EEG-based design creativity exploration through recurrence quantification analysis

For developing brain computer interface (BCI) applications, electroencephalography (EEG) is the most widely used measurement method due to its noninvasiveness, high temporal resolution, and portability. EEG signal contains sufficient neural information about each human task, which makes the extracting, and decoding of each task-related information is still challenging, especially to improve the existing BCI performances. In this paper, we present a comparison analysis to find the most relevant features and the most suitable classification method for decoding motor imagery for EEG-based BCI. Therefore, some signal processing and machine learning techniques have applied for features extraction and classification phases. For the decomposition of EEG signal, we used three type of features [EEG signal mean, root mean square (RMS) and Relative of band power (RBP)]. In addition, we investigated an analytical comparison between three methods of classification [Support Vector Machine (SVM), Linear Discriminant Analysis and K-Nearest Neighbors]. The methods were validated using a publicly available dataset (BCI Competition IV-III-a) to discriminate between two mental states (right and left hand movements) using 10-fold cross-validation. SVM method gave better classification accuracy of 76.4% using relative band powers as potential EEG features.

Depression recognition based on the reconstruction of phase space of EEG signals and geometrical features

Frontal EEG Asymmetry in Major Depression, Dysthymia and Bipolar Disorder

Brain Computer Interface (BCI) provides an individual to communicate using brain activity through Electroencephalogram (EEG) for controlling devices. Robotic arm is one such application which assists physically challenged people in day to day activities. The proposed method helps to interact and control the robotic arm wirelessly with user friendly interface. The wireless module and hardware interface used are cost effective. In this work, visual evoked potential based motor-imaginary hand movements like left, right, up and down hand movements are considered. Enobio-8 device is used for acquiring EEG signals. Visual evoked potential concept is adapted for acquiring the EEG signals from 14 healthy subjects of age group 20–23. These signals are pre-processed using a band pass filter of 2 to 40Hz to remove all the artifacts. Multilevel wavelet transform is used for extracting the features from specific band of interest. K-Nearest Neighbour (KNN), Linear Discriminant Analysis (LDA) and Support Vector Machine (SVM) classifiers are used for classifying motor-imaginary hand movements. Robotic arm is interfaced with the Arduino uno board and it is wirelessly controlled from EEG signals via HC-05 Bluetooth module. The results obtained from LDA for two scenarios: left/right and up/down movements is 87.5%. LDA showed better performance when compared to KNN and SVM. The accuracy of KNN is 56% (left/right) and 62% (up/down). The accuracy of SVM is 81% (left/right) and 68% (up/down). The result from LDA is promising for bringing wireless mind-controlled robots much closer to the human hand.

Electrocardiographic (ECG) signals often consist of unwanted noises and speckles. In order to remove the noises, various image processing filters are used in various studies. In this paper, FIR and IIR filters are initially used to remove the linear and nonlinear delay present in the input ECG signal. In addition, filters are used to remove unwanted frequency components from the input ECG signal. Linear Discriminant Analysis (LDA) is used to reduce the features present in the input ECG signal. Support Vector Machines (SVM) is widely used for pattern recognition. However, traditional SVM method does not applicable to compute different characteristics of the features of data sets. In this paper, we use SVM model with a weighted kernel function method to classify more features from the input ECG signal. SVM model with a weighted kernel function method is significantly identifies the Q wave, R wave and S wave in the input ECG signal to classify the heartbeat level such as Left Bundle Branch Block (LBBB), Right Bundle Branch Block (RBBB), Premature Ventricular Contraction (PVC) and Premature Atrial Contractions (PACs). The performance of the proposed Linear Discriminant Analysis (LDA) with enhanced kernel based Support Vector Machine (SVM) method is comparatively analyzed with other machine learning approaches such as Linear Discriminant Analysis (LDA) with multilayer perceptron (MLP), Linear Discriminant Analysis (LDA) with Support Vector Machine (SVM), and Principal Component Analysis (PCA) with Support Vector Machine (SVM). The calculated RMSE, MAPE, MAE, R2 and Q2 for the proposed Linear Discriminant Analysis (LDA) with enhanced kernel based Support Vector Machine (SVM) method is low when compared with other approaches such as LDA with MLP, and PCA with SVM and LDA with SVM. Finally, Sensitivity, Specificity and Mean Square Error (MSE) are calculated to prove the effectiveness of the proposed Linear Discriminant Analysis (LDA) with an enhanced kernel based Support Vector Machine (SVM) method.

