Stress Detection using EEG Signal Based on Fast Walsh Hadamard transform and Voting Classifier

Mental stress is currently a significant concern, especially among the young. Stress adversely affects the overall performance of people’s work, and in certain cases, can even cause serious health issues. Everyone experiences stress in life. A unique way to identify and classify stress levels based on Electroencephalogram (EEG) is proposed in this manuscript. In this work, fast Walsh Hadamard transform is used to generate all frequencies which exist in the EEG signals. The range of alpha, beta, gamma, and delta from index value is calculated in subsequent stage. Principal component analysis (PCA) is applied for the feature dimensional reduction which is followed by the standard scaler. The PSD vector has been calculated for healthy and unhealthy EEG signal groups using the Welch method. The PSD vector is used an input to the voting classifier which is the combination of the k-NN and logistic regression classifier. The experimental results found that the proposed method provides better results when compared to the existing methods in terms of Accuracy (Acc) and Mean Square Error (MSE). The proposed method achieves a highest classification accuracy of 94.22%

Efficient Coding of the Embedded Signal in Steganographic Systems with Multiple Access

Today, steganographic systems with multiple access are of considerable importance. In such sys-tems, the orthogonal Walsh-Hadamard transform is most often used for multiplexing and divid-ing channels, which leads to the need for efficient coding of the Walsh-Hadamard transform coefficients for the convenience of their subsequent embedding. The purpose of the research is to develop a theoretical basis for efficient coding of the embedded signal in steganographic sys-tems with multiple access with an arbitrary number of users N, based on MC-CDMA technology. This purpose was fulfilled by forming the theoretical basis for constructing effective codes de-signed to encode the embedded signal in steganographic systems with multiple access. The most important results obtained are the proposed and proven relations that determine both the possible values of the Walsh-Hadamard transform coefficients, for a given value of the number of divid-ed channels, and the probability of occurrence of the given values of the Walsh-Hadamard transform coefficients, which allow the construction of effective codes to represent the embed-ded signal. In the case of the number of divided channels N=4, we propose to use a constant amplitude code that provides a smaller value of the average codeword length in comparison with the Huffman code, while the constructed code has correcting capabilities. The significance of the obtained results is determined by the possibility of using the developed theoretical basis when constructing effective codes for encoding the embedded signal in steganographic systems with multiple access at an arbitrary value of the number of divided channels N.