Earticle

모델 인버전은 원본 학습 데이터 없이, 사전 학습된 모델로부터 반복적인 최적화를 통해 합성 입력을 복원하는 데이 터 없는 학습에서 널리 사용되는 기법이다. 그러나 최신 비전 트랜스포머에 이를 적용할 경우, 고비용의 셀프 어텐 션 메커니즘으로 인해 큰 계산적 부담이 발생하게 된다. 이를 중요하지 않은 패치들을 모두 제거함으로써 효율성을 향상시키는 희소 모델 인버전이 제안되었다. 하지만 데이터가 없는 상황에서 검증 데이터의 부재로 인한 학습 불안 정성의 증폭은 여전히 해결해야 할 문제로 남아 있다. 검증 데이터가 없는 환경에서는 모델의 정확도가 불확실해지 고, 변동성이 커지므로, 모델의 강건성 향상이 필수적이다. 본 논문에서는 데이터 없는 환경에서 생성되는 이미지의 품질과 다양성을 일관되게 유지하여, 정확도에 대한 표준편차를 낮추고 강건성을 향상시키는 방법을 제안한다. 제안 한 Adaptive AEM은 패치 제거 이후의 중요도를 재조정해 엔트로피 최소화를 촉진시킨다. 실험 결과, 제안한 방법 으로 생성된 이미지를 사용하면 이전 방법론에 비해 데이터 없는 양자화에서는 최대 72%, 데이터 없는 지식 증류 에서는 최대 49%까지 정확도의 표준편차를 줄여 모델을 강건하게 만들 수 있음을 입증한다.

Model inversion is a widely used technique in data-free learning, where synthetic inputs are reconstructed from a pretrained model through iterative optimization without access to the original training data. However, when applied to modern Vision Transformers, the high computational cost of the self-attention mechanism poses a significant challenge. Sparse Model Inversion (SMI) has been proposed to improve efficiency by removing non-essential patches. Nevertheless, in the absence of real validation data, the instability of training remains an unresolved issue, as model accuracy becomes uncertain and exhibits high variance. To address this, we propose a method that consistently preserves the quality and diversity of generated images in data-free environments, thereby reducing the standard deviation of accuracy and enhancing model robustness. The proposed Adaptive AEM readjusts the importance after patch removal to promote entropy minimization. Experimental results demonstrate that using images generated by our method reduces the standard deviation of accuracy by up to 72% in data-free quantization and up to 49% in data-free knowledge distillation, compared to previous approaches, leading to significantly more robust models.

In this paper, we propose a new method for generating convolution filters of a convolutional neural network (CNN) model as linear combinations of only a few basis filters that are provided as input features. In our approach, best coefficients of the linear combinations are searched (trained) with the given input basis filters (IBFs) to reconstruct the convolution filter parameters. Since all the convolution filters can be generated by the linear combinations of the IBFs, the size of a CNN model can be compressed if the number of coefficients for the linear combinations is less than that of filter parameters. Our primary goal is to investigate the possibility of expressing filters with a small set of IBFs by linear combinations. The second goal is to compress a model so that it can be beneficial when the model is distributed and stored (particularly downloaded to mobile devices through Wi-Fi).

