Individual Identification by Late Information Fusion of EmgCNN and EmgLSTM from Electromyogram Signals.

This paper is concerned with individual identification by late fusion of two-stream deep networks from Electromyogram (EMG) signals. EMG signal has more advantages on security compared to other biosignals exposed visually, such as the face, iris, and fingerprints, when used for biometrics, at least in the aspect of visual exposure, because it is measured through contact without any visual exposure. Thus, we propose an ensemble deep learning model by late information fusion of convolutional neural networks (CNN) and long short-term memory (LSTM) from EMG signals for robust and discriminative biometrics. For this purpose, in the ensemble model's first stream, one-dimensional EMG signals were converted into time-frequency representation to train a two-dimensional convolutional neural network (EmgCNN). In the second stream, statistical features were extracted from one-dimensional EMG signals to train a long short-term memory (EmgLSTM) that uses sequence input. Here, the EMG signals were divided into fixed lengths, and feature values were calculated for each interval. A late information fusion is performed by the output scores of two deep learning models to obtain a final classification result. To confirm the superiority of the proposed method, we use an EMG database constructed at Chosun University and a public EMG database. The experimental results revealed that the proposed method showed performance improvement by 10.76% on average compared to a single stream and the previous methods.

Body and Hand-Object ROI-Based Behavior Recognition Using Deep Learning.

Behavior recognition has applications in automatic crime monitoring, automatic sports video analysis, and context awareness of so-called silver robots. In this study, we employ deep learning to recognize behavior based on body and hand-object interaction regions of interest (ROIs). We propose an ROI-based four-stream ensemble convolutional neural network (CNN). Behavior recognition data are mainly composed of images and skeletons. The first stream uses a pre-trained 2D-CNN by converting the 3D skeleton sequence into pose evolution images (PEIs). The second stream inputs the RGB video into the 3D-CNN to extract temporal and spatial features. The most important information in behavior recognition is identification of the person performing the action. Therefore, if the neural network is trained by removing ambient noise and placing the ROI on the person, feature analysis can be performed by focusing on the behavior itself rather than learning the entire region. Therefore, the third stream inputs the RGB video limited to the body-ROI into the 3D-CNN. The fourth stream inputs the RGB video limited to ROIs of hand-object interactions into the 3D-CNN. Finally, because better performance is expected by combining the information of the models trained with attention to these ROIs, better recognition will be possible through late fusion of the four stream scores. The Electronics and Telecommunications Research Institute (ETRI)-Activity3D dataset was used for the experiments. This dataset contains color images, images of skeletons, and depth images of 55 daily behaviors of 50 elderly and 50 young individuals. The experimental results showed that the proposed model improved recognition by at least 4.27% and up to 20.97% compared to other behavior recognition methods.

Intelligent Deep Models Based on Scalograms of Electrocardiogram Signals for Biometrics.

This paper conducts a comparative analysis of deep models in biometrics using scalogram of electrocardiogram (ECG). A scalogram is the absolute value of the continuous wavelet transform coefficients of a signal. Since biometrics using ECG signals are sensitive to noise, studies have been conducted by transforming signals into a frequency domain that is efficient for analyzing noisy signals. By transforming the signal from the time domain to the frequency domain using the wavelet, the 1-D signal becomes a 2-D matrix, and it could be analyzed at multiresolution. However, this process makes signal analysis morphologically complex. This means that existing simple classifiers could perform poorly. We investigate the possibility of using the scalogram of ECG as input to deep convolutional neural networks of deep learning, which exhibit optimal performance for the classification of morphological imagery. When training data is small or hardware is insufficient for training, transfer learning can be used with pretrained deep models to reduce learning time, and classify it well enough. In this paper, AlexNet, GoogLeNet, and ResNet are considered as deep models of convolutional neural network. The experiments are performed on two databases for performance evaluation. Physikalisch-Technische Bundesanstalt (PTB)-ECG is a well-known database, while Chosun University (CU)-ECG is directly built for this study using the developed ECG sensor. The ResNet was 0.73%-0.27% higher than AlexNet or GoogLeNet on PTB-ECG-and the ResNet was 0.94%-0.12% higher than AlexNet or GoogLeNet on CU-ECG.

An EigenECG Network Approach Based on PCANet for Personal Identification from ECG Signal.

