• Journal of Industrial Convergence
• /
• v.20 no.3
• /
• pp.33-40
• /
• 2022

Recently, IoT-linked services have been used in various environments, and IoT and artificial intelligence technologies are being fused. However, since technologies that process IoT data stably are not fully supported, research is needed for this. In this paper, we propose a processing technique that can optimize IoT data after generating embedded vectors based on machine learning for IoT data. In the proposed technique, for processing efficiency, embedded vectorization is performed based on QR such as index of IoT data, collection location (binary values of X and Y axis coordinates), group index, type, and type. In addition, data generated by various IoT devices are integrated and managed so that load balancing can be performed in the IoT data collection process to asymmetrically link IoT data. The proposed technique processes IoT data to be orthogonalized based on hash so that IoT data can be asymmetrically grouped. In addition, interference between IoT data may be minimized because it is periodically generated and grouped according to IoT data types and characteristics. Future research plans to compare and evaluate proposed techniques in various environments that provide IoT services.

• The korean journal of orthodontics
• /
• v.21 no.1 s.33
• /
• pp.197-221
• /
• 1991

The purpose of the present study was to investigate the differences of EMG activity of the masticatory muscles between normal occlusion and Class III malocclusion during various jaw functions. 46 subjects of 18.4-25.7 years were employed in this study: 26 subjects were normal occlusions, and 20 subjects were Class III malocclusions. The EMG data from the anterior and posterior temporal, anterior and posterior masseter muscles in both sides as mandibular elevators and supra-hyoid muscle group (close to the anterior belly of digastric muscle in right side) as mandibular depressor were recorded with the Medelec MS 25 electromyographic machine. The EMG recordings were analyzed during mandibular rest position, maximal biting, mastication with chewing gum, and swallowing of peanuts. All data were recorded and statistically processed. 1. The maximal mean amplitude of the anterior temporal muscle was stronger significantly in Class III malocclusion than in normal occlusion, and then the posterior temporal was weaker during mandibular rest position. 2. The maximal mean amplitudes in the anterior and posterior temporal muscles and the anterior masseter muscle of Class III malocclusion was weaker significantly than that of normal occlusion during maximal biting. 3. During mastication of the chewing gum, the maximal mean amplitudes of Class III malocclusion was weaker significantly than normal occlusion in the anterior and posterior temporal muscles of the working side, and the duration of Class III malocclusion was longer in the anterior temporal muscles of both aides, and the posterior temporal and the anterior masseter muscle of the balancing side. There were significant increasings of the latency in balancing anterior temporal, working posterior temporal muscles and supra-hyoid muscle group of Class III malocclusion. The silent period durations was 16.36 ms in Class III malocclusion while 10.76 ms in normal occlusion, which was statistically different (P < 0.05). 4. At swallowing of peanuts, the maximal mean amplitude of Class malocclusion was weaker significantly in the posterior temporal muscle than that of normal occlusion. There was no significant difference of duration between normal occlusion and Class III malocclusion. 5 The muscle activities of Class III malocclusion had a tendency of decrease less than normal occlusion. And then the muscle activities of the anterior temporal and anterior masseter muscles in Class III malocclusion showed the tendency of the increase more than other muscles of Class III malocclusion.

• Journal of the Korea Society for Simulation
• /
• v.17 no.2
• /
• pp.63-74
• /
• 2008

The design of best efficient production process is common requirements of the production strategy department and the process planning department to maximize the revenue and accomplish target production volumes in the production periods. And they use several general methods for that-line-balancing, removing of the bottle-neck process, facility ramp-up, increasing of the worker's utilization, etc. But, those methods have depended on analytic, static and arithmetic calculations, yet. So, irregular work-waiting time causing the delay time isn't include in extracting production capacity, especially in the line production process. The work-waiting time is changed irregularly along the variation of each machine and very important for calculate real product lead-time and forecasting target production volumes. At this thesis, i'm going to mention the importance of the delay time of conveyor system which can be extracted by discrete-event simulation. And suggest it as a new main variable that must be considered at designing new production system. Then experimented and tested that's effects in the H-company case, conveyor based line production process.

