http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Lightweight CNN based Meter Digit Recognition
( Akshay Kumar Sharma ),( Kyung Ki Kim ) 한국센서학회 2021 센서학회지 Vol.30 No.1
Image processing is one of the major techniques that are used for computer vision. Nowadays, researchers are using machine learning and deep learning for the aforementioned task. In recent years, digit recognition tasks, i.e., automatic meter recognition approach using electric or water meters, have been studied several times. However, two major issues arise when we talk about previous studies: first, the use of the deep learning technique, which includes a large number of parameters that increase the computational cost and consume more power; and second, recent studies are limited to the detection of digits and not storing or providing detected digits to a database or mobile applications. This paper proposes a system that can detect the digital number of meter readings using a lightweight deep neural network (DNN) for low power consumption and send those digits to an Android mobile application in real-time to store them and make life easy. The proposed lightweight DNN is computationally inexpensive and exhibits accuracy similar to those of conventional DNNs.
Lightweight image classifier for CIFAR-10
( Akshay Kumar Sharma ),( Amrita Rana ),( Kyung Ki Kim ) 한국센서학회 2021 센서학회지 Vol.30 No.5
Image classification is one of the fundamental applications of computer vision. It enables a system to identify an object in an image. Recently, image classification applications have broadened their scope from computer applications to edge devices. The convolutional neural network (CNN) is the main class of deep learning neural networks that are widely used in computer tasks, and it delivers high accuracy. However, CNN algorithms use a large number of parameters and incur high computational costs, which hinder their implementation in edge hardware devices. To address this issue, this paper proposes a lightweight image classifier that provides good accuracy while using fewer parameters. The proposed image classifier diverts the input into three paths and utilizes different scales of receptive fields to extract more feature maps while using fewer parameters at the time of training. This results in the development of a model of small size. This model is tested on the CIFAR-10 dataset and achieves an accuracy of 90% using .26M parameters. This is better than the state-of-the-art models, and it can be implemented on edge devices.
Real -Time ECG Signal Acquisition and Processing Using LabVIEW
( Akshay Kumar Sharma ),( Kyung Ki Kim ) 한국센서학회 2020 센서학회지 Vol.29 No.3
The incidences of cardiovascular diseases are rapidly increasing worldwide. The electrocardiogram (ECG) is a test to detect and monitor heart issues via electric signals in the heart. Presently, detecting heart disease in real time is not only possible but also easy using the myDAQ data acquisition device and LabVIEW. Hence, this paper proposes a system that can acquire ECG signals in real time, as well as detect heart abnormalities, and through light-emitting diodes (LEDs) it can simultaneously reveal whether a particular waveform is in range or otherwise. The main hardware components used in the system are the myDAQ device, Vernier adapter, and ECG sensor, which are connected to ECG monitoring electrodes for data acquisition from the human body, while further processing is accomplished using the LabVIEW software. In the Results section, the proposed system is compared with some other studies based on the features detected. This system is tested on 10 randomly selected people, and the results are presented in the Simulation Results section.
Kumar Akshay,Vij Ankush,Huh Seok Hwan,Kim Jong-Woo,Sharma Mohit K.,Kumari Kavita,Yadav Naveen,Akram Fazli,구본흔 한국물리학회 2023 Current Applied Physics Vol.49 No.-
We investigated the influence of structural disorders on the magnetic and magnetocaloric (MC) properties upon A-site rare-earth substitution in A1.4Sr1.6Mn2O7 (A = La, Pr, Nd) Ruddlesden-Popper (R–P) compounds. The samples were produced through the solid-state method, and the structural analysis indicated formation of R–P phase with the Jahn-Teller distortion parameter varying from highest in La1.4Sr1.6Mn2O7 (LSMO) to Nd1.4Sr1.6Mn2O7 (NSMO) and followed by Pr1.4Sr1.6Mn2O7 (PSMO). Hence, the magnetization value was increased in LSMO sample implying an enhanced interbilayer and interlayer spin correlations. It resulted in a high value of MC parameters like temperature average entropy change (TEC) and relative cooling power (RCP) of 4.21 J/kgK and 87 J/kg for LSMO, while lowest value of 0.53 J/kgK and 27 J/kg for PSMO respectively, at 2.5 T field. The room temperature MC response in PSMO, whereas a large TEC in LSMO and NSMO compounds advocate their candidacy in broad range of refrigeration applications.
Effect of hydrazine on structural, morphological and magnetic properties of SmCo-Co nanocomposites
Kumari Kavita,Kumar Akshay,Park Su-Jeong,Sharma Mohit K.,Yadav Naveen,Kumar Manish,Kumar Shalendra,Huh Seok-Hwan,Kim Jong-Woo,Koo Bon-Heun 한국물리학회 2023 Current Applied Physics Vol.53 No.-
In the present work, one-dimensional (1-D) SmCo-Co magnetic nanocomposites are prepared in a single-pot chemical synthesis in the presence of external magnetic field with varying amounts of hydrazine hydrate with samples named as: SC-2 mL, SC-4 mL, SC-6 mL and SC-8 mL. The Rietveld refinement of XRD patterns revealed the formation of Sm2Co17 (P63/mmc), Sm(OH)3 (P63/m) and hcp-Co (P63/mmc) phases. The 1-D nanocomposites are found to possess the highest aspect ratio (~6.3), lowest crystallite size (~49 nm) and highest developed strain (~4.76 x 10-3) corresponding to SC-4 mL. The magnetic response of the samples is found to be affected by the hydrazine amount showing highest saturation magnetization (~156 emu/g) and effective magnetic anisotropy (~1.2 x 106 erg/cm3) for SC-4 mL with highest exchange coupling observed using Bloch law fitting. The results indicate suppressing behaviour of hydrazine amount to be utilized up to a certain limit.