• International Journal of Advanced Culture Technology
• /
• v.5 no.2
• /
• pp.74-81
• /
• 2017

Recently, there are many companies that use systems based on artificial intelligence. The accuracy of artificial intelligence depends on the amount of learning data and the appropriate algorithm. However, it is not easy to obtain learning data with a large number of entity. Less data set have large generalization errors due to overfitting. In order to minimize this generalization error, this study proposed DGA(Dropout Genetic Algorithm) which can expect relatively high accuracy even though data with a less data set is applied to machine learning based genetic algorithm to deep learning based dropout. The idea of this paper is to determine the active state of the nodes. Using Gradient about loss function, A new fitness function is defined. Proposed Algorithm DGA is supplementing stochastic inconsistency about Dropout. Also DGA solved problem by the complexity of the fitness function and expression range of the model about Genetic Algorithm As a result of experiments using MNIST data proposed algorithm accuracy is 75.3%. Using only Dropout algorithm accuracy is 41.4%. It is shown that DGA is better than using only dropout.

• Advances in concrete construction
• /
• v.9 no.3
• /
• pp.257-265
• /
• 2020

Many failures of concrete structures are related to steel corrosion. For this reason, it is important to recognize how the carbonation can affect the durability of reinforced concrete structures. The repeatability of the carbonation depth measure in a specimen of concrete sprayed with a phenolphthalein solution is consistently low whereby it is necessary to have an impartial method to measure the carbonation depth. This study presents two automatic algorithms to detect the non-carbonated zone in concrete specimens. The first algorithm is based solely on digital processing image (DPI), mainly morphological and threshold techniques. The second algorithm is based on artificial intelligence, more specifically on an array of Kohonen networks, but also using some DPI techniques to refine the results. Moreover, another algorithm was developed with the purpose of measure the carbonation depth from the image obtained previously.

• The Journal of Information Systems
• /
• v.25 no.4
• /
• pp.23-36
• /
• 2016

Purpose Recently, many researchers have paid much attention to the Artificial Intelligence fields of GVGP, PCG. The paper suggests that the improved MCTS algorithm to apply for the framework can generate better AI agent. Design/methodology/approach As noted, the MCTS generate magnificent performance without an advanced training and in turn, fit applying to the field of GVGP which does not need prior knowledge. The improved and modified MCTS shows that the survival rate is increased interestingly and the search can be done in a significant way. The study was done with 2 different sets. Findings The results showed that the 10 training set which was not given any prior knowledge and the other training set which played a role as validation set generated better performance than the existed MCTS algorithm. Besed upon the results, the further study was suggested.

• International Journal of Internet, Broadcasting and Communication
• /
• v.11 no.2
• /
• pp.50-58
• /
• 2019

The clear and specific objective of this study is to design a false news discriminator algorithm for news articles transmitted on a text-based basis and an architecture that builds it into a system (H/W configuration with Hadoop-based in-memory technology, Deep Learning S/W design for bigdata and SNS linkage). Based on learning data on actual news, the government will submit advanced "fake news" test data as a result and complete theoretical research based on it. The need for research proposed by this study is social cost paid by rumors (including malicious comments) and rumors (written false news) due to the flood of fake news, false reports, rumors and stabbings, among other social challenges. In addition, fake news can distort normal communication channels, undermine human mutual trust, and reduce social capital at the same time. The final purpose of the study is to upgrade the study to a topic that is difficult to distinguish between false and exaggerated, fake and hypocrisy, sincere and false, fraud and error, truth and false.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.6
• /
• pp.834-841
• /
• 2022

Recently, applying artificial intelligence technologies in various fields of production has drawn an upsurge of research interest due to the increase for smart factory and artificial intelligence technologies. A great deal of effort is being made to introduce artificial intelligence algorithms into the defect detection task. Particularly, detection of defects on the surface of metal has a higher level of research interest compared to other materials (wood, plastics, fibers, etc.). In this paper, we compare and analyze the speed and performance of defect classification by combining machine learning techniques (Support Vector Machine, Softmax Regression, Decision Tree) with dimensionality reduction algorithms (Principal Component Analysis, AutoEncoders) and two convolutional neural networks (proposed method, ResNet). To validate and compare the performance and speed of the algorithms, we have adopted two datasets ((i) public dataset, (ii) actual dataset), and on the basis of the results, the most efficient algorithm is determined.

• Journal of Korean Society on Water Environment
• /
• v.35 no.4
• /
• pp.370-378
• /
• 2019

In the recent years, various studies have presented stable and economic methods for increased regulations and compliance in sewage treatment plants. In some sewage treatment plants, the effluent concentration exceeded the regulations, or the effluent concentration was manipulated. This indicates that the process is currently inefficient to operate and control sewage treatment plants. The operation and control method of sewage treatment plant is mathematically dealing with a physical and chemical mechanism for the anticipated situation during operation. In addition, there are some limitations, such as situations that are different from the actual sewage treatment plant. Therefore, it is necessary to find a more stable and economical way to enhance the operational and control method. AI (Artificial Intelligence) technology is selected among various methods. There are very few cases of applying and utilizing AI technology in domestic sewage treatment plants. In addition, it failed to define specific definitions of applying AI technologies. The purpose of this study is to present the application of AI technology to domestic sewage treatment plants by comparing and analyzing various cases. This study presented the AI technology algorithm system, verification method, data collection, energy and operating costs as methods of applying AI technology.