We herein propose an EigenECG Network (EECGNet) based on the principal component analysis network (PCANet) for the personal identification of electrocardiogram (ECG) from human biosignal data. The EECGNet consists of three stages. In the first stage, ECG signals are preprocessed by normalization and spike removal. The R peak points in the preprocessed ECG signals are detected. Subsequently, ECG signals are transformed into two-dimensional images to use as the input to the EECGNet. Further, we perform patch-mean removal and PCA algorithm similar to the PCANet from the transformed two-dimensional images. The second stage is almost the same as the first stage, where the mean removal and PCA process are repeatedly performed in the cascaded network. In the final stage, the binary quantization, block sliding, and histogram computation are performed. Thus, this EECGNet performs well without the use of back-propagation to obtain features from the visual content. We constructed a Chosun University (CU)-ECG database from an ECG sensor implemented by ourselves. Further, we used the well-known MIT Beth Israel Hospital (BIH) ECG database. The experimental results clearly reveal the good performance and effectiveness of the proposed method compared with conventional algorithms such as PCA, auto-encoder (AE), extreme learning machine (ELM), and ensemble extreme learning machine (EELM).

Design of Ensemble Stacked Auto-Encoder for Classification of Horse Gaits with MEMS Inertial Sensor Technology.

This paper discusses the classification of horse gaits for self-coaching using an ensemble stacked auto-encoder (ESAE) based on wavelet packets from the motion data of the horse rider. For this purpose, we built an ESAE and used probability values at the end of the softmax classifier. First, we initialized variables such as hidden nodes, weight, and max epoch using the options of the auto-encoder (AE). Second, the ESAE model is trained by feedforward, back propagation, and gradient calculation. Next, the parameters are updated by a gradient descent mechanism as new parameters. Finally, once the error value is satisfied, the algorithm terminates. The experiments were performed to classify horse gaits for self-coaching. We constructed the motion data of a horse rider. For the experiment, an expert horse rider of the national team wore a suit containing 16 inertial sensors based on a wireless network. To improve and quantify the performance of the classification, we used three methods (wavelet packet, statistical value, and ensemble model), as well as cross entropy with mean squared error. The experimental results revealed that the proposed method showed good performance when compared with conventional algorithms such as the support vector machine (SVM).

Zerumbone, a Tropical Ginger Sesquiterpene of Zingiber officinale Roscoe, Attenuates α-MSH-Induced Melanogenesis in B16F10 Cells.

Zerumbone (ZER), an active constituent of the Zingiberaceae family, has been shown to exhibit several biological activities, such as anti-inflammatory, anti-allergic, anti-microbial, and anti-cancer; however, it has not been studied for anti-melanogenic properties. In the present study, we demonstrate that ZER and Zingiber officinale (ZO) extract significantly attenuate melanin accumulation in α-melanocyte-stimulating hormone (α-MSH)-stimulated mouse melanogenic B16F10 cells. Further, to elucidate the molecular mechanism by which ZER suppresses melanin accumulation, we analyzed the expression of melanogenesis-associated transcription factor, microphthalmia-associated transcription factor (MITF), and its target genes, such as tyrosinase, tyrosinase-related protein 1 (TYRP1), and tyrosinase-related protein 2 (TYRP2), in B16F10 cells that are stimulated by α-MSH. Here, we found that ZER inhibits the MITF-mediated expression of melanogenic genes upon α-MSH stimulation. Additionally, cells treated with different concentrations of zerumbone and ZO showed increased extracellular signal-regulated kinases 1 and 2 (ERK1/2) phosphorylation, which are involved in the degradation mechanism of MITF. Pharmacological inhibition of ERK1/2 using U0126 sufficiently reversed the anti-melanogenic effect of ZER, suggesting that increased phosphorylation of ERK1/2 is required for its anti-melanogenic activity. Taken together, these results suggest that ZER and ZO extract can be used as active ingredients in skin-whitening cosmetics because of their anti-melanogenic effect.

Algal Bloom Prediction Using Extreme Learning Machine Models at Artificial Weirs in the Nakdong River, Korea.

In this study, we design an intelligent model to predict chlorophyll-a concentration, which is the primary indicator of algal blooms, using extreme learning machine (ELM) models. Modeling algal blooms is important for environmental management and ecological risk assessment. For this purpose, the performance of the designed models was evaluated for four artificial weirs in the Nakdong River, Korea. The Nakdong River has harmful annual algal blooms that can affect health due to exposure to toxins. In contrast to conventional neural network (NN) that use backpropagation (BP) learning methods, ELMs are fast learning, feedforward neural networks that use least square estimates (LSE) for regression. The weights connecting the input layer to the hidden nodes are randomly assigned and are never updated. The dataset used in this study includes air temperature, rainfall, solar radiation, total nitrogen, total phosphorus, N/P ratio, and chlorophyll-a concentration, which were collected on a weekly basis from January 2013 to December 2016. Here, upstream chlorophyll-a concentration data was used in our ELM2 model to improve algal bloom prediction performance. In contrast, the ELM1 model only uses downstream chlorophyll-a concentration data. The experimental results revealed that the ELM2 model showed better performance in comparison to the ELM1 model. Furthermore, the ELM2 model showed good prediction and generalization performance compared to multiple linear regression (LR), conventional neural network with backpropagation (NN-BP), and adaptive neuro-fuzzy inference system (ANFIS).