최근 인간과 기계 간의 상호작용에 대한 연구가 활발히 이뤄지고 있으며, 언어에 담긴 정보뿐 아니라 음성에 내포된 감정을 인식하기 위해 딥러닝 모델이 적용되고 있다. 딥러닝을 활용한 음성언어 감정 인식 기술은 주로 모바일 및 IoT기기, 그리고 임베디드 시스템과 같은 제한된 컴퓨팅 자원 환경에 적용된다. 딥러닝 모델의 계층을 깊게 쌓아 정확도를 높일수록 그 연산량과 크기가 증가하기 때문에 제한된 컴퓨팅 자원으로 구동하는데 어려움이 발생한다. 본 논문에서는 가중치 가지치기와 가중치 군집화, 두 가지 기법을 각각 음성언어 감정 인식을 위한 딥러닝 모델에 적용하고 데스크탑 PC와 임베디드 시스템 환경에서 정확도와 추론 시간을 검증했다. 실험에 사용한 임베디드 보드는 NVIDIA사의 Jetson AGX Xavier이다. 가중치 가지치기 기법은 데스크탑 PC 환경에서 18.55%, 임베디드 보드 환경에서 17.84%, 가중치 군집화 기법은 데스크탑 PC 환경에서 15.32%, 임베디드 보드 환경에서 15.08%만큼 추론 시간을 개선했으며, 정확도는 두 기법 모두 기준 모델과 큰 차이가 없음을 확인하였다.

Purpose: The purpose of the study is to evaluate the distance and location of the rescuer to patient for the effective chest compressions qualities. Methods: The subjects were 42 students who earned the basic lifesaving technique and had informed consents to participate in the study from May 1 to 20 in 2013. The position of the rescuers included model-0(reference point), model-1(10 cm distance), model-2(20 cm distance), and model-kn(kneeling up). Results: The mean depth of compression was 50.6±6.6 mm in Model-0, 48.7±8.2 mm in Model-1, 44.2±10.4 mm in Model-2, and 51.8±6.0 mm in Model-kn. There were statistically significant differences between each Model(p<.001). Conclusion: The closer distance between rescuer and patient could provide more effective chest compressions. Kneeling on the bed stance provided the deeper chest compression consistently than the stool stance.

In this paper, a new approach is proposed to investigate the characteristics behavior of concrete under uniaxial and biaxial compression using the theory of plasticity. This approach is based on artificial neural networks (ANNs), especially radial basis function (RBF) in conjunction with the models of theory of plasticity. The main advantage of the proposed approach is to estimate the quality of the results with accuracy equivalent to the experiments. Another advantage of the proposed ANNs models are that it takes into account the uniaxial as well as the biaxial compression strain. The proposed models were evaluated against several experimental results available in the open literature for the behavior of the force and deformation of the two types of compression tests. Good agreement has been found between our models and those presented elsewhere.

Image compression-decompression methods have become increasingly crucial in modern times, facilitating the transfer of high-quality images while minimizing file size and internet traffic. Historically, early image compression relied on rudimentary codecs, aiming to compress and decompress data with minimal loss of image quality. Recently, a novel compression framework leveraging colorization techniques has emerged. These methods, originally developed for infusing grayscale images with color, have found application in image compression, leading to colorization-based coding. Within this framework, the encoder plays a crucial role in automatically extracting representative pixels—referred to as color seeds—and transmitting them to the decoder. The decoder, utilizing colorization methods, reconstructs color information for the remaining pixels based on the transmitted data. In this paper, we propose a novel approach to image compression, wherein we decompose the compression task into grayscale image compression and colorization tasks. Unlike conventional colorization-based coding, our method focuses on the colorization process rather than the extraction of color seeds. Moreover, we employ the Denoising Diffusion Null-Space Model (DDNM) for colorization, ensuring high-quality color restoration and contributing to superior compression rates. Experimental results demonstrate that our method achieves higher-quality decompressed images compared to standard JPEG and JPEG2000 compression schemes, particularly in high compression rate scenarios.

A new distributed algorithm of data ccompression based on hierarchical cluster model for sensor networks s proposed, the basic ideas of which are as follows, firstly the whole sensor network is mapped into a kind f hierarchical clusters model, and then different wavelet transform models are used to commit data ompression in inner and super clusters respectively, according to the relative regularity of sensor nodes eployed in the inner clusters, and the relative irregularity of sensor nodes deployed in super cluster. heoretical analyses and simulation results show that, the above new methods have good performance of pproximation, and can compress data and reduce the amount of data efficiently. So, it can prolong the ifetime of the whole sensor network to a greater degree.

