SCHRODINGER OPERATOR

CROSS-REFERENCE TO RELATED APPLICATIONS

[0001] This application claims priority to U.S. Provisional Patent Application No. 62/807,515, filed on February 19, 2019, entitled“SIGNAL CHARACTERIZATION USING SQUARED EIGENFUNCTIONS OF THE SCHRODINGER OPERATOR FOR FEATURE GENERATION,” and U.S. Provisional Patent Application No.

62/867,370, filed on June 27, 2019, entitled“FEATURE GENERATION BASED ON EIGENFUNCTIONS OF THE SCHRODINGER OPERATOR,” the disclosures of which are incorporated herein by reference in their entirety.

BACKGROUND

TECHNICAL FIELD

[0002] Embodiments of the subject matter disclosed herein generally relate to generating a feature that characterizes input data, and more specifically, to extracting discriminative properties of signals that make up the input data and to use these properties to classify the input data.

DISCUSSION OF THE BACKGROUND

[0003] With the advance of electronic devices in each science field, the amount of signals generated and collected for analysis has increased tremendously. Generally, those that analyze the collected signals, in any science field, look for a peak in the signal, where the peak usually is significative for characterizing the phenomenon that is under study. Thus, a common task for these projects is detecting the maximum or minimum of a given collected signal. While this task is conventional for a clean signal, if the signal is very noisy or if the recorded data includes many signals, the task becomes more complicated.

[0004] In a concrete example, the presence of peaks in biomedical signals often reflects different chemical and/or biological activities in the human body. An example of such signal is the Magnetoencephalography (MEG) signal. The MEG is a functional neuroimaging modality that measures the magnetic activity of the brain. It uses an array of highly sensitive sensors or magnetometers, called superconducting quantum interference devices (SQUIDs). The MEG signal is less distorted by the intervening tissues between the neural source and the SQUIDs comparing to electroencephalogram (EEG) signal. The MEG signals are very useful for the detection and the treatment of various diseases in the brain as the MEG signals help in localizing the region of the brain which produces the abnormal electrical activities which causes the neurological disorder.

[0005] Due to the recent introduction of the MEG method in clinical practice, the spike detection using MEG signals is an emerging research field. Different methods were proposed for spikes detection using EEG/MEG signals. However, few methods exists for spike detection using the MEG signal [1 ], [2], [3]. For example, in [1 ], an independent component analysis (ICA) method has been proposed with a multi-channel MEG spikes localization method, which decomposes spike-like and background components into separate spatial topographies and associated time series. The detection is performed using a thresholding technique. Another method is the common spatial patterns (CSP) and linear discriminant analysis (LDA) method (CSP-LDA) [2] The latter is similar to the method in [1] except for the classification stage, where the LDA classifier is used for the detection.

[0006] Moreover, an Amplitude Thresholding and Dynamic Time Warping (AT- DTW) approach has been proposed in [3]. This method uses amplitude thresholding to localize abnormal activities, to specify the region in the brain where the

abnormalities happen, and to select the affected channels. For the spike detection, the method employs dynamic time warping. The previously cited works reported a maximum sensitivity and specificity of 92.4% and 95.8%, respectively. Most of these methods study the MEG signal in its time domain, and some of them do not take advantage of recent advances in machine learning classifiers due to the complexity of the MEG signal.

[0007] Therefore, a pertinent characterization of MEG signals, which allows the definition of discriminative features, is necessary for an effective use of classifiers for spike detection. It is also necessary that the introduced feature vector is of reduced dimension to improve the effectiveness of the classification

[0008] However, the existing methods are still not optimal in terms of feature generation and size of the feature. Thus, there is a need for a new method for feature generation that can overcome these limitations.

SUMMARY

[0009] According to an embodiment, there is a method for generating a feature associated with input data. The method includes receiving the input data; projecting the input data with a set of square functions of the Schrodinger

operator; selecting the feature to be a number of the negative eigenvalues l _nh of the Schrodinger operator; and classifying the input data based on the feature.

[0010] According to another embodiment, there is a computing device for generating a feature associated with input data. The computing device includes an interface for receiving the input data; and a processor connected to the interface. The processor is configured to project the input data with a set of square functions of the Schrodinger operator; select the feature to be a number of the negative eigenvalues l _nh of the Schrodinger operator; and classify the input data based on the feature.

