• 전자통신동향분석
• /
• 제34권2호
• /
• pp.40-50
• /
• 2019

Considerable accuracy improvements in deep learning have recently been achieved in many applications that require large amounts of computation and expensive memory. However, recent advanced techniques for compacting and accelerating the deep learning model have been developed for deployment in lightweight devices with constrained resources. Lightweight deep learning techniques can be categorized into two schemes: lightweight deep learning algorithms (model simplification and efficient convolutional filters) in nature and transferring models into compact/small ones (model compression and knowledge distillation). In this report, we briefly summarize various lightweight deep learning techniques and possible research directions.

• 대한임베디드공학회논문지
• /
• 제17권2호
• /
• pp.77-83
• /
• 2022

In this paper, the two-stage object detection approach is proposed to implement a deep learning-based label inspection system on edge computing environments. Since the label printed on the products during the production process contains important information related to the product, it is significantly to check the label information is correct. The proposed system uses the lightweight deep learning model that able to employ in the low-performance edge computing devices, and the two-stage object detection approach is applied to compensate for the low accuracy relatively. The proposed Two-Stage object detection approach consists of two object detection networks, Label Area Detection Network and Character Detection Network. Label Area Detection Network finds the label area in the product image, and Character Detection Network detects the words in the label area. Using this approach, we can detect characters precise even with a lightweight deep learning models. The SF-YOLO model applied in the proposed system is the YOLO-based lightweight object detection network designed for edge computing devices. This model showed up to 2 times faster processing time and a considerable improvement in accuracy, compared to other YOLO-based lightweight models such as YOLOv3-tiny and YOLOv4-tiny. Also since the amount of computation is low, it can be easily applied in edge computing environments.

• 센서학회지
• /
• 제30권1호
• /
• pp.15-19
• /
• 2021

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.

• 한국컴퓨터정보학회논문지
• /
• 제28권10호
• /
• pp.17-25
• /
• 2023

본 논문에서는 의류 디자인 도면 이미지의 글자 검출을 위한 경량화된 딥러닝 네트워크를 제안하였다. 최근 의류 디자인 산업에서 Digital Transformation의 중요성이 대두되면서, 디지털 도구를 활용한 의류 디자인 도면 작성이 강조되고 있으며, 디지털화된 의류 디자인 도면의 활용 가능성을 고려할 때, 도면에서 글자 검출과 인식이 중요한 첫 단계로 간주된다. 이 연구에서는 기존의 글자 검출 딥러닝 모델을 기반으로 의류 도면 이미지의 특수성을 고려하여 경량화된 네트워크를 설계하였으며, 별도로 수집한 의류 도면 데이터 셋을 추가하여 딥러닝 모델을 학습시켰다. 실험 결과, 제안한 딥러닝 모델은 의류 도면 이미지에서 기존 글자 검출 모델보다 약 20% 높은 성능을 보였다. 따라서 이 논문은 딥러닝 모델의 최적화와 특수한 글자 정보 검출 등의 연구를 통해 의류 디자인 분야에서의 Digital Transformation에 기여할 것으로 기대한다.

• 한국인터넷방송통신학회논문지
• /
• 제24권1호
• /
• pp.1-8
• /
• 2024

실시간 처리 및 프라이버시 강화를 위해 인공지능 모델을 엣지에서 동작시킬 수 있는 온디바이스 AI 기술이 각광받고 있다. 지능형 사물인터넷 기술이 다양한 산업에 적용되면서 온디바이스 AI 기술을 활용한 서비스가 크게 증가하고 있다. 그러나 일반적인 딥러닝 모델은 추론 및 학습을 위해 많은 연산 자원을 요구하고 있다. 따라서 엣지에 적용되는 경량 기기에서 딥러닝 모델을 동작시키기 위해 양자화나 가지치기와 같은 다양한 경량화 기법들이 적용되어야 한다. 본 논문에서는 다양한 경량화 기법 중 가지치기 기술을 중심으로 엣지 컴퓨팅 기기에서 딥러닝 모델을 경량화하여 적용할 수 있는 방안을 분석한다. 특히, 동적 및 정적 가지치기 기법을 적용하여 경량화된 비전 모델의 추론 속도, 정확도 그리고 메모리 사용량을 시험한다. 논문에서 분석된 내용은 실시간 특성이 중요한 지능형 영상 관제 시스템이나 자율 이동체의 영상 보안 시스템에 적용될 수 있다. 또한 사물인터넷 기술이 적용되는 다양한 서비스와 산업에 더욱 효과적으로 활용될 수 있을 것으로 기대된다.

