Search

Objective: Non-invasive foetal electrocardiography (NI-FECG) has the potential to provide more additional clinical information for detecting and diagnosing fetal diseases. We propose and demonstrate a deep learning approach for fetal QRS complex detection from raw NI-FECG signals by using a convolutional neural network (CNN) model. The main objective is to investigate whether reliable fetal QRS complex detection performance can still be obtained from features of single-channel NI-FECG signals, without canceling maternal ECG (MECG) signals., Approach: A deep learning method is proposed for recognizing fetal QRS complexes. Firstly, we collect data from set-a of the PhysioNet/computing in Cardiology Challenge database. The sample entropy method is used for signal quality assessment. Part of the bad quality signals is excluded in the further analysis. Secondly, in the proposed method, the features of raw NI-FECG signals are normalized before they are fed to a CNN classifier to perform fetal QRS complex detection. We use precision, recall, F-measure and accuracy as the evaluation metrics to assess the performance of fetal QRS complex detection., Main Results: The proposed deep learning method can achieve relatively high precision (75.33%), recall (80.54%), and F-measure scores (77.85%) compared with three other well-known pattern classification methods, namely KNN, naive Bayes and SVM., Significance: the proposed deep learning method can attain reliable fetal QRS complex detection performance from the raw NI-FECG signals without canceling MECG signals. In addition, the influence of different activation functions and signal quality assessment on classification performance are evaluated, and results show that Relu outperforms the Sigmoid and Tanh on this particular task, and better classification performance is obtained with the signal quality assessment step in this study.

High precision segmentation of organs or lesions in medical image is a vital challenge issue for intelligent analysis of medical image, it has important clinical application value for auxiliary diagnosis and treatment of diseases. Recently, in solving challenging problems such as medical image information representation and accurate modeling of non-Euclidean spatial physiological tissue structures, the graph deep learning based medical image segmentation technology has made important breakthroughs, and it has shown significant information feature extraction and characterization advantages. The merged technology also can obtain more accurate segmentation results, which has become an emerging research hotspot in this field. In order to better promote the research and development of the deep learning segmentation algorithm for medical image graphs, this paper makes a systematic summary of the technological progress and application status in this field. The paper introduces the definition of graphs and the basic structure of graph convolutional networks, and elaborates on spectral graph convolution and spatial graph convolution operations. Then, according to the three technical structure modes of GCN combined with residual module, attention mechanism module and learning module, the research progress in medical image segmentation has been encapsulated. The application and development of graph deep learning algorithms based medical image segmentation are summarized and prospected to provide references and guiding principles for the technical development of related researches. [ABSTRACT FROM AUTHOR]

With the acceleration of aging process of population structure, the single resident lifestyle is increasing on account of the high cost of care services and the privacy invasion concern. It is essential to monitor the activities of solitary elderly to find the emergency and lifestyle deviation, as independent life cannot be maintained due to physical or mental problems. The unobtrusive systems are the most preferred choice for the real-life long-term monitoring, while the camera and wearable devices based systems are not suitable due to the privacy and uncomfortableness, respectively. We propose a novel sensor-based activity recognition model based on the two-layer multi-granularity framework and the emergent paradigm with marker-based stigmergy. The stigmergy based marking subsystem builds features by aggregating the context-aware information and generating the two-dimensional activity pheromone trail. The two-layer framework consists of coarse-grained and fine-grained classification subsystems. The coarse-grained subsystem identifies whether the input completed activity segmented by the traditional method is easily-confused, and utilizes our generalized segmentation method to increase the inter-cluster distance. The fine-grained subsystem employs machine learning or deep learning classifiers to realize the activity recognition task. The proposed model is a data-driven model based on the information self-organization. It does not need sophisticated domain knowledge, and can fully mine the hidden feature structure containing semantically related information and spatio-temporal characteristics. The experimental results demonstrate the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

Discriminative feature learning is critical for person re-identification. To obtain abundant visual information from the input person image, we first propose a novel network that extracts multi-scale patch-level deep features. Then, we propose an improved softmax loss function for learning more compact and more discriminative feature vectors. Specifically, we integrate feature pyramid blocks and region-level global average pooling functions into the feature extraction network, introduce the well-established normalization techniques in face recognition algorithms into person re-ID, and penalize the redundancy in feature vectors by minimizing the l 1,2 norm of the weight matrix in the softmax layer. Experiments on three large-scale datasets under the standard settings show the effectiveness of the proposed method. Moreover, we report our cross-domain re-ID results by training re-ID models on source datasets and testing them on other target datasets. [ABSTRACT FROM AUTHOR]

Abstract This paper concerns the issue of monitoring elderly behavior in the context of ambient assisted living (AAL). Under the framework of online daily habit modeling (ODHM), we employ the emergent representation for activities of daily living (ADLs) with position-based stigmergy, and then combine it with convolution neural networks (CNNs) to accomplish the tasks of recognizing ADLs. In addition, we propose a new paradigm of activity summarization with the robustness to break interruptions. Radio tomographic imaging (RTI) is promoted as a simple yet flexible way of facilitating the required position-based stigmergy. Such position-based AAL systems can benefit the advantages of having no need any sophisticated domain models in analyzing and understanding ADLs while no burden training is involved in ODHM. Moreover, the emergent based data aggregation and deep learning of CNN together allow the recognition of ADLs at a fine-grained level, which contributes to the performance improvement of ODHM. Experimental results demonstrate the effectiveness of the proposed approach. [ABSTRACT FROM AUTHOR]