• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.4
• /
• pp.161-167
• /
• 2019

Recently, demand forecasting techniques have been actively studied due to interest in stable power supply with surging power demand, and increase in spread of smart meters that enable real-time power measurement. In this study, we proceeded the deep learning prediction model experiments which learns actual measured power usage data of home and outputs the forecasting result. And we proceeded pre-processing with moving average method. The predicted value made by the model is evaluated with the actual measured data. Through this forecasting, it is possible to lower the power supply reserve ratio and reduce the waste of the unused power. In this paper, we conducted experiments on three types of networks: Multi Layer Perceptron (MLP), Recurrent Neural Network (RNN), and Long Short Term Memory (LSTM) and we evaluate the results of each scheme. Evaluation is conducted with following method: MSE(Mean Squared Error) method and MAE(Mean Absolute Error).

• Journal of the Institute of Convergence Signal Processing
• /
• v.21 no.4
• /
• pp.183-194
• /
• 2020

Recently, the number of hip dysplasia (DDH) that occurs during infant and child growth has been increasing. DDH should be detected and treated as early as possible because it hinders infant growth and causes many other side effects In this study, two modelling techniques were used for multiple training techniques. Based on the results after the first transformation, the training was designed to be possible even with a small amount of data. The vertical flip, rotation, width and height shift functions were used to improve the efficiency of the model. Adam optimization was applied for parameter learning with the learning parameter initially set at 2.0 x 10e-4. Training was stopped when the validation loss was at the minimum. respectively A novel image overlay system using 3D laser scanner and a non-rigid registration method is implemented and its accuracy is evaluated. By using the proposed system, we successfully related the preoperative images with an open organ in the operating room

• Journal of Advanced Navigation Technology
• /
• v.19 no.6
• /
• pp.484-491
• /
• 2015

Aerial scene is greatly increased by the introduction and supply of the image due to the growth of digital optical imaging technology and development of the UAV. It has been used as the extraction of ground properties, classification, change detection, image fusion and mapping based on the aerial image. In particular, in the image analysis and utilization of deep learning algorithm it has shown a new paradigm to overcome the limitation of the field of pattern recognition. This paper presents the possibility to apply a more wide range and various fields through the segmentation and classification of aerial scene based on the Deep learning(ConvNet). We build 4-classes image database consists of Road, Building, Yard, Forest total 3000. Each of the classes has a certain pattern, the results with feature vector map come out differently. Our system consists of feature extraction, classification and training. Feature extraction is built up of two layers based on ConvNet. And then, it is classified by using the Multilayer perceptron and Logistic regression, the algorithm as a classification process.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2022.11a
• /
• pp.29-30
• /
• 2022

The unit-water content has a very significant effect on the durability of the construction structure and the quality of concrete. Although there are various methods for measuring the unit-water content, there are problems of time required for measurement, precision, and reproducibility. Recently, there is an FDR sensor capable of measuring moisture content in real time through an apparent dielectric constant change of electromagnetic waves. In addition, various artificial intelligence techniques that can non-linearly supplement the accuracy of FDR sensors are being studied. In this study, the accuracy of unit-water content measurement was compared and evaluated using machine learning and deep learning techniques after normalizing the data secured in concrete using frequency domain reflectometry (FDR) sensors used to measure soil moisture at home and abroad. The result of comparing the accuracy of machine learning and deep learning is judged to be excellent in the accuracy of deep learning, which can well express the nonlinear relationship between FDR sensor data and concrete unit-water content.

• Journal of Convergence for Information Technology
• /
• v.11 no.5
• /
• pp.30-37
• /
• 2021

Various devices are connected to the Internet, and attacks using the Internet are occurring. Among such attacks, there are attacks that use malicious URLs to make users access to wrong phishing sites or distribute malicious viruses. Therefore, how to detect such malicious URL attacks is one of the important security issues. Among recent deep learning technologies, neural networks are showing good performance in image recognition, speech recognition, and pattern recognition. This neural network can be applied to research that analyzes and detects patterns of malicious URL characteristics. In this paper, performance analysis according to various parameters was performed on a method of detecting malicious URLs using neural networks. In this paper, malicious URL detection performance was analyzed while changing the activation function, learning rate, and neural network structure. The experimental data was crawled by Alexa top 1 million and Whois to build the data, and the machine learning library used TensorFlow. As a result of the experiment, when the number of layers is 4, the learning rate is 0.005, and the number of nodes in each layer is 100, the accuracy of 97.8% and the f1 score of 92.94% are obtained.