딥 러닝의 발전으로 다양한 AI 기반의 응용이 많아지고, 그 모델의 규모도 매우 커지고 있다. 그러나 임베디드 기기와 같이 자원이 제한적인 환경에서는 모델의 적용이 어렵거나 전력 부족 등의 문제가 존재한다. 이를 해결하기 위해 서 클라우드 기술 또는 오프로딩 기술을 활용하거나, 모델의 매개변수 개수를 줄이거나 계산을 최적화하는 등의 경량화 방법이 제안되었다. 본 논문에서는 다양한 프레임워크들의 상호 교환 포맷으로 사용되고 있는 ONNX(개방형 신경망 교환 포맷) 포맷에 딥러닝 경량화 방법 중 학습된 모델의 양자화를 적용한다. 경량화 전 모델과의 신경망 구조와 추론 성능을 비교하고, 양자화를 위한 다양한 모듈 방식를 분석한다. 실험을 통해 ONNX의 양자화 결과, 정확도는 차이가 거의 없으며 기존 모델보다 매개변수 크기가 압축되었으며 추론 시간 또한 전보다 최적화되었음을 알 수 있었다.

Due to the development of deep learning and AI, the scale of the model has grown, and it has been integrated into other fields to blend into our lives. However, in environments with limited resources such as embedded devices, it is exist difficult to apply the model and problems such as power shortages. To solve this, lightweight methods such as clouding or offloading technologies, reducing the number of parameters in the model, or optimising calculations are proposed. In this paper, quantization of learned models is applied to ONNX models used in various framework interchange formats, neural network structure and inference performance are compared with existing models, and various module methods for quantization are analyzed. Experiments show that the size of weight parameter is compressed and the inference time is more optimized than before compared to the original model.

The compression of CAD models is a key technology for realizing Internet-based collaborative product development because big model sizes often prohibit us to achieve a rapid product information transmission. Although there exist some algorithms for compressing discrete CAD models, original precise CAD models are focused on in this paper. Here, the characteristics of hierarchical structures in CAD models and the distribution of their redundant data are exploited for developing a novel data encoding method. In the method, different encoding rules are applied to different types of data. Geometric data is a major concern for reducing model sizes. For geometric data, the control points of B-spline curves and surfaces are compressed with the second-order predictions in a local coordinate system. Based on analysis to the distortion induced by quantization, an efficient method for computation of the distortion is provided. The results indicate that the data size of CAD models can be decreased efficiently after compressed with the proposed method.

The present study investigated the role of ERK in the onset of mechanical and cold allodynia in a rat model of compression of the trigeminal ganglion by examining changes in the air-puff thresholds and number of scratches following the intracisternal injection of PD98059, a MEK inhibitor. Male Sprague Dawley rats weighing between 250 and 260 g were used. Under anesthesia, the rats were mounted onto a stereotaxic frame and received 4% agar ($10\;{\mu}l$) solution to compress the trigeminal ganglion. In the control group, the animals were given a sham operation without the application of agar. Changes in behavior were examined at 3 days before and at 3, 7, 10, 14, 17, 21, 24, 30, and 40 days after surgery. Compression of the trigeminal ganglion significantly decreased the air-puff thresholds. Mechanical allodynia was established within 3 days and persisted over postoperative day 24. To evaluate cold allodynia, nociceptive scratching behavior was monitored after acetone application on the vibrissa pad of the rats. Compression of the trigeminal ganglion was found to produce significant cold allodynia, which persisted for more than 40 days after surgery. On postoperative day 14, the intracisternal administration of $1\;{\mu}g$ or $10\;{\mu}g$ of PD98059 in the rat model significantly decreased the air-puff thresholds on both the ipsilateral and contralateral side. The intracisternal administration of $10\;{\mu}g$ of PD98059 also significantly alleviated the cold allodynia, compared with the vehicle-treated group. These results suggest that central ERK plays an important role in the development of mechanical and cold allodynia in rats with compression of the trigeminal ganglion and that a targeted blockade of this pathway is a potential future treatment strategy for trigeminal neuralgia-like nociception.

