A wearable neuro-feedback system is proposed with a low-power SoC (NFS), which supports mental status monitoring electroencephalography (EEG) and transcranial electrical stimulation (tES) for neuro-modulation. Self-configured independent component analysis (ICA) implemented to accelerate source separation at low power. Moreover, an embedded support vector machine (SVM) enables online classification, configuring the ICA accelerator adaptively depending on types of decomposed components. Owing...

Bladder volume assessments are crucial for managing urinary disorders. Ultrasound imaging (US) is a preferred noninvasive, cost-effective modality bladder observation and measurements. However, the high operator dependency of US major challenge due to difficulty in evaluating ultrasound images without professional expertise. To address this issue, image-based automatic estimation methods have been introduced, but most conventional require high-complexity computing resources that not...

The wearable mental-health monitoring platform is proposed for mobile mental healthcare system. headband type of 50g and consumes 1.1mW. For the health two specific functions (independent component analysis (ICA) nonlinear chaotic (NCA)) are implemented into CMOS integrated circuits. ICA extracts heart rate variability (HRV) from EEG, then NCA largest lyapunov exponent (LLE) as physiological marker to identify stress states. extracted HRV only 1.84% different obtained by simple ECG...

A compact electro-acupuncture (EA) system is proposed for a multi-modal feedback EA treatment. It composed of needle, patch, and an interconnecting conductive thread. The 3 cm diameter patch implemented with adaptive stimulator IC small coin battery on the planar-fashionable circuit board (P-FCB) technology. can form closed current loop even single measure electromyography (EMG) skin temperature to analyze stimulation status as well supply programmable (40 μA-1 mA) 5 different modes. large...

A system control technique (changing the interaction mode) is needed to provide various spatial techniques for virtual, augmented and mixed reality (VR/AR/MR) applications. We propose HandPoseMenu, a hand posture-based virtual menus in 3D space. HandPoseMenu recognizes non-dominant hand's posture using depth sensor that attached wearable display presents menu corresponding beside hand. When user selects desired function among presented as dominant hand, mode changes. The combination of two...

Inspecting the sealing integrity of lead tabs is an important means ensuring reliability and safety pouch-type lithium-ion (Li-ion) batteries with a thin multi-layered aluminum (Al) laminated film. This paper presents new air-coupled ultrasonic non-destructive testing (NDT) inspection method based on leaky Lamb wave transmission; reception for evaluating between tab Al pouch The proposed uses critical incidence angle air layer fastest velocity to maximize signal-to-noise ratio in...

Kidney volume is associated with renal function and the severity of diseases, thus accurate assessment kidney important. Although voxel count method reported to be more than several methods, its laborious time-consuming process considered as a main limitation. In need new technology that fast manual method, aim this study was develop first deep learning model for automatic detection estimation from computed tomography (CT) images dogs. A total 182,974 image slices 386 CT scans 211 dogs were...

Introduction Spondylosis deformans is a non-inflammatory osteophytic reaction that develops to re-establish the stability of weakened joints between intervertebral discs. However, assessing these changes using radiography subjective and difficult. In human medicine, attempts have been made use artificial intelligence accurately diagnose difficult ambiguous diseases in medical imaging. Deep learning, form intelligence, most commonly used imaging data analysis. It technique utilizes neural...

Recently, mental diseases have been successfully treated by neuro-feedback therapy based on Quantitative EEG (QEEG) and Event Related Potential (ERP) online data measurements. The U.S. Food Drug Administration (FDA) approved the first test for diagnosing attention deficit hyperactivity disorder (ADHD) in 2013 [1]. signals are measured an cap analyzed a high performance computer to extract not only power at predetermined frequency site combinations, but also degree of coherence between all...

For live television broadcast such as the educational program for children conducted through viewer participation, smooth integration of virtual contents and interaction between casts them are quite important issues. Recently there have been many attempts to make aggressive use interactive in due advancement AR/VR technology studio technology. These previous works limitations that do not support real-time 3D space recognition or immersive interaction. In this sense, we propose an augmented...

