This paper presents a new classifier called total margin-based adaptive fuzzy support vector machines (TAF-SVM) that deals with several problems that may occur in support vector machines (SVMs) when applied to the face recognition. The proposed TAF-SVM not only solves the overfitting problem resulted from the outlier with the approach of fuzzification of the penalty, but also corrects the skew of the optimal separating hyperplane due to the very imbalanced data sets by using different cost algorithm. In addition, by introducing the total margin algorithm to replace the conventional soft margin algorithm, a lower generalization error bound can be obtained. Those three functions are embodied into the traditional SVM so that the TAF-SVM is proposed and reformulated in both linear and nonlinear cases. By using two databases, the Chung Yuan Christian University (CYCU) multiview and the facial recognition technology (FERET) face databases, and using the kernel Fisher's discriminant analysis (KFDA) algorithm to extract discriminating face features, experimental results show that the proposed TAF-SVM is superior to SVM in terms of the face-recognition accuracy. The results also indicate that the proposed TAF-SVM can achieve smaller error variances than SVM over a number of tests such that better recognition stability can be obtained

Major depressive disorder (MDD) has become a leading contributor to the global burden of disease; however, there are currently no reliable biological markers or physiological measurements for efficiently and effectively dissecting the heterogeneity of MDD. Here we propose a novel method based on scalp electroencephalography (EEG) signals and a robust spectral-spatial EEG feature extractor called kernel eigen-filter-bank common spatial pattern (KEFB-CSP). The KEFB-CSP first filters the multi-channel raw EEG signals into a set of frequency sub-bands covering the range from theta to gamma bands, then spatially transforms the EEG signals of each sub-band from the original sensor space to a new space where the new signals (i.e., CSPs) are optimal for the classification between MDD and healthy controls, and finally applies the kernel principal component analysis (kernel PCA) to transform the vector containing the CSPs from all frequency sub-bands to a lower-dimensional feature vector called KEFB-CSP. Twelve patients with MDD and twelve healthy controls participated in this study, and from each participant we collected 54 resting-state EEGs of 6 s length (5 min and 24 s in total). Our results show that the proposed KEFB-CSP outperforms other EEG features including the powers of EEG frequency bands, and fractal dimension, which had been widely applied in previous EEG-based depression detection studies. The results also reveal that the 8 electrodes from the temporal areas gave higher accuracies than other scalp areas. The KEFB-CSP was able to achieve an average EEG classification accuracy of 81.23% in single-trial analysis when only the 8-electrode EEGs of the temporal area and a support vector machine (SVM) classifier were used. We also designed a voting-based leave-one-participant-out procedure to test the participant-independent individual classification accuracy. The voting-based results show that the mean classification accuracy of about 80% can be achieved by the KEFP-CSP feature and the SVM classifier with only several trials, and this level of accuracy seems to become stable as more trials (i.e., <7 trials) are used. These findings therefore suggest that the proposed method has a great potential for developing an efficient (required only a few 6-s EEG signals from the 8 electrodes over the temporal) and effective (~80% classification accuracy) EEG-based brain-computer interface (BCI) system which may, in the future, help psychiatrists provide individualized and effective treatments for MDD patients.

Major depressive disorder (MDD) is a global healthcare issue and one of the leading causes of disability. Machine learning combined with non-invasive electroencephalography (EEG) has recently been shown to have the potential to diagnose MDD. However, most of these studies analyzed small samples of participants recruited from a single source, raising serious concerns about the generalizability of these results in clinical practice. Thus, it has become critical to re-evaluate the efficacy of various common EEG features for MDD detection across large and diverse datasets. To address this issue, we collected resting-state EEG data from 400 participants across four medical centers and tested classification performance of four common EEG features: band power (BP), coherence, Higuchi’s fractal dimension, and Katz’s fractal dimension. Then, a sequential backward selection (SBS) method was used to determine the optimal subset. To overcome the large data variability due to an increased data size and multi-site EEG recordings, we introduced the conformal kernel (CK) transformation to further improve the MDD as compared with the healthy control (HC) classification performance of support vector machine (SVM). The results show that (1) coherence features account for 98% of the optimal feature subset; (2) the CK-SVM outperforms other classifiers such as K-nearest neighbors (K-NN), linear discriminant analysis (LDA), and SVM; (3) the combination of the optimal feature subset and CK-SVM achieves a high five-fold cross-validation accuracy of 91.07% on the training set (140 MDD and 140 HC) and 84.16% on the independent test set (60 MDD and 60 HC). The current results suggest that the coherence-based connectivity is a more reliable feature for achieving high and generalizable MDD detection performance in real-life clinical practice.