The present study investigated the role of ERK in the onset of mechanical and cold allodynia in a rat model of compression of the trigeminal ganglion by examining changes in the air-puff thresholds and number of scratches following the intracisternal injection of PD98059, a MEK inhibitor. Male Sprague Dawley rats weighing between 250 and 260 g were used. Under anesthesia, the rats were mounted onto a stereotaxic frame and received 4% agar (10 μl) solution to compress the trigeminal ganglion. In the control group, the animals were given a sham operation without the application of agar. Changes in behavior were examined at 3 days before and at 3, 7, 10, 14, 17, 21, 24, 30, and 40 days after surgery. Compression of the trigeminal ganglion significantly decreased the air-puff thresholds. Mechanical allodynia was established within 3 days and persisted over postoperative day 24. To evaluate cold allodynia, nociceptive scratching behavior was monitored after acetone application on the vibrissa pad of the rats. Compression of the trigeminal ganglion was found to produce significant cold allodynia,which persisted for more than 40 days after surgery. On postoperative day 14, the intracisternal administration of 1 μg or 10 μg of PD98059 in the rat model significantly decreased the air-puff thresholds on both the ipsilateral and contralateral side. The intracisternal administration of 10 μg of PD98059 also significantly alleviated the cold allodynia,compared with the vehicle-treated group. These results suggest that central ERK plays an important role in the development of mechanical and cold allodynia in rats with compression of the trigeminal ganglion and that a targeted blockade of this pathway is a potential future treatment strategy for trigeminal neuralgia-like nociception.

The beneficial effects of graduated compression stockings (GCS) in prophylaxis and treatment of venous disorders of human lower extremity have been recognized. However, their pressure functional performances are variable and unstable in practical applications, and the exact mechanisms of action remain controversial. Direct surface pressure measurements and indirect material properties testing are not enough for fully understanding the interaction between stocking and leg. A three dimensional (3D) biomechanical mathematical model for numerically simulating the interaction between leg and GCS in dynamic wear was developed based on the actual geometry of the female leg obtained from 3D reconstruction of MR images and the real size and mechanical properties of the compression stocking prototype. The biomechanical solid leg model consists of bones and soft tissues, and an orthotropic shell model is built for the stocking hose. The dynamic putting-on process is simulated by defining the contact of finite relative sliding between the two objects. The surface pressure magnitude and distribution along the different height levels of the leg and stress profiles of stockings were simulated. As well, their dynamic alterations with time processing were quantitatively analyzed. Through validation, the simulated results showed a reasonable agreement with the experimental measurements, and the simulated pressure gradient distribution from the ankle to the thigh (100:67:30) accorded with the advised criterion by the European committee for standardization. The developed model can be used to predict and visualize the dynamic pressure and stress performances exerted by compression stocking in wear, and to optimize the material mechanical properties in stocking design, thus, helping us understand mechanisms of compression action and improving medical functions of GCS.

온-디바이스 머신러닝은 비용 효율성, 데이터 프라이버시, 응답성 측면에서의 강점으로 인해 점차 인기를 얻고 있다. 그러나 소형 임베디드 시스템에서는 메모리 용량이 제한적이기 때문에 심층 신경망 모델을 처리하기 쉽지 않다. 이전 연구에서는 양자화나 가지치기와 같은 다양한 모델 압축 기법들을 제안하였다. 그러나 이러한 기법들은 일반적으로 압축으로 인한 정확도 손실을 최소화하기 위해 적절한 데이터 샘플을 사용한 세심한 미세 조정을 필요로 한다. 본 연구에서는 유사한 컨볼루션 커널을 클러스터링하고 가지치기하여 입력 모델을 압축하는 새로운 훈련 후 모델 압축 방법을 제안한다. 본 연구에서 제안된 방법은 커널 간의 유사성만을 고려하므로 데이터 샘플을 필요로하지 않는다. 본 연구는 대표적인 신경망 모델을 사용하여 제안된 방법을 평가하고 적은 정확도 손실로도 메모리 사용량을 효과적으로 줄일 수 있다는 것을 입증한다.

