A system for the automated detection of alcoholism based on EEG signals using the discrete cosine harmonic wavelet packet transform (DCHWPT)

Abstract

A system for detecting alcoholism using EEG signal processing, comprising: an EEG signal acquisition module configured to acquire digitized EEG signals from a plurality of electrodes placed on the scalp of a subject according to a 10-20 electrode placement system; a signal preprocessing module operationally connected to the EEG signal acquisition module and configured to preprocess the acquired digitized EEG signals, the preprocessed EEG signals being stored in a database containing signals from both alcohol-dependent and control subjects;a computing unit comprising at least one processor with dedicated memory, wherein the processor is configured to receive the preprocessed digitized EEG signals and perform a multi-resolution signal decomposition based on the discrete cosine harmonic wavelet packet transform (DCHWPT) to generate transformed signal representations corresponding to different frequency subbands; a feature extraction module connected to the computing unit and configured to extract a variety of features from the transformed signal representations; a feature selection module configured to perform a statistical test to reduce the dimensionality of the extracted features and retain only relevant features;a classification module configured to categorize EEG signals into an alcoholic or control category based on the retained relevant features; and an output module connected to the classification module, the output module comprising a user interface configured to display the classified results to the user.

Description

AREA OF INVENTION The present disclosure relates to an EEG signal processing system with DCHWPT-based decomposition. In particular, the invention relates to a system for performing multi-resolution signal decomposition using discrete cosine harmonic wavelet packet transform (DCHWPT) for automated alcoholism detection based on EEG data. BACKGROUND OF THE INVENTION Alcoholism, characterized by chronic and excessive alcohol consumption, leads to severe physical and psychological dependence and has serious health consequences such as liver damage, neurological disorders, and various chronic diseases. According to the World Health Organization (WHO), alcohol abuse contributes to approximately 2.6 million deaths annually and is responsible for 4.7% of the global burden of disease. Chronic alcohol consumption impairs cognitive function and leads to memory loss, reduced visuospatial skills, and other cognitive deficits associated with alcohol dependence. Conventional methods for detecting alcoholism, such as surveys and questionnaires, are unreliable due to their subjective nature. Neuroimaging techniques, particularly electroencephalography (EEG), offer a more objective approach by directly measuring brain activity. However, EEG data are complex, multichannel, and often noisy, making manual analysis difficult. Visual observation alone is insufficient to reliably distinguish between the EEG signals of alcoholics and control subjects, necessitating automated methods for accurate detection. Several older research methods have employed signal decomposition techniques for alcoholism detection using EEG signals. These include continuous wavelet transform (CWT), empirical mode decomposition (EMD), variational mode decomposition (VMD), and fast fractional Fourier transform, combined with machine learning classifiers. While these methods have shown promising results, they have significant limitations. Traditional discrete wavelet transforms (DWTs) require decimation followed by interpolation in the subband decomposition, necessitating band-limiting and image-suppression filters. DWTs also suffer from shift variance, where small changes in the input signals cause significant changes in the wavelet coefficients, thus limiting the detection of transient features in EEG signals. Fourier-based transforms exhibit spectral leakage due to abrupt data discontinuities in the discrete Fourier transform (DFT), generating complex-valued coefficients that increase computational complexity. Many existing approaches rely on complex feature extraction and classification techniques with manually generated features, based more on the expertise of the researchers than on systematic optimization. There is a need for an improved EEG signal processing system that overcomes these limitations through shift-invariant signal decomposition, avoidance of aliasing effects without decimation and interpolation filters, use of real-valued coefficients to simplify calculation, and efficient detection of transient EEG features associated with alcoholism through a straightforward and comprehensive framework. SUMMARY OF THE INVENTION The present invention provides an EEG signal processing system for automated alcoholism detection using discrete cosine harmonic wavelet packet transform (DCHWPT). The system utilizes DCHWPT for multiresolution decomposition of EEG signals, generating real-valued coefficients to simplify computation and enabling shift-invariant analysis suitable for detecting transient EEG features associated with alcoholism. The system extracts