• Korean Journal of Artificial Intelligence
• /
• v.11 no.4
• /
• pp.15-20
• /
• 2023

Machine learning is comprised of supervised learning, unsupervised learning and reinforcement learning as the type of data and processing mechanism. In this paper, as input and output are unclear and it is difficult to apply the concrete modeling mathematically, reinforcement learning method are applied for crawling robot in this paper. Especially, Q-Learning is the most effective learning technique in model free reinforcement learning. This paper presents a method to implement a crawling robot that is operated by finding the most optimal crawling method through trial and error in a dynamic environment using a Q-learning algorithm. The goal is to perform reinforcement learning to find the optimal two motor angle for the best performance, and finally to maintain the most mature and stable motion about EV3 Crawling robot. In this paper, for the production of the crawling robot, it was produced using Lego Mindstorms with two motors, an ultrasonic sensor, a brick and switches, and EV3 Classroom SW are used for this implementation. By repeating 3 times learning, total 60 data are acquired, and two motor angles vs. crawling distance graph are plotted for the more understanding. Applying the Q-learning reinforcement learning algorithm, it was confirmed that the crawling robot found the optimal motor angle and operated with trained learning, and learn to know the direction for the future research.

• The Journal of Korea Robotics Society
• /
• v.19 no.1
• /
• pp.106-116
• /
• 2024

Ensuring robust 3D object detection is a core challenge for autonomous driving systems operating in urban environments. To tackle this issue, various 3D representation, including point cloud, voxels, and pillars, have been widely adopted, making use of LiDAR, Camera, and Radar sensors. These representations improved 3D object detection performance, but real-world urban scenarios with unexpected situations can still lead to numerous false positives, posing a challenge for robust 3D models. This paper presents a post-processing algorithm that dynamically adjusts object detection thresholds based on the distance from the ego-vehicle. While conventional perception algorithms typically employ a single threshold in post-processing, 3D models perform well in detecting nearby objects but may exhibit suboptimal performance for distant ones. The proposed algorithm tackles this issue by employing adaptive thresholds based on the distance from the ego-vehicle, minimizing false negatives and reducing false positives in the 3D model. The results show performance enhancements in the 3D model across a range of scenarios, encompassing not only typical urban road conditions but also scenarios involving adverse weather conditions.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.24 no.3
• /
• pp.63-67
• /
• 2024

Recently, artificial intelligence (AI) workloads encompassing various industries such as smart logistics, FinTech, and entertainment are being executed on the cloud. In this paper, we address the scheduling issues of various AI workloads on a multi-tenant cloud system composed of heterogeneous GPU clusters. Traditional scheduling decreases GPU utilization in such environments, degrading system performance significantly. To resolve these issues, we present a new scheduling approach utilizing genetic algorithm-based optimization techniques, implemented within a process-based event simulation framework. Trace driven simulations with diverse AI workload traces collected from Alibaba's MLaaS cluster demonstrate that the proposed scheduling improves GPU utilization compared to conventional scheduling significantly.

• Korean Journal of Artificial Intelligence
• /
• v.12 no.3
• /
• pp.9-15
• /
• 2024

This paper addresses the critical need for quadcopters in GPS-denied indoor environments by proposing a novel attitude control mechanism that enables autonomous navigation without external guidance. Utilizing AR marker detection integrated with a dual PID controller algorithm, this system ensures accurate maneuvering and positioning of the quadcopter by compensating for the absence of GPS, a common limitation in indoor settings. This capability is paramount in environments where traditional navigation aids are ineffective, necessitating the use of quadcopters equipped with advanced sensors and control systems. The actual position and location of the quadcopter is achieved by AR marker detection technique with the image processing system. Moreover, in order to enhance the reliability of the attitude PID control, the dual closed loop control feedback PID control with dual update periods is suggested. With AR marker detection technique and autonomous attitude control, the proposed quadcopter system decreases the need of additional sensor and manual manipulation. The experimental results are demonstrated that the quadrotor's autonomous attitude control and operation with the dual closed loop control feedback PID controller with hierarchical (inner-loop and outer-loop) command update period is successfully performed under the non-GPS aided indoor environment and it enhanced the reliability of the attitude and the position PID controllers within 17 seconds. Therefore, it is concluded that the proposed attitude control mechanism is very suitable to GPS-denied indoor environments, which enables a quadcopter to autonomously navigate and hover without external guidance or control.