On-device machine learning is becoming more popular for its strengths in cost efficiency, data privacy, and responsiveness. However, processing deep neural network models on small embedded systems is challenging due to their limited memory capacity. Previous work has proposed various model compression techniques, such as quantization and pruning. However, the techniques generally require careful fine-tuning with proper data samples to minimize accuracy loss from compression. This work proposes a new post-training model compression method that compresses the input model by clustering and pruning similar convolution kernels. The proposed method does not require data samples because it considers the similarity between kernels only. This work evaluates the proposed method with representative neural network models and demonstrates that the method can effectively reduce memory usage on average with small accuracy loss.

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.

본 논문에서는 효율적인 압축 기법과 멀티미디어를 위한 다 해상도 3D 얼굴 모델 전송, 그리고 저비트율 응용에 대해 제안하고자 한다. 일반적으로 얼굴 모델은 3D 레이저 디지타이저에 의해서 얻어지게 되고 애니메이션, 비디오게임, 비디오 회의와 같은 응용 범위에 따라 여러 해상도로 재양자화 되어진다. 3D 디지털화된 얼굴 모델을 정합하고 재양자화 하기 위해서 2D 템플릿을 변형함으로써 압축 모델을 얻을 수 있다. 현재까지의 연구에서 다섯 가지 해상도로 계층적 2D 얼굴 와이어프레임 템플릿을 만들었다. 변형 과정에서 2D 템플릿은 얼굴 특징점과 제안된 PCAT(piecewise chainlet affine transformation)에 의해 바뀌게 된다. 재양자화된 후 3D 디지털화된 모델은 인지하지 못할 정도로 손실이 줄어들게 된다. 더욱이, 본 논문에서 제안한 계층적 데이터 구조를 갖는 다 해상도 얼굴모델은 통신망에서 점진적으로 알려지고 사용되어질 것이다.

In this paper, we proposed an approach to efficiently compress and transmit multiresoltion 3D lariat models for multimedia and very low bit rate applications. A personal facial model is obtained by a 3D laser digitizer, and further re-quantized at several resolutions according to different scope of applications, such as animation, video game, and video conference. By deforming 2D templates to match and re-quantize a 3D digitized facial model, we obtain its compressed model. In the present study, we create hierarchical 2D lariat wireframe templates are adapted according to facial feature points and the proposed piecewise chainlet affined transformation(PACT) method. The 3D digitized model after requantization are reduced significantly without perceptual loss. Moreover the proposed multiresoulation lariat models possessed of hierarchial data structure are apt to be progressively transmitted and displayed across internet.

이 연구의 목적은 바텀애시 골재와 기포를 융합한 경량 콘크리트(bottom ash based lightweight concrete, LWC-BF)의 압축 응력-변형률 모델 제시이다. Yang 등이 제시한 응력-변형률 곡선식에서 LWC-BF 9 배합의 실험으로부터 얻은 탄성계수, 최대응력 시 변형률 그리고 최대응력 이후 최대응력의 50% 응력 시 변형률 값들을 이용하여 상승부와 하강부의 기울기를 결정하였다. 제시된 모델은 기포 혼입율의 증가와 함께 감소되는 초기 강성 및 증가되는 하강부 기울기를 잘 반영하면서 실험결과와 잘 일치하였다. 제시된 모델의 예측값과 실험값의 평균제곱근 오차로부터 결정된 평균값과 표준편차는 각각 0.19와 0.08로서 각각 1.23과 0.47 값을 보이는 fib 2010 모델에 비해 현저히 낮았다.