[0011 ] According to still another embodiment, there is a non-transitory computer readable medium including computer executable instructions, wherein the instructions, when executed by a processor, implement instructions for generating a feature as in the method discussed above.

BRIEF DESCRIPTION OF THE DRAWINGS

[0012] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate one or more embodiments and, together with the description, explain these embodiments. In the drawings:

[0013] Figure 1 is a schematic illustration of a method that applies the Schrodinger operator for reconstructing a signal;

[0014] Figure 2 is a flowchart of a method for generating a feature associated with a signal, by using the Schrodinger operator;

[0015] Figure 3 schematically illustrates as the input data is analyzed using the Schrodinger operator for generating a feature and then classifying the input data based on the feature;

[0016] Figure 4 illustrates MEG signals that are noisy and have multiple peaks;

[0017] Figure 5 illustrates an algorithm that uses the Schrodinger operator for reconstructing a signal;

[0018] Figure 6 illustrates actual results obtained with the novel method discussed herein when applied to a number of patients;

[0019] Figure 7 illustrates the results obtained with the novel method versus the existing methods;

[0020] Figure 8 illustrates the spectrum of the Schrodinger operator for positive and negative eigenvalues; [0021] Figure 9 is a flowchart of a method for generating a feature based on a signal; and

[0022] Figure 10 is a schematic diagram of a computing device that implements the novel methods discussed herein.

DETAILED DESCRIPTION

[0023] The following description of the embodiments refers to the

accompanying drawings. The same reference numbers in different drawings identify the same or similar elements. The following detailed description does not limit the invention. Instead, the scope of the invention is defined by the appended claims.

For simplicity, the following embodiments are discussed with regard to MEG signals. However, the methods and systems discussed herein are equally applicable to any signal that exhibits peaks. For example, the methods discussed herein can be applied to water peak estimation, water suppression signal in magnetic resonance spectroscopy (MRS) signals, MRS signal denoising, pulse-shaped signal

decomposition and denoising, etc. The novel methods can be integrated in any processing unit to process biomedical signals such as MRS signals,

electroencephalogram (EEG) signals, or any other pulse-shaped signal.

[0024] Reference throughout the specification to“one embodiment” or“an embodiment” means that a particular feature, structure or characteristic described in connection with an embodiment is included in at least one embodiment of the subject matter disclosed. Thus, the appearance of the phrases“in one embodiment” or“in an embodiment” in various places throughout the specification is not necessarily referring to the same embodiment. Further, the particular features, structures or characteristics may be combined in any suitable manner in one or more

embodiments. [0025] According to an embodiment, there is a method that introduces a new characterization of signals. The signals may be spectrum data, biomedical signals or any other type of signal. This new characterization generates new features that can be used for the classification of the signals. The proposed feature generation technique is based on the semi-classical analysis (SCSA) method, which includes the projection of the input signal into a set of functions given by the squared eigenfunctions of the Schrodinger operator associated to the negative eigenvalues, and whose potential is given by the input signal. The computed eigenvalues, eigenfunctions and their different combinations introduce new types of features, which can be used all together or in different combination forms to provide a suitable and accurate discrimination of the data signals.

[0026] More specifically, as illustrated in Figure 1 , input data 1 10 is collected in the time domain. The input data 1 10 includes at least one noisy signal 1 12. The input data is used with the Schrodinger operator 1 14 to generate plural

eigenfunctions 1 16, corresponding to plural eigenvalues 1 18. Then, a feature is generated and this feature is used for selecting significative eigenfunctions. A signal 120 is constructed based on the selected eigenfunctions and the corresponding eigenvalues. The signal 120 has the noise removed and its peak 122 can be easily identified. Having identified the peak of the signal, the classification of the signal can now be performed.

[0027] The process illustrated in Figure 1 is now discussed in more detail. Figure 2 is a flowchart of a method for generating a feature that characterizes a set of signals (called herein the input data) and uses the generated feature to classify the input data. For a better understanding of the method, actual MEG input data 300 (see Figure 3) was received in step 200. For this embodiment, the MEG input data has been collected from nine healthy subjects (see data 302) and nine epileptic subjects (see data 304). A total of 18 MEG data segments, each of 15 minutes duration and 26 channels was recorded with a sampling frequency of 1 kHz. The data was then filtered by Spatiotemporal signal space separation method and off-line band-pass filtered for 1 - 50 Hz. The input data was analyzed by neurologists, which marked the MEG spike locations. The total number of spikes in this input data was found by the neurologists to be about 166.

