• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.1
• /
• pp.27-32
• /
• 2019

Research that implements the classification process through Deep Learning algorithm, one of the outstanding human abilities, includes a unimodal model, a multi-modal model, and a multi-modal method using music videos. In this study, the results were better by suggesting a system to analyze each song's spectrum into short samples and vote for the results. Among Deep Learning algorithms, CNN showed superior performance in the category of music genre compared to RNN, and improved performance when CNN and RNN were applied together. The system of voting for each CNN result by Deep Learning a short sample of music showed better results than the previous model and the model with Softmax layer added to the model performed best. The need for the explosive growth of digital media and the automatic classification of music genres in numerous streaming services is increasing. Future research will need to reduce the proportion of undifferentiated songs and develop algorithms for the last category classification of undivided songs.

• Smart Media Journal
• /
• v.8 no.3
• /
• pp.31-40
• /
• 2019

To understand how a Convolutional Neural Network (CNN) model captures the features of a pattern to determine which class it belongs to, in this paper, we use Gradient-weighted Class Activation Mapping (Grad-CAM) to visualize and analyze how well a CNN model behave on the CNU weeds dataset. We apply this technique to Resnet model and figure out which features this model captures to determine a specific class, what makes the model get a correct/wrong classification, and how those wrong label images can cause a negative effect to a CNN model during the training process. In the experiment, Grad-CAM highlights the important regions of weeds, depending on the patterns learned by Resnet, such as the lobe and limb on 미국가막사리, or the entire leaf surface on 단풍잎돼지풀. Besides, Grad-CAM points out a CNN model can localize the object even though it is trained only for the classification problem.

• Journal of the Semiconductor & Display Technology
• /
• v.20 no.1
• /
• pp.99-103
• /
• 2021

Warpage defect detecting of scaffold is very important in biosensor production. Because warpaged scaffold cause problem in cell culture. Currently, there is no detection equipment to warpaged scaffold. In this paper, we produced detection model for shape warpage detection using deep learning based CNN. We confirmed the shape of the scaffold that is widely used in cell culture. We produced scaffold specimens, which are widely used in biosensor fabrications. Then, the scaffold specimens were photographed to collect image data necessary for model manufacturing. We produced the detecting model of scaffold warpage defect using Densenet among CNN models. We evaluated the accuracy of the defect detection model with mAP, which evaluates the detection accuracy of deep learning. As a result of model evaluating, it was confirmed that the defect detection accuracy of the scaffold was more than 95%.

• Korean Journal of Remote Sensing
• /
• v.37 no.4
• /
• pp.719-731
• /
• 2021

This study proposes a two-stage hybrid classification model for crop classification using multi-temporal remote sensing images; the model combines feature embedding by using an autoencoder (AE) with a convolutional neural network (CNN) classifier to fully utilize features including informative temporal and spatial signatures. Long short-term memory (LSTM)-based AE (LAE) is fine-tuned using class label information to extract latent features that contain less noise and useful temporal signatures. The CNN classifier is then applied to effectively account for the spatial characteristics of the extracted latent features. A crop classification experiment with multi-temporal unmanned aerial vehicle images is conducted to illustrate the potential application of the proposed hybrid model. The classification performance of the proposed model is compared with various combinations of conventional deep learning models (CNN, LSTM, and convolutional LSTM) and different inputs (original multi-temporal images and features from stacked AE). From the crop classification experiment, the best classification accuracy was achieved by the proposed model that utilized the latent features by fine-tuned LAE as input for the CNN classifier. The latent features that contain useful temporal signatures and are less noisy could increase the class separability between crops with similar spectral signatures, thereby leading to superior classification accuracy. The experimental results demonstrate the importance of effective feature extraction and the potential of the proposed classification model for crop classification using multi-temporal remote sensing images.

• Journal of Broadcast Engineering
• /
• v.23 no.3
• /
• pp.345-350
• /
• 2018

CNN (convolution neural network) has become the most popular artificial intelligence technique and shows remarkable performance in image classification task. In this paper, we propose a CNN-based classification method for various street images as well as a method of evaluating the safety score for the street. The proposed method consists of learning four types of street images using CNN and classifying input street images using the learned CNN model followed by evaluating the safety score. During the learning process, four types of street images are collected and augmented, and then CNN learning is performed. It is shown that learned CNN model classifies input images correctly and the safety scores are evaluated quantitatively by combining the probabilities of different street types.

