• 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.

• Journal of the Korean Society of Industry Convergence
• /
• v.25 no.6_3
• /
• 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 Technology Services
• /
• v.8 no.1
• /
• pp.203-215
• /
• 2009

This paper illustrates the application of co-occurrence theory to generate lightweight ontologies semi-automatically. The proposed model includes three steps of a (Semi-) Automatic creation of Ontology; (they are conceptually named as) the Syntactic-based Ontology, the Semantic-based Ontology and the Ontology Refinement. Each of these three steps are designed to interactively work together, so as to generate Lightweight Ontologies. The Syntactic-based Ontology step includes generating Association words using co-occurrence in web documents. The Semantic-based Ontology step includes the Alignment large Association words with small Ontology, through the process of semantic relations by contextual terms. Finally, the Ontology Refinement step includes the domain expert to refine the lightweight Ontologies. We also conducted a case study to generate lightweight ontologies in specific domains(news domain). In this paper, we found two directions including (1) employment co-occurrence theory to generate Syntactic-based Ontology automatically and (2) Alignment large Association words with small Ontology to generate lightweight ontologies semi-automatically. So far as the design and the generation of big Ontology is concerned, the proposed research will offer useful implications to the researchers and practitioners so as to improve the research level to the commercial use.

• Journal of the Korean Recycled Construction Resources Institute
• /
• v.7 no.3
• /
• pp.216-223
• /
• 2019

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.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.19 no.3
• /
• pp.151-158
• /
• 2024

Although on-device artificial intelligence (AI) has gained attention to diagnosing machine faults in real time, most previous studies did not consider the model retraining and redeployment processes that must be performed in real-world industrial environments. Our study addresses this challenge by proposing an on-device AI-based real-time machine fault diagnosis system that utilizes continual learning. Our proposed system includes a lightweight convolutional neural network (CNN) model, a continual learning algorithm, and a real-time monitoring service. First, we developed a lightweight 1D CNN model to reduce the cost of model deployment and enable real-time inference on the target edge device with limited computing resources. We then compared the performance of five continual learning algorithms with three public bearing fault datasets and selected the most effective algorithm for our system. Finally, we implemented a real-time monitoring service using an open-source data visualization framework. In the performance comparison results between continual learning algorithms, we found that the replay-based algorithms outperformed the regularization-based algorithms, and the experience replay (ER) algorithm had the best diagnostic accuracy. We further tuned the number and length of data samples used for a memory buffer of the ER algorithm to maximize its performance. We confirmed that the performance of the ER algorithm becomes higher when a longer data length is used. Consequently, the proposed system showed an accuracy of 98.7%, while only 16.5% of the previous data was stored in memory buffer. Our lightweight CNN model was also able to diagnose a fault type of one data sample within 3.76 ms on the Raspberry Pi 4B device.

• Journal of Sensor Science and Technology
• /
• v.30 no.5
• /
• pp.286-289
• /
• 2021

Image classification is one of the fundamental applications of computer vision. It enables a system to identify an object in an image. Recently, image classification applications have broadened their scope from computer applications to edge devices. The convolutional neural network (CNN) is the main class of deep learning neural networks that are widely used in computer tasks, and it delivers high accuracy. However, CNN algorithms use a large number of parameters and incur high computational costs, which hinder their implementation in edge hardware devices. To address this issue, this paper proposes a lightweight image classifier that provides good accuracy while using fewer parameters. The proposed image classifier diverts the input into three paths and utilizes different scales of receptive fields to extract more feature maps while using fewer parameters at the time of training. This results in the development of a model of small size. This model is tested on the CIFAR-10 dataset and achieves an accuracy of 90% using .26M parameters. This is better than the state-of-the-art models, and it can be implemented on edge devices.

• Steel and Composite Structures
• /
• v.18 no.4
• /
• pp.1001-1021
• /
• 2015

Ultra-lightweight cement composite (ULCC) with a compressive strength of 60 MPa and density of $1,450kg/m^3$ has been developed and used in the steel-concrete-steel (SCS) sandwich structures. This paper investigates the structural performances of SCS sandwich composite beams with ULCC as filled material. Overlapped headed shear studs were used to provide shear and tensile bond between the face plate and the lightweight core. Three-dimensional nonlinear finite element (FE) model was developed for the ultimate strength analysis of such SCS sandwich composite beams. The accuracy of the FE analysis was established by comparing the predicted results with the quasi-static tests on the SCS sandwich beams. The FE model was also applied to the nonlinear analysis on curved SCS sandwich beam and shells and the SCS sandwich beams with J-hook connectors and different concrete core including ULCC, lightweight concrete (LWC) and normal weight concrete (NWC). Validations were also carried out to check the accuracy of the FE analysis on the SCS sandwich beams with J-hook connectors and curved SCS sandwich structure. Finally, recommended FE analysis procedures were given.

• International Journal of Contents
• /
• v.18 no.2
• /
• 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.

• Coupled systems mechanics
• /
• v.12 no.4
• /
• pp.315-335
• /
• 2023

The building sector has seen a huge increase in the use of lightweight concrete recently, which might result in saving in both cost and time. As a result, the study has been done on various types of concrete, including lightweight (LC), heavyweight (HC), and ordinary concrete (OC), to understand how they react to earthquake loads. The comparisons between their responses have also been taken into account in order to acquire the optimal reaction for various materials in building work. The findings demonstrate that LWC building models are more earthquake-resistant than the other varieties due to the reduction in building weight which can be a curial factor in the resistance of earthquake forces. Another crucial factor that was taken into study is the combination of various types of concrete [HC, LC, and OC] in the structural components. On the other hand, the bending moments and shear forces of LC had reduced to 17% and 19%, respectively, when compared to OC. Otherwise, the bending moment and shear force demand responses in the HC model reach their maximum values by more than 34% compared to the reference model OC. In addition, the results show that the LCC-OCR (light concrete column and ordinary concrete roof) and OCC-LCR (ordinary concrete for the column and light concrete for the roof) models' responses have fewer values than the other types.