Cross-Domain Transfer Learning for PCG Diagnosis Algorithm.

Cardiechema is a way to reflect cardiovascular disease where the doctor uses a stethoscope to help determine the heart condition with a sound map. In this paper, phonocardiogram (PCG) is used as a diagnostic signal, and a deep learning diagnostic framework is proposed. By improving the architecture and modules, a new transfer learning and boosting architecture is mainly employed. In addition, a segmentation method is designed to improve on the existing signal segmentation methods, such as R wave to R wave interval segmentation and fixed segmentation. For the evaluation, the final diagnostic architecture achieved a sustainable performance with a public PCG database.

Healthcare knowledge of relationship between time series electrocardiogram and cigarette smoking using clinical records.

BACKGROUND: In the few studies of clinical experience available, cigarette smoking may be associated with ischemic heart disease and acute coronary events, which can be reflected in the electrocardiogram (ECG). However, there is no formal proof of a significant relationship between cigarette smoking and electrocardiogram results. In this study, we therefore investigate and prove the relationship between electrocardiogram and smoking using unsupervised neural network techniques. METHODS: In this research, a combination of two techniques of pattern recognition; feature extraction and clustering neural networks, is specifically investigated during the diagnostic classification of cigarette smoking based on different electrocardiogram feature extraction methods, such as the reduced binary pattern (RBP) and Wavelet features. In this diagnostic system, several neural network models have been obtained from the different training subsets by clustering analysis. Unsupervised neural network of clustering cigarette smoking was then implemented based on the self-organizing map (SOM) with the best performance. RESULTS: Two ECG datasets were investigated and analysed in this prospective study. One is the public PTB diagnostic ECG databset with 290 samples (age 17-87, mean 57.2; 209 men and 81 women; 73 smoking and 133 non-smoking). The other ECG database is from Taichung Veterans General Hospital (TVGH) and includes 480 samples (240 smoking, and 240 non-smoking). The diagnostic accuracy regarding smoking and non-smoking in the PTB dataset reaches 80.58% based on the RBP feature, and 75.63% in the second dataset based on Wavelet feature. CONCLUSIONS: The electrocardiogram diagnostic system performs satisfactorily in the cigarette smoking habit analysis task, and demonstrates that cigarette smoking is significantly associated with the electrocardiogram.

Correction: Staining Pattern Classification of Antinuclear Autoantibodies Based on Block Segmentation in Indirect Immunofluorescence Images.

[This corrects the article DOI: 10.1371/journal.pone.0113132.].

Clustering Analysis of Aging Diseases and Chronic Habits With Multivariate Time Series Electrocardiogram and Medical Records.

BACKGROUND: With recent technology, multivariate time-series electrocardiogram (ECG) analysis has played an important role in diagnosing cardiovascular diseases. However, discovering the association of wide range aging disease and chronic habit with ECG analysis still has room to be explored. This article mainly analyzes the possible relationship between common aging diseases or chorionic habits of medical record and ECG, such as diabetes, obesity, and hypertension, or the habit of smoking. METHODS: In the research, we first conducted different ECG features, such as those of reduced binary pattern, waveform, and wavelet and then performed a k-means clustering analysis on the correlation between ECGs and the aforementioned diseases and habits, from which it is expected to find a firm association between them and the best characteristics that can be used for future research. RESULTS: In summary, we discovered a weak and strong evidence between ECG and medical records. For strong evidence, most patients with diabetes are always assigned into a specified group no matter the number of classes in the k-means clustering, which means we can find their association between them. For weak evidence, smokers, obesity, and hypertension have less unique ECG feature vector, enabling clustering them into specific groups, so the ECGs might be used to identify smokers, obesity, and hypertension. It is also interesting that we found obesity and hypertension, which are thought to be related to cardiovascular system. However, they are not highly correlated in our clustering analysis, which might indirectly tell us that the impact of obesity and hypertension to our body is various. In addition, the clustering effect of waveform feature is better than the other two methods.

Electrocardiograph Identification Using Hybrid Quantization Sparse Matrix and Multi-Dimensional Approaches.

Electrocardiograph (ECG) technology is vital for biometric security, and blood oxygen is essential for human survival. In this study, ECG signals and blood oxygen levels are combined to increase the accuracy and efficiency of human identification and verification. The proposed scheme maps the combined biometric information to a matrix and quantifies it as a sparse matrix for reorganizational purposes. Experimental results confirm a much better identification rate than in other ECG-related identification studies. The literature shows no research in human identification using the quantization sparse matrix method with ECG and blood oxygen data combined. We propose a multi-dimensional approach that can improve the accuracy and reduce the complexity of the recognition algorithm.

Time sequence image analysis of positron emission tomography using wavelet transformation.

This paper presents the time sequence image analysis technique of positron emission tomography (PET) using a wavelet transformation method. The abdominal cavity of a person taking [18F]Fluoro-2-deoxy-2-D-glucose (18F-FDG) was scanned by the dynamic PET. The organ selection with dynamic PET images was conducted by the wavelet transformation to implement automatic selection of the region of interest (ROI). The image segmentation was carried out by the processes of sampling, wavelet transformation, erosion, dilation, and superimposition. Wavelet constructed image (WCI) contours were created by sampling 512 images from 1960 consecutive dynamic sequence PET images. The image segmentation technology developed can help doctors automatically select ROI, accurately identify lesion locations of organs, and thus effectively reduce human operation time and errors.

An intelligent health monitoring system using radio-frequency identification technology.