statistical features from the decomposed signal representations. Feature selection is performed using statistical dimensionality reduction tests, and classification is achieved through machine learning classifiers with 10-fold cross-validation. The system achieves high accuracy in distinguishing between alcohol-dependent and healthy subjects, thus providing an objective and automated solution for alcohol dependence detection. The present disclosure relates to a system for detecting alcoholism using EEG signal processing. The system comprises: an EEG signal acquisition module for acquiring digitized EEG signals from multiple electrode-based sensors placed on the scalp of a test subject according to a 10-20 electrode system; a signal preprocessing module connected to the EEG signal acquisition module that preprocesses the acquired digitized EEG signals, the preprocessed EEG signals being stored in a database containing signals from alcohol-dependent and healthy subjects; a computing unit with at least one processor and dedicated memory that receives the preprocessed digitized EEG signals and performs multiresolution signal decomposition based on the Discrete Cosine Harmonic Wavelet-Packet Transform (DCHWPT) to generate transformed signal representations for different frequency subbands;A feature extraction module connected to the processing unit that extracts multiple features from the transformed signal representations; a feature selection module configured to perform a statistical test to reduce the dimensionality of the extracted features and retain only relevant features; a classification module configured to categorize the EEG signals into an alcoholic or control category based on the retained relevant features; and an output module connected to the classification module, the output module comprising a user interface configured to display the classified results to the user. The aim of the present disclosure is to provide an EEG signal processing system which, by using the discrete cosine harmonic wavelet packet transform, eliminates the need for decimation and interpolation filters and thereby avoids the requirements for aliasing and anti-imaging filters that arise in conventional discrete wavelet transform methods. The aim of the present disclosure is to provide a computationally efficient signal decomposition solution that generates real-valued coefficients using discrete cosine transformation instead of complex-valued coefficients using discrete Fourier transformation, thereby reducing computational complexity and enabling real-time EEG signal analysis. The aim of the present disclosure is to provide a shift-invariant multiresolution signal decomposition system capable of detecting transient, non-periodic EEG features associated with alcoholism that are difficult to capture using shift-variant traditional wavelet transformations. The aim of this disclosure is to provide a comprehensive and straightforward feature extraction framework that derives statistical descriptors from decomposed EEG signals, thereby enabling efficient characterization of alcohol-induced neuronal activity patterns without relying on manually created features. The purpose of this disclosure is to provide an automated alcoholism detection system with high diagnostic performance, offering an objective alternative to subjective, self-reported survey methods for screening for alcohol dependence. To further clarify the advantages and features of the present disclosure, the invention is described in more detail with reference to specific embodiments illustrated in the accompanying drawings. It is understood that these drawings merely show typical embodiments of the invention and are therefore not to be understood as limiting its scope of protection. The invention is described and explained in more detail and with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE IMAGES These and other features, aspects and advantages of the present disclosure will be better understood if the following detailed description is read with reference to the accompanying drawings, in which identical symbols represent identical parts, wherein: Fig. 1 shows a block diagram of a system for the detection of alcoholism by means of EEG signal processing according to an embodiment of the present disclosure; and Fig. 2 shows a diagram illustrating the operation of the proposed system for the detection of alcoholism by means of EEG signal processing according to an embodiment of the present disclosure. Furthermore, those skilled in the art will recognize that the elements in the drawings are simplified and not necessarily drawn to scale. For example, the flowcharts illustrate the process by highlighting the main steps to facilitate understanding of this disclosure. With regard to the construction of the device, one or more components may be represented in the drawings by conventional symbols. The drawings may show only those specific details relevant to understanding the embodiments of this disclosure, so as not to clutter the drawings with details that are already apparent to those skilled in the art from the description contained herein. DETAILED DESCRIPTION: To facilitate understanding of the principles of the invention, reference