• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.10
• /
• pp.3668-3684
• /
• 2021

Video action recognition is widely used in video surveillance, behavior detection, human-computer interaction, medically assisted diagnosis and motion analysis. However, video action recognition can be disturbed by many factors, such as background, illumination and so on. Two-stream convolutional neural network uses the video spatial and temporal models to train separately, and performs fusion at the output end. The multi segment Two-Stream convolutional neural network model trains temporal and spatial information from the video to extract their feature and fuse them, then determine the category of video action. Google Xception model and the transfer learning is adopted in this paper, and the Xception model which trained on ImageNet is used as the initial weight. It greatly overcomes the problem of model underfitting caused by insufficient video behavior dataset, and it can effectively reduce the influence of various factors in the video. This way also greatly improves the accuracy and reduces the training time. What's more, to make up for the shortage of dataset, the kinetics400 dataset was used for pre-training, which greatly improved the accuracy of the model. In this applied research, through continuous efforts, the expected goal is basically achieved, and according to the study and research, the design of the original dual-flow model is improved.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.15 no.3
• /
• pp.1-14
• /
• 2019

The 4th Industrial Revolution, intelligent automobile application technology is evolving beyond the limit of the mobile device to a variety of application software and multi-media collective technology with big data-based AI(artificial intelligence) technology. with the recent commercialization of 5G mobile communication service, artificial intelligent automobile technology, which is a fusion of automobile and IT technology, is evolving into more intelligent automobile service technology, and each multimedia platform service and application developed in such distributed environment is being developed Accordingly, application software technology developed with a single system SoC of a portable terminal device through various service technologies is absolutely required. In this paper, smart device design for ontology design of intelligent automobile open platform enables to design intelligent automobile middleware software design technology such as Android based SVC Codec and real time video and graphics processing that is not expressed in single ASIC application software technology as SoC based application designWe have experimented in smart device environment through researches, and newly designed service functions of various terminal devices provided as open platforms and application solutions in SoC environment and applied standardized interface analysis technique and proved this experiment.

• The Journal of Korea Robotics Society
• /
• v.18 no.3
• /
• pp.293-298
• /
• 2023

The military is facing a continuous decrease in personnel, and in order to cope with potential accidents and challenges in operations, efforts are being made to reduce the direct involvement of personnel by utilizing the latest technologies. Recently, the use of various sensors related to Manned-Unmanned Teaming and artificial intelligence technologies has gained attention, emphasizing the need for flexible utilization methods. In this paper, we propose four dataset construction methods that can be used for effective training of robots that can be deployed in military operations, utilizing not only RGB image data but also data acquired from IR image sensors. Since there is no publicly available dataset that combines RGB and IR image data, we directly acquired the dataset within buildings. The input values were constructed by combining RGB and IR image sensor data, taking into account the field of view, resolution, and channel values of both sensors. We compared the proposed method with conventional RGB image data classification training using the same learning model. By employing the proposed image data fusion method, we observed improved stability in training loss and approximately 3% higher accuracy.

• Korean Journal of Remote Sensing
• /
• v.39 no.4
• /
• pp.459-466
• /
• 2023

In the last decade, artificial intelligence's dramatic advancement with the development of various deep learning techniques has significantly contributed to remote sensing fields and satellite image applications. Among many prominent areas, super-resolution research has seen substantial growth with the release of several benchmark datasets and the rise of generative adversarial network-based studies. However, most previously published remote sensing benchmark datasets represent spatial resolution within approximately 10 meters, imposing limitations when directly applying for super-resolution of small objects with cm unit spatial resolution. Furthermore, if the dataset lacks a global spatial distribution and is specialized in particular land covers, the consequent lack of feature diversity can directly impact the quantitative performance and prevent the formation of robust foundation models. To overcome these issues, this paper proposes a method to generate benchmark datasets by simulating the modulation transfer functions of the sensor. The proposed approach leverages the simulation method with a solid theoretical foundation, notably recognized in image fusion. Additionally, the generated benchmark dataset is applied to state-of-the-art super-resolution base models for quantitative and visual analysis and discusses the shortcomings of the existing datasets. Through these efforts, we anticipate that the proposed benchmark dataset will facilitate various super-resolution research shortly in Korea.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.4
• /
• pp.1200-1215
• /
• 2023

With the development of IoT and artificial intelligence, location-based services are getting more and more attention. For solving the current problem that indoor positioning error is large and generalization is poor, this paper proposes a Model Stacking Algorithm for Indoor Positioning System using WiFi fingerprinting. Firstly, we adopt a model stacking method based on Bayesian optimization to predict the location of indoor targets to improve indoor localization accuracy and model generalization. Secondly, Taking the predicted position based on model stacking as the observation value of particle filter, collaborative particle filter localization based on model stacking algorithm is realized. The experimental results show that the algorithm can control the position error within 2m, which is superior to KNN, GBDT, Xgboost, LightGBM, RF. The location accuracy of the fusion particle filter algorithm is improved by 31%, and the predicted trajectory is close to the real trajectory. The algorithm can also adapt to the application scenarios with fewer wireless access points.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.5
• /
• pp.737-745
• /
• 2023

This paper discusses a study on developing an artificial intelligence model to detect incidents of fires in distribution switchboard using thermal images. The objective of the research is to preprocess collected thermal images into suitable data for object detection models and design a model capable of determining the occurrence of fires within distribution panels. The study utilizes thermal image data from AI-HUB's industrial complex for training. Two CNN-based deep learning object detection algorithms, namely Faster R-CNN and RetinaNet, are employed to construct models. The paper compares and analyzes these two models, ultimately proposing the optimal model for the task.

• Journal of Broadcast Engineering
• /
• v.23 no.3
• /
• pp.351-360
• /
• 2018

Human emotion recognition is a research topic that is receiving continuous attention in computer vision and artificial intelligence domains. This paper proposes a method for classifying human emotions through multiple neural networks based on multi-modal signals which consist of image, landmark, and audio in a wild environment. The proposed method has the following features. First, the learning performance of the image-based network is greatly improved by employing both multi-task learning and semi-supervised learning using the spatio-temporal characteristic of videos. Second, a model for converting 1-dimensional (1D) landmark information of face into two-dimensional (2D) images, is newly proposed, and a CNN-LSTM network based on the model is proposed for better emotion recognition. Third, based on an observation that audio