[0028] A signal 303 from the input data 302 (i.e., an MEG signal from a healthy subject) and a signal 305 from the input data 304 (i.e., an MEG signal from an epileptic subject) are shown in Figure 4. The signals are illustrated in this figure as a normalized intensity versus a recording time. The insert of Figure 4 shows approximately a second worth of the two signals 303 and 305. It is noted that signal 305 exhibits plural spikes 307.

[0029] In step 202, the input signal 300 is split into frames, for example, using sliding frames. In one application, a sliding frame 306 includes 100 sample points and the sliding frame slides with a step of 2 samples, i.e., the frame 306 is moved 2 samples and another 100 samples points are considered for a second sliding frame, and so on. The inset of Figure 4 corresponds to a single sliding frame. Other numbers may be used for the size of the sliding frame and for the step of moving the frame. [0030] The signals from each frame 306 are then concatenated in step 204 to build a classification dataset 310. Note that for this specific embodiment, the MEG signals include 26 channels, i.e., 26 different sensors have been used to collect each MEG signal. For other types of signals, the number of sensors may be fewer or more. Regardless of the number of sensors, the signals in each channel are concatenated for each given frame, to generate a single signal. Two different classes are defined in this embodiment, the negative samples 312 and the positive samples 314. The negative samples 312 include the frames from the healthy subjects 302 and the positive samples 314 include the frames from the epileptic subjects 304. Each class includes the same number of frames.

[0031] In step 206, one or more features is generated for these signals. For this step, the semi-classical signal analysis (SCSA) 320 is applied. The SCSA analysis is now discussed in more detail. The SCSA uses signal-dependent functions given by the squared eigenfunctions of the Schrodinger operator to decompose the signal (see, for example, [4] and [5]). The potential V of the

Schrodinger operator H(y), in this case, is given by the positive function y(t) representing the signal. The Schrodinger operator is written as follows:

where H is the Schrodinger operator, V is the potential, h is a constant, t is the time, and d indicates a derivative. For the SCSA analysis, the potential V is selected to be the positive function y(t) representing the signal, which means that equation (1 ) becomes:

The Schrodinger equation for the SCSA analysis is given by:

where \ (t) is the eigenfunction of the Schrodinger operator, and l is the eigenvalue of the Schrodinger operator.

[0032] Based on the SCSA analysis, a real positive input signal y(t) can be approximated by plural signals yh(t), which are given by:

where n varies from 1 to Nh, and n represents the negative eigenvalues _nh of the Schrodinger operator H(y). In addition, l _1h < ··· < l _nh < 0. The accuracy of the reconstructed signal y _h (t) depends on the value of h and also on how many negative eigenvalues l _nh are used. Equation (4) provides an exact reconstruction of the original signal y(t) when h converges to zero. When the value of h decreases, the number of eigenvalues l _nh increases and the reconstruction improves.

However, as the h converges to zero, the calculation amount increases and may become unpractical for a practical application for which the computer power is limited. Thus, for a real situation, a balance between the value of h and the amount of computational power necessary to reconstruct the signal needs to be found.

Figure 5 schematically illustrates the SCSA reconstruction algorithm.

[0033] The SCSA analysis is used in step 206 to generate a feature associated with the signals 302 and 304. The SCSA analysis has been used for reconstruction and de-noising of some biomedical signals such as the Magnetic Resonance Spectroscopy (MRS) spectra and the Arterial Blood Pressure (ABP) [6], [7] Due to the localized and shape-dependent structure of the squared

eigenfunctions of the Schrodinger operator, the SCSA analysis introduces an

effective analysis tool for pulse shaped signals (signals with peaks).

[0034] In this embodiment, the feature 330 is related to the number of negative eigenvalues that are used to reconstruct the signal for each frame 306. For this purpose, the parameter is introduced as being the lower feature size and it is

defined as:

where N _hi is the number of negative eigenvalues of the i ^th frame for a given value h, and M is number of frames. This means that for each frame i, a corresponding number N _hi of negative eigenvalues l _nh is selected in step 206 to reconstruct the signal for that frame, and then, based on equation (5), the minimum number of negative eigenvalues is selected for all the frames. Thus, for each frame of the M frames used in these calculations, only negative eigenvalues are used for reconstructing the signals, and the negative eigenvalues is the generated feature 330.

