Výsledky vyhledávání

Akademický článek

Adaptive Scaling Filter Pruning Method for Vision Networks With Embedded Devices

Autor: Hyunjun Ko, Jin-Ku Kang, Yongwoo Kim

Publikováno v: IEEE Access, Vol 12, Pp 123771-123781 (2024)

Owing to improvements in computing power, deep learning technology using convolutional neural networks (CNNs) has recently been used in various fields. However, using CNNs on edge devices is challenging because of the large computation required to ac

Externí odkaz: https://doaj.org/article/63cfae2d75234feca5dd66f837b0d494

Zobrazit plný text záznamu

Akademický článek

A ±0.48°C (3σ) Inaccuracy BJT-Based Temperature Sensor With 241 μs Conversion Time for Display Driver IC in 40 nm CMOS

Autor: Yong-Sung Ahn, Jeong-Mi Park, Jin-Ku Kang, Jaehoon Jun

Publikováno v: IEEE Access, Vol 11, Pp 132843-132851 (2023)

This paper describes a fast BJT-based temperature sensor with ±0.48°C inaccuracy embedded in a display driver integrated circuit (DDIC) for detecting the temperature of a display module. It utilizes the base-emitter voltage difference between two B

Externí odkaz: https://doaj.org/article/b822b0fa6b0543fdaf12a7da9523f0e3

Zobrazit plný text záznamu

Akademický článek

A Low-Cost Fully Integer-Based CNN Accelerator on FPGA for Real-Time Traffic Sign Recognition

Autor: Jaemyung Kim, Jin-Ku Kang, Yongwoo Kim

Publikováno v: IEEE Access, Vol 10, Pp 84626-84634 (2022)

Traffic sign recognition (TSR) technology allows the vehicle to recognize road signs through a camera and use it for driving. For traffic safety, TSR is one of the core technologies constituting advanced driver assistance systems (ADAS), and several

Externí odkaz: https://doaj.org/article/b568c0e30ffe47b38b863171dd455b2f

Zobrazit plný text záznamu

Akademický článek

An Overhead-Reduced Key Coding Technique for High-Speed Serial Interface

Autor: Jaepil Bak, Taek-Joon An, Youngwoo Kim, Jin-Ku Kang

Publikováno v: IEEE Access, Vol 10, Pp 21187-21192 (2022)

This paper describes a packet-based overhead-reduced (OR) key coding technique for a high-speed serial interface. The 8B10B code is a de facto standard coding technique in the application but its bit-overhead is 25%. The proposed key coding technique

Externí odkaz: https://doaj.org/article/311d13d87fbe4ea9b2b5fc302a4a5fa7

Zobrazit plný text záznamu

Akademický článek

Target Capacity Filter Pruning Method for Optimized Inference Time Based on YOLOv5 in Embedded Systems

Autor: Jihun Jeon, Jaemyung Kim, Jin-Ku Kang, Sungtae Moon, Yongwoo Kim

Publikováno v: IEEE Access, Vol 10, Pp 70840-70849 (2022)

Recently, convolutional neural networks (CNNs), which exhibit excellent performance in the field of computer vision, have been in the spotlight. However, as the networks become wider for higher accuracy, the number of parameters and the computational

Externí odkaz: https://doaj.org/article/22d11f616efe4e8fa33d0e359d30c3aa

Zobrazit plný text záznamu

Akademický článek

A Resource Efficient Integer-Arithmetic-Only FPGA-Based CNN Accelerator for Real-Time Facial Emotion Recognition

Autor: Jaemyung Kim, Jin-Ku Kang, Yongwoo Kim

Publikováno v: IEEE Access, Vol 9, Pp 104367-104381 (2021)

Recently, many researches have been conducted on recognition of facial emotion using convolutional neural networks (CNNs), which show excellent performance in computer vision. To obtain a high classification accuracy, a CNN architecture with many par

Externí odkaz: https://doaj.org/article/48a475eb754348ceb900caa1fe484ac7

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání