• IEMEK Journal of Embedded Systems and Applications
• /
• v.17 no.2
• /
• 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.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.12
• /
• pp.3904-3922
• /
• 2022

As a research hotspot, pedestrian detection has a wide range of applications in the field of computer vision in recent years. However, current pedestrian detection methods have problems such as insufficient detection accuracy and large models that are not suitable for large-scale deployment. In view of these problems mentioned above, a lightweight pedestrian detection and early warning method using a new model called you only look once (Yolov5) is proposed in this paper, which utilizing advantages of Yolov5s model to achieve accurate and fast pedestrian recognition. In addition, this paper also optimizes the loss function of the batch normalization (BN) layer. After sparsification, pruning and fine-tuning, got a lot of optimization, the size of the model on the edge of the computing power is lower equipment can be deployed. Finally, from the experimental data presented in this paper, under the training of the road pedestrian dataset that we collected and processed independently, the Yolov5s model has certain advantages in terms of precision and other indicators compared with traditional single shot multiBox detector (SSD) model and fast region-convolutional neural network (Fast R-CNN) model. After pruning and lightweight, the size of training model is greatly reduced without a significant reduction in accuracy, and the final precision reaches 87%, while the model size is reduced to 7,723 KB.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.5
• /
• pp.1433-1449
• /
• 2023

In recent years, the rapid development of social networks has led to a rapid increase in the amount of information available on the Internet, which contains a large amount of sensitive information related to pornography, politics, and terrorism. In the aspect of sensitive image detection, the existing machine learning algorithms are confronted with problems such as large model size, long training time, and slow detection speed when auditing and supervising. In order to detect sensitive images more accurately and quickly, this paper proposes a multiclassification sensitive image detection method based on lightweight Convolutional Neural Network. On the basis of the EfficientNet model, this method combines the Ghost Module idea of the GhostNet model and adds the SE channel attention mechanism in the Ghost Module for feature extraction training. The experimental results on the sensitive image data set constructed in this paper show that the accuracy of the proposed method in sensitive information detection is 94.46% higher than that of the similar methods. Then, the model is pruned through an ablation experiment, and the activation function is replaced by Hard-Swish, which reduces the parameters of the original model by 54.67%. Under the condition of ensuring accuracy, the detection time of a single image is reduced from 8.88ms to 6.37ms. The results of the experiment demonstrate that the method put forward has successfully enhanced the precision of identifying multi-class sensitive images, significantly decreased the number of parameters in the model, and achieved higher accuracy than comparable algorithms while using a more lightweight model design.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.1
• /
• pp.105-110
• /
• 2022

Traffic sign recognition plays an important role in solving traffic-related problems. Traffic sign recognition and classification systems are key components for traffic safety, traffic monitoring, autonomous driving services, and autonomous vehicles. A lightweight model, applicable to portable devices, is an essential aspect of the design agenda. We suggest a lightweight convolutional neural network model with residual blocks for traffic sign recognition systems. The proposed model shows very competitive results on publicly available benchmark data.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.2
• /
• pp.914-934
• /
• 2016

In the mobile distributed environment, an entity may move across domains with great frequency. How to utilize the trust information in the previous domains and quickly establish trust relationships with others in the current domain remains a challenging issue. The classic trust models do not support cross-domain and the existing cross-domain trust models are not in a fully distributed way. This paper improves the outstanding Certified Reputation (CR) model and proposes a Lightweight Cross-domain Trust (LCT) model for the mobile distributed environment in a fully distributed way. The trust certifications, in which the trust ratings contain various trust aspects with different interest preference weights, are collected and provided by the trustees. Furthermore, three factors are comprehensively considered to ease the issue of collusion attacks and make the trust certifications more accurate. Finally, a cross-domain scenario is deployed and implemented, and the comprehensive experiments and analysis are conducted. The results demonstrate that our LCT model obviously outperforms the Bayesian Network (BN) model and the CR model in our cross-domain scenario, and significantly improves the successful interaction rates of the honest entities without increasing the risks of interacting with the malicious entities.