• Journal of Aerospace System Engineering
• /
• v.16 no.4
• /
• pp.45-52
• /
• 2022

In the field of UAM, which is attracting attention as a next-generation transportation system, technology developments for using UAVs have been actively conducted in recent years. Since UAVs adopted with these technologies are mainly operated in urban areas, it is imperative that accidents are prevented. However, it is not easy to predict the abnormal flight state of an UAV causing a crash, because of its strong non-linearity. In this paper, we propose a method for predicting a flight state of an UAV, based on a CNN-LSTM hybrid model. To predict flight state variables at a specific point in the future, the proposed model combines the CNN model extracting temporal and spatial features between flight data, with the LSTM model extracting a short and long-term temporal dependence of the extracted features. Simulation results show that the proposed method has better performance than the prediction methods, which are based on the existing artificial neural network model.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.12
• /
• pp.4706-4724
• /
• 2020

With various structured data, such as the company size, loan balance, and savings accounts, the voice of customer (VOC), which is text data containing contact history and counseling details was analyzed in this study. To analyze unstructured data, the term frequency-inverse document frequency (TF-IDF) analysis, semantic network analysis, sentiment analysis, and a convolutional neural network (CNN) were implemented. A performance comparison of the models revealed that the predictive model using the CNN provided the best performance with regard to predictive power, followed by the model using the TF-IDF, and then the model using semantic network analysis. In particular, a character-level CNN and a word-level CNN were developed separately, and the character-level CNN exhibited better performance, according to an analysis for the Korean language. Moreover, a systematic selection model for optimal text mining techniques was proposed, suggesting which analytical technique is appropriate for analyzing text data depending on the context. This study also provides evidence that the results of previous studies, indicating that individual customers leave when their loyalty and switching cost are low, are also applicable to corporate customers and suggests that VOC data indicating customers' needs are very effective for predicting their behavior.

• Journal of Information Processing Systems
• /
• v.19 no.6
• /
• pp.842-857
• /
• 2023

Currently, most sentiment classification models on microblogging platforms analyze sentence parts of speech and emoticons without comprehending users' emotional inclinations and grasping moral nuances. This study proposes a hybrid sentiment analysis model. Given the distinct nature of microblog comments, the model employs a combined stop-word list and word2vec for word vectorization. To mitigate local information loss, the TextCNN model, devoid of pooling layers, is employed for local feature extraction, while BiLSTM is utilized for contextual feature extraction in deep learning. Subsequently, microblog comment sentiments are categorized using a classification layer. Given the binary classification task at the output layer and the numerous hidden layers within BiLSTM, the Tanh activation function is adopted in this model. Experimental findings demonstrate that the enhanced TextCNN-BiLSTM model attains a precision of 94.75%. This represents a 1.21%, 1.25%, and 1.25% enhancement in precision, recall, and F1 values, respectively, in comparison to the individual deep learning models TextCNN. Furthermore, it outperforms BiLSTM by 0.78%, 0.9%, and 0.9% in precision, recall, and F1 values.

• Journal of the Institute of Convergence Signal Processing
• /
• v.21 no.2
• /
• pp.73-78
• /
• 2020

Musculoskeletal disease is often caused by sitting down for long period's time or by bad posture habits. In order to prevent musculoskeletal disease in daily life, it is the most important to correct the bad sitting posture to the right one through real-time monitoring. In this study, to detect the sitting information of user's without any constraints, we propose posture measurement system based on multi-channel pressure sensor and CNN model for classifying sitting posture types. The proposed CNN model can analyze 5 types of sitting postures based on sitting posture information. For the performance assessment of posture classification CNN model through field test, the accuracy, recall, precision, and F1 of the classification results were checked with 10 subjects. As the experiment results, 99.84% of accuracy, 99.6% of recall, 99.6% of precision, and 99.6% of F1 were verified.

• Journal of Broadcast Engineering
• /
• v.25 no.2
• /
• pp.200-207
• /
• 2020

Recently, deep neural networks such as CNN are showing excellent performance in various fields such as image classification, object recognition, visual quality enhancement, etc. However, as the model size and computational complexity of deep learning models for most applications increases, it is hard to apply neural networks to IoT and mobile environments. Therefore, neural network compression algorithms for reducing the model size while keeping the performance have been being studied. In this paper, we apply few compression methods to CNN models and evaluate their performances in the embedded environment. For evaluate the performance, the classification performance and inference time of the original CNN models and the compressed CNN models on the image inputted by the camera are evaluated in the embedded board equipped with QCS605, which is a customized AI chip. In this paper, a few CNN models of MobileNetV2, ResNet50, and VGG-16 are compressed by applying the methods of pruning and matrix decomposition. The experimental results show that the compressed models give not only the model size reduction of 1.3~11.2 times at a classification performance loss of less than 2% compared to the original model, but also the inference time reduction of 1.2~2.21 times, and the memory reduction of 1.2~3.8 times in the embedded board.