A novel method based on convolutional neural networks for deriving standard 12-lead ECG from serial 3-lead ECG

Frontiers of Information Technology & Electronic Engineering - Reconstruction of a 12-lead electrocardiogram (ECG) from a serial 3-lead ECG has been researched in the past to satisfy the need...     

Role of Co in formation of Ni-Ti clusters in maraging stainless steel

The effect of Co addition on the formation of Ni-Ti clusters in maraging stainless steel was studied by three dimensional atom probe (3DAP) and first-principles calculation. The cluster analysis based on the maximum separation approach showed an increase in size but a decrease in density of Ni-Ti clusters with increasing the Co content. The first-principles calculation indicated weaker Co-Ni (Co-Ti) interactions than Co-Ti (Fe-Ti) interactions, which should be the essential reason for the change of distribution characteristics of Ni-Ti clusters in bcc Fe caused by Co addition.     

Imaging of two-dimensional unsaturated moisture flows in uncracked and cracked cement-based materials using electrical capacitance tomography

The development of visualizing tools to monitor unsaturated moisture flow in cement-based materials is of great importance, as most degradation processes in cement-based materials are connected to and take place in the presence moisture. This paper investigates the ability of electrical capacitance tomography (ECT) to image two-dimensional (2D) unsaturated moisture flow in cement-based materials. In ECT, the electrical permittivity distribution within an object is reconstructed based on measured capacitances between electrodes attached on the object’s surface. In a series of experiments, mortar specimens with and without discrete cracks were imaged with ECT during a 2D moisture ingress. The results show that ECT is able to monitor the evolution of the moisture flow, and to approximate the shape and position of the moisture front. These findings indicate that ECT is a viable method for monitoring and visualizing 2D unsaturated moisture flow in cement-based materials in the presence and absence of discrete cracks.     

Effect of ZnO layer thickness upon optoelectrical properties of NiO/ ZnO heterojunction prepared at room temperature

In this work, p-NiO/n-ZnO heterostructures were successfully prepared at room temperature using RF sputtering technique. The influence of ZnO layer thickness on the performance of the heterojunction was investigated. The deposited ZnO layers have a hexagonal Wurtzite structure with preferable growth orientations along (002) and (103) for thinner films. Increasing the thickness results in more crystallographic orientation randomness. The current–voltage measurements of the realized heterojunctions showed a clear rectifying behavior. The measured ideality factor varies from 2.5 to 1.6 according to the thickness of ZnO layer. The series resistance of the device is enlarged with increasing ZnO thickness. The deduced parameters from the I–V characteristics suggest that 200 nm is the optimal thickness of the ZnO layer according to our experimental conditions. We attribute the relatively better performance of this thickness to achieving reasonable compensation between serial resistance and ideality factor. The best heterojunction was tested and successfully used as a UV detector.     

Improving weld formability by a novel dual-rotation bobbin tool friction stir welding

A novel dual-rotation bobbin tool friction stir welding (DBT-FSW) was developed, in which the upper shoulder (US) and lower shoulder (LS) have different rotational speeds. This process was tried to weld 3.2 mm thick aluminum-lithium alloy sheets. The metallographic analysis and torque measurement were carried out to characterize the weld formability. Experimental results show that compared to conventional bobbin tool friction stir welding, the DBT-FSW has an excellent process stability, and can produce the defect-free joints in a wider range of welding parameters. These can be attributed to the significant improvement of material flow caused by the formation of a staggered layer structure and the unbalanced force between the US and LS during the DBT-FSW process.     

Cross-Layer Optimization of Dynamic Packet Assignment for Video Transmission Over IEEE 802.11e Networks

Video transmission over IEEE 802.11e wireless networks still shows poor performance for large bandwidth demand and frequently changed environments. Thus, several enhancements of IEEE 802.11e were proposed. On the other hand, big frames and simultaneous sending of adjacent frames always cause packet dropping for buffer overflow. In the past, we proposed an IEEE 802.11e enhancement named DFAA and a content aware mechanism to solve the above problems. The motivation of this paper is to find a proper way to integrate these two mechanisms. A DFAA enhancement (DFAA-E) is proposed to make up the insufficiency of content aware mechanism. Experiments results show that the combination of DFAA-E and content aware mechanism improves the video decoded quality greatly. And its performance can be further enhanced by selecting the suitable settings of certain parameters.     

Automatic breast tumor detection in ABVS images based on convolutional neural network and superpixel patterns

Breast cancer is one of the most common female malignancies, as well as the second leading cause of mortality for women. Early detection and treatment can dramatically decrease the mortality rate. Recently, automated breast volume scanner (ABVS) has become one of the most frequently used diagnose methods for breast tumor screening because of its operator-independent and reproducible advantages. However, it is a challenging job to obtain the tumors’ accurate locations and shapes by reviewing hundreds of ABVS slices. In this paper, a novel computer-aided detection (CADe) system is developed to reduce clinicians’ reading time and improve the efficiency. The CADe system mainly contains three parts: tumor candidate acquisition, false-positive reduction and tumor segmentation. Firstly, a local phase-based approach is built to obtain breast tumor candidates for further recognition. Subsequently, a convolutional neural network (CNN) is applied to reduce false positives (FPs). The introduction of CNN can help to avoid complicated feature extraction as well as elevate the accuracy and efficiency. Finally, superpixel-based segmentation is used to outline the breast tumor. Here, superpixel-based local binary pattern (SLBP) is proposed to assist the segmentation, which improves the performance. The methods were evaluated on a clinical ABVS dataset whose abnormal cases were manually labeled by an experienced radiologist. The experiment results were mainly composed of two parts. At the FP reduction stage, the proposed CNN achieved 100% and 78.12% sensitivity with FPs/case of 2.16 and 0. At the segmentation stage, our SLBP obtained 82.34% true positive, 15.79% false positive and 83.59% Dice similarity. In summary, the proposed CADe system demonstrated promising potential to detect and outline breast tumors in ABVS images.

     

Design and fabrication of an on-chip micro flow cytometer with integrated micro-lens

Microsystem Technologies - In this paper, the design and fabrication of an on-chip micro flow cytometer chip with integrated micro-lens with a size of...