• International Journal of Advanced Culture Technology
• /
• v.10 no.3
• /
• pp.360-370
• /
• 2022

Demand for machine learning systems continues to grow, and cloud machine learning platforms are widely used to meet this demand. Recently, the performance improvement of the application processor of smartphones has become an opportunity for the machine learning platform to move from the cloud to On-Device AI, and mobile applications equipped with machine learning functions are required. In this paper, machine learning tools for mobile applications are investigated and compared the characteristics of these tools.

• International Journal of Advanced Culture Technology
• /
• v.10 no.1
• /
• pp.230-235
• /
• 2022

This study is to select an optimal object detection algorithm for designing a self-checkout counter to improve the inconvenience of payment systems for products without existing barcodes. To this end, a performance comparison analysis of YOLO v2, Tiny YOLO v2, and the latest YOLO v5 among deep learning-based object detection algorithms was performed to derive results. In this paper, performance comparison was conducted by forming learning data as an example of 'donut' in a bakery store, and the performance result of YOLO v5 was the highest at 96.9% of mAP. Therefore, YOLO v5 was selected as the artificial intelligence object detection algorithm to be applied in this paper. As a result of performance analysis, when the optimal threshold was set for each donut, the precision and reproduction rate of all donuts exceeded 0.85, and the majority of donuts showed excellent recognition performance of 0.90 or more. We expect that the results of this paper will be helpful as the fundamental data for the development of an automatic payment system using AI self-service technology that is highly usable in the non-face-to-face era.

• Journal of Information Processing Systems
• /
• v.16 no.5
• /
• pp.1074-1082
• /
• 2020

Recently, research has been actively conducted to create artificial intelligence agents that learn games through reinforcement learning. There are several factors that determine performance when the agent learns a game, but using any of the activation functions is also an important factor. This paper compares and evaluates which activation function gets the best results if the agent learns the game through reinforcement learning in the 2D racing game environment. We built the agent using a reinforcement learning algorithm and a neural network. We evaluated the activation functions in the network by switching them together. We measured the reward, the output of the advantage function, and the output of the loss function while training and testing. As a result of performance evaluation, we found out the best activation function for the agent to learn the game. The difference between the best and the worst was 35.4%.

• ETRI Journal
• /
• v.42 no.5
• /
• pp.686-699
• /
• 2020

In this paper, we propose a supervised-learning-based spatial performance prediction (SLPP) framework for next-generation heterogeneous communication networks (HCNs). Adaptive asset placement, dynamic resource allocation, and load balancing are critical network functions in an HCN to ensure seamless network management and enhance service quality. Although many existing systems use measurement data to react to network performance changes, it is highly beneficial to perform accurate performance prediction for different systems to support various network functions. Recent advancements in complex statistical algorithms and computational efficiency have made machine-learning ubiquitous for accurate data-based prediction. A robust network performance prediction framework for optimizing performance and resource utilization through a linear discriminant analysis-based prediction approach has been proposed in this paper. Comparison results with different machine-learning techniques on real-world data demonstrate that SLPP provides superior accuracy and computational efficiency for both stationary and mobile user conditions.

• Journal of Korean Society for Quality Management
• /
• v.50 no.3
• /
• pp.459-471
• /
• 2022

Purpose: The purpose of this study was to increase prediction accuracy for an anomaly interval identified using an artificial intelligence-based time series anomaly detection technique by establishing a pre-processing process. Methods: Significant variables were extracted by applying feature selection techniques, and anomalies were derived using the TadGAN time series anomaly detection algorithm. After applying machine learning and deep learning methodologies using normal section data (excluding anomaly sections), the explanatory power of the anomaly sections was demonstrated through performance comparison. Results: The results of the machine learning methodology, the performance was the best when SHAP and TadGAN were applied, and the results in the deep learning, the performance was excellent when Chi-square Test and TadGAN were applied. Comparing each performance with the papers applied with a Conventional methodology using the same data, it can be seen that the performance of the MLR was significantly improved to 15%, Random Forest to 24%, XGBoost to 30%, Lasso Regression to 73%, LSTM to 17% and GRU to 19%. Conclusion: Based on the proposed process, when detecting unsupervised learning anomalies of data that are not actually labeled in various fields such as cyber security, financial sector, behavior pattern field, SNS. It is expected to prove the accuracy and explanation of the anomaly detection section and improve the performance of the model.