Long-term care (LTC) for the elderly has become extremely important in recent years. It is necessary for the different physiological monitoring systems to be integrated on the same interface to help oversee and manage the elderly's needs. This paper presents a novel health monitoring system for LTC services using radio-frequency identification (RFID) technology. Dual-band RFID protocols were included in the system, in which the high-frequency (HF) band of 13.56 MHz was used to identify individuals and the microwave band of 2.45 GHz was used to monitor physiological information. Distinct physiological data, including oxyhemoglobin saturation by pulse oximetry (SpO2), blood pressure, blood sugar, electrocardiogram (ECG) readings, body temperature, and respiration rate, were monitored by various biosensors. The intelligent RFID health monitoring system provided the features of the real-time acquisition of biomedical signals and the identification of personal information pertaining to the elderly and patients in nursing homes.

ECG Sensor Card with Evolving RBP Algorithms for Human Verification.

It is known that cardiac and respiratory rhythms in electrocardiograms (ECGs) are highly nonlinear and non-stationary. As a result, most traditional time-domain algorithms are inadequate for characterizing the complex dynamics of the ECG. This paper proposes a new ECG sensor card and a statistical-based ECG algorithm, with the aid of a reduced binary pattern (RBP), with the aim of achieving faster ECG human identity recognition with high accuracy. The proposed algorithm has one advantage that previous ECG algorithms lack-the waveform complex information and de-noising preprocessing can be bypassed; therefore, it is more suitable for non-stationary ECG signals. Experimental results tested on two public ECG databases (MIT-BIH) from MIT University confirm that the proposed scheme is feasible with excellent accuracy, low complexity, and speedy processing. To be more specific, the advanced RBP algorithm achieves high accuracy in human identity recognition and is executed at least nine times faster than previous algorithms. Moreover, based on the test results from a long-term ECG database, the evolving RBP algorithm also demonstrates superior capability in handling long-term and non-stationary ECG signals.

Sparse Matrix for ECG Identification with Two-Lead Features.

Electrocardiograph (ECG) human identification has the potential to improve biometric security. However, improvements in ECG identification and feature extraction are required. Previous work has focused on single lead ECG signals. Our work proposes a new algorithm for human identification by mapping two-lead ECG signals onto a two-dimensional matrix then employing a sparse matrix method to process the matrix. And that is the first application of sparse matrix techniques for ECG identification. Moreover, the results of our experiments demonstrate the benefits of our approach over existing methods.

Staining pattern classification of antinuclear autoantibodies based on block segmentation in indirect immunofluorescence images.

Indirect immunofluorescence based on HEp-2 cell substrate is the most commonly used staining method for antinuclear autoantibodies associated with different types of autoimmune pathologies. The aim of this paper is to design an automatic system to identify the staining patterns based on block segmentation compared to the cell segmentation most used in previous research. Various feature descriptors and classifiers are tested and compared in the classification of the staining pattern of blocks and it is found that the technique of the combination of the local binary pattern and the k-nearest neighbor algorithm achieve the best performance. Relying on the results of block pattern classification, experiments on the whole images show that classifier fusion rules are able to identify the staining patterns of the whole well (specimen image) with a total accuracy of about 94.62%.

Signal waveform detection with statistical automaton for internet and web service streaming.

In recent years, many approaches have been suggested for Internet and web streaming detection. In this paper, we propose an approach to signal waveform detection for Internet and web streaming, with novel statistical automatons. The system records network connections over a period of time to form a signal waveform and compute suspicious characteristics of the waveform. Network streaming according to these selected waveform features by our newly designed Aho-Corasick (AC) automatons can be classified. We developed two versions, that is, basic AC and advanced AC-histogram waveform automata, and conducted comprehensive experimentation. The results confirm that our approach is feasible and suitable for deployment.

Hiding patients confidential datainthe ECG signal viaa transform-domain quantization scheme.

Watermarking is the most widely used technology in the field of copyright and biological information protection. In this paper, we use quantization based digital watermark encryption technology on the Electrocardiogram (ECG) to protect patient rights and information. Three transform domains, DWT, DCT, and DFT are adopted to implement the quantization based watermarking technique. Although the watermark embedding process is not invertible, the change of the PQRST complexes and amplitude of the ECG signal is very small and so the watermarked data can meet the requirements of physiological diagnostics. In addition, the hidden information can be extracted without knowledge of the original ECG data. In other words, the proposed watermarking scheme is blind. Experimental results verify the efficiency of the proposed scheme.

Wavelet-based watermarking and compression for ECG signals with verification evaluation.

In the current open society and with the growth of human rights, people are more and more concerned about the privacy of their information and other important data. This study makes use of electrocardiography (ECG) data in order to protect individual information. An ECG signal can not only be used to analyze disease, but also to provide crucial biometric information for identification and authentication. In this study, we propose a new idea of integrating electrocardiogram watermarking and compression approach, which has never been researched before. ECG watermarking can ensure the confidentiality and reliability of a user's data while reducing the amount of data. In the evaluation, we apply the embedding capacity, bit error rate (BER), signal-to-noise ratio (SNR), compression ratio (CR), and compressed-signal to noise ratio (CNR) methods to assess the proposed algorithm. After comprehensive evaluation the final results show that our algorithm is robust and feasible.

Computer-assisted system with multiple feature fused support vector machine for sperm morphology diagnosis.

Sperm morphology is an important technique in identifying the health of sperms. In this paper we present a new system and novel approaches to classify different kinds of sperm images in order to assess their health. Our approach mainly relies on a one-dimensional feature which is extracted from the sperm's contour with gray level information. Our approach can handle rotation and scaling of the image. Moreover, it is fused with SVM classification to improve its accuracy. In our evaluation, our method has better performance than the existing approaches to sperm classification.