• Proceedings of the KIEE Conference
• /
• 2004.11c
• /
• pp.190-192
• /
• 2004

In this paper, we propose a low bit-rate embedded video compression scheme with 3-D block partition coding in the wavelet domain. The proposed video compression scheme includes multi-level 3-dimensional dyadic wavelet decomposition, raster scanning within each subband, formation of block, 3-D partitioning of block, and adaptive arithmetic entropy coding. Although the proposed video compression scheme is quit simple, it produces bit-stream with good features, including SNR scalability from the embedded nature. Experimental results demonstrate that the proposed video compression scheme is quit competitive to other good wavelet-based video coders in the literature.

• Journal of Korea Multimedia Society
• /
• v.14 no.1
• /
• pp.94-102
• /
• 2011

To alleviate the size and bandwidth requirement in JPEG2000 system, a new Embedded Compression(EC) algorithm with minor image quality drop is proposed. For both random accessibility and low latency, very simple and efficient hadamard transform based compression algorithm is devised. We reduced LL intermediate memory and code-block memory to about half size and achieved significant memory bandwidth reductions(about 52~73%) through proposed multi-mode algorithms, without requiring any modification in JPEG2000 standard algorithm.

• The Journal of Korea Robotics Society
• /
• v.17 no.2
• /
• pp.133-141
• /
• 2022

This paper introduces model compression algorithms which make a deep neural network smaller and faster for embedded systems. The model compression algorithms can be largely categorized into pruning, quantization and knowledge distillation. In this study, gradual pruning, quantization aware training, and knowledge distillation which learns the activation boundary in the hidden layer of the teacher neural network are integrated. As a large deep neural network is compressed and accelerated by these algorithms, embedded computing boards can run the deep neural network much faster with less memory usage while preserving the reasonable accuracy. To evaluate the performance of the compressed neural networks, we evaluate the size, latency and accuracy of the deep neural network, DenseNet201, for image classification with CIFAR-10 dataset on the NVIDIA Jetson Xavier.

• The KIPS Transactions:PartA
• /
• v.9A no.4
• /
• pp.405-412
• /
• 2002

The embedded system has less fast CPU and lower memory than PC(personal Computer) or Workstation system. Therefore embedded operating is system is designed to efficiently use the limited resource in the system. Virtual memory management or the embedded linux have a low efficiency when page fault is occurred to get a data from I/O device. Because a data is moving from the swap device to main memory. This paper suggests virtual memory compression algorithm for improving in virtual memory management and capacity of space. In this paper, we present a way to performance implement a virtual memory compression system that achieves significant improvement for the embedded system.

• Advances in nano research
• /
• v.9 no.2
• /
• pp.69-82
• /
• 2020

In this paper, a new explicit analytical formula is derived for the critical buckling load of Double Walled Carbon Nanotubes (DWCNTs) embedded in Winkler elastic medium without taking into account the effects of the nonlocal parameter, which indicates the effects of the surrounding elastic matrix combined with the intertube Van der Waals (VdW) forces. Furthermore, we present a model which predicts that the critical axial buckling load embedded in Winkler, Pasternak or Kerr elastic medium under axial compression using the nonlocal Donnell shell theory, this model takes into account the effects of internal small length scale and the VdW interactions between the inner and outer nanotubes. The present model predicts that the critical axial buckling load of embedded DWCNTs is greater than that without medium under identical conditions and parameters. We can conclude that the embedded DWCNTs are less susceptible to axial buckling than those without medium.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.15 no.5
• /
• pp.205-214
• /
• 2020

With the recent development of hardware and software technology, interest in the development of wearable devices is increasing. In particular, wearable devices require algorithms suitable for low-power and low-capacity embedded devices. Among them, there is an increasing demand for a signal compression algorithm that reduces communication overhead, in order to increase the efficiency of storage and transmission of electrocardiogram (ECG) signals requiring long-time measurement. Because normal beats occupy most of the signal with similar shapes, a high rate of signal compression is possible if normal beats are represented by a template. In this paper, we propose an algorithm for determining the normal beat template using the template cluster and Pearson similarity. Also, the template is expressed effectively as a few vertices through linear approximation algorithm. In experiment of Datum 234 of MIT-BIH arrhythmia database (MIT-BIH ADB) provided by Physionet, a compression ratio was 33.44:1, and an average distribution of root mean square error (RMSE) was 1.55%.

• The KIPS Transactions:PartA
• /
• v.15A no.5
• /
• pp.269-274
• /
• 2008

Recently, lots of embedded processors which can run streaming multimedia with high resolution display are introduced. Among the applications running on these embedded processors, real-time audio streaming is one of the applications that suffer from the lack of energy and memory space. In this paper, we propose a novel data compression method on scratch-pad memory, which saves both useful space on the scratch-pad memory and energy. We have implemented the data compression scheme on the GDM1202 real-time audio streaming processor, and the performance results show that we obtained 13.3% energy saving while maintaining comparable application performance to that of the non-compression case.

• The KIPS Transactions:PartB
• /
• v.9B no.1
• /
• pp.83-90
• /
• 2002

In this work, an improved method of EZW is suggested for efficient compression and transmission of image data. Here, coding efficiency is accomplished by embedded coding of significant coefficients using lower-level insignificant coefficients, and coding time is decreased by pre-coding of lower-level coefficients in coefficient detection. In simulation of designed architecture, the performance improvement of 1dB PSNR is confirmed compared with the results by the original En method.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.7 no.3
• /
• pp.157-162
• /
• 2012

In this paper, we propose a flight data storing system for effective data processing. Since the flight data contains critical information and their sizes are vast, encryption and compression would be needed to manage the flight data in effect. And we implemented the flight data storing system using an embedded board with DSP based on DPCM compression and AES encryption. Especially, we applied the reordering technique to advance the security function. From the simulations for two type data of voice and avionics, we found the developed system is well performed.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.18 no.1
• /
• pp.1-7
• /
• 2023

In this paper, we implement a lossless compression technique for time-series data generated by IoT (Internet of Things) devices to reduce the disk spaces. The proposed compression technique reduces the size of the encoded data by selectively applying CNN (Convolutional Neural Networks) or Delta encoding depending on the situation in the Forecasting algorithm that performs prediction on time series data. In addition, the proposed technique sequentially performs zigzag encoding, splitting, and bit packing to increase the compression ratio. We showed that the proposed compression method has a compression ratio of up to 1.60 for the original data.