Classification of K-Pop Dance Movements Based on Skeleton Information Obtained by a Kinect Sensor.

This paper suggests a method of classifying Korean pop (K-pop) dances based on human skeletal motion data obtained from a Kinect sensor in a motion-capture studio environment. In order to accomplish this, we construct a K-pop dance database with a total of 800 dance-movement data points including 200 dance types produced by four professional dancers, from skeletal joint data obtained by a Kinect sensor. Our classification of movements consists of three main steps. First, we obtain six core angles representing important motion features from 25 markers in each frame. These angles are concatenated with feature vectors for all of the frames of each point dance. Then, a dimensionality reduction is performed with a combination of principal component analysis and Fisher's linear discriminant analysis, which is called fisherdance. Finally, we design an efficient Rectified Linear Unit (ReLU)-based Extreme Learning Machine Classifier (ELMC) with an input layer composed of these feature vectors transformed by fisherdance. In contrast to conventional neural networks, the presented classifier achieves a rapid processing time without implementing weight learning. The results of experiments conducted on the constructed K-pop dance database reveal that the proposed method demonstrates a better classification performance than those of conventional methods such as KNN (K-Nearest Neighbor), SVM (Support Vector Machine), and ELM alone.

An Incremental Radial Basis Function Network Based on Information Granules and Its Application.

This paper is concerned with the design of an Incremental Radial Basis Function Network (IRBFN) by combining Linear Regression (LR) and local RBFN for the prediction of heating load and cooling load in residential buildings. Here the proposed IRBFN is designed by building a collection of information granules through Context-based Fuzzy C-Means (CFCM) clustering algorithm that is guided by the distribution of error of the linear part of the LR model. After adopting a construct of a LR as global model, refine it through local RBFN that captures remaining and more localized nonlinearities of the system to be considered. The experiments are performed on the estimation of energy performance of 768 diverse residential buildings. The experimental results revealed that the proposed IRBFN showed good performance in comparison to LR, the standard RBFN, RBFN with information granules, and Linguistic Model (LM).

Estimation of Energy Expenditure Using a Patch-Type Sensor Module with an Incremental Radial Basis Function Neural Network.

Conventionally, indirect calorimetry has been used to estimate oxygen consumption in an effort to accurately measure human body energy expenditure. However, calorimetry requires the subject to wear a mask that is neither convenient nor comfortable. The purpose of our study is to develop a patch-type sensor module with an embedded incremental radial basis function neural network (RBFNN) for estimating the energy expenditure. The sensor module contains one ECG electrode and a three-axis accelerometer, and can perform real-time heart rate (HR) and movement index (MI) monitoring. The embedded incremental network includes linear regression (LR) and RBFNN based on context-based fuzzy c-means (CFCM) clustering. This incremental network is constructed by building a collection of information granules through CFCM clustering that is guided by the distribution of error of the linear part of the LR model.

Classification of Horse Gaits Using FCM-Based Neuro-Fuzzy Classifier from the Transformed Data Information of Inertial Sensor.

In this study, we classify four horse gaits (walk, sitting trot, rising trot, canter) of three breeds of horse (Jeju, Warmblood, and Thoroughbred) using a neuro-fuzzy classifier (NFC) of the Takagi-Sugeno-Kang (TSK) type from data information transformed by a wavelet packet (WP). The design of the NFC is accomplished by using a fuzzy c-means (FCM) clustering algorithm that can solve the problem of dimensionality increase due to the flexible scatter partitioning. For this purpose, we use the rider's hip motion from the sensor information collected by inertial sensors as feature data for the classification of a horse's gaits. Furthermore, we develop a coaching system under both real horse riding and simulator environments and propose a method for analyzing the rider's motion. Using the results of the analysis, the rider can be coached in the correct motion corresponding to the classified gait. To construct a motion database, the data collected from 16 inertial sensors attached to a motion capture suit worn by one of the country's top-level horse riding experts were used. Experiments using the original motion data and the transformed motion data were conducted to evaluate the classification performance using various classifiers. The experimental results revealed that the presented FCM-NFC showed a better accuracy performance (97.5%) than a neural network classifier (NNC), naive Bayesian classifier (NBC), and radial basis function network classifier (RBFNC) for the transformed motion data.

