Breath Analyzer for Real-Time Exercise Fat Burning Prediction: Oral and Alveolar Breath Insights with CNN.

The increasing prevalence of obesity and metabolic disorders has created a significant demand for personalized devices that can effectively monitor fat metabolism. In this study, we developed an advanced breath analyzer system designed to provide real-time monitoring of exercise-induced fat burning by analyzing volatile organic compounds (VOCs) present in both oral and alveolar breath. Acetone in exhaled breath and β-hydroxybutyric acid (BOHB) in the blood are both biomarkers closely linked to the metabolic fat burning process occurring in the liver, particularly after exercise.

Visual Indicator for Intradialytic Hypotension Prediction Using Variation and Compensation of Heart Rate.

Background: To date, most intradialytic hypotension (IDH) studies have proposed technologies to comprehensively predict the occurrence of IDH using the patient's baseline information and ultrafiltration (UF) information, but it is difficult to apply the technologies while identifying the patient's condition in real time.

Methods: In this study, we propose an IDH indicator that uses heart rate (HR) change information to identify the patient's condition in real time and visually shows whether IDH has occurred. The data used were collected from 40 dialysis patients in a clinical trial conducted in the Artificial Kidney Unit at Yeungnam University Medical Center, Korea, from 18 July to 29 November 2023.

Inverse design of compact silicon photonic waveguide reflectors and their application for Fabry-Perot resonators.

Silicon photonic waveguide resonators, such as microring resonators, photonic crystal waveguide cavities, and Fabry-Perot resonators based on the distributed Bragg reflectors, are key device components for silicon-based photonic integrated circuits (Si-PIC). For the Si-PIC with high integration density, the device footprints of the conventional photonic waveguide resonators need to be more compact. Inverse design, which is operated by the design expectation and different from the conventional design methods, has been investigated for reducing the photonic device components nowadays.

Advanced Bearing-Fault Diagnosis and Classification Using Mel-Scalograms and FOX-Optimized ANN.

Accurate and reliable bearing-fault diagnosis is important for ensuring the efficiency and safety of industrial machinery. This paper presents a novel method for bearing-fault diagnosis using Mel-transformed scalograms obtained from vibrational signals (VS). The signals are windowed and pass through a Mel filter bank, converting them into a Mel spectrum.

Online Service Function Chain Planning for Satellite-Ground Integrated Networks to Minimize End-to-End (E2E) Delay.

The combination of software-defined networking (SDN) and satellite-ground integrated networks (SGINs) is gaining attention as a key infrastructure for meeting the granular quality-of-service (QoS) demands of next-generation mobile communications. However, due to the unpredictable nature of end-user requests and the limited resource capacity of low Earth orbit (LEO) satellites, improper Virtual Network Function (VNF) deployment can lead to significant increases in end-to-end (E2E) delay. To address this challenge, we propose an online algorithm that jointly deploys VNFs and forms routing paths in an event-driven manner in response to end-user requests.

Multi-Scale 3D Cephalometric Landmark Detection Based on Direct Regression with 3D CNN Architectures.

Background: Cephalometric analysis is important in diagnosing and planning treatments for patients, traditionally relying on 2D cephalometric radiographs. With advancements in 3D imaging, automated landmark detection using deep learning has gained prominence. However, 3D imaging introduces challenges due to increased network complexity and computational demands.

Rapid activation of a solution-processed aluminum oxide gate dielectric through intense pulsed light irradiation.

In this study, we report rapid activation of a solution-processed aluminum oxide gate dielectric film to reduce its processing time under ambient atmosphere. Aluminum precursor films were exposed to a high energy light-pulse and completely converted into dielectric films within 30 seconds (450 pulses). The aluminum oxide gate dielectric film irradiated using intense pulsed light with 450 pulses exhibits a smooth surface and a leakage current density of less than 10 A cm at 2 MV cm.

Regulating Entanglement Networks of Fibrillatable Binders for Sub-20-µm Thick, Robust, Dry-Processed Solid Electrolyte Membranes in All-Solid-State Batteries.

Despite significant advancements in all-solid-state batteries (ASSBs), the reliance on thick solid electrolyte (SE) membranes hinders their commercial viability. Although the dry process using polytetrafluoroethylene (PTFE) binder is proposed for thin SE membranes, a comprehensive understanding of the correlation between PTFE fibrillation and SE membrane quality remains lacking. Here an important guidance is provided for producing durable SE membranes that can be reduced to sub-20-µm thickness by regulating the entanglement networks of PTFE.

High-precision extracellular-vesicle isolation-analysis integrated platform for rapid cancer diagnosis directly from blood plasma.

