Deep Learning-based Multi-class Classification for Neonatal Respiratory Diseases on Chest Radiographs in Neonatal Intensive Care Units.

Objective Accurate and timely interpretation of chest radiographs is essential for assessing respiratory distress and guiding clinical management to improve outcomes of critically ill newborns. This study aimed to introduce a deep learning-based automated algorithm designed to classify various neonatal respiratory diseases and healthy lungs using a large dataset of high-quality, multi-class labeled chest X-ray images from neonatal intensive care units (NICUs). Methods Portable supine chest X-ray images for six common conditions (healthy lung, respiratory distress syndrome (RDS), transient tachypnea of the newborn (TTN), air leak syndrome (ALS), atelectasis, and bronchopulmonary dysplasia (BPD)) and demographic variables (gestational age and birth weight) were retrospectively collected from 10 university hospitals in Korea.

3D printed energy devices: generation, conversion, and storage.

The energy devices for generation, conversion, and storage of electricity are widely used across diverse aspects of human life and various industry. Three-dimensional (3D) printing has emerged as a promising technology for the fabrication of energy devices due to its unique capability of manufacturing complex shapes across different length scales. 3D-printed energy devices can have intricate 3D structures for significant performance enhancement, which are otherwise impossible to achieve through conventional manufacturing methods.

High-radiation-exposure tasks in Korean pressurized heavy-water reactors.

This study analysed the occupational dose in Korean pressurized heavy-water reactors (PHWRs) and identified tasks involving high radiation exposure. The average individual dose was sufficiently low to be below the annual effective dose limit for radiation workers and is even lower than the dose limit for the general public. However, some workers received relatively higher doses than others.

Recycled, Contaminated, Crumpled Aluminum Foil-Driven Triboelectric Nanogenerator.

With rapid urbanization and global population growth, the amount of wasted aluminum foil is significantly increasing. Most deformed and contaminated foil is difficult to recycle; hence, it is landfilled or incinerated, causing environmental pollution. Therefore, using aluminum foil waste for electricity may be conducive to addressing environmental problems.

Ultrahigh Performance, Serially Stackable, Breeze Driven Triboelectric Generator via Ambient Air Ionizing Channel.

Currently, wind energy harvesting is in the limelight. However, with the existing electromagnetic wind generators, it is difficult to harvest multifariously-wasted breezes. To harvest energy from winds at a wide range of speeds, wind-driven triboelectric nanogenerators (TENGs) are studied.

Relief of knee flexion contracture and gait improvement following adaptive training for an assist device in a transtibial amputee: A case study.

Background: Management of a knee contracture is important for regaining gait ability in transtibial amputees. However, there has been little study of prosthesis training for enhancing mobility and improving range of motion in cases of restricted knee extension.

Objective: This study aimed to evaluate the effects of adaptive training for an assist device (ATAD) for a transtibial amputee with a knee flexion contracture (KFC).