• Smart Media Journal
• /
• v.12 no.5
• /
• pp.28-35
• /
• 2023

In this study, we propose a new light-weight model RoutingConvNet with fewer parameters to improve the applicability and practicality of speech emotion recognition. To reduce the number of learnable parameters, the proposed model connects bidirectional MFCCs on a channel-by-channel basis to learn long-term emotion dependence and extract contextual features. A light-weight deep CNN is constructed for low-level feature extraction, and self-attention is used to obtain information about channel and spatial signals in speech signals. In addition, we apply dynamic routing to improve the accuracy and construct a model that is robust to feature variations. The proposed model shows parameter reduction and accuracy improvement in the overall experiments of speech emotion datasets (EMO-DB, RAVDESS, and IEMOCAP), achieving 87.86%, 83.44%, and 66.06% accuracy respectively with about 156,000 parameters. In this study, we proposed a metric to calculate the trade-off between the number of parameters and accuracy for performance evaluation against light-weight.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.05a
• /
• pp.483-486
• /
• 2020

Age estimation and gender classification for human is a classic problem in computer vision. Almost research focus just only one task and the models are too heavy to run on low-cost system. In our research, we aim to apply multitasking learning to perform both task on a lightweight model which can achieve good precision on embedded system in the real time.

• Journal of Convergence for Information Technology
• /
• v.10 no.8
• /
• pp.23-34
• /
• 2020

Recently, the artificial intelligence deep learning field has been hard to commercialize due to the high computing power and the price problem of computing resources. In this paper, we apply a double pruning techniques to evaluate the performance of the in-depth neural network and various datasets. Double pruning combines basic Network-slimming and Parameter-prunning. Our proposed technique has the advantage of reducing the parameters that are not important to the existing learning and improving the speed without compromising the learning accuracy. After training various datasets, the pruning ratio was increased to reduce the size of the model.We confirmed that MobileNet-V3 showed the highest performance as a result of NetScore performance analysis. We confirmed that the performance after pruning was the highest in MobileNet-V3 consisting of depthwise seperable convolution neural networks in the Cifar 10 dataset, and VGGNet and ResNet in traditional convolutional neural networks also increased significantly.

• The Korean Journal of Applied Statistics
• /
• v.34 no.6
• /
• pp.979-993
• /
• 2021

Acoustic scene classification (ASC) categorizes an audio file based on the environment in which it has been recorded. This has long been studied in the detection and classification of acoustic scenes and events (DCASE). In this study, we considered the problem that ASC faces in real-world applications that the model used should have low-complexity. We compared several models that apply light-weight techniques. First, a base CNN model was proposed using log mel-spectrogram, deltas, and delta-deltas features. Second, depthwise separable convolution, linear bottleneck inverted residual block was applied to the convolutional layer, and Quantization was applied to the models to develop a low-complexity model. The model considering low-complexity was similar or slightly inferior to the performance of the base model, but the model size was significantly reduced from 503 KB to 42.76 KB.

• Journal of Biomedical Engineering Research
• /
• v.45 no.1
• /
• pp.1-9
• /
• 2024

Communication with others plays an important role in human social interaction and information exchange in modern society. However, some individuals have difficulty in communicating due to dysarthria. Therefore, it is necessary to develop effective diagnostic techniques for early treatment of the dysarthria. In the present study, we propose a mobile device-based methodology that enables to automatically classify dysarthria type. The light-weight CNN model was trained by using the open audio dataset of Korean patients with dysarthria. The trained CNN model can successfully classify dysarthria into related subtype disease with 78.8%~96.6% accuracy. In addition, the user-friendly mobile application was also developed based on the trained CNN model. Users can easily record their voices according to the selected inspection type (e.g. word, sentence, paragraph, and semi-free speech) and evaluate the recorded voice data through their mobile device and the developed mobile application. This proposed technique would be helpful for personal management of dysarthria and decision making in clinic.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.3
• /
• pp.367-373
• /
• 2022

As deep learning-based autonomous driving technology develops, artificial intelligence models for various purposes have been studied. Based on these studies, several models were used simultaneously to develop autonomous driving systems. It can occur by increasing hardware resource consumption. We propose a multi-tasks model using a shared backbone to solve this problem. This can solve the increase in the number of backbones for using AI models. As a result, in the proposed lightweight model, the model parameters could be reduced by more than 50% compared to the existing model, and the speed could be improved. In addition, each lane can be classified through lane detection using the instance segmentation method. However, further research is needed on the decrease in accuracy compared to the existing model.

• Journal of Korea Society of Industrial Information Systems
• /
• v.29 no.1
• /
• pp.77-89
• /
• 2024

This paper presents an unmanned store management system that can provide inventory management and theft prevention for displayed products using a small camera that can monitor the shelves of sold products in small and medium-sized stores. This system is a service solution that integrates object recognition, real-time communication, security management, access management, and mobile authentication. The proposed system uses a custom YOLOv5-x model to recognize objects on the display, measure quantities in real time, and support real-time data communication with servers through Raspberry Pie. In addition, the number of objects in the database and the object recognition results are compared to detect suspected theft situations and provide burial images at the time of theft. The proposed unmanned store solution is expected to improve the efficiency of small and medium-sized unmanned store operations and contribute to responding to theft.

• Journal of Bio-Environment Control
• /
• v.26 no.4
• /
• pp.411-417
• /
• 2017

Environmental and growth factors such as light intensity, vapor pressure deficit, and leaf area index are important variables that can change the transpiration rate of plants. The objective of this study was to compare the transpiration rates estimated by modified Penman-Monteith model and artificial neural network. The transpiration rate of paprika (Capsicum annuum L. cv. Fiesta) was obtained by using the change in substrate weight measured by load cells. Radiation, temperature, relative humidity, and substrate weight were collected every min for 2 months. Since the transpiration rate cannot be accurately estimated with linear equations, a modified Penman-Monteith equation using compensated radiation (Shin et al., 2014) was used. On the other hand, ANN was applied to estimating the transpiration rate. For this purpose, an ANN composed of an input layer using radiation, temperature, relative humidity, leaf area index, and time as input factors and five hidden layers was constructed. The number of perceptons in each hidden layer was 512, which showed the highest accuracy. As a result of validation, $R^2$ values of the modified model and ANN were 0.82 and 0.94, respectively. Therefore, it is concluded that the ANN can estimate the transpiration rate more accurately than the modified model and can be applied to the efficient irrigation strategy in soilless cultures.