is made below to the embodiment illustrated in the drawings, which is described using specific terms. It is understood, however, that this does not limit the scope of protection of the invention. Rather, modifications and further developments of the illustrated system, as well as further applications of the inventive principles depicted therein, are conceivable, insofar as they would typically occur to a person skilled in the art in the field of the invention. It will be clear to those skilled in the art that the foregoing general description and the following detailed description are exemplary and explanatory of the invention and are not to be understood as a limitation of it. References to “an aspect”, “another aspect”, or similar phrases in this description mean that a particular feature, structure, or property described in connection with the embodiment is included in at least one embodiment of the present disclosure. Therefore, phrases such as “in one embodiment”, “in another embodiment”, and similar expressions in this description may, but do not necessarily, all refer to the same embodiment. The terms "includes," "comprehensive," or similar expressions denote non-exclusive inclusion. Thus, a procedure or method containing a list of steps does not only include those steps but may also include further steps not explicitly listed or inherent in the procedure or method. Likewise, the statement "includes..." for one or more devices, subsystems, elements, structures, or components, without further limitations, does not preclude the existence of other devices, subsystems, elements, structures, or components. Unless otherwise defined, all technical and scientific terms used herein have the same meanings generally known to those skilled in the art in the field to which this invention belongs. The systems, methods, and examples described herein serve only for illustration and are not to be understood as limiting. Embodiments of the present disclosure are described in detail below with reference to the accompanying drawings. The functional units described in this specification are referred to as devices. A device may be implemented in programmable hardware such as processors, digital signal processors, central processing units, FPGAs, PALs, PLDs, cloud processing systems, or similar. Devices may also be implemented in software for execution by various processor types. An identified device may contain executable code and, for example, comprise one or more physical or logical blocks of computer instructions, which may be organized as an object, procedure, function, or other construct. However, the executable files of an identified device need not be physically related; they may consist of different instructions stored in different locations that, when logically combined, constitute the device and fulfill its purpose. The executable code of a device or module can consist of a single instruction or multiple instructions and can even extend across different code sections, applications, and storage media. Similarly, operational data within the device can be identified and represented, and can exist in any suitable form and be organized in any data structure. The operational data can be captured as a single data record or distributed across various storage media and may exist, at least partially, as electronic signals within a system or network. References to “a selected embodiment”, “an embodiment”, or “an embodiment” in this description mean that a particular feature, structure, or property described in connection with the embodiment is included in at least one embodiment of the disclosed subject matter. Therefore, the phrases “a selected embodiment”, “in an embodiment”, or “in an embodiment” appearing at different points in this description do not necessarily refer to the same embodiment. Furthermore, the described features, structures, or properties can be combined in one or more embodiments in any suitable manner. The following description contains numerous specific details to enable a comprehensive understanding of the embodiments of the disclosed subject matter. However, a person skilled in the art will recognize that the disclosed subject matter can also be realized without one or more of the specific details or with other methods, components, materials, etc. In other cases, known structures, materials, or processes are not presented or described in detail so as not to obscure aspects of the disclosed subject matter. According to the exemplary embodiments, the disclosed computer programs or modules can be executed in a variety of ways, for example, as an application running in the memory of a device or as a hosted application running on a server and communicating with the device application or browser via various standard protocols such as TCP / IP, HTTP, XML, SOAP, REST, JSON, and other suitable protocols. The disclosed computer programs can be written in programming languages ​​that run either in the device's memory or on a hosted server, such as BASIC, COBOL, C, C++, Java, Pascal, or scripting languages ​​such as JavaScript, Python, Ruby, PHP, Perl, or other suitable programming languages. Some of the described embodiments involve data transmission over a network, such as the