• Computers and Concrete
• /
• 제32권3호
• /
• pp.327-337
• /
• 2023

Concrete is the most widely used building material, with various types including high- and ultra-high-strength, reinforced, normal, and lightweight concretes. However, accurately predicting concrete properties is challenging due to the geotechnical design code's requirement for specific characteristics. To overcome this issue, researchers have turned to new technologies like machine learning to develop proper methodologies for concrete specification. In this study, we propose a highly accurate deep learning-based predictive model to investigate the compressive strength (UCS) of lightweight concrete with natural aggregates (pumice). Our model was implemented on a database containing 249 experimental records and revealed that water, cement, water-cement ratio, fine-coarse aggregate, aggregate substitution rate, fine aggregate replacement, and superplasticizer are the most influential covariates on UCS. To validate our model, we trained and tested it on random subsets of the database, and its performance was evaluated using a confusion matrix and receiver operating characteristic (ROC) overall accuracy. The proposed model was compared with widely known machine learning methods such as MLP, SVM, and DT classifiers to assess its capability. In addition, the model was tested on 25 laboratory UCS tests to evaluate its predictability. Our findings showed that the proposed model achieved the highest accuracy (accuracy=0.97, precision=0.97) and the lowest error rate with a high learning rate (R2=0.914), as confirmed by ROC (AUC=0.971), which is higher than other classifiers. Therefore, the proposed method demonstrates a high level of performance and capability for UCS predictions.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권2호
• /
• pp.600-616
• /
• 2021

SIMON and SPECK are two families of lightweight block ciphers that have excellent performance on hardware and software platforms. At CRYPTO 2019, Gohr first introduces the differential cryptanalysis based deep learning on round-reduced SPECK32/64, and finally reduces the remaining security of 11-round SPECK32/64 to roughly 38 bits. In this paper, we are committed to evaluating the safety of SIMON cipher under the neural differential cryptanalysis. We firstly prove theoretically that SIMON is a non-Markov cipher, which means that the results based on conventional differential cryptanalysis may be inaccurate. Then we train a residual neural network to get the 7-, 8-, 9-round neural distinguishers for SIMON32/64. To prove the effectiveness for our distinguishers, we perform the distinguishing attack and key-recovery attack against 15-round SIMON32/64. The results show that the real ciphertexts can be distinguished from random ciphertexts with a probability close to 1 only by 2^8.7 chosen-plaintext pairs. For the key-recovery attack, the correct key was recovered with a success rate of 23%, and the data complexity and computation complexity are as low as 2⁸ and 2^20.1 respectively. All the results are better than the existing literature. Furthermore, we briefly discussed the effect of different residual network structures on the training results of neural distinguishers. It is hoped that our findings will provide some reference for future research.

• 한국산업융합학회 논문집
• /
• 제25권6_3호
• /
• pp.1285-1291
• /
• 2022

In this paper, we propose a low-cost, low-power embedded environment-based deep learning lightweight model for input images to recognize laundry management codes. Laundry franchise companies mainly use barcode recognition-based systems to record laundry consignee information and laundry information for laundry collection management. Conventional laundry collection management systems using barcodes require barcode printing costs, and due to barcode damage and contamination, it is necessary to improve the cost of reprinting the barcode book in its entirety of 1 billion won annually. It is also difficult to do. Recognition performance is improved by applying the VGG model with 7 layers, which is a reduced-transformation of the VGGNet model for number recognition. As a result of the numerical recognition experiment of service parts drawings, the proposed method obtained a significantly improved result over the conventional method with an F1-Score of 0.95.

• Journal of Information Processing Systems
• /
• 제18권1호
• /
• pp.12-25
• /
• 2022

In recent years, deep convolutional neural networks have made significant progress in the research of single image super-resolution. However, it is difficult to be applied in practical computing terminals or embedded devices due to a large number of parameters and computational effort. To balance these problems, we propose CSRNet, a lightweight neural network based on channel split residual learning structure, to reconstruct highresolution images from low-resolution images. Lightweight refers to designing a neural network with fewer parameters and a simplified structure for lower memory consumption and faster inference speed. At the same time, it is ensured that the performance of recovering high-resolution images is not degraded. In CSRNet, we reduce the parameters and computation by channel split residual learning. Simultaneously, we propose a double-upsampling network structure to improve the performance of the lightweight super-resolution network and make it easy to train. Finally, we propose a new evaluation metric for the lightweight approaches named 100_FPS. Experiments show that our proposed CSRNet not only speeds up the inference of the neural network and reduces memory consumption, but also performs well on single image super-resolution.

• International Journal of Contents
• /
• 제18권2호
• /
• pp.68-80
• /
• 2022

The health of the human heart is commonly measured using ECG (Electrocardiography) signals. To identify any anomaly in the human heart, the time-sequence of ECG signals is examined manually by a cardiologist or cardiac electrophysiologist. Lightweight anomaly detection on ECG signals in an embedded system is expected to be popular in the near future, because of the increasing number of heart disease symptoms. Some previous research uses deep learning networks such as LSTM and BiLSTM to detect anomaly signals without any handcrafted feature. Unfortunately, lightweight LSTMs show low precision and heavy LSTMs require heavy computing powers and volumes of labeled dataset for symptom classification. This paper proposes an ECG anomaly detection system based on two level BiLSTM for acceptable precision with lightweight networks, which is lightweight and usable at home. Also, this paper presents a new threshold technique which considers statistics of the current ECG pattern. This paper's proposed model with BiLSTM detects ECG signal anomaly in 0.467 ~ 1.0 F₁ score, compared to 0.426 ~ 0.978 F₁ score of the similar model with LSTM except one highly noisy dataset.