• Computers and Concrete
• /
• v.32 no.3
• /
• 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.

• Computers and Concrete
• /
• v.16 no.3
• /
• pp.449-466
• /
• 2015

This paper aims to study the local bond stress-slip behavior of reinforcing bars embedded in lightweight aggregate concrete (LWAC). The experimental variables of the local bond stress-slip tests include concrete strength (20, 40 and 60 MPa), deformed steel bar size (#4, #6 and #8) and coarse aggregate (normal weight aggregate, reservoir sludge lightweight aggregate and waterworks sludge lightweight aggregate). The test results show that the ultimate bond strength increased with the increase of concrete compressive strength. Moreover, the larger the rib height to the diameter ratio ($h/d_b$) of the deformed steel bars is, the greater the ultimate bond stress is. In addition, the suggestion value of the CEB-FIP Model Code to the LWAC specimen's ultimate bond stress is more conservative than that of the normal weight concrete.

• Journal of the Korea Society of Computer and Information
• /
• v.10 no.6 s.38
• /
• pp.239-252
• /
• 2005

Ubiquitous Sensor Network(USN) , the core technology for the Ubiquitous environments ,must be operated in the restrictive battery capacity and computing. From this cause, USN needs the lightweight design for low electric energy and the minimum computing. The previous mutual authentication. based on J$\emptyset$sang's trust model, in USN has a character that makes the lightweight mutual authentication possible in conformity with minimum computing. But, it has an imperfection at the components of representing the trust from a lightweight point of view. In this paper, we improve on the J$\emptyset$sang's trust model to apply a lightweight mutual authentication in USN. The proposed trust model in USN defines the trust information with the only degree of trust-entity(x)'s belief. The defined trust information has a superiority over the J$\emptyset$sang's trust model from a computing Point of view. because it computes information by Probability and logic operation(AND).

• Smart Media Journal
• /
• v.12 no.2
• /
• pp.56-65
• /
• 2023

In broadcasts such as news and coverage programs, voice is modulated to protect the identity of the informant. Adjusting the pitch is commonly used voice modulation method, which allows easy voice restoration to the original voice by adjusting the pitch. Therefore, since broadcast voice modulation methods cannot properly protect the identity of the speaker and are vulnerable to security, a new voice modulation method is needed to replace them. In this paper, using the Lightweight speech de-identification model as the evaluation target model, we compare speech de-identification performance with broadcast voice modulation method using pitch modulation. Among the six modulation methods in the Lightweight speech de-identification model, we experimented on the de-identification performance of Korean speech as a human test and EER(Equal Error Rate) test compared with broadcast voice modulation using three modulation methods: McAdams, Resampling, and Vocal Tract Length Normalization(VTLN). Experimental results show VTLN modulation methods performed higher de-identification performance in both human tests and EER tests. As a result, the modulation methods of the Lightweight model for Korean speech has sufficient de-identification performance and will be able to replace the security-weak broadcast voice modulation.

• International Journal of Concrete Structures and Materials
• /
• v.2 no.2
• /
• pp.123-136
• /
• 2008

A new plastic-damage constitutive model applicable to lightweight concrete (LWC) and normal weight concrete (NWC) is proposed in this paper based on both continuum damage mechanics and plasticity theories. Two damage variables are used to represent tensile and compressive damage independently. The effective stress is computed in the Drucker-Prager multi-surface plasticity framework. The stress is then computed by multiplication of the damaged part and the effective part. The proposed model is coded as a user material subroutine and incorporated in a finite element analysis software. The constitutive integration algorithm is implemented by adopting the operator split involving elastic predictor, plastic corrector and damage corrector. The numerical study shows that the algorithm is efficient and robust in the finite element analysis. Experimental investigation is conducted to verify the proposed model involving both static and dynamic tests. The very good agreement between the numerical results and experimental results demonstrates the capability of the proposed model to capture the behaviors of LWC and NWC structures for static and impact loading.