• Asian Pacific Journal of Cancer Prevention
• /
• v.16 no.4
• /
• pp.1435-1442
• /
• 2015

Purpose: To study the patient load, treatment pattern, survival outcome and its predictors in patients with brain metastases treated by radiotherapy. Materials and Methods: Data for patients with brain metastases treated by radiotherapy between 2003 and 2007 were collected from medical records, the hospital information system database, and a population-based tumor registry database until death or at least 5 years after treatment and retrospectively reviewed. Results: The number of treatments for brain metastases gradually increased from 48 in 2003 to 107 in 2007, with more than 70% from lung and breast cancers. The majority were treated with whole brain radiation of 30 Gy (3 Gy X 10 fractions) by cobalt-60 machine, using radiation alone. The overall median survival of the 418 patients was 3.9 months. Cohort analysis of relative survival after radiotherapy was as follows: 52% at 3 months, 18% at 1 year and 3% at 5 years in males; and 66% at 3 months, 26% at 1 year and 7% at 5 years in females. Multivariate analysis demonstrated that the patients treated with combined modalities had a better prognosis. Poor prognostic factors included primary cancer from the lung or gastrointestinal tract, emergency or urgent consultation, poor performance status (ECOG 3-4), and a hemoglobin level before treatment of less than 10 g/dl. Conclusions: This study identified an increasing trend of patient load with brain metastases. Possible over-treatment and under-treatment were demonstrated with a wide range of survival results. Practical prognostic scoring systems to assist in decision-making for optimal treatment of different patient groups is absolutely necessary; it is a key strategy for balancing good quality of care and patient load.

• Journal of KIISE:Databases
• /
• v.28 no.3
• /
• pp.418-429
• /
• 2001

Recently, a GIS has been applicable to the most important computer applications such as urban information systems and transportation information systems. These applications require spatial operations for an efficient management of a large volume of data. In particular, a spatial join among basic operations has the property that its response time is increased exponentially according to the number of spatial objects included in the operation. Therefore, it is not proper to the systems demanding the fast response time. To satisfy these requirements, the efficient parallel processing of spatial joins has been required. In this paper, the efficient method for creating and allocating tasks to balance statically the load of each processor in a parallel spatial join is presented. A task graph is developed in which a vertex weight is calculated by the cost model I have proposed. Then, it is partitioned through a graph partitioning algorithm. According to the experiments in CC16 parallel machine, our method made an improvement in the static load balance by decreasing the variance of a task execution time on each processor.

• Korean Journal of Remote Sensing
• /
• v.40 no.1
• /
• pp.93-101
• /
• 2024

Accurate field crop classification is essential for various agricultural applications, yet existing methods face challenges due to diverse crop types and complex field conditions. This study aimed to address these issues by combining support vector machine (SVM) models with multi-seasonal unmanned aerial vehicle (UAV) images, texture information extracted from Gray Level Co-occurrence Matrix (GLCM), and RGB spectral data. Twelve high-resolution UAV image captures spanned March-October 2021, while field surveys on three dates provided ground truth data. We focused on data from August (-A), September (-S), and October (-O) images and trained four support vector classifier (SVC) models (SVC-A, SVC-S, SVC-O, SVC-AS) using visual bands and eight GLCM features. Farm maps provided by the Ministry of Agriculture, Food and Rural Affairs proved efficient for open-field crop identification and served as a reference for accuracy comparison. Our analysis showcased the significant impact of hyperparameter tuning (C and gamma) on SVM model performance, requiring careful optimization for each scenario. Importantly, we identified models exhibiting distinct high-accuracy zones, with SVC-O trained on October data achieving the highest overall and individual crop classification accuracy. This success likely stems from its ability to capture distinct texture information from mature crops.Incorporating GLCM features proved highly effective for all models,significantly boosting classification accuracy.Among these features, homogeneity, entropy, and correlation consistently demonstrated the most impactful contribution. However, balancing accuracy with computational efficiency and feature selection remains crucial for practical application. Performance analysis revealed that SVC-O achieved exceptional results in overall and individual crop classification, while soybeans and rice were consistently classified well by all models. Challenges were encountered with cabbage due to its early growth stage and low field cover density. The study demonstrates the potential of utilizing farm maps and GLCM features in conjunction with SVM models for accurate field crop classification. Careful parameter tuning and model selection based on specific scenarios are key for optimizing performance in real-world applications.