transmission of various inputs or files. The network may include, for example, the internet, wide area networks (WANs), local area networks (LANs), analog or digital wired and wireless telephone networks (e.g., PSTN, ISDN, cellular networks, and xDSL), radio, television, cable, satellite, and / or other transmission or tunneling mechanisms for data. It may include multiple networks or subnetworks, each of which may, for example, have a wired or wireless data path. The network may include a circuit-switched voice network, a packet-switched data network, or another network for transmitting electronic data. For example, it may be based on the Internet Protocol (IP) or Asynchronous Transfer Mode (ATM) and support voice communication using VoIP, Voice over ATM, or similar protocols.In one embodiment, the network comprises a mobile network configured for the exchange of text or SMS messages. Examples of networks include Personal Area Networks (PAN), Storage Area Networks (SAN), Home Area Networks (HAN), Campus Area Networks (CAN), Local Area Networks (LAN), Wide Area Networks (WAN), Metropolitan Area Networks (MAN), Virtual Private Networks (VPN), Enterprise Private Networks (EPN), the Internet, Global Area Networks (GAN), and so on. The present invention relates to a system that uses the discrete cosine harmonic wavelet packet transform (DCHWPT) for automated alcoholism detection using EEG data. Fig. 1 shows a block diagram of a system for detecting alcoholism using EEG signal processing according to an embodiment of the present disclosure. The system according to Fig. 1 comprises: an EEG signal acquisition module (102) for acquiring digitized EEG signals from multiple electrode-based sensors placed on the scalp of a subject according to a 10-20 electrode placement system; a signal preprocessing module (104) connected to the EEG signal acquisition module (102) that preprocesses the acquired digitized EEG signals, the preprocessed EEG signals being stored in a database containing signals from alcohol-dependent and control subjects; a computing unit (106) with at least one processor (106a) with dedicated memory, the processor (106a) receiving the preprocessed digitized EEG signals and performing multiresolution signal decomposition based on the Discrete Cosine Harmonic Wavelet-Packet Transform (DCHWPT) to generate transformed signal representations corresponding to different frequency subbands;A feature extraction module (108) connected to the computing unit (106) and configured to extract a variety of features from the transformed signal representations; a feature selection module (110) configured to perform a statistical test to reduce the dimensionality of the extracted features and retain only relevant features; a classification module (112) configured to classify the EEG signals into an alcoholic category or a control category based on the retained relevant features; and an output module (114) connected to the classification module (112), the output module (114) comprising a user interface (114a) configured to display the classified results to the user. In one embodiment, the EEG signal acquisition module (102) is configured to acquire EEG signals from 64 channels, each EEG signal having a sampling rate of 256 Hz and the measured sampling length of each EEG signal being one second. In one embodiment, the signal preprocessing module (104) is configured to suppress artifacts such as eye blinks and muscle movements. In one embodiment, the processor (106a) of the computing unit (106) is configured to implement a multi-resolution signal decomposition based on the Discrete Cosine Harmonic Wavelet-Packet Transform (DCHWPT). The processor (106a) is configured to: decompose the signal by grouping the DCT coefficients; apply the inverse discrete cosine transform (IDCT) to the concatenated coefficients to reconstruct the original signal, effectively reversing the transformation operations and restoring the time-domain representation of the signal; and perform efficient signal decomposition by multi-stage decomposition, where each node corresponds to a specific frequency band and enables detailed feature extraction, generating transformed signal representations for each frequency subband at each decomposition level. In one embodiment, the DCHWPT decomposes both approximation coefficients and detail coefficients at each decomposition level to generate a complete binary tree of wavelet coefficients corresponding to different frequency subbands. In one embodiment, the feature selection module (110) is configured to apply a Student's t-test to the extracted features to identify statistically significant features and reduce the dimensionality of the feature space by retaining only significant features. The features enable the precise quantification of signal characteristics and allow the observation of differences in the EEG of both alcohol-dependent and healthy subjects. In one embodiment, the classification module (112) comprises at least one machine learning classifier selected from the group consisting of: Support Vector Machine (SVM) classifier, neural network classifier and ensemble classifier. The machine learning classifier is trained to distinguish between EEG signal patterns of alcoholics