as the objective function, which is the variance ratio of the classes. The CSP method easily overfits the data when the number of training trials is not sufficiently large and it is sensitive to daily variation of multichannel electrode placement, which limits its applicability for everyday use in BMI systems. To overcome these problems, the amount of channels that is used in projections, should be limited to some adequate number. We introduce a spatially sparse projection (SSP) method that renders unconstrained minimization possible via a new objective function with an approximated ℓ1 penalty. We apply our new algorithm with a baseline regularization to the ECoG data involving finger movements to gain stability with respect to the number of sparse channels. © 2013 IEEE.
Open Access
Classification of agricultural kernels using impact acoustic signal processing
(2006) Onaran, İbrahim
The quality is the main factor that directly affects the price for many agricultural produces. The quality depends on different properties of the produce. Most important property is associated with health of consumers. Other properties mostly depend on the type of concerned vegetable. For instance, emptiness is important for hazelnuts while openness is crucial for the pistachio nuts. Therefore, the agricultural produces should be separated according to their quality to maintain the consumers health and increase the price of the produce in international trades. Current approaches are mostly based on invasive chemical analysis of some selected food items or sorting food items according to their color. Although chemical analysis gives the most accurate results, it is impossible to analyze large quantities of food items. The impact sound signal processing can be used to classify these produces according to their quality. These methods are inexpensive, noninvasive and most of all they can be applied in real-time to process large amount of food. Several signal processing methods for extracting impact sound features are proposed to classify the produces according to their quality. These methods are including time and frequency domain methods. Several time and frequency domain methods including Weibull parameters, maximum points and variances in time windows, DFT (Discrete Fourier Transform) coefficients around the maximum spectral points etc. are used to extract the features from the impact sound. In this study, we used hazelnut and wheat kernel impact sounds. The success rate over 90% is achieved for all types produces.
Open Access
Detection of empty hazelnuts from fully developed nuts by impact acoustics
(IEEE, 2005) Onaran, İbrahim; Dülek, Berkan; Pearson, T. C.; Yardımcı, Y.; Çetin, A. Enis
Shell-kernel weight ratio is the main determinate of quality and price of hazelnuts. Empty hazelnuts and nuts containing undeveloped kernels may also contain mycotoxin producing molds, which can cause cancer. A prototype system was set up to detect empty hazelnuts by dropping them onto a steel plate and processing the acoustic signal generated when kernels impact the plate. The acoustic signal was processed by five different methods: 1) modeling of the signal in the time domain, 2) computing time domain signal variances in short time windows, 3) analysis of the frequency spectra magnitudes, 4) maximum amplitude values in short time windows, and 5) line spectral frequencies (LSFs). Support Vector Machines (SVMs) were used to select a subset of features and perform classification. 98% of fully developed kernels and 97% of empty kernels were correctly classified.
Open Access
Extraction of sparse spatial filters using Oscillating Search
(IEEE, 2012) Onaran, İbrahim; İnce, N. Fırat; Abosch, A.; Çetin, A. Enis
Common Spatial Pattern algorithm (CSP) is widely used in Brain Machine Interface (BMI) technology to extract features from dense electrode recordings by using their weighted linear combination. However, the CSP algorithm, is sensitive to variations in channel placement and can easily overfit to the data when the number of training trials is insufficient. Construction of sparse spatial projections where a small subset of channels is used in feature extraction, can increase the stability and generalization capability of the CSP method. The existing 0 norm based sub-optimal greedy channel reduction methods are either too complex such as Backward Elimination (BE) which provided best classification accuracies or have lower accuracy rates such as Recursive Weight Elimination (RWE) and Forward Selection (FS) with reduced complexity. In this paper, we apply the Oscillating Search (OS) method which fuses all these greedy search techniques to sparsify the CSP filters. We applied this new technique on EEG dataset IVa of BCI competition III. Our results indicate that the OS method provides the lowest classification error rates with low cardinality levels where the complexity of the OS is around 20 times lower than the BE. © 2012 IEEE.
Open Access
Falling person detection using multi-sensor signal processing
(IEEE, 2007) Töreyin, Behçet Uğur; Soyer, Emin Birey; Onaran, İbrahim; Çetin, A. Enis
Falls are one of the most important problems for frail and elderly people living independently. Early detection of falls is vital to provide a safe and active lifestyle for elderly. In this paper, signals produced by sound and passive infrared (PIR) sensors are simultaneously analyzed to detect suddenly falling elderly people. A typical room in a supportive home can be equipped with sound and PIR sensors. Hidden Markov models are trained for regular and unusual activities of an elderly person and a pet for each sensor signal. Decisions of HMMs can be fused together to reach a final decision.