• The Journal of Korean Academic Society of Nursing Education
• /
• v.21 no.3
• /
• pp.350-360
• /
• 2015

Purpose: The purpose of this study was to evaluate the effectiveness and retention period of immediate remediation for infant cardiopulmonary resuscitation (CPR) in child care teachers. Methods: This study used a nonequivalent comparison pre- and post-test design to measure knowledge about and confidence in infant CPR and an interrupted time-series design to determine skill performance. The experimental group (n=25) received both immediate remediation and video learning for infant CPR, and the comparison group (n=28) received video learning only. Knowledge and confidence were measured before and after 4 weeks. Their skill performance was tested immediately, and 4 weeks, 8 weeks, 12 weeks, and 24 weeks after intervention. Data analysis consisted of ${\chi}^2$ tests, t-tests, paired t-tests, and a generalized linear mixed model. Results: There were significant increases in knowledge and confidence within the experimental group. Skill performance showed a significant difference according to the group factor (F=10.81, p=.002) and measurement time (F=146.80, p<.001). The experimental group maintained significantly higher skill performance than did the comparison group. Conclusion: These findings support the necessity of immediate remediation education for infant CPR to maintain skill performance. In addition, appropriate renewal time and the improvement of training programs for child care teachers are necessary.

• Journal of IKEEE
• /
• v.25 no.3
• /
• pp.412-419
• /
• 2021

In this paper, we propose a performance improvement of the LwF method using efficient path selection in Continuous Learning Environment. We compare performance and structure with conventional LwF. For comparison, we experiment with performance using MNIST, EMNIST, Fashion MNIST, and CIFAR10 data with different complexity configurations. Experiments show up to 20% improvement in accuracy for each task, which mitigating the Catastrophic Forgetting phenomenon in Continuous Learning environments.

• Journal of information and communication convergence engineering
• /
• v.21 no.3
• /
• pp.225-232
• /
• 2023

Owing to advancements in intelligent transportation systems (ITS) and artificial-intelligence technologies, various machine-learning models can be employed to simulate and predict the number of traffic accidents under different weather conditions. Furthermore, we can analyze the relationship between weather and traffic accidents, allowing us to assess whether the current weather conditions are suitable for travel, which can significantly reduce the risk of traffic accidents. In this study, we analyzed 30000 traffic flow data points collected by traffic cameras at nearby intersections in Washington, D.C., USA from October 2012 to May 2017, using Pearson's heat map. We then predicted, analyzed, and compared the performance of the correlation between continuous features by applying several machine-learning algorithms commonly used in ITS, including random forest, decision tree, gradient-boosting regression, and support vector regression. The experimental results indicated that the gradient-boosting regression machine-learning model had the best performance.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.12 no.6
• /
• pp.591-596
• /
• 2019

In this paper, we implemented a deep learning operation structure with less influence of local PC performance. In general, the deep learning model has a large amount of computation and is heavily influenced by the performance of the processing PC. In this paper, we implemented deep learning operation using AWS and streaming server to reduce this limitation. First, deep learning operations were performed on AWS so that deep learning operation would work even if the performance of the local PC decreased. However, with AWS, the output is less real-time relative to the input when computed. Second, we use streaming server to increase the real-time of deep learning model. If the streaming server is not used, the real-time performance is poor because the images must be processed one by one or by stacking the images. We used the YOLO v3 model as a deep learning model for performance comparison experiments, and compared the performance of local PCs with instances of AWS and GTX1080, a high-performance GPU. The simulation results show that the test time per image is 0.023444 seconds when using the p3 instance of AWS, which is similar to the test time per image of 0.027099 seconds on a local PC with the high-performance GPU GTX1080.

• Journal of the Korean Institute of Educational Facilities
• /
• v.18 no.2
• /
• pp.25-33
• /
• 2011

This study performs the objective evaluation on simple comparison and calculation works by students under LED illumination conditions according to three types of color temperatures (7000K, 5000K, 3000K) in the classroom, Since the objective of this study is to develop an electric lighting conditions suitable for students in the classroom, the learning performance under three types of LED illumination conditions were analyzed. The 4 kinds of simple tests concerning with learning performance were developed and test results under natural light and LED illumination by 3 types of color temperatures were analyzed. There were differences by t-test in most cases among simple experiment results of different illumination conditions ($p{\leq}.05$). It was confirmed that illumination condition plays an important role when students simply compare words or perform arithmetic calculations. The experimental results of this study might be applied to designing better luminous environment.