and control subjects. The ensemble classifier comprises an ensemble subspace discriminant classifier, which combines multiple subspace discriminant classifiers operating on random sets of features. The present invention presents a system that utilizes the discrete cosine harmonic wavelet packet transform (DCHWPT) for automated alcoholism detection from EEG data. The system benefits from the simple computational nature of the DCT and, unlike the DFT, provides precise real coefficients. It retains the advantages of the HWT, such as integrated decimation and interpolation, whereas the DWT requires anti-aliasing and anti-imaging filters. The wavelet packet transform (WPT) improves multi-resolution analysis, and the shift invariance of the DCHWPT enables the effective detection of transient EEG signals associated with alcoholism. The extracted features provide a comprehensive statistical EEG description. Dimensional reduction is performed using a t-test, and model performance is evaluated based on accuracy, sensitivity, specificity, and F1 score with 10-fold cross-validation.The system surpasses traditional methods and achieves the performance of leading EEG-based algorithms for alcoholism detection. This study demonstrates the effectiveness of DCHWPT in alcoholism detection, thus laying the foundation for future research in the field of advanced diagnostic applications for alcoholism. Fig. 2 shows a diagram illustrating the workflow of the proposed system for detecting alcoholism using EEG signal processing according to an embodiment of the present disclosure. The system shown in Fig. 2 illustrates an EEG signal processing system consisting of an EEG signal input and preprocessing module, a DCHWPT-based multi-stage signal decomposition module, a feature extraction module, a feature selection module, and a classification module. This module generates outputs indicative of alcohol-induced EEG signal patterns. The proposed system includes a computing unit with at least one processor that processes digitized EEG signals from one or more EEG channels. The processor receives the digitized EEG signals and performs DCHWPT-based multi-stage signal decomposition. This decomposition produces transformed signal representations corresponding to different frequency bands across multiple resolution levels, thus enabling improved time-frequency characterization of the EEG signals.The use of DCHWPT enables efficient signal decomposition with real-valued coefficients, which reduces computational complexity and improves spectral localization compared to conventional wavelet or Fourier-based signal processing methods. In one embodiment, the processor is additionally configured to process the transformed signal representations to extract spectral, statistical, or complexity-related features. These extracted features can be used to generate classification features that indicate characteristic EEG signal patterns associated with alcohol-induced neuronal activity. The system operates as a computer-based signal processing system and requires no special hardware, allowing the described functionality to be executed on a standard computer. An exemplary embodiment of the EEG signal processing system is shown in Fig. 2. The EEG signal processing system for the detection of alcoholism consists of several interconnected modules configured to process EEG signals in clearly defined steps, as shown in Fig. 2. The system includes an EEG signal acquisition module that records EEG signals from sensors attached to the subjects' scalps, which capture the electrical activity of the brain. The system also includes a database for storing the recorded EEG signals. In this implementation, the database contains signals from 45 alcohol-dependent and 45 non-alcohol-dependent subjects. Each subject completed five measurement sessions, resulting in a total of 225 signals per group and 450 EEG signals. The system utilizes publicly available EEG datasets from alcohol-dependent and non-alcohol-dependent subjects in the KDD UCI archives. The EEG signals were recorded using a 10-20 electrode system from a total of 122 subjects (77 alcohol-dependent and 45 non-alcohol-dependent) with 120 measurement sessions. Each measurement session comprised 64 channels (electrodes), forming the complete EEG database. Standardized images were displayed to the subjects during signal recording. Each EEG signal has a sample length of one second and a sampling rate of 256 Hz. The system is configured to suppress artifacts such as blinking and muscle movements.After data preprocessing, the system contains 225 data sets from alcohol-dependent and 225 data sets from non-alcohol-dependent subjects. In one embodiment, the system includes a signal decomposition module for decomposing EEG signals using discrete cosine harmonic wavelet packet transform (DCHWPT). The DCHWPT implementation decomposes both approximation and detail coefficients at each decomposition level. This results in a complete binary tree of wavelet coefficients, enabling detailed analysis and synthesis of the signal. The DCHWPT decomposes the signal by grouping the coefficients of the discrete cosine transform (DCT). The system includes an inverse discrete cosine transform (IDCT) module that