[0035] One way to select the number N _hi of negative eigenvalues l _nh that is used to reconstruct the signal for each frame, is to define a set threshold value.

Then, for a given instant, reconstruct the signal with a given number of negative eigenvalues l _nh and calculate a different between the original signal and the reconstructed signal at the given instant. If the difference is smaller than the set threshold value, the given number of negative eigenvalues corresponds to N _hi . If not, increase the given number of negative eigenvalues and evaluate again the difference between the original signal and the reconstructed signal. Repeat this process until the difference is smaller than the set threshold value and that is the value of the given number of negative eigenvalues. This is only one way to determine the N _hi for each frame. Other criteria may be used for selecting the negative eigenvalues l _nh that reproduce the original signal for each frame.

[0036] The feature 330 is fed in step 208 to a classifier 340 for classifying the reconstructed signals. The classifier 340 may be, for example, a Support Vector Machine (SVM) predictive model. The SVM model may be developed in 5-fold cross- validation (CV) process with the following subjects: 1734 spiky frames and 1734 healthy frames from different MEG test sessions of the eight healthy and eight epileptic patients.

[0037] The performance of the classifier 340 has been measured using the average accuracy, the sensitivity, the specificity and other metrics defined as follows:

where TP _n , FP _n , TN _n , and FN _n are the True Positive, False Positive, True Negative, and False Negative values, respectively, for the n ^th fold. Note that these values are calculated by comparing the results of the classifier 340 made in step 208, and the actual peaks determined by the expert neurologists based on the input data 300.

[0038] Table 1 (see Figure 6) shows that with the same average number of negative eigenvalues lower values of h improves the classification performance.

This is an expected result because lower values of h improve the accuracy of the reconstruction as shown in [4] However, the value of h cannot be very small due to the limited number of points, which limits the number of negative eigenvalues that can be numerically computed.

[0039] The results of the method illustrated in Figure 2 were compared to the existing spikes detection approaches using MEG signal reported in [3]. In this regard, Table II (see Figure 7) shows that the SCSA-based features improve the detection sensitivity and achieves higher specificity compared to two of the existing methods. Moreover, the method of Figure 2 reduces the generated feature’s size to one. This is shown in Figure 8, which shows that the spectrum (represented on the Y axis of the figure) of the Schrodinger operator separates the positive class 314 from the negative class 312 as only the first negative eigenvalues are used as the generated feature, which are the most dominant and representative eigenvalues. Note that Figure 8 plots the spectrum of the Schrodinger operator versus the number of negative eigenvalues Nh, and for this specific example, Thus, this algorithm reduces the size of the feature to one or a similar small number, which becomes very efficient from a computational point of view

[0040] A method for generating a feature having a small size is now discussed with regard to Figure 9. The includes a step 900 of receiving the input data, a step 902 of projecting the input data with a set of square functions of the Schrodinger

operator, a step 904 of selecting the feature to be a number of the negative eigenvalues l _nh of the Schrodinger operator, and a step 906 of classifying the input data based on the feature. The method may also include a step of splitting the input data into frames, and/or concatenating plural signals from a frame to form a single signal, and/or using the single signal as a potential for the Schrodinger operator, and/or reconstructing the single signal using the set of square functions of the

Schrodinger operator and the number of the negative eigenvalues of the

Schrodinger operator, and/or identifying a peak of the reconstructed single signal. In one application, the step of classifying includes classifying the input data based on the peak.

[0041] The methods discussed herein advantageously present a new feature generation and dimensionality reduction algorithm. While the algorithm has been presented as a specific application for epileptic spikes detection in MEG signals, the same algorithm may be used for any signal that requires spike identification. The algorithm projects an input signal into the discrete spectrum of the Schrodinger operator and then selects a number of eigenvalues to be used for regenerating the signal from the eigenfunctions of the Schrodinger operator. As illustrated in Figures 6 and 7, the novel algorithm obtains the highest sensitivity up to 92.52% with a specificity of 89.10% for a given dataset.

[0042] The above-discussed procedures and methods may be implemented in a computing device as illustrated in Figure 10. Hardware, firmware, software or a combination thereof may be used to perform the various steps and operations described herein.