Intelligent predictor of energy expenditure with the use of patch-type sensor module.

This paper is concerned with an intelligent predictor of energy expenditure (EE) using a developed patch-type sensor module for wireless monitoring of heart rate (HR) and movement index (MI). For this purpose, an intelligent predictor is designed by an advanced linguistic model (LM) with interval prediction based on fuzzy granulation that can be realized by context-based fuzzy c-means (CFCM) clustering. The system components consist of a sensor board, the rubber case, and the communication module with built-in analysis algorithm. This sensor is patched onto the user’s chest to obtain physiological data in indoor and outdoor environments. The prediction performance was demonstrated by root mean square error (RMSE). The prediction performance was obtained as the number of contexts and clusters increased from 2 to 6, respectively. Thirty participants were recruited from Chosun University to take part in this study. The data sets were recorded during normal walking, brisk walking, slow running, and jogging in an outdoor environment and treadmill running in an indoor environment, respectively. We randomly divided the data set into training (60%) and test data set (40%) in the normalized space during 10 iterations. The training data set is used for model construction, while the test set is used for model validation. The experimental results revealed that the prediction error on treadmill running simulation was improved by about 51% and 12% in comparison to conventional LM for training and checking data set, respectively.

Development of quantum-based adaptive neuro-fuzzy networks.

In this study, we are concerned with a method for constructing quantum-based adaptive neuro-fuzzy networks (QANFNs) with a Takagi-Sugeno-Kang (TSK) fuzzy type based on the fuzzy granulation from a given input-output data set. For this purpose, we developed a systematic approach in producing automatic fuzzy rules based on fuzzy subtractive quantum clustering. This clustering technique is not only an extension of ideas inherent to scale-space and support-vector clustering but also represents an effective prototype that exhibits certain characteristics of the target system to be modeled from the fuzzy subtractive method. Furthermore, we developed linear-regression QANFN (LR-QANFN) as an incremental model to deal with localized nonlinearities of the system, so that all modeling discrepancies can be compensated. After adopting the construction of the linear regression as the first global model, we refined it through a series of local fuzzy if-then rules in order to capture the remaining localized characteristics. The experimental results revealed that the proposed QANFN and LR-QANFN yielded a better performance in comparison with radial basis function networks and the linguistic model obtained in previous literature for an automobile mile-per-gallon prediction, Boston Housing data, and a coagulant dosing process in a water purification plant.

Face recognition using an enhanced independent component analysis approach.

This paper is concerned with an enhanced independent component analysis (ICA) and its application to face recognition. Typically, face representations obtained by ICA involve unsupervised learning and high-order statistics. In this paper, we develop an enhancement of the generic ICA by augmenting this method by the Fisher linear discriminant analysis (LDA); hence, its abbreviation, FICA. The FICA is systematically developed and presented along with its underlying architecture. A comparative analysis explores four distance metrics, as well as classification with support vector machines (SVMs). We demonstrate that the FICA approach leads to the formation of well-separated classes in low-dimension subspace and is endowed with a great deal of insensitivity to large variation in illumination and facial expression. The comprehensive experiments are completed for the facial-recognition technology (FERET) face database; a comparative analysis demonstrates that FICA comes with improved classification rates when compared with some other conventional approaches such as eigenface, fisherface, and the ICA itself.

Face recognition using fuzzy integral and wavelet decomposition method.

In this paper, we develop a method for recognizing face images by combining wavelet decomposition, Fisherface method, and fuzzy integral. The proposed approach is comprised of four main stages. The first stage uses the wavelet decomposition that helps extract intrinsic features of face images. As a result of this decomposition, we obtain four subimages (namely approximation, horizontal, vertical, and diagonal detailed images). The second stage of the approach concerns the application of the Fisherface method to these four decompositions. The choice of the Fisherface method in this setting is motivated by its insensitivity to large variation in light direction, face pose, and facial expression. The two last phases are concerned with the aggregation of the individual classifiers by means of the fuzzy integral. Both Sugeno and Choquet type of fuzzy integral are considered as the aggregation method. In the experiments we use n-fold cross-validation to assure high consistency of the produced classification outcomes. The experimental results obtained for the Chungbuk National University (CNU) and Yale University face databases reveal that the approach presented in this paper yields better classification performance in comparison to the results obtained by other classifiers.