Weiting Chen

Classification of surface EMG signals using optimal wavelet packet method based on Davies-Bouldin criterion.

In this paper we present an optimal wavelet packet (OWP) method based on Davies-Bouldin criterion for the classification of surface electromyographic signals. To reduce the feature dimensionality of the outputs of the OWP decomposition, the principle components analysis was employed. Then we chose a neural network classifier to discriminate four types of prosthesis movements. The proposed method achieved a mean classification accuracy of 93.75%, which outperformed the method using the energy of wavelet packet coefficients (with mean classification accuracy 86.25%) and the fuzzy wavelet packet method (87.5%).

A random forest model based classification scheme for neonatal amplitude-integrated EEG

BackgroundModern medical advances have greatly increased the survival rate of infants, while they remain in the higher risk group for neurological problems later in life. For the infants with encephalopathy or seizures, identification of the extent of brain injury is clinically challenging. Continuous amplitude-integrated electroencephalography (aEEG) monitoring offers a possibility to directly monitor the brain functional state of the newborns over hours, and has seen an increasing application in neonatal intensive care units (NICUs).MethodsThis paper presents a novel combined feature set of aEEG and applies random forest (RF) method to classify aEEG tracings. To that end, a series of experiments were conducted on 282 aEEG tracing cases (209 normal and 73 abnormal ones). Basic features, statistic features and segmentation features were extracted from both the tracing as a whole and the segmented recordings, and then form a combined feature set. All the features were sent to a classifier afterwards. The significance of feature, the data segmentation, the optimization of RF parameters, and the problem of imbalanced datasets were examined through experiments. Experiments were also done to evaluate the performance of RF on aEEG signal classifying, compared with several other widely used classifiers including SVM-Linear, SVM-RBF, ANN, Decision Tree (DT), Logistic Regression(LR), ML, and LDA.ResultsThe combined feature set can better characterize aEEG signals, compared with basic features, statistic features and segmentation features respectively. With the combined feature set, the proposed RF-based aEEG classification system achieved a correct rate of 92.52% and a high F1-score of 95.26%. Among all of the seven classifiers examined in our work, the RF method got the highest correct rate, sensitivity, specificity, and F1-score, which means that RF outperforms all of the other classifiers considered here. The results show that the proposed RF-based aEEG classification system with the combined feature set is efficient and helpful to better detect the brain disorders in newborns.

A new framework to combine vertical and horizontal information for face recognition

We present an efficient feature extraction framework named two-dimensional combined complex discriminant analysis (2DCCDA) for face recognition. In this framework, 2DLDA is performed vertically and, at the same time, horizontally. That is, both vertical and horizontal discriminant information can be extracted separately. Then both the horizontal and the vertical feature matrices are combined into a complex feature matrix. A complex version of 2DLDA is introduced to extract the discriminant complex features of this complex feature matrix for feature selection. Experiments on the AT&T and AR databases show that 2DCCDA achieves satisfactory performance not only under the conditions of varied facial expression and lighting configuration but also under the conditions where the pose and sample size are varied.

Analysis of Amplitude-Integrated EEG in the Newborn Based on Approximate Entropy

Amplitude-integrated electroencephalographic (aEEG), a cerebral-function-monitoring method, is widely used in response to the clinical needs for continuous EEG monitoring. In this paper, we present an approach to analyze aEEG in newborns based on approximate entropy (ApEn). Unlike the traditional aEEG signal processing and diagnosing methods, the Box-Cox transformation is substituted for semilogarithmic amplitude compression to keep the continuity of the signal, reduce the excessive compression of chaotic information in high amplitudes, and use ApEn, rather than the amplitudes of the borders, to estimate the degree of chaos in the signal. Experiments with aEEGs of 120 cases (32 normal and 88 abnormal of full-term infants, and 57 cases of preterm infants) were conducted to validate the effectiveness of the proposed method. The results show an aEEG signal analyzed based on the proposed algorithm always belongs to an abnormal case and needs to be examined by physicians if the corresponding indicator is considered abnormal. The novel description of aEEG could be helpful in detecting brain disorders in the newborn as a new clinical target.

Classification of neonatal amplitude-integrated EEG using random forest model with combined feature

Amplitude integrated electroencephalogram (aEEG), a cerebral function monitoring method, is widely used in response to the clinical needs for continuous EEG monitoring. The focus work of this paper is presenting a novel combined feature set of aEEG and applying random forest (RF) method to identify the normal and abnormal aEEG tracing. To that end, a complete experimental evaluation was conducted on 282 aEEG tracing cases (209 normal and 73 abnormal infants). Instead of the traditional aEEG signal processing and diagnosing methods only based on linear features, we considered both statistical and non-linear features. In our experiments, we extracted and combined different types of features for integrated and segmented signals. The experiments examined the RF algorithmic issues including parameter optimization, segmentation of data and imbalanced datasets processing. The performance of the RF was compared to five commonly used classifiers. The result shows that classification accuracy of our method is up to 91.46%. This also indicates our combined feature set is effective for aEEG classification. Besides, the RF-based method can reach exceptional specificity. This novel method to automatically detect aEEG could help medical staff to monitor the progress of infants at all times.

