• Journal of Advanced Navigation Technology
• /
• v.25 no.4
• /
• pp.299-304
• /
• 2021

Existing human activity recognition systems detect activities through devices such as wearable sensors and cameras. However, these methods require additional devices and costs, especially for cameras, which cause privacy issue. Using WiFi signals that are already installed can solve this problem. In this paper, we propose a CNN-based human activity recognition system using channel state information of WiFi signals, and present results of designing and implementing accelerated hardware structures. The system defined four possible behaviors during studying in indoor environments, and classified the channel state information of WiFi using convolutional neural network (CNN), showing and average accuracy of 91.86%. In addition, for acceleration, we present the results of an accelerated hardware structure design for fully connected layer with the highest computation volume on CNN classifiers. As a result of performance evaluation on FPGA device, it showed 4.28 times faster calculation time than software-based system.

• Journal of Convergence for Information Technology
• /
• v.12 no.1
• /
• pp.31-38
• /
• 2022

This paper applies an expert independent unsupervised neural network learning-based multivariate time series data analysis model, MSCRED(Multi-Scale Convolutional Recurrent Encoder-Decoder), and to overcome the limitation, because the MCRED is based on Auto-encoder model, that train data must not to be contaminated, by using learning data sampling technique, called Subset Sampling Validation. By using the vibration data of power plant equipment that has been labeled, the classification performance of MSCRED is evaluated with the Anomaly Score in many cases, 1) the abnormal data is mixed with the training data 2) when the abnormal data is removed from the training data in case 1. Through this, this paper presents an expert-independent anomaly diagnosis framework that is strong against error data, and presents a concise and accurate solution in various fields of multivariate time series data.

• Phonetics and Speech Sciences
• /
• v.13 no.4
• /
• pp.47-53
• /
• 2021

Autoregressive Text-to-Speech (TTS) models suffer from inference instability and slow inference speed. Inference instability occurs when a poorly predicted sample at time step t affects all the subsequent predictions. Slow inference speed arises from a model structure that forces the predicted samples from time steps 1 to t-1 to predict the sample at time step t. In this study, an end-to-end non-autoregressive fast text-to-speech model is suggested as a solution to these problems. The results of this study show that this model's Mean Opinion Score (MOS) is close to that of Tacotron 2 - WaveNet, while this model's inference speed and stability are higher than those of Tacotron 2 - WaveNet. Further, this study aims to offer insight into the improvement of non-autoregressive models.

• Journal of Convergence for Information Technology
• /
• v.12 no.1
• /
• pp.39-44
• /
• 2022

The purpose of this study is to extract the type, location, and absolute size of an object in an image using a deep learning algorithm, predict the relative distance between objects, and use this to detect contact between objects. To analyze the size ratio of objects, YOLO, a CNN-based object detection algorithm, is used. Through the YOLO algorithm, the absolute size and position of an object are extracted in the form of coordinates. The extraction result extracts the ratio between the size in the image and the actual size from the standard object-size list having the same object name and size stored in advance, and predicts the relative distance between the camera and the object in the image. Based on the predicted value, it detects whether the objects are in contact.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.1
• /
• pp.15-23
• /
• 2022

Among the learning methods for Continuous Learning environments, "Learning without Forgetting" has fixed regularization strengths, which can lead to poor performance in environments where various data are received. We suggest a way to set weights variable by identifying the features of the data we want to learn. We applied weights adaptively using correlation and complexity. Scenarios with various data are used for evaluation and experiments showed accuracy increases by up to 5% in the new task and up to 11% in the previous task. In addition, it was found that the adaptive weight value obtained by the algorithm proposed in this paper, approached the optimal weight value calculated manually by repeated experiments for each experimental scenario. The correlation coefficient value is 0.739, and overall average task accuracy increased. It can be seen that the method of this paper sets an appropriate lambda value every time a new task is learned, and derives the optimal result value in various scenarios.