This paper proposes the postcard system which recognizes a card using camera within device (PC/Smart TV/Tablet PC) and augments video of sender fit to size. The postcards or picture cards used in our work are trained advance. proposed consists two parts, management module augmented reality module. manages playable videos makes ID as link between card. data is mentioned above estimates also its three-dimensional position. sent get according After that, synthesizes position As result, shows...

Many television shows have been produced that synthesize virtual objects or make use of interactions between cast members and objects. Recently, many attempts made to apply augmented reality (AR) technology the production interactive broadcast content using special effects, even during a live broadcast. In this study, we present ARStudio, an AR-based broadcasting system can transmit by synthesizing them in real time 3D structure set space recognized multiple cameras. Also, introduce new...

Intervertebral disc disease is the most common spinal cord-related in dogs, caused by material protrusion or extrusion that compresses cord, leading to clinical symptoms. Diagnosis involves identifying radiographic signs such as intervertebral space narrowing, increased opacity of foramen, spondylosis deformans, and magnetic resonance imaging findings like cord compression lesions, alongside symptoms neurological examination findings. narrowing on radiographs finding extrusion. This study...

Background Among high-income countries, South Korea has a considerable tuberculosis (TB) burden; North one of the highest TB burdens in world. Predicting impact control strategies on burden can help to efficiently implement programmes. Methods We designed deterministic compartmental model Korea. After calibration with notification incidence data from Korea, for 2040 was predicted according four different intervention strategies: latent infection (LTBI) treatment, rapid diagnosis, active...

As embedded systems, such as smartphones with limited resources, have become increasingly popular, active research has recently been conducted on performing on-device deep learning in systems. Therefore, this study, we propose a framework that is specialized for systems the operation processing structure of which differs from standard PCs. The proposed supports an OpenCL-based accelerator engine operations various Moreover, parallel performance OpenCL maximized through kernel optimized GPUs,...

Ultrasound assessment of fetal biometry is widely used for gestational age prediction and abnormal growth diagnosis. However, manual biometric measurements require time-consuming procedures, while automated measurement methods remain challenging in terms accuracy hardware complexity. This paper proposes a system-on-chip (SoC) solution automatic based on deep learning. For end-to-end measurements, hardware-friendly bilateral segmentation network (H-BiSeNet) was designed optimized multiple...

Plane wave imaging (PWI) in medical ultrasound is becoming an important reconstruction method with high frame rates and new clinical applications. Recently, single PWI based on deep learning (DL) has been studied to overcome lowered of traditional multiple PW transmissions. However, due the lack appropriate ground truth images, DL-based still remains challenging for performance improvements. To address this issue, paper, we propose a unsupervised approach, i.e., coherence (DCL)-based DL...

An interactive bulletin board is a system for interchanging information between public screen and mobile device. Nowadays, there are many studies on interactions different devices such as Microsoft Surface smart board.For an board, we propose marker detection method that relies the camera of Our proposed system, which has some advantages over other works, needs no particular hardware, projector, touch screen, or special camera. Moreover, whole process can be simply performed with actions...

자율주행 차량의 기술이 발전함에 따라 차량 운전자 및 탑승자의 역할이 적어지고, 인포테인먼트 서비스 콘텐츠의 수요가 증가하고 있다. 그에 기존의 방법을 벗어나 내부의 디스플레이를 통해 정보를 차량에 증강하여 탑승자에서 전달하는 기술은 차량에서 중요한 요소가 되었다. 증강현실 가이드의 경우 지면의 2차원 기반으로 입력 영상에 가상 객체를 오버레이 하는 사용하여 단순 정보 전달은 가능하나 탑승자와 주변 환경과의 상호작용 3차원 객체의 실 객체 가림 현상을 처리하는 것은 제약이 있었다. 본 논문에서는 이러한 문제를 극복하기 위하여 정밀 2D 맵을 공간을 생성하고 실감가이드를 제공하는 시스템을 구축하였다. 제안하는 시스템은 실제 환경의 테스트 베드 내에서 내에 설치한 투명 활용하여 탑승자가 환경과 인터랙티브한 체험하는 실증서비스를 검증하였다.