Open Access
Human face detection in video using edge projections
(SPIE, 2006) Türkan, Mehmet; Dülek, Berkan; Onaran, İbrahim; Çetin, A. Enis
In this paper, a human face detection method in images and video is presented. After determining possible face candidate regions using color information, each region is filtered by a high-pass filter of a wavelet transform. In this way, edges of the region are highlighted, and a caricature-like representation of candidate regions is obtained. Horizontal, vertical and filter-like projections of the region are used as feature signals in dynamic programming (DP) and support vector machine (SVM) based classifiers. It turns out that the support vector machine based classifier provides better detection rates compared to dynamic programming in our simulation studies.
Open Access
A hybrid SVM/HMM based system for the state detection of individual finger movements from multichannel ECoG signals
(IEEE, 2011) Onaran, İbrahim; Ince, N.F.; Çetin, A. Enis; Abosch, A.
A hybrid state detection algorithm is presented for the estimation of baseline and movement states which can be used to trigger a free paced neuroprostethic. The hybrid model was constructed by fusing a multiclass Support Vector Machine (SVM) with a Hidden Markov Model (HMM), where the internal hidden state observation probabilities were represented by the discriminative output of the SVM. The proposed method was applied to the multichannel Electrocorticogram (ECoG) recordings of BCI competition IV to identify the baseline and movement states while subjects were executing individual finger movements. The results are compared to regular Gaussian Mixture Model (GMM)-based HMM with the same number of states as SVM-based HMM structure. Our results indicate that the proposed hybrid state estimation method out-performs the standard HMM-based solution in all subjects studied with higher latency. The average latency of the hybrid decoder was approximately 290ms. © 2011 IEEE.
Open Access
Projections onto convex sets (POCS) based optimization by lifting
(IEEE, 2013) Çetin, A. Enis; Bozkurt, Alican; Günay, Osman; Habiboglu, Yusuf Hakan; Köse, K.; Onaran, İbrahim; Tofighi, Mohammad; Sevimli, Rasim Akın
A new optimization technique based on the projections onto convex space (POCS) framework for solving convex and some non-convex optimization problems are presented. The dimension of the minimization problem is lifted by one and sets corresponding to the cost function are defined. If the cost function is a convex function in RN the corresponding set which is the epigraph of the cost function is also a convex set in RN+1. The iterative optimization approach starts with an arbitrary initial estimate in R N+1 and an orthogonal projection is performed onto one of the sets in a sequential manner at each step of the optimization problem. The method provides globally optimal solutions in total-variation, filtered variation, l1, and entropic cost functions. It is also experimentally observed that cost functions based on lp; p < 1 may be handled by using the supporting hyperplane concept. The new POCS based method can be used in image deblurring, restoration and compressive sensing problems. © 2013 IEEE.
Open Access
A signal representation approach for discrimination between full and empty hazelnuts
(IEEE, 2007) Onaran, İbrahim; İnce, N. F.; Tevfik, A. H.; Çetin, A. Enis
We apply a sparse signal representation approach to impact acoustic signals to discriminate between empty and full hazelnuts. The impact acoustic signals are recorded by dropping the hazelnut shells on a metal plate. The impact signal is then approximated within a given error limit by choosing codevectors from a special dictionary. This dictionary was generated from sub-dictionaries that are individually generated for the impact signals corresponding to empty and full hazelnut. The number of codevectors selected from each sub-dictionary and the approximation error within initial codevectors are used as classification features and fed to a Linear Discriminant Analysis (LDA). We also compare this algorithm with a baseline approach. This baseline approach uses features which describe the time and frequency characteristics of the given signal that were previously used for empty and full hazelnut separation. Classification accuracies of 98.3% and 96.8% were achieved by the proposed approach and base algorithm respectively. The results we obtained show that sparse signal representation strategy can be used as an alternative classification method for undeveloped hazelnut separation with higher accuracies.