• Journal of the Economic Geographical Society of Korea
• /
• v.25 no.1
• /
• pp.171-181
• /
• 2022

The real estate price index plays key roles as quantitative data in real estate market analysis. International organizations including OECD publish the real estate price indexes by country, and the Korea Real Estate Board announces metropolitan-level and municipal-level indexes. However, when the index is set on the smaller spatial unit level than metropolitan and municipal-level, problems occur: missing values. As the spatial scope is narrowed down, there are cases where there are few or no transactions depending on the unit period, which lead index calculation difficult or even impossible. This study suggests a supervised learning-based machine learning model to compensate for missing values that may occur due to no transaction in a specific range and period. The models proposed in our research verify the accuracy of predicting the existing values and missing values.

• Journal of the Korean Society of Industry Convergence
• /
• v.25 no.2_1
• /
• pp.177-184
• /
• 2022

The automatic defect sorting function of machinery parts is being introduced to the automation of the manufacturing process. In the final stage of automation of the manufacturing process, it is necessary to apply computer vision rather than human visual judgment to determine whether there is a defect. In this paper, we introduce a deep learning method to improve the classification performance of typical mechanical parts, such as welding parts, galvanized round plugs, and electro galvanized nuts, based on the results of experiments. In the case of poor welding, the method to further increase the depth of layer of the basic deep learning model was effective, and in the case of a circular plug, the surrounding data outside the defective target area affected it, so it could be solved through an appropriate pre-processing technique. Finally, in the case of a nut plated with zinc, since it receives data from multiple cameras due to its three-dimensional structure, it is greatly affected by lighting and has a problem in that it also affects the background image. To solve this problem, methods such as two-dimensional connectivity were applied in the object segmentation preprocessing process. Although the experiments suggested that the proposed methods are effective, most of the provided good/defective images data sets are relatively small, which may cause a learning balance problem of the deep learning model, so we plan to secure more data in the future.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.20 no.6
• /
• pp.242-263
• /
• 2021

This paper presents a method to implement a low-cost driving simulator for developing autonomous driving algorithms. This is implemented by using GTA V, a physical engine-based commercial game software, containing a function to emulate output and data of various sensors for autonomous driving. For this, NF of Script Hook V is incorporated to acquire GT data by accessing internal data of the software engine, and then, various sensor data for autonomous driving are generated. We present an overall function of the developed driving simulator and perform a verification of individual functions. We explain the process of acquiring GT data via direct access to the internal memory of the game engine to build up an autonomous driving algorithm development environment. And, finally, an example applicable to artificial neural network training and performance evaluation by processing the emulated sensor output is included.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.16 no.6
• /
• pp.1355-1362
• /
• 2021

Recently, not only congenital hearing impairment, but also the number of people with hearing impairment due to acquired factors is increasing. The environment in which sign language can be learned is poor. Therefore, this study intends to present a sign language (sign language number/sign language text) evaluation system as a sign language learning assistance tool for sign language learners. Therefore, in this paper, sign language is captured as an image using OpenCV and Convolutional Neural Network (CNN). In addition, we study a system that recognizes sign language behavior using MediaPipe, converts the meaning of sign language into text-type data, and provides it to users. Through this, self-directed learning is possible so that learners who learn sign language can judge whether they are correct dez. Therefore, we develop a sign language learning assistance system that helps us learn sign language. The purpose is to propose a sign language learning assistance system as a way to support sign language learning, the main language of communication for the hearing impaired.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.11
• /
• pp.491-500
• /
• 2021

In this study, we propose a method for detecting fall behavior using MS Kinect v2 RGBD Camera-based Human-Skeleton Keypoints and a 2-Stacked Bi-LSTM model. In previous studies, skeletal information was extracted from RGB images using a deep learning model such as OpenPose, and then recognition was performed using a recurrent neural network model such as LSTM and GRU. The proposed method receives skeletal information directly from the camera, extracts 2 time-series features of acceleration and distance, and then recognizes the fall behavior using the 2-Stacked Bi-LSTM model. The central joint was obtained for the major skeletons such as the shoulder, spine, and pelvis, and the movement acceleration and distance from the floor were proposed as features of the central joint. The extracted features were compared with models such as Stacked LSTM and Bi-LSTM, and improved detection performance compared to existing studies such as GRU and LSTM was demonstrated through experiments.