Real-time Classification of Fetal Status Based on Deep Learning and Cardiotocography Data.

This study uses convolutional neural networks (CNNs) and cardiotocography data for the real-time classification of fetal status in the mobile application of a pregnant woman and the computer server of a data expert at the same time (The sensor is connected with the smartphone, which is linked with the web server for the woman and the computer server for the expert). Data came from 5249 (or 4833) cardiotocography traces in Anam Hospital for the mobile application (or the computer server). 150 data cases of 5-minute duration were extracted from each trace with 141,001 final cases for the mobile application and for the computer server alike. The dependent variable was fetal status with two categories (Normal, Abnormal) for the mobile application and three categories (Normal, Middle, Abnormal) for the computer server. The fetal heart rate served as a predictor for the mobile application and the computer server, while uterus contraction for the computer server only. The 1-dimension (or 2-dimension) Resnet CNN was trained for the mobile application (or the computer server) during 800 epochs. The sensitivity, specificity and their harmonic mean of the 1-dimension CNN for the mobile application were 94.9%, 91.2% and 93.0%, respectively. The corresponding statistics of the 2-dimension CNN for the computer server were 98.0%, 99.5% and 98.7%. The average inference time per 1000 images was 6.51 micro-seconds. Deep learning provides an efficient model for the real-time classification of fetal status in the mobile application and the computer server at the same time.

Infiltration of Solution-Processable Solid Electrolytes into Conventional Li-Ion-Battery Electrodes for All-Solid-State Li-Ion Batteries.

Bulk-type all-solid-state lithium-ion batteries (ASLBs) have the potential to be superior to conventional lithium-ion batteries (LIBs) in terms of safety and energy density. Sulfide SE materials are key to the development of bulk-type ASLBs because of their high ionic conductivity (max of ∼10-2 S cm-1) and deformability. However, the severe reactivity of sulfide materials toward common polar solvents and the particulate nature of these electrolytes pose serious complications for the wet-slurry process used to fabricate ASLB electrodes, such as the availability of solvent and polymeric binders and the formation of ionic contacts and networks. In this work, we report a new scalable fabrication protocol for ASLB electrodes using conventional composite LIB electrodes and homogeneous SE solutions (Li6PS5Cl (LPSCl) in ethanol or 0.4LiI-0.6Li4SnS4 in methanol). The liquefied LPSCl is infiltrated into the tortuous porous structures of LIB electrodes and solidified, providing intimate ionic contacts and favorable ionic percolation. The LPSCl-infiltrated LiCoO2 and graphite electrodes show high reversible capacities (141 and 364 mA h g-1) at 0.14 mA cm-2 (0.1 C) and 30 °C, which are not only superior to those for conventional dry-mixed and slurry-mixed ASLB electrodes but also comparable to those for liquid electrolyte cells. Good electrochemical performance of ASLBs employing the LPSCl-infiltrated LiCoO2 and graphite electrodes at 100 °C is also presented, highlighting the excellent thermal stability and safety of ASLBs.

Na3 SbS4 : A Solution Processable Sodium Superionic Conductor for All-Solid-State Sodium-Ion Batteries.

All-solid-state sodium-ion batteries that operate at room temperature are attractive candidates for use in large-scale energy storage systems. However, materials innovation in solid electrolytes is imperative to fulfill multiple requirements, including high conductivity, functional synthesis protocols for achieving intimate ionic contact with active materials, and air stability. A new, highly conductive (1.1 mS cm(-1) at 25 °C, Ea =0.20 eV) and dry air stable sodium superionic conductor, tetragonal Na3 SbS4 , is described. Importantly, Na3 SbS4 can be prepared by scalable solution processes using methanol or water, and it exhibits high conductivities of 0.1-0.3 mS cm(-1) . The solution-processed, highly conductive solidified Na3 SbS4 electrolyte coated on an active material (NaCrO2 ) demonstrates dramatically improved electrochemical performance in all-solid-state batteries.

Solution-Processable Glass LiI-Li4 SnS4 Superionic Conductors for All-Solid-State Li-Ion Batteries.

A new, highly conductive (4.1 × 10(-4) S cm(-1) at 30 °C), highly deformable, and dry-air-stable glass 0.4LiI-0.6Li4 SnS4 is prepared using a homogeneous methanol solution. The solution process enables the wetting of any exposed surface of the active materials with highly conductive solidified electrolytes (0.4LiI-0.6Li4 SnS4), resulting in considerable improvements in the electrochemical performance of these electrodes over conventional mixture electrodes.

Bendable and thin sulfide solid electrolyte film: a new electrolyte opportunity for free-standing and stackable high-energy all-solid-state lithium-ion batteries.

Bulk-type all-solid-state lithium batteries (ASLBs) are considered a promising candidate to outperform the conventional lithium-ion batteries. Unfortunately, the current technology level of ASLBs is in a stage of infancy in terms of cell-based (not electrode-material-based) energy densities and scalable fabrication. Here, we report on the first ever bendable and thin sulfide solid electrolyte films reinforced with a mechanically compliant poly(paraphenylene terephthalamide) nonwoven (NW) scaffold, which enables the fabrication of free-standing and stackable ASLBs with high energy density and high rate capabilities. The ASLB, using a thin (∼70 µm) NW-reinforced SE film, exhibits a 3-fold increase of the cell-energy-density compared to that of a conventional cell without the NW scaffold.

Interfacial architecture for extra Li⁺ storage in all-solid-state lithium batteries.

The performance of nanocomposite electrodes prepared by controlled ball-milling of TiS2 and a Li2S-P2S5 solid electrolyte (SE) for all-solid-state lithium batteries is investigated, focusing on the evolution of the microstructure. Compared to the manually mixed electrodes, the ball-milled electrodes exhibit abnormally increased first-charge capacities of 416 mA h g(-1) and 837 mA h g(-1) in the voltage ranges 1.5-3.0 V and 1.0-3.0 V, respectively, at 50 mA g(-1) and 30°C. The ball-milled electrodes also show excellent capacity retention of 95% in the 1.5-3.0 V range after 60 cycles as compared to the manually mixed electrodes. More importantly, a variety of characterization techniques show that the origin of the extra Li(+) storage is associated with an amorphous Li-Ti-P-S phase formed during the controlled ball-milling process.