reconstructs the original signal from the concatenated coefficients, thus reversing the transformation. The IDCT module ensures that the signal retains its original properties after transformation and processing.It successfully restores the time-domain representation of the signal, thus demonstrating the effectiveness of the transformation in preserving essential signal characteristics. The wavelet packet transform (WPT) extends the traditional wavelet transform (WT) by decomposing approximation and detail coefficients at each level. This results in a finer frequency resolution of the signal components. The WPT is particularly well-suited for analyzing complex, non-stationary signals such as EEG signals. The discrete cosine harmonic wavelet packet transform (DCHWPT) further improves the WPT by integrating the discrete cosine transform (DCT) and the harmonic wavelet transform (HWT). The DCHWPT leverages the computational efficiency and real coefficients of the DCT for precise and efficient signal decomposition.The hierarchical structure represents the multi-stage signal decomposition, with each node corresponding to a specific frequency band, thus enabling detailed feature extraction and analysis. The system includes a feature extraction module configured to extract features from the sixteen different sub-bands. The feature extraction module is configured to determine different features for sixteen different sub-bands. The system includes a feature selection module that reduces the dimensionality of the feature space, retaining only the most relevant features. The module applies a Student's t-test, a nonparametric statistical test. This test is performed using a statistical tool to select significant features and reduce complexity. The system includes a classification module that categorizes EEG signals into "alcoholics" (AL) and "control group" (CN). The module utilizes various machine learning classifiers, including support vector machines (SVMs), neural networks, and ensemble classifiers. Classification is performed using the MATLAB application "Classification Learner." The classifiers are configured to evaluate their performance in distinguishing between the two categories. The system employs 10-fold cross-validation to ensure the robustness and generalizability of the classification results. The ensemble subspace discriminant classifier combines multiple subspace discriminant classifiers operating on random feature sets. This configuration improves robustness and accuracy by leveraging the diversity of the classifiers for better generalization in high-dimensional and complex classification tasks. The quadratic SVM uses a second-degree polynomial kernel, enabling the classifier to represent quadratic relationships and separate classes that are inseparable in feature space. The wide neural network is configured with a large number of neurons in its hidden layers, allowing it to capture complex patterns. System performance is evaluated based on three different components: signal processing decomposition, statistical validation of the extracted features, and machine learning classification performance in distinguishing between alcohol-dependent and control subjects based on the extracted features. The signal decomposition module is configured to decompose the EEG signal into 16 subbands across four decomposition levels using discrete cosine harmonic wavelet transforms (DCHWPT). Subband decomposition is performed for both alcoholics and control subjects, with zeros padded to achieve a uniform scale size. Visual differentiation between the signals of alcoholics and control subjects based on these subbands is virtually impossible, necessitating statistical methods and machine learning algorithms for precise classification. Before performing a t-test to compare means, an F-test is conducted to check for the equality of variances between the two samples. The F-test examines whether the variances are statistically equal, with the null hypothesis being that there is no difference in the variances. If the F-test indicates equal variances (p > 0.05), a pooled t-test for two samples is used, assuming equal variances. However, if the F-test results indicate unequal variances (p ≤ 0.05), the Welch t-test is used, as it does not require equal variances and allows for a more precise analysis in such cases. The classification module achieves different performance indicators across various classifiers and exhibits high accuracy. The proposed system, which utilizes the discrete cosine harmonic wavelet packet transform, demonstrates superior performance with high accuracy compared to various advanced systems. The proposed system achieves superior performance in the precise classification of EEG signals for alcoholism detection. The drawings and the preceding description illustrate embodiments. Those skilled in the art will recognize that one or more of the described elements can be combined to form a single functional element. Alternatively, certain elements can be divided into several functional elements. Elements of one embodiment can be added to another. For example, the process flows described here can be modified and are not limited to the manner described herein. Furthermore, the actions