Electromyographic (EMG) signals recognition is a complex pattern recognition problem due to its property of large variations in signals and features. This paper proposes a novel EMG classifier called cascaded kernel learning machine (CKLM) to achieve the goal of high-accuracy EMG recognition. First, the EMG signals are acquired by three surface electrodes placed on three different muscles. Second, EMG features are extracted by autoregressive model (ARM) and EMG histogram. After the feature extraction, the CKLM is performed to classify the features. CKLM is composed of two different kinds of kernel learning machines: generalized discriminant analysis (GDA) algorithm and support vector machine (SVM). By using GDA, both the goals of the dimensionality reduction of input features and the selection of discriminating features, named kernel FisherEMG, can be reached. Then, SVM combined with one-against-one strategy is executed to classify the kernel FisherEMG. By cascading SVM with GDA, the input features will be nonlinearly mapped twice by radial-basis function (RBF). As a result, a linear optimal separating hyperplane can be found with the largest margin of separation between each pair of postures' classes in the implicit dot product feature space. In addition, we develop a digital signal processor (DSP)-based EMG classification system for the control of a multi-degrees-of-freedom prosthetic hand for the practical implementation. Based on the clinical experiments, the results show that the proposed CKLM is superior to other frequently used methods, such as k-nearest neighbor algorithm, multilayer neural network, and SVM. The best EMG recognition rate 93.54% is obtained by CKLM.

Support vector data description (SVDD) has become a very attractive kernel method due to its good results in many novelty detection problems. However, the decision function of SVDD is expressed in terms of the kernel expansion, which results in a run-time complexity linear in the number of support vectors. For applications where fast real-time response is needed, how to speed up the decision function is crucial. This paper aims at dealing with the issue of reducing the testing time complexity of SVDD. A method called fast SVDD (F-SVDD) is proposed. Unlike the traditional methods which all try to compress a kernel expansion into one with fewer terms, the proposed F-SVDD directly finds the preimage of a feature vector, and then uses a simple relationship between this feature vector and the SVDD sphere center to re-express the center with a single vector. The decision function of F-SVDD contains only one kernel term, and thus the decision boundary of F-SVDD is only spherical in the original space. Hence, the run-time complexity of the F-SVDD decision function is no longer linear in the support vectors, but is a constant, no matter how large the training set size is. In this paper, we also propose a novel direct preimage-finding method, which is noniterative and involves no free parameters. The unique preimage can be obtained in real time by the proposed direct method without taking trial-and-error. For demonstration, several real-world data sets and a large-scale data set, the extended MIT face data set, are used in experiments. In addition, a practical industry example regarding liquid crystal display micro-defect inspection is also used to compare the applicability of SVDD and our proposed F-SVDD when faced with mass data input. The results are very encouraging.

In the last decade, unobtrusive (device-free and non-privacy invasive) recognition of activities of daily living (ADLs) for an individual in a smart home has been studied by many researchers. However, the unobtrusive recognition of multi-resident activities in a smart home is hardly studied. We propose a novel RGB activity image-based DCNN classifier for the unobtrusive recognition of the multi-resident activities (Bed_to_Toilet, Bed, Breakfast, Lunch, Leave_home, Laundry, Dinner, Night_wandering, R2_work, and R1_medicine) using Cairo open dataset provided by CASAS project. The open dataset is collected by environmental sensors (PIR and temperature sensors) in Cairo testbed while an adult couple with a dog was living for 55 days. The dataset is preprocessed with activity segmentation, sliding window, and RGB activity image conversion steps. The experimental results demonstrate that our classifier has the highest total accuracy of 95.2% among the previously developed machine learning classifiers that employed the same dataset. Moreover, the proposed RGB activity image was proven to be helpful for increasing the recognition rate. Therefore, we conclude that the proposed DCNN classifier is a useful tool for the unobtrusive recognition of the multi-resident activity in a home.