• The Journal of the Acoustical Society of Korea
• /
• v.40 no.2
• /
• pp.130-138
• /
• 2021

This paper presents an effective structure by applying various normalization to Convolutional Neural Networks (CNN) for seismic event classification. Normalization techniques can not only improve the learning speed of neural networks, but also show robustness to noise. In this paper, we analyze the effect of input data normalization and hidden layer normalization on the deep learning model for seismic event classification. In addition an effective model is derived through various experiments according to the structure of the applied hidden layer. As a result of various experiments, the model that applied input data normalization and weight normalization to the first hidden layer showed the most stable performance improvement.

• Smart Structures and Systems
• /
• v.32 no.2
• /
• pp.83-99
• /
• 2023

The temperature prediction approaches of three important locations in an operational longitudinal slab track-bridge structure by using three typical neural network methods based on the field measuring platform of four meteorological factors and internal temperature. The measurement experiment of four meteorological factors (e.g., ambient temperature, solar radiation, wind speed, and humidity) temperature in the three locations of the longitudinal slab and base plate of three important locations (e.g., mid-span, beam end, and Wide-Narrow Joint) were conducted, and then their characteristics were analyzed, respectively. Furthermore, temperature prediction effects of three locations under five various meteorological conditions are tested by using three neural network methods, respectively, including the Artificial Neural Network (ANN), the Long Short-Term Memory (LSTM), and the Convolutional Neural Network (CNN). More importantly, the predicted effects of solar radiation in four meteorological factors could be identified with three indicators (e.g., Root Means Square Error, Mean Absolute Error, Correlation Coefficient of R2). In addition, the LSTM method shows the best performance, while the CNN method has the best prediction effect by only considering a single meteorological factor.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.35S no.11
• /
• pp.144-151
• /
• 1998

In this paper, it is applied the analysis properties of mathematical morphology in order to process MIN/MAX operation on the basis of combination of predefined and weighted structuring element to FCNN having the structure of CNN combined with fuzzy logic between template and input/output. In this paper, as the fuzzy estimator is applied to the image including noise, thus it could be found the noise removal as well as the edge detection in the process of computer simulation. We could analyze and compare the results of edge detection using FCNN, CNN and median filter to which the erosion operation of morphology is applied. This paper could apply the static template and the variable template to FCNN using the quantization fuzzy function, in result we could confirm that the performance of FCNN got to improve in the process of computer simulation.

• Journal of Korea Society of Industrial Information Systems
• /
• v.24 no.4
• /
• pp.1-8
• /
• 2019

Plant phenomics is a technique for observing and analyzing morphological features in order to select plant varieties of excellent traits. The conventional methods is difficult to apply to the phenomics system. because the color threshold value must be manually changed according to the detection target. In this paper, we propose the convolution neural network (CNN) structure that can automatically segment plants from the background for the phenomics system. The LeafNet consists of nine convolution layers and a sigmoid activation function for determining the presence of plants. As a result of the learning using the LeafNet, we obtained a precision of 98.0% and a recall rate of 90.3% for the plant seedlings images. This confirms the applicability of the phenomics system.

• Journal of the Architectural Institute of Korea Structure & Construction
• /
• v.36 no.3
• /
• pp.113-120
• /
• 2020

The purpose of this study is to compare the models of Deep Learning-based Convolution Neural Network(CNN) for concrete crack detection. The comparison models are AlexNet, GoogLeNet, VGG16, VGG19, ResNet-18, ResNet-50, ResNet-101, and SqueezeNet which won ImageNet Large Scale Visual Recognition Challenge(ILSVRC). To train, validate and test these models, we constructed 3000 training data and 12000 validation data with 256×256 pixel resolution consisting of cracked and non-cracked images, and constructed 5 test data with 4160×3120 pixel resolution consisting of concrete images with crack. In order to increase the efficiency of the training, transfer learning was performed by taking the weight from the pre-trained network supported by MATLAB. From the trained network, the validation data is classified into crack image and non-crack image, yielding True Positive (TP), True Negative (TN), False Positive (FP), False Negative (FN), and 6 performance indicators, False Negative Rate (FNR), False Positive Rate (FPR), Error Rate, Recall, Precision, Accuracy were calculated. The test image was scanned twice with a sliding window of 256×256 pixel resolution to classify the cracks, resulting in a crack map. From the comparison of the performance indicators and the crack map, it was concluded that VGG16 and VGG19 were the most suitable for detecting concrete cracks.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.10
• /
• pp.1551-1558
• /
• 2022