of a flowchart need not be performed in the sequence shown; nor do all actions necessarily need to be carried out. Actions that do not depend on other actions can be performed in parallel with the other actions. The scope of protection of the embodiments is in no way limited by these specific examples. Numerous variations, whether explicitly stated in the description or not, such as...Differences in structure, dimensions, and materials are possible. The scope of protection of the embodiments is at least as comprehensive as described by the following claims. The advantages, other benefits, and problem solutions have been described above with reference to specific embodiments. However, the advantages, benefits, problem solutions, and any components that can effect or enhance an advantage, benefit, or solution are not to be construed as critical, necessary, or essential features or components of the claims. REFERENCES 100 A system for detecting alcoholism using EEG signal processing. 102 EEG signal acquisition module 104 Signal preprocessing module 106 Computing unit 106a At least one processor 108 Feature extraction module 110 Feature selection module 112 Classification module 114 Output module 114a User interface 202 EEG signal input 204 EEG signal preprocessing 206 DCHWPT decomposition of the EEG signal 208 Multi-resolution levels 210 Feature extraction 212 Feature selection 214 Classification 216 Output indicating an alcohol-related EEG signal pattern

Claims

A system for detecting alcoholism using EEG signal processing, comprising: an EEG signal acquisition module configured to acquire digitized EEG signals from a plurality of electrodes placed on the scalp of a subject according to a 10-20 electrode placement system; a signal preprocessing module operationally connected to the EEG signal acquisition module and configured to preprocess the acquired digitized EEG signals, the preprocessed EEG signals being stored in a database containing signals from both alcohol-dependent and control subjects;a computing unit comprising at least one processor with dedicated memory, wherein the processor is configured to receive the preprocessed digitized EEG signals and perform a multi-resolution signal decomposition based on the discrete cosine harmonic wavelet packet transform (DCHWPT) to generate transformed signal representations corresponding to different frequency subbands; a feature extraction module connected to the computing unit and configured to extract a variety of features from the transformed signal representations; a feature selection module configured to perform a statistical test to reduce the dimensionality of the extracted features and retain only relevant features;a classification module configured to categorize EEG signals into an alcoholic or control category based on the retained relevant features; and an output module connected to the classification module, the output module comprising a user interface configured to display the classified results to the user. System according to claim 1, wherein the EEG signal acquisition module is configured to acquire EEG signals from 64 channels, each EEG signal having a sampling rate of 256 Hz and the measured sampling length of each EEG signal being one second. System according to claim 1, wherein the signal preprocessing module is configured to suppress artifacts such as eye blinks and muscle movements. System according to claim 1, wherein the processor of the computing unit is configured to implement a multi-resolution signal decomposition based on the Discrete Cosine Harmonic Wavelet-Packet Transform (DCHWPT), wherein the processor is configured as follows: decomposition of the signal by grouping the DCT coefficients; application of the inverse discrete cosine transform (IDCT) to the concatenated coefficients to reconstruct the original signal, effectively reversing the transformation operations and thus restoring the time-domain representation of the signal; and performance of efficient signal decomposition by multi-stage decomposition, wherein each node corresponds to a specific frequency band and enables detailed feature extraction, generating transformed signal representations for each frequency subband at each decomposition level. System according to claim 1, wherein the DCHWPT decomposes both approximation coefficients and detail coefficients at each decomposition level to generate a complete binary tree of wavelet coefficients corresponding to different frequency subbands. System according to claim 1, wherein the features enable the precise quantification of the signal characteristics and thus allow the observation of differences in the EEG in both alcohol-dependent and healthy subjects. System according to claim 1, wherein the feature selection module is configured to apply a Student's t-test to the extracted features in order to identify statistically significant features and reduce the dimensionality of the feature space by retaining only significant features. System according to claim 1, wherein the classification module comprises: at least one machine learning classifier from the group, wherein the machine learning classifier is trained to distinguish between alcohol-induced and control EEG signal patterns.

Images