[0043] Computing device 1000 suitable for performing the activities described in the embodiments discussed above may include a server 1001. Such a server 1001 may include a central processor (CPU) 1002 coupled to a random access memory (RAM) 1004 and to a read-only memory (ROM) 1006. ROM 1006 may also be other types of storage media to store programs, such as programmable ROM (PROM), erasable PROM (EPROM), etc. Processor 1002 may communicate with other internal and external components through input/output (I/O) circuitry 1008 and bussing 1010 to provide control signals and the like. Processor 1002 carries out a variety of functions as are known in the art, as dictated by software and/or firmware instructions.

[0044] Server 1001 may also include one or more data storage devices, including hard drives 1012, CD-ROM drives 1014 and other hardware capable of reading and/or storing information, such as DVD, etc. In one embodiment, software for carrying out the above-discussed steps may be stored and distributed on a CD- ROM or DVD 1016, a USB storage device 1018 or other form of media capable of portably storing information. These storage media may be inserted into, and read by, devices such as CD-ROM drive 1014, disk drive 1012, etc. Server 1001 may be coupled to a display 1020, which may be any type of known display or presentation screen, such as LCD, plasma display, cathode ray tube (CRT), etc. A user input interface 1022 is provided, including one or more user interface mechanisms such as a mouse, keyboard, microphone, touchpad, touch screen, voice-recognition system, etc.

[0045] Server 1001 may be coupled to other devices, such as medical instruments, detectors, sensors, etc. The server may be part of a larger network configuration as in a global area network (GAN) such as the Internet 1028, which allows ultimate connection to various landline and/or mobile computing devices.

[0046] The disclosed embodiments provide a method and system that is capable to detect and classify peaks associated with one or more signals. The embodiments are intended to cover alternatives, modifications and equivalents, which are included in the spirit and scope of the invention as defined by the appended claims. Further, in the detailed description of the embodiments, numerous specific details are set forth in order to provide a comprehensive understanding of the claimed invention. However, one skilled in the art would understand that various embodiments may be practiced without such specific details.

[0047] Although the features and elements of the present embodiments are described in the embodiments in particular combinations, each feature or element can be used alone without the other features and elements of the embodiments or in various combinations with or without other features and elements disclosed herein.

[0048] This written description uses examples of the subject matter disclosed to enable any person skilled in the art to practice the same, including making and using any devices or systems and performing any incorporated methods. The patentable scope of the subject matter is defined by the claims, and may include other examples that occur to those skilled in the art. Such other examples are intended to be within the scope of the claims.

REFERENCES

[1 ] A. Ossadtchi, S. Baillet, J. C. Mosher, D. Thyerlei, W. Sutherling, and R. M.

Leahy,“Automated interictal spike detection and source localization in

magnetoencephalography using independent components analysis and spatio- temporal clustering,” Clinical Neurophysiology, vol. 1 15, no. 3, pp. 508-522, 2004.

[2] M. I. Khalid, T. Alotaiby, S. A. Aldosari, S. A. Alshebeili, M. H. Al-Hameed, F. S.

Y. Almohammed, and T. S. Alotaibi,“Epileptic MEG Spikes Detection Using

Common Spatial Patterns and Linear Discriminant Analysis,” IEEE Access, vol. 4, pp. 4629—4634, 2016.

[3] M. I. Khalid, T. N. Alotaiby, S. A. Aldosari, S. A. Alshebeili, M. H. Alhameed, and V. Poghosyan,“Epileptic MEG Spikes Detection Using Amplitude Thresholding and Dynamic Time Warping,” IEEE Access, vol. 5, pp. 1 1 658-1 1 667, 2017.

[4] T.-M. Laleg-Kirati, E. Crepeau, and M. Sorine,“Semi-classical signal analysis,” Mathematics of Control, Signals, and Systems, vol. 25, no. 1 , pp. 37-61 , 2013.

[5] B. Helffer and T.-M. Laleg-Kirati, On semi-classical questions related to signal analysis,” Asymptotic Analysis.

[6] T.-M. Laleg, E. Crepeau, Y. Papelier, and M. Sorine,“Arterial blood pressure analysis based on scattering transform i,” in Engineering in Medicine and Biology Society, 2007. EMBS 2007. 29th Annual International Conference of the IEEE. IEEE, 2007, pp. 5326-5329.

[7] T. Laleg-Kirati, J. Zhang, E. Achten, and H. Serrai,“Spectral data de-noising using semi-classical signal analysis: application to localized MRS,” NMR in

Biomedicine, vol. 29, no. 10, pp. 1477-1485, 2016.