• Journal of Computing Science and Engineering
• /
• v.11 no.4
• /
• pp.121-129
• /
• 2017

Feature selection has been widely established as an efficient technique for microarray data analysis. Feature selection aims to search for the most important feature/gene subset of a given dataset according to its relevance to the current target. Unsupervised feature selection is considered to be challenging due to the lack of label information. In this paper, we propose a novel method for unsupervised feature selection, which incorporates embedded learning and $l_{2,1}-norm$ sparse regression into a framework to select genes in microarray data analysis. Local tangent space alignment is applied during embedded learning to preserve the local data structure. The $l_{2,1}-norm$ sparse regression acts as a constraint to aid in learning the gene weights correlatively, by which the proposed method optimizes for selecting the informative genes which better capture the interesting natural classes of samples. We provide an effective algorithm to solve the optimization problem in our method. Finally, to validate the efficacy of the proposed method, we evaluate the proposed method on real microarray gene expression datasets. The experimental results demonstrate that the proposed method obtains quite promising performance.

• Journal of the Korea Computer Industry Society
• /
• v.3 no.9
• /
• pp.1287-1294
• /
• 2002

The algorithm method for progressive image coding based on discrete wavelet transform presented in a paper. After discrete wavelet transform and extract edge information through edge detection, and then designed efficient coding method more then established embedded coding algorithm using expanded EZW algorithm. Generally, edges have a relatively higher influence on image reconstruction. Occurred DWT on image, and can classify significant coefficients and non-significant coefficients. Using property that edge part has appeared significant coefficient in the paper. Especially, we confirmed that higher frequency sub region on DWT image present homogenous direction property. And on embedded coding, which are effective and well-directed information have higher priority to image reconstruction on transmission. Therefore, our technique algorithm system perform better than that of the conventional method such as progressive image coding application.

• Journal of IKEEE
• /
• v.17 no.4
• /
• pp.564-569
• /
• 2013

The current embedded devices are growing rapidly in the multi-core, and these demand fast boot time. But method of previous boot uses core only one. The method includes parallel techniques and modification of CPU Frequency policy. Parallel methods, after analyzing the Android boot process with analysis tool, applied to location where a lot of CPU operation. CPU Frequency policy is modified for high performance of core. The proposed method was applied to S5PV310 dual core and Exynos4412 quad core embedded system. As a result of the experiment, we found that the proposed method makes boot time fast about 20.71% and 31.34% in dual core and quad core environment as compared with the previous method.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.16 no.5
• /
• pp.165-172
• /
• 2016

This paper presents an implementation of a live audio streaming system using the Raspberry Pi 3 embedded computer. This system is a live streaming system not file-based streaming. This is a push streaming system which converts the incoming analog audio signal to digital samples and broadcasts them to multiple connected users concurrently. Since the server software is developed in Java language, it can be installed on any other embedded computers without any modification. We concluded that ESCatcher can service live streaming about 60 users concurrently through calculations and experiments, And also we achieved the delay time of a little bit more than 40ms between arrival of audio source and play on the android device.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.9
• /
• pp.1-8
• /
• 2023

This paper presents the control strategy of Auto-leveling equipment (ALE) of Multi-function radar (MFR) for vehicle using Embedded System. MFR implements surveillance patrol missions such as surface-to-air missiles and fighters with constant rotation. ALE consists of 4 Auto-leveling modules (ALM) and retains the stability with maintaining level. The gradient of vehicle can be measured and controlled by embedded systems. This paper contributes for improvement the system design with the ALM 1 set modeling. The validity of the modeling is verified using MATLAB/Simulink.

• Proceedings of the Korean Information Science Society Conference
• /
• 2010.06a
• /
• pp.119-120
• /
• 2010

• Journal of Computing Science and Engineering
• /
• v.6 no.2
• /
• pp.79-88
• /
• 2012

Power continues to be a driving force in central processing units (CPU) design. Most of the advanced breakthroughs in power have been in a realm that is applicable to workstation CPUs. Advanced power management systems will manage temperature, dynamic voltage scaling and dynamic frequency scaling in a CPU. The use of power management systems for microcontrollers and embedded CPUs has been modest, and mostly focuses on very large scale integration (VLSI) level optimizations compared to system level optimizations. In this paper, a dynamic frequency controlling (DFC) technique is introduced, to lay the foundation of a system level power management system for commercial microcontrollers. The DFC technique allows a commercial microcontroller to have minor modifications on both the hardware and software side, to allow the clock frequency to change to save power; results in this study show a 10% savings. By adding an additional layer of software abstraction at the interrupt level, the microcontroller can operate without having knowledge of the current clock frequency, and this can be accomplished without having to use an embedded operating system.