Abstract: Heart disease is one of the leading causes of death worldwide, making early detection and accurate diagnosis crucial for reducing mortality rates and improving patient outcomes. This study aims to evaluate the effectiveness of four machine learning algorithms—Logistic Regression, Random Forest, Support Vector Machine (SVM), and K-Nearest Neighbors (KNN)—in predicting heart disease, with a focus on enhancing model performance using Linear Discriminant Analysis (LDA) for feature reduction. Among the models, SVM achieved the highest accuracy at 84.24%, followed by Logistic Regression at 83.70%. Although Random Forest and KNN showed lower accuracies, all models benefited from LDA's dimensionality reduction. This study suggests that SVM, combined with LDA, offers an optimal solution for early and accurate heart disease prediction in the healthcare industry. Keywords: feature reduction; heart disease; linear discriminant analysis (LDA); machine learning; SVM Abstrak: Penyakit jantung merupakan salah satu penyebab utama kematian di seluruh dunia, sehingga deteksi dini dan diagnosis yang akurat sangat penting untuk menurunkan angka kematian dan meningkatkan hasil pengobatan pasien. Penelitian ini bertujuan untuk mengevaluasi efektivitas empat algoritma pembelajaran mesin—Regresi Logistik, Random Forest, Support Vector Machine (SVM), dan K-Nearest Neighbors (KNN)—dalam memprediksi penyakit jantung, dengan fokus pada peningkatan kinerja model menggunakan Analisis Diskriminan Linear (LDA) untuk reduksi fitur. Di antara model yang diuji, SVM mencapai akurasi tertinggi sebesar 84,24%, diikuti oleh Regresi Logistik dengan 83,70%. Meskipun Random Forest dan KNN menunjukkan akurasi yang lebih rendah, semua model memperoleh manfaat dari reduksi dimensi yang diberikan oleh LDA. Studi ini menunjukkan bahwa SVM yang dikombinasikan dengan LDA merupakan solusi optimal untuk prediksi penyakit jantung secara dini dan akurat dalam industri kesehatan. Kata kunci: linear discriminant analysis (LDA); machine learning; penyakit jantung; reduksi fitur; SVM.

Intellectual detection and validation of automated mammogram breast cancer images by multi-class SVM using deep learning classification

In this paper, we propose a near real-time effective face recognition system for consumer applications. Since the nature of application domain requires real time result and better accuracy, it poses a serious challenge. To address this challenge, we study various classification techniques, namely, support vector machine (SVM), linear discriminant analysis (LDA) and K nearest neighbor (KNN). We observe that although KNN is as effective as SVM but KNN prohibits its usage due to high response time when data is high dimensional. To speed up KNN retrieval, we propose a feature reduction technique using principle component analysis (PCA) to facilitate near real time face recognition along with better accuracy. We apply KNN after we reduce the number of features by PCA. Hence, we test various classification approaches, namely, SVM, KNN, KNN with PCA, LDA, and LDA with PCA on a benchmark dataset and demonstrate the effectiveness of KNN with PCA over SVM and LDA

Emotion is an essential mental and physiological state that influences on the cognition, learning, communication and decision making; it could be changed between different cases like happiness, sadness, and anger as a reaction to external stimuli. Some disabled people or autistic children are unable to express their emotions which form a communication gap between them and the outside world. This makes emotion recognition plays an important role in filling this gap. This paper focuses on investigating the human emotions from two physiological signals; EEG and EMG, using recurrence quantification analysis (RQA) approach. Features optimization has been applied using one-way analysis of variance (ANOVA) test. Three supervised classifiers (regression tree, support vector machine, and k-nearest neighbor) have been used for classifying signals into three cases for each one of the two emotional dimensions (arousal and valence). The achieved accuracy reached to 94% for arousal and 92% for valence dimension.

With the increasing competiveness in the field of food production growing at a faster pace across the globe, quality is one of the most desirable features that a product should possess. The ability to produce quality as well as safety food is the most prerequisite factors for both, national and international market. This paper explains the recently developed approaches and latest research efforts related to the assessment of the quality of different food products through comparison of multivariate techniques and examine the potential for their deployment. Here, there is a comparison of the abilities of nine different multivariate classification methods: linear discriminant analysis (LDA), quadratic discriminant analysis (QDA), regularized discriminant analysis (RDA), soft independent modeling of class analogy (SIMCA), partial least squares (PLS) classification, K-nearest neighbor (KNN), support vector machines (SVM), probabilistic neural network (PNN), and multilayer perceptron (ANN-MLP). The overall results sufficiently demonstrate the fact that the probabilistic neural network (PNN) method has the potential to determine the quality of various food products significantly with high accuracy. Keywords: Food quality inspection, artificial intelligence techniques, wavelet transform, probabilistic neural network (PNN) approaches Cite this Article Syed Sumera Ali, Sayyad Ajij D. Review Paper on Efficient Quality Inspection of Food Products Using Neural Network Classification. Journal of Artificial Intelligence Research & Advances . 2017; 4(1): 1–14p.