Automatic fall detection of human in video using combination of features

The problem of automatically fall detection of older people living alone is a popular research topic since falls are one of the major health hazards among the aging population aged 65 and above and the population of them in China is more than 100 million. In this paper, we present an automatic human fall detection framework based on video surveillance which can improve safety of elders in indoor environments. First, a vision component was used to detect and extract moving people in videos from static cameras. Then, we combine Histograms of Oriented Gradients(HOG),Local Binary Pattern(LBP)and feature extracted by the Deep Learning Framework Caffe to form a new augmented feature and the feature is named HLC. We use HLC to represent a persons motion state in a frame of a video sequence. Because the process of fall is a sequence of movements, we use HLC features which were extracted from continuous frames of a video sequence to implement the fall detection. With the help of the HLC feature, we achieve an average fall detection result of 93.7% sensitivity and 92.0% specificity on three different datasets.

Effective identification and localization of immature precursors in bone marrow biopsy

Abstract Abnormal localization of immature precursors (ALIP) aggregating and clustering in bone marrow biopsy appears earlier than that of bone marrow smears in detection of the relapse of acute myelocytic leukemia (AML). But traditional manual ALIP recognition has many shortcomings such as prone to false alarms, neglect of distribution law before three immature precursor cells gathered, and qualitative analysis instead of quantitative one. So, it is very important to develop a novel automatic method to identify and localize immature precursor cells for computer-aided diagnosis, to disclose their patterns before ALIP with the development of AML. The contributions of this paper are as follows. (1) After preprocessing the image with Otsu method, we identify both precursor cells and trabecular bone by multiple morphological operations and thresholds. (2) We localize the precursors in different regions according to their distances with the nearest trabecular bone based on chamfer distance transform, followed by discussion for the presumptions and limitations of our method. The accuracy of recognition and localization is evaluated based on a comparison with visual evaluation by two blinded observers.

Securing Cookies with a MAC Address Encrypted Key Ring

Most web services providers use cookies to personalize the customers’ access to the website. A cookie contains a user’s privacy and important identification which can be used to identify the user. However, cookies are not as safe as we take it for granted. There are still some potential safety hazards in cookies. For example, the contents in the cookies can be easily changed, thus it will result in some safety threats to the user or the website. This paper proposes a new cookie security policy based on a MAC address encrypted key ring. It can make the cookies have higher confidentiality and higher efficiency. It is also easy to deploy and meets the user’s higher security requirements.

Selecting discriminant eigenfaces by using binary feature selection

Eigenface (PCA) and Fisherface (LDA) are two of the most commonly used subspace techniques in the area of face recognition. PCA maximizes not only intersubject variation but also the intrasubject variation without considering the class label even if they are available. LDA is prone to overfitting when the training data set is small, which wildly exists in face recognition. In this work, we present a binary feature selection (BFS) method to choose the most suitable set of eigenfaces for classification when only a small number of training samples per subject are available. In the proposed method, we make use of class label, look on two subjects as a group, and then the most suitable eigenfaces that help to identify these two subjects are picked out to form the binary classifier. The final classifier is the integration of these binary classifiers by voting. Experiments on the AR and AT&T face databases with small training data set prove that our proposed method outperforms not only traditional PCA and LDA but also some state of the art methods.

Patch Based Face Recognition via Fast Collaborative Representation Based Classification and Expression Insensitive Two-Stage Voting

Small sample size (SSS) is one of the most challenging problems in Face Recognition (FR). Recently the collaborative representation based classification with l2-norm regularization (CRC) shows very effective face recognition performance with low computational cost. Patch based CRC (PCRC) also could well handle the SSS problem, and a more effective method is conducted PCRC on different scales with various patch sizes (MSPCRC). However, computation of reconstruction residuals on all patches is still time consuming. In this paper, we devote to improve the performance for SSS problem in face recognition and decrease the computational cost. First, fast collaborative representation based classification (FCRC) is proposed to further decrease the computational cost of CRC. Instead of computing reconstruction residual on all classes, FCRC computes the residual on a small subset of classes which has a big coefficient, such a category full make use of the discrimination of representation coefficients and decrease the computational cost. Our experiments results show that FCRC has a significantly lower computational cost than CRC and slightly outperforms CRC. FCRC is especially powerful when it is applied on patches. To further improve the performance under varying expression, we use a two-stage voting method to combine the recognition outputs of all patches. Extended experiments show that the proposed two-stage voting based FCRC (TSPFCRC) outperforms many state-of-the-art face recognition algorithms and have a significantly lower computational cost.