Cancer-derived small extracellular vesicles (sEVs) in body fluids hold promise as biomarkers for cancer diagnosis. For sEV-based liquid biopsy, isolation of sEVs with a high-purity and cancer-sEV detection with an extremely high sensitivity are essential because body fluids include much higher density of normal-cell-derived sEVs and other biomolecules and bioparticles. Here, we propose an isolation-analysis-integrated cancer-diagnosis platform based on dielectrophoresis(DEP)-ELISA technique which enables a three orders of magnitude higher sensitivity over conventional ELISA method and direct cancer diagnosis from blood plasma with high accuracy.

For a clinical application of optical triangulation to assess respiratory rate using an RGB camera and a line laser.

This paper presents a non-contact and unrestrained respiration monitoring system based on the optical triangulation technique. The proposed system consists of a red-green-blue (RGB) camera and a line laser installed to face the frontal thorax of a human body. The underlying idea of the work is that the camera and line laser are mounted in opposite directions, unlike other research.

GloGen: PPG prompts for few-shot transfer learning in blood pressure estimation.

With the rapid advancements in machine learning, its applications in the medical field have garnered increasing interest, particularly in non-invasive health monitoring methods. Blood pressure (BP) estimation using Photoplethysmogram (PPG) signals presents a promising opportunity for real-time, continuous monitoring. However, existing models often struggle with generalization, especially for high-risk groups like hypotension and hypertension, where precise predictions are crucial.

Dynamically reconfigurable shape-morphing and tactile display via hydraulically coupled mergeable and splittable PVC gel actuator.

Shape-morphing displays alter their surface geometry to convey information through three-dimensional shapes. However, rapid transformation into seamless shapes with multimodal tactile sensations poses challenges. Here, we introduce a versatile soft shape-morphing and tactile display, using a novel actuator that combines a PVC gel composite, dielectric liquid, and an electrode array.

Minimal-gain-printed silicon nanolaser.

While there have been notable advancements in Si-based optical integration, achieving compact and efficient continuous-wave (CW) III-V semiconductor nanolasers on Si at room temperature remains a substantial challenge. This study presents an innovative approach: the on-demand minimal-gain-printed Si nanolaser. By using a carefully designed minimal III-V optical gain structure and a precise on-demand gain-printing technique, we achieve lasing operation with superior spectral stability under pulsed conditions and observe a strong signature of CW operation at room temperature.

Composite Ensemble Learning Framework for Passive Drone Radio Frequency Fingerprinting in Sixth-Generation Networks.

The rapid evolution of drone technology has introduced unprecedented challenges in security, particularly concerning the threat of unconventional drone and swarm attacks. In order to deal with threats, drones need to be classified by intercepting their Radio Frequency (RF) signals. With the arrival of Sixth Generation (6G) networks, it is required to develop sophisticated methods to properly categorize drone signals in order to achieve optimal resource sharing, high-security levels, and mobility management.

LSPR-susceptible metasurface platform for spectrometer-less and AI-empowered diagnostic biomolecule detection.

In response to the growing demand for biomolecular diagnostics, metasurface (MS) platforms based on high-Q resonators have demonstrated their capability to detect analytes with smart data processing and image analysis technologies. However, high-Q resonator meta-atom arrays are highly sensitive to the fabrication process and chemical surface functionalization. Thus, spectrum scanning systems are required to monitor the resonant wavelength changes at every step, from fabrication to practical sensing.

Resting-state frontal electroencephalography (EEG) biomarkers for detecting the severity of chronic neuropathic pain.

Increasing evidence is present to enable pain measurement by using frontal channel EEG-based signals with spectral analysis and phase-amplitude coupling. To identify frontal channel EEG-based biomarkers for quantifying pain severity, we investigated band-power features to more complex features and employed various machine learning algorithms to assess the viability of these features. We utilized a public EEG dataset obtained from 36 patients with chronic pain during an eyes-open resting state and performed correlation analysis between clinically labelled pain scores and EEG features from Fp1 and Fp2 channels (EEG band-powers, phase-amplitude couplings (PAC), and its asymmetry features).

Well-Tempered Medical Prompt Engineering for Explainable Extubation.

This study investigated whether the large language model (LLM) utilizes sufficient domain knowledge to reason about critical medical events such as extubation. In detail, we tested whether the LLM accurately comprehends given tabular data and variable importance and whether it can be used in complement to existing ML models such as XGBoost.

MuDE: Multi-agent decomposed reward-based exploration.

In cooperative multi-agent reinforcement learning, agents jointly optimize a centralized value function based on the rewards shared by all agents and learn decentralized policies through value function decomposition. Although such a learning framework is considered effective, estimating individual contribution from the rewards, which is essential for learning highly cooperative behaviors, is difficult. In addition, it becomes more challenging when reinforcement and punishment, help in increasing or decreasing the specific behaviors of agents, coexist because the processes of maximizing reinforcement and minimizing punishment can often conflict in practice.