• Journal of Information Processing Systems
• /
• v.17 no.6
• /
• pp.1115-1126
• /
• 2021

Plant disease is one of the most irritating problems for agriculture growers. Thus, timely detection of plant diseases is of high importance to practical value, and corresponding measures can be taken at the early stage of plant diseases. Therefore, numerous researchers have made unremitting efforts in plant disease identification. However, this problem was not solved effectively until the development of artificial intelligence and big data technologies, especially the wide application of deep learning models in different fields. Since the symptoms of plant diseases mainly appear visually on leaves, computer vision and machine learning technologies are effective and rapid methods for identifying various kinds of plant diseases. As one of the fruits with the highest nutritional value, apple production directly affects the quality of life, and it is important to prevent disease intrusion in advance for yield and taste. In this study, an improved deep residual network is proposed for apple leaf disease identification in a novel way, a global residual connection is added to the original residual network, and the local residual connection architecture is optimized. Including that 1,977 apple leaf disease images with three categories that are collected in this study, experimental results show that the proposed method has achieved 98.74% top-1 accuracy on the test set, outperforming the existing state-of-the-art models in apple leaf disease identification tasks, and proving the effectiveness of the proposed method.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.1
• /
• pp.413-435
• /
• 2018

Although the accuracy of handwritten character recognition based on deep networks has been shown to be superior to that of the traditional method, the use of an overly deep network significantly increases time consumption during parameter training. For this reason, this paper took the training time and recognition accuracy into consideration and proposed a novel handwritten character recognition algorithm with newly designed network structure, which is based on an extended nonlinear kernel residual network. This network is a non-extremely deep network, and its main design is as follows:(1) Design of an unsupervised apriori algorithm for intra-class clustering, making the subsequent network training more pertinent; (2) presentation of an intermediate convolution model with a pre-processed width level of 2;(3) presentation of a composite residual structure that designs a multi-level quick link; and (4) addition of a Dropout layer after the parameter optimization. The algorithm shows superior results on MNIST and SVHN dataset, which are two character benchmark recognition datasets, and achieves better recognition accuracy and higher recognition efficiency than other deep structures with the same number of layers.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.3
• /
• pp.962-975
• /
• 2020

The accurate segmentation of infant brain MR image into white matter (WM), gray matter (GM), and cerebrospinal fluid (CSF) is very important for early studying of brain growing patterns and morphological changes in neurodevelopmental disorders. Because of inherent myelination and maturation process, the WM and GM of babies (between 6 and 9 months of age) exhibit similar intensity levels in both T1-weighted (T1w) and T2-weighted (T2w) MR images in the isointense phase, which makes brain tissue segmentation very difficult. We propose a deep network architecture based on U-Net, called Triple Residual Multiscale Fully Convolutional Network (TRMFCN), whose structure exists three gates of input and inserts two blocks: residual multiscale block and concatenate block. We solved some difficulties and completed the segmentation task with the model. Our model outperforms the U-Net and some cutting-edge deep networks based on U-Net in evaluation of WM, GM and CSF. The data set we used for training and testing comes from iSeg-2017 challenge (http://iseg2017.web.unc.edu).

• Journal of Korean Society on Water Environment
• /
• v.27 no.3
• /
• pp.334-341
• /
• 2011

The free residual chlorine of tap water samples, collected from 266 faucets on the water pipe network in Daegu City, was between 0.1 and 0.79 mg/L. On microorganic tests, general bacteria and the coliform goup were not detected and thus the tap water was turned out to be fit to drink. In particular, samples of which free residual chlorine was 0.1 mg/L and over were cultured in R2A agar media at $25^{\circ}C$ for 7 days, and as a result heterotrophic bacteria were detected in 65.9% of samples; (1). The closer tap water got to the faucet from the stilling basin, the lower residual chlorine concentration became but the more the bacterial count became. And, more bacteria were detected in the R2A agar medium than in the PCA medium. (2). In the case of separated strains, most colonies were reddish or yellowish. 16S rRNA sequence was identified as Methylobacterium sp. and Williamsia sp., and yellow strain was identified as Sphingomonas sp., Sphingobium sp., Novosphingobium sp., Blastomonas sp., Rhodococcus sp. and Microbacterium sp. White strain was identified as Staphylococcus sp. (3). Sterilized tap water in polyethylene bottles was inoculated with separated strain and was left as it was for 2 months. As a result, bio-film was observed in tap water inoculated with Methylobacterium sp. and Sphingomonas sp. It was found that heterotrophic bacteria increased when free residual chlorine was removed from tap water in the water pipe network. Thus, there is a need to determine a base value for heterotrophic bacteria in order to check the cleanliness of tap water in the water pipe network.