Introduction: Body mass index (BMI) is an acceptable method to measure overweight and obesity among the population. Objectives: The aim of this study was evaluating the application of machine learning algorithms for classifying body mass index for clinical purposes. Patients and Methods: In this descriptive study, we selected the dataset of 1316 people who selected randomly from all area of Ardabil city in Iran. Dataset included demographic and anthropometric data. Classification algorithms such as random forest (RF), Gaussian Naive Bayes (GNB), decision tree (DT), support vector machines (SVM), multi-layer perceptron (MLP), K-nearest neighbors (KNN) and logistic regression (LR) with 10-fold cross-validation were conducted to classify the data based on BMI. The performance of algorithms was evaluated with precision, recall, mean squared errors (MSE) and accuracy indices. All programing done by Python 3.7 in Jupyter Notebook. Results: According to the BMI, 603(45.8%) of all samples were normal and 713 (54.2%) were at-risk. The precision of RF, GNB, DT, SVM, MLP, KNN and LR for people at risk were 0.93, 0.86, 0.99, 0.82, 100, 0.82 and 0.99 respectively. Additionally, the accuracy of RF, GNB, DT, SVM, MLP, KNN and LR were 95%, 83%, 100%, 82%, 100%, 82% and 100 %. Conclusion: The comparison of the classifying algorithms showed that, the LR, MLP and DT had the higher accuracy than the other algorithms in detecting of people at-risk.

Distinguishing cognitive states using electroencephalography local activation and functional connectivity patterns

Detecting cognitive states during learning tasks is an essential component in neurocognitive experiments for assessing and enhancing the cognitive performance of individuals. Studies have demonstrated that mental state recognition systems utilizing brain signals are proficient in the automated monitoring of learners’ cognitive states. The current study focuses on developing an efficient individualized and cross-subject cognitive state assessment model based on Electroencephalography (EEG) patterns during learning tasks. For this study, EEGs of 20 healthy subjects were recorded during a resting state followed by a learning task and examined EEG activations patterns in a wide perspective of feature types and rhythms. The extracted features included time-domain features such as Hjorth parameters, Wavelet-based features, and Spectral entropy. Three classifiers, Support Vector Machine, k-Nearest Neighbor, and Linear Discriminant Analysis were employed to recognize the mental state. A new EEG-based attention index using band ratios is proposed and is demonstrated as an effective predictor for recognizing attentive reading. The proposed model can yield recognition performance with an accuracy of 92.9% in the subject-dependent approach and 77.2% in the subject-independent approach with the Support Vector Machine Classifier. The findings are useful for the design and development of neurofeedback systems that monitor and enhance the cognitive performance in healthy individuals, as well as in individuals with cognitive deficits.

Epilepsy is a common neurological disorder that is characterized by the recurrence of seizures. Electroencephalogram (EEG) signals are widely used to diagnose seizures. Because of the non-linear and dynamic nature of the EEG signals, it is difficult to effectively decipher the subtle changes in these signals by visual inspection and by using linear techniques. Therefore, non-linear methods are being researched to analyze the EEG signals. In this work, we use the recorded EEG signals in Recurrence Plots (RP), and extract Recurrence Quantification Analysis (RQA) parameters from the RP in order to classify the EEG signals into normal, ictal, and interictal classes. Recurrence Plot (RP) is a graph that shows all the times at which a state of the dynamical system recurs. Studies have reported significantly different RQA parameters for the three classes. However, more studies are needed to develop classifiers that use these promising features and present good classification accuracy in differentiating the three types of EEG segments. Therefore, in this work, we have used ten RQA parameters to quantify the important features in the EEG signals.These features were fed to seven different classifiers: Support vector machine (SVM), Gaussian Mixture Model (GMM), Fuzzy Sugeno Classifier, K-Nearest Neighbor (KNN), Naive Bayes Classifier (NBC), Decision Tree (DT), and Radial Basis Probabilistic Neural Network (RBPNN). Our results show that the SVM classifier was able to identify the EEG class with an average efficiency of 95.6%, sensitivity and specificity of 98.9% and 97.8%, respectively.

The internet of reality or augmented reality has been considered a breakthrough and an outstanding critical mutation with an emphasis on data mining leading to dismantling of some of its assumptions among several of its stakeholders. In this work, we study the pillars of these technologies connected to web usage as the Internet of things (IoT) system's healthcare infrastructure. We used several data mining techniques to evaluate the online advertisement data set, which can be categorized as high dimensional with 1,553 attributes, and the imbalanced data set, which automatically simulates an IoT discrimination problem. The proposed methodology applies Fischer linear discrimination analysis (FLDA) and quadratic discrimination analysis (QDA) within random projection (RP) filters to compare our runtime and accuracy with support vector machine (SVM), K-nearest neighbor (KNN), and Multilayer perceptron (MLP) in IoT-based systems. Finally, the impact on number of projections was practically experimented, and the sensitivity of both FLDA and QDA with regard to precision and runtime was found to be challenging. The modeling results show not only improved accuracy, but also runtime improvements. When compared with SVM, KNN, and MLP in QDA and FLDA, runtime shortens by 20 times in our chosen data set simulated for a healthcare framework. The RP filtering in the preprocessing stage of the attribute selection, fulfilling the model's runtime, is a standpoint in the IoT industry.Index Terms: Data Mining, Random Projection, Fischer Linear Discriminant Analysis, Online Advertisement Dataset, Quadratic Discriminant Analysis, Feature Selection, Internet of Things.