We propose a two-tier cooperative computing system comprised of a mobile device and an edge server for partial offloading of multi-branch structures in Fog/Edge Computing environments in this paper. The proposed system includes an algorithm for splitting up application service processing by using reconstructive linearization techniques for multi-branch structures, as well as an optimal collaboration algorithm based on partial offloading between mobile device and edge server. Furthermore, we formulate computation offloading and CNN layer scheduling as latency minimization problems and simulate the effectiveness of the proposed system. As a result of the experiment, the proposed algorithm is suitable for both DAG and chain topology, adapts well to different network conditions, and provides efficient task processing strategies and processing time when compared to local or edge-only executions. Furthermore, the proposed system can be used to conduct research on the optimization of the model for the optimal execution of application services on mobile devices and the efficient distribution of edge resource workloads.

• Journal of IKEEE
• /
• v.26 no.3
• /
• pp.364-372
• /
• 2022

This paper proposes the design and implementation results for human and object classification systems utilizing frequency modulated continuous wave (FMCW) radar sensor. Such a system requires the process of radar sensor signal processing for multi-target detection and the process of deep learning for the classification of human and object. Since deep learning requires such a great amount of computation and data processing, the lightweight process is utmost essential. Therefore, binary neural network (BNN) structure was adopted, operating convolution neural network (CNN) computation in a binary condition. In addition, for the real-time operation, a hardware accelerator was implemented and verified via FPGA platform. Based on performance evaluation and verified results, it is confirmed that the accuracy for multi-target classification of 90.5%, reduced memory usage by 96.87% compared to CNN and the run time of 5ms are achieved.

• Journal of Positioning, Navigation, and Timing
• /
• v.11 no.3
• /
• pp.217-227
• /
• 2022

In order to provide a location-based services regardless of indoor or outdoor space, it is important to provide position information of the terminal regardless of location. Among the wireless/mobile communication resources used for this purpose, Long Term Evolution (LTE) signal is a representative infrastructure that can overcome spatial limitations, but the positioning method based on the location of the base station has a disadvantage in that the accuracy is low. Therefore, a fingerprinting technique, which is a pattern recognition technology, has been widely used. The simplest yet widely applied algorithm among Fingerprint positioning technologies is k-Nearest Neighbors (kNN). However, in the kNN algorithm, it is difficult to find the optimal K value with the lowest positioning error for each location to be estimated, so it is generally fixed to an appropriate K value and used. Since the optimal K value cannot be applied to each estimated location, therefore, there is a problem in that the accuracy of the overall estimated location information is lowered. Considering this problem, this paper proposes a technique for adaptively varying the K value by using a Convolutional Neural Network (CNN) model among Artificial Neural Network (ANN) techniques. First, by using the signal information of the measured values obtained in the service area, an image is created according to the Physical Cell Identity (PCI) and Band combination, and an answer label for supervised learning is created. Then, the structure of the CNN is modeled to classify K values through the image information of the measurements. The performance of the proposed technique is verified based on actual data measured in the testbed. As a result, it can be seen that the proposed technique improves the positioning performance compared to using a fixed K value.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.3
• /
• pp.449-458
• /
• 2023

Many people think that sign language is only for people who are deaf and cannot speak, but of course it is necessary for people who want to talk with them. One of the biggest challenges in ASL(American Sign Language) alphabet recognition is the high inter-class similarities and high intra-class variance. In this paper, we proposed an architecture that can overcome these two problems, which performs similarity learning to reduces inter-class similarities and intra-class variance between images. The proposed architecture consists of the same convolutional neural network with a double configuration that shares parameters (weights and biases) and also applies the Keras API to reduce similarity learning and variance through this pathway. The similarity learning results the use of the dual CNN shows that the accuracy is improved by reducing the similarity and variability between classes by not including the poor results of the two classes.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.7 no.10
• /
• pp.935-943
• /
• 2017

CNN (Convolution neural network), which is used for image classification and speech recognition among neural networks learning based on positive data, has been continuously developed to have a high performance structure to date. There are many difficulties to utilize in an embedded system with limited resources. Therefore, we use GPU (General-Purpose Computing on Graphics Processing Units), which is used for general-purpose operation of GPU to solve the problem because we use pre-learned weights but there are still limitations. Since CNN performs simple and iterative operations, the computation speed varies greatly depending on the thread allocation and utilization method in the Single Instruction Multiple Thread (SIMT) based GPGPU. To solve this problem, there is a thread that needs to be relaxed when performing Convolution and Pooling operations with threads. The remaining threads have increased the operation speed by using the method used in the following feature maps and kernel calculations.