• Journal of the Institute of Electronics Engineers of Korea TE
• /
• v.39 no.2
• /
• pp.34-43
• /
• 2002

In this paper, with the reference of the pulse wave acquired by the pulse-checking device, it is measured the impedance on the key measuring points of the 12 kyungmaks of the human body's left and right by using 24-channels Yangdorak machine. Then, based on the Fuzzy theory, this study diagnosed the each meridian's strength and weakness. After that, both the strengthening and weakening stimulus of magnetic fields are applied to the dominant direction to find out how the degree of strength and weakness of the meridian changed. Ultimately, the magnetic therapy that can stimulate the magnetic field at the time of diagnosis and thereby balancing the interactive of five-system(O-hang) have been materialized. For the stimulation of magnetic fields, a stimulating device which can change the direction and time on a specific part of the key measuring points of the limbs of 24 kyungmaks have been developed and used. The therapeutic methods are as follows. First, the strength and weakness of the meridian have been determined. Second, both the extremely weak meridian of Yin(Shade) and Yang(Shine), and the extremely strong meridian of Yin and Yang were adjusted by applying appropriate ascending and descending stimuli respectively. All these adjusting processes can now be carried out automatically on a personal computer(PC). 

• Journal of Intelligence and Information Systems
• /
• v.11 no.2
• /
• pp.59-79
• /
• 2005

Export containers in a container terminal are usually classified into a few weight groups and those belonging to the same group are placed together on a same stack. The reason for this stacking by weight groups is that it becomes easy to have the heavier containers be loaded onto a ship before the lighter ones, which is important for the balancing of the ship. However, since the weight information available at the time of container arrival is only an estimate, those belonging to different weight groups are often stored together on a same stack. This becomes the cause of extra moves, or rehandlings, of containers at the time of loading to fetch out the heavier containers placed under the lighter ones. In this paper, we use machine learning techniques to derive a classifier that can classify the containers into the weight groups with improved accuracy. We also show that a more useful classifier can be derived by applying a cost-sensitive learning technique, for which we introduce a scheme of searching for a good cost matrix. Simulation experiments have shown that our proposed method can reduce about 5$\sim$7% of rehandlings when compared to the traditional weight grouping method.

• The Journal of Society for e-Business Studies
• /
• v.24 no.3
• /
• pp.19-33
• /
• 2019

Recently, manufacturers have been struggling to efficiently use production equipment as their production methods become more sophisticated and complex. Typical factors hindering the efficiency of the manufacturing process include setup cost due to job change. Especially, in the process of using expensive production equipment such as semiconductor / LCD process, efficient use of equipment is very important. Balancing the tradeoff between meeting the deadline and minimizing setup cost incurred by changes of work type is crucial planning task. In this study, we developed a scheduling model to achieve the goal of minimizing the duedate and setup costs by using reinforcement learning in parallel machines with duedate and work preparation costs. The proposed model is a Deep Q-Network (DQN) scheduling model and is a reinforcement learning-based model. To validate the effectiveness of our proposed model, we compared it against the heuristic model and DNN(deep neural network) based model. It was confirmed that our proposed DQN method causes less due date violation and setup costs than the benchmark methods.

• Korean Journal of Remote Sensing
• /
• v.35 no.6_4
• /
• pp.1319-1326
• /
• 2019

The KARI(Korea Aerospace Research Institute) operates the government satellite information application consultation to cope with ever-increasing demand for satellite images in the public sector, and carries out various support projects including the generation and provision of mosaic images on the Korean Peninsula every year to enhance user convenience and promote the use of satellite images. In particular, the government has wanted to increase the utilization of mosaic images on the Korean Peninsula and seek to classify and update mosaic images so that users can use them in their businesses easily. However, it is necessary to test and verify whether the classification results of the mosaic images can be utilized in the field since the original spectral information is distorted during pan-sharpening and color balancing, and there is a limitation that only R, G, and B bands are provided. Therefore, in this study, the reliability of the classification result of the mosaic image was compared to the result of KOMPSAT-3 image. The study found that the accuracy of the classification result of KOMPSAT-3 image was between 81~86% (overall accuracy is about 85%), while the accuracy of the classification result of mosaic image was between 69~72% (overall accuracy is about 72%). This phenomenon is interpreted not only because of the distortion of the original spectral information through pan-sharpening and mosaic processes, but also because NDVI and NDWI information were extracted from KOMPSAT-3 image rather than from the mosaic image, as only three color bands(R, G, B) were provided. Although it is deemed inadequate to distribute classification results extracted from mosaic images at present, it is believed that it will be necessary to explore ways to minimize the distortion of spectral information when making mosaic images and to develop classification techniques suitable for mosaic images as well as the provision of NIR band information. In addition, it is expected that the utilization of images with limited spectral information could be increased in the future if related research continues, such as the comparative analysis of classification results by geomorphological characteristics and the development of machine learning methods for image classification by objects of interest.