• Journal of Broadcast Engineering
• /
• v.26 no.4
• /
• pp.429-440
• /
• 2021

With the recent development of deep convolutional neural network learning, deep learning techniques applied to single image super-resolution are showing good results. One of the existing deep learning-based super-resolution techniques is RDN(Residual Dense Network), in which the initial feature information is transmitted to the last layer using residual dense blocks, and subsequent layers are restored using input information of previous layers. However, if all hierarchical features are connected and learned and a large number of residual dense blocks are stacked, despite good performance, a large number of parameters and huge computational load are needed, so it takes a lot of time to learn a network and a slow processing speed, and it is not applicable to a mobile system. In this paper, we use the residual dense structure, which is a continuous memory structure that reuses previous information, and the residual dense channel attention block using the channel attention method that determines the importance according to the feature map of the image. We propose a method that can increase the depth to obtain a large receptive field and maintain a concise model at the same time. As a result of the experiment, the proposed network obtained PSNR as low as 0.205dB on average at 4× magnification compared to RDN, but about 1.8 times faster processing speed, about 10 times less number of parameters and about 1.74 times less computation.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2019.06a
• /
• pp.98-101
• /
• 2019

At present, deep convolutional neural networks have made a very important contribution in single-image super-resolution. Through the learning of the neural networks, the features of input images are transformed and combined to establish a nonlinear mapping of low-resolution images to high-resolution images. Some previous methods are difficult to train and take up a lot of memory. In this paper, we proposed a simple and compact deep recursive residual network learning the features for single image super resolution. Global residual learning and local residual learning are used to reduce the problems of training deep neural networks. And the recursive structure controls the number of parameters to save memory. Experimental results show that the proposed method improved image qualities that occur in previous methods.

• Journal of radiological science and technology
• /
• v.46 no.4
• /
• pp.277-285
• /
• 2023

In this study, pneumonia identification networks with the small number of layers were constructed by using chest X-ray images. The networks had similar trainable-parameters, and the performance of the trained models was quantitatively evaluated with the modification of the network architectures. A total of 6 networks were constructed: convolutional neural network (CNN), VGGNet, GoogleNet, residual network with identity blocks, ResNet with bottleneck blocks and ResNet with identity and bottleneck blocks. Trainable parameters for the 6 networks were set in a range of 273,921-294,817 by adjusting the output channels of convolution layers. The network training was implemented with binary cross entropy (BCE) loss function, sigmoid activation function, adaptive moment estimation (Adam) optimizer and 100 epochs. The performance of the trained models was evaluated in terms of training time, accuracy, precision, recall, specificity and F1-score. The results showed that the trained models with the small number of layers precisely detect pneumonia from chest X-ray images. In particular, the overall quantitative performance of the trained models based on the ResNets was above 0.9, and the performance levels were similar or superior to those based on the CNN, VGGNet and GoogleNet. Also, the residual blocks affected the performance of the trained models based on the ResNets. Therefore, in this study, we demonstrated that the object detection networks with the small number of layers are suitable for detecting pneumonia using chest X-ray images. And, the trained models based on the ResNets can be optimized by applying appropriate residual-blocks.

• International journal of advanced smart convergence
• /
• v.12 no.4
• /
• pp.142-146
• /
• 2023

We present a method for generating 3D structures and rendering objects by combining VAE (Variational Autoencoder) and GAN (Generative Adversarial Network). This approach focuses on generating and rendering 3D models with improved quality using residual learning as the learning method for the encoder. We deep stack the encoder layers to accurately reflect the features of the image and apply residual blocks to solve the problems of deep layers to improve the encoder performance. This solves the problems of gradient vanishing and exploding, which are problems when constructing a deep neural network, and creates a 3D model of improved quality. To accurately extract image features, we construct deep layers of the encoder model and apply the residual function to learning to model with more detailed information. The generated model has more detailed voxels for more accurate representation, is rendered by adding materials and lighting, and is finally converted into a mesh model. 3D models have excellent visual quality and accuracy, making them useful in various fields such as virtual reality, game development, and metaverse.

• Journal of Advanced Navigation Technology
• /
• v.22 no.5
• /
• pp.375-383
• /
• 2018

In order to apply the Network RTK (real time kinematics) technology, which has been used for positioning of stationary points, to the navigation of vehicles, its infrastructure should provide correction data with a quality indicator that can show the expected accuracy in real time. In this paper, we analyzed various indicator generation algorithms such as I95 (ionospheric index 95) / G95 (geodetic index 95), SBI (semivariance based index) and RIU (residual interpolation uncertainty). We also applied them to the raw observables from the reference stations of National Geographic Information Institute and VRS (virtual reference station) users, and then examined its feasibility to be used as a real-time performance index of the Network RTK rover. 24 hour data analysis shows that the RIU index, which can represent the non-linearty of the correction, has the strongest correlation with the Network RTK rover accuracy. Therefore, RIU index is expected to be used as a real-time performance index of the Network RTK rover.

• Journal of Korea Water Resources Association
• /
• v.55 no.1
• /
• pp.59-70
• /
• 2022

Water distribution systems (WDSs) are a representative infrastructure injecting chlorine to disinfect the pathogenic microorganisms and supplying water from sources to consumers. Also, WDSs prescribe to maintain the usual standard (0.1-4.0 mg/L) of residual chlorine. However, the user's usage pattern, water age, network shape, and type affect the hydraulic features (i.e. nodal pressure, pipe velocity) and water quality features (i.e., the residual chlorine concentration). Therefore, this study developed an optimization approach for optimizing WDSs considering water quality-hydraulic factors using Multi-objective Harmony Search (MOHS). The design cost and the system resilience were applied as the design objective functions, and the nodal pressure and the concentration of residual chlorine are used as constraints. The derived optimal designs through this approach were analyzed according to network characteristics such as the network shapes and type. These optimal designs can meet the safety of economic and water quality aspects to increase user acceptance.