• Journal of Positioning, Navigation, and Timing
• /
• v.9 no.3
• /
• pp.273-284
• /
• 2020

The performance of Global Navigation Satellite System (GNSS) chipset and Inertial Measurement Unit (IMU) sensors embedded in smartphones for location-based services (LBS) is limited due to the economic reasons for their mass production. Therefore, it is necessary to efficiently process the output data of the smartphone's embedded sensors in order to derive the optimum navigation values and, as a previous step, output performance of smartphone embedded sensors needs to be verified. This paper analyzes the navigation performance of such devices by processing the raw measurements data output from smartphones. For this, up-to-dated versions of smartphones provided by Samsung (Galaxy s10e) and Xiaomi (Mi 8) are used in the test experiment to compare their performances and characteristics. The GNSS and IMU data are extracted and saved by using an open market application software (Geo++ RINEX Logger & Mobile MATLAB), and then analyzed in post-processing manner. For GNSS chipset, data is extracted from static environments and verified the position, Carrier-to-Noise (C/N₀), Radio Frequency Interference (RFI) performance. For IMU sensor, the validity of navigation and various location-based-services is predicted by extracting, storing and analyzing data in static and dynamic environments.

• JSTS:Journal of Semiconductor Technology and Science
• /
• v.11 no.4
• /
• pp.295-301
• /
• 2011

A triple-band transceiver module for 2.3/2.5/3.5 GHz mobile WiMAX, IEEE 802.16e, applications is introduced. The suggested transceiver module consists of RFIC, reconfigurable/multi-resonance MIMO antenna, embedded PCB, mobile WiMAX base band, memory and channel selection front-end module. The RFIC is fabricated in $0.13{\mu}m$ RF CMOS process and has 3.5 dB noise figure(NF) of receiver and 1 dBm maximum power of transmitter with 68-pin QFN package, $8{\times}8\;mm^2$ area. The area reduction of transceiver module is achieved by using embedded PCB which decreases area by 9% of the area of transceiver module with normal PCB. The developed triple-band mobile WiMAX transceiver module is tested by performing radio conformance test(RCT) and measuring carrier to interference plus noise ratio (CINR) and received signal strength indication (RSSI) in each 2.3/2.5/3.5 GHz frequency.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.18 no.3
• /
• pp.89-100
• /
• 2023

Recently, on-device artificial intelligence (AI) solutions using mobile devices and embedded edge devices have emerged in various fields, such as computer vision, to address network traffic burdens, low-energy operations, and security problems. Although vision transformer deep learning models have outperformed conventional convolutional neural network (CNN) models in computer vision, they require more computations and parameters than CNN models. Thus, they are not directly applicable to embedded edge devices with limited hardware resources. Many researchers have proposed various model compression methods or lightweight architectures for vision transformers; however, there are only a few studies evaluating the effects of model compression techniques of vision transformers on performance. Regarding this problem, this paper presents a performance evaluation of vision transformers on embedded platforms. We investigated the behaviors of three vision transformers: DeiT, LeViT, and MobileViT. Each model performance was evaluated by accuracy and inference time on edge devices using the ImageNet dataset. We assessed the effects of the quantization method applied to the models on latency enhancement and accuracy degradation by profiling the proportion of response time occupied by major operations. In addition, we evaluated the performance of each model on GPU and EdgeTPU-based edge devices. In our experimental results, LeViT showed the best performance in CPU-based edge devices, and DeiT-small showed the highest performance improvement in GPU-based edge devices. In addition, only MobileViT models showed performance improvement on EdgeTPU. Summarizing the analysis results through profiling, the degree of performance improvement of each vision transformer model was highly dependent on the proportion of parts that could be optimized in the target edge device. In summary, to apply vision transformers to on-device AI solutions, either proper operation composition and optimizations specific to target edge devices must be considered.