• Journal of Convergence for Information Technology
• /
• v.10 no.6
• /
• pp.140-146
• /
• 2020

Since the current crime prevention systems have a standard mechanism that victims request for help by themselves or ask for help from a third party nearby, it is difficult to obtain appropriate help in situations where a prompt response is not possible. In this study, we proposed and developed an automatic rescue request model and system using Deep Learning and OpenCV. This study is based on the prerequisite that immediate and precise threat detection is essential to ensure the user's safety. We validated and verified that the system identified by more than 99% of the object's accuracy to ensure the user's safety, and it took only three seconds to complete all necessary algorithms. We plan to collect various types of threats and a large amount of data to reinforce the system's capabilities so that the system can recognize and deal with all dangerous situations, including various threats and unpredictable cases.

• The Journal of the Convergence on Culture Technology
• /
• v.4 no.4
• /
• pp.393-399
• /
• 2018

The development of unmanned AI continues, and the development of AI unmanned is aimed at more efficiently, accurately, and speedily the work that has been resolved by manpower such as industry, welfare, and manpower. AI unmanned technology is evolving in various places, and it is time to switch to unmanned systems from many industries and factories. We take this into consideration, and use the Deep Learning technology, which is one of the core technologies of artificial intelligence (AI), not the manpower but the fruits that pour the rails at once in a large orchard. We want to study the unmanned fruit sorting machine that can be operated under manager's supervision without dividing the fruit by type and grade and dividing by country of origin and grade. This unmanned automated classification system aims to reduce the labor cost by minimizing the manpower and to improve the

• Journal of the Korea Convergence Society
• /
• v.13 no.1
• /
• pp.51-62
• /
• 2022

AI-based speed prediction studies have been conducted quite actively. However, while the importance of explainable AI is emerging, the study of interpreting and reasoning the AI-based speed predictions has not been carried out much. Therefore, in this paper, 'Explainable Deep Graph Neural Network (GNN)' is devised to analyze the speed prediction and assess the nearby road influence for reasoning the critical contributions to a given road situation. The model's output was explained by comparing the differences in output before and after masking the input values of the GNN model. Using TOPIS traffic speed data, we applied our GNN models for the major congested roads in Seoul. We verified our approach through a traffic flow simulation by adjusting the most influential nearby roads' speed and observing the congestion's relief on the road of interest accordingly. This is meaningful in that our approach can be applied to the transportation network and traffic flow can be improved by controlling specific nearby roads based on the inference results.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.3
• /
• pp.571-580
• /
• 2022

Marine deposited waste is a major cause of problems such as a lot of damage and an increase in the estimated amount of garbage due to abandoned fishing grounds caused by ghost fishing. In this paper, we implement a real-time marine deposited waste detection artificial intelligence system to understand the actual conditions of waste fishing gear usage, distribution, loss, and recovery, and study methods for performance improvement. The system was implemented using the yolov5 model, which is an excellent performance model for real-time object detection, and the 'data screening process' and 'class segmentation' method of learning data were applied as performance improvement methods. In conclusion, the object detection results of datasets that do screen unnecessary data or do not subdivide similar items according to characteristics and uses are better than the object recognition results of unscreened datasets and datasets in which classes are subdivided.

• Journal of Convergence for Information Technology
• /
• v.12 no.2
• /
• pp.47-53
• /
• 2022

Recently, with the change of the intelligent security paradigm, study to apply various information generated from various information security systems to AI-based anomaly detection is increasing. Therefore, in this study, in order to convert log-like time series data into a vector, which is a numerical feature, the CBOW and Skip-gram inference methods of deep learning-based Word2Vec model and statistical method based on the coincidence frequency were used to transform the published ADFA system call data. In relation to this, an experiment was carried out through conversion into various embedding vectors considering the dimension of vector, the length of sequence, and the window size. In addition, the performance of the embedding methods used as well as the detection performance were compared and evaluated through GRU-based anomaly detection model using vectors generated by the embedding model as an input. Compared to the statistical model, it was confirmed that the Skip-gram maintains more stable performance without biasing a specific window size or sequence length, and is more effective in making each event of sequence data into an embedding vector.