Open Access
Spatial decoding of oscillatory neural activity for brain computer interfacing
(2013) Onaran, İbrahim
Neuroprosthetics (NP) aim to restore communication between people with debilitating motor impairments and their environments. To provide such a communication channel, signal processing techniques converting neurophysiological signals into neuroprosthetic commands are required. In this thesis, we develop robust systems that use the electrocorticogram (ECoG) signals of individuated finger movements and electroencephalogram (EEG) signals of hand and foot movement imageries. We first develop a hybrid state detection algorithm for the estimation of baseline (resting) and movement states of the finger movements which can be used to trigger a free paced neuroprosthetic using the ECoG signals. The hybrid model is constructed by fusing a multiclass support vector machine (SVM) with a hidden Markov model (HMM), in which the internal hidden state observation probabilities are represented by the discriminative output of the SVM. We observe that the SVM based movement decoder improves accuracy for both large and small numbers of training dataset. Next, we tackle the problem of classifying multichannel ECoG related to individual finger movements for a brain machine interface (BMI). For this particular problem we use common spatial pattern (CSP) method which is a popular method in BMI applications, to extract features from the multichannel neural activity through a set of spatial projections. Since we try to classify more than two classes, our algorithm extends the binary CSP algorithm to multiclass problem by constructing a redundant set of spatial projections that are tuned for paired and group-wise discrimination of finger movements. The groupings are constructed by merging the data of adjacent fingers and contrasting them to the rest, such as the first two fingers (thumb and index) vs. the others (middle, ring and little). In the remaining parts of the thesis, we investigate the problems of CSP method and propose techniques to overcome these problems. The CSP method generally overfits the data when the number of training trials is not sufficiently large and it is sensitive to daily variation of multichannel electrode placement, which limits its applicability for everyday use in BMI systems. The amount of channels used in projections should be limited to some adequate number to overcome these problems. We introduce a spatially sparse projection (SSP) method, taking advantage of the unconstrained minimization of a new objective function with approximated `1 penalty. Furthermore, we investigate the greedy `0 norm based channel selection algorithms and propose oscillating search (OS) method to reduce the number of channels. OS is a greedy search technique that uses backward elimination (BE), forward selection (FS) and recursive weight elimination (RWE) techniques to improve the classification accuracy and computational complexity of the algorithm in case of small amount of training data. Finally, we fuse the discriminative and the representative characteristic of the data using a baseline regularization to improve the classification accuracy of the spatial projection methods.
Open Access
Subset selection with structured dictionaries in classification
(EURASIP, 2007) İnce, N. F.; Göksu, F.; Tewfik, A. H.; Onaran, İbrahim; Çetin, A. Enis
This paper describes a new approach for the selection of discriminant time-frequency features for classification. Unlike previous approaches that use the individual discrimination power of expansion coefficients, the proposed approach selects a subset of features by implementing a classifier directed pruning of an initial redundant set of candidate features. The candidate features are calculated from a structured redundant time-frequency analysis of the signal, such as an undecimated wavelet transform. We show that the proposed approach has a performance that is as good as or better than traditional classification approaches while using a much smaller number of features. In particular, we provide experimental results to demonstrate the superior performance of the algorithm in the area of impact acoustic classification for food kernel inspection. The proposed algorithm achieved 91.8% and 98.5% classification accuracies in separating open shell from closed shell pistachio nuts and discriminating between empty and full hazelnuts respectively. Traditional methods used in this area resulted in 82% and 97% classification accuracies respectively.
Open Access
Wheat and hazelnut inspection with impact acoustics time-frequency patterns
(ASABE, 2007-06) İnce, N. F.; Onaran, İbrahim; Tewfik, A. H.; Kalkan, H.; Pearson, T.; Çetin, A. Enis; Yardimci, Y.
Kernel damage caused by insects and fungi is one of the most common reason for poor flour quality. Cracked hazelnut shells are prone to infection by cancer producing mold. We propose a new adaptive time-frequency classification procedure for detecting cracked hazelnut shells and damaged wheat kernels using impact acoustic emissions recorded by dropping wheat kernels or hazelnut shells on a steel plate. The proposed algorithm is based on a flexible local discriminant bases (F-LDB) procedure. The F-LDB method combines local cosine packet analysis and a frequency axis clustering approach which supports individual time and frequency band adaptation. Discriminant features are extracted from the adaptively segmented acoustic signal, sorted according to a Fisher class separability criterion, post processed by principal component analysis and fed to linear discriminant. We describe experimental results that establish the superior performance of the proposed approach when compared with prior techniques reported in the literature or used in the field. Our approach achieved classification accuracy in paired separation of undamaged wheat kernels from IDK, Pupae and Scab damaged kernels with 96%, 82% and 94%. For hazelnuts the accuracy was 97.1%.