The objective of this study is to propose a reliable stress-strain model in compression for lightweight concrete using bottom ash aggregates and air foam(LWC-BF). The slopes of the ascending and descending branches in the fundamental equation form generalized by Yang et al. were determined from the regression analyses of different data sets(including the modulus of elasticity and strains at the peak stress and 50% peak stress at the post-peak performance) obtained from 9 LWC-BF mixtures. The proposed model exhibits a good agreement with test results, revealing that the initial slope decreases whereas the decreasing rate in the stress at the descending branch increases with the increase in foam content. The mean and standard deviation of the normalized root-square mean errors calculated from the comparisons of experimental and predicted stress-strain curves are 0.19 and 0.08, respectively, for the proposed model, which indicates significant lower values when compared with those(1.23 and 0.47, respectively) calculated using fib 2010 model.

In recent years, compression ignition engine has been equipped with some control devices such as common rail injection system and turbocharger. In order to control the large number of input parameter appropriately in consideration of $NO_x$, HC and engine power as the engine output objectives. The model construction which reproduces the characteristic value of $NO_x$, HC and engine power from input parameter is needed. In this research, the stepwise method was applied to construct the compression ignition engine model. By using the preliminary experimental data of single cylinder compression ignition engine, the prediction model of $NO_x$, HC and engine power on single injection compression ignition engine was built and compared with the main experimental data.

본 논문에서는 주어진 이미지를 균일하게 블록화 시킨 후 각각의 Range 블록에서 Domain 블록을 찾아나간다. 각 Range 블록마다 Domain 블록이 찾아지게 되면 픽셀별로 포인팅을 하게 한다. 이러한 포인팅을 이용하여 링크드 리스트를 만들어 나가게 되면 사이클을 포함하게 되는 링크드 리스트가 조인된 형태의 모습을 갖게 된다. 그러면 사이클을 포함하는 이러한 형태의 픽셀의 평균값을 계산하여 뿌려주게 되는 것이다.

The purposes of this study are to verify a reasonable model of material characteristic and to propose a rational model of reinforcement characteristic considering monotonic and cyclic loading about manufactured reinforcing steel in Korea. Longitudinal reinforcements of the plastic hinge region were behaved tensile deformation and compressional deformation by direction of lateral loading. However Confinement steels were behaved only tensile deformation by lateral loading. Transverse steels were laid the state of tension in the lateral loading of time, and they were laid state that stress is zero when it was removed lateral load. The tests for cyclic tension loading were performed for test variable as yield strength and reinforcement bar sizes. It was estimated that the total strain energy per unit volume was 74 $MJ/m^3$. The modified ultimate concrete compression strain model was proposed based on experimental study of cyclic tension test for manufactured reinforcing steel in Korea.

횡방향으로 구속된 콘크리트의 응력-변형률 거동은 구속되지 않은 콘크리트와는 다른 거동을 한다. 보통강도 콘크리트에서 구속효과를 고려한 콘크리트 재료모델로는 Mander 모델이 대표적이며 고강도 콘크리트의 구속효과의 경우 여러 연구자들에 의하여 제안된 모델 중 공시체 수준의 실험결과와 잘 일치하는 Sakino-Sun 모델을 사용하였다. 보통강도에서는 Mander모델을 고강도 콘크리트에서는 Sakino-Sun 모델을 사용하였으나 중간 강도인 30-40MPa의 강도에서 Mander 모델과 Sakino-Sun 모델의 적용시 실험결과와 해석결과가 다소 차이를 보이며 또한 두 모델은 적용할 수 있는 최대 또는 최소 콘크리트 압축강도의 한계범위가 명확하지 않다. 따라서 이 연구에서는 30-40MPa의 강도의 횡방향으로 구속된 콘크리트의 비선형 재료모델을 제안하고 실제 30-40MPa의 압축강도를 갖는 콘크리트 공시체의 일축압축시험 결과와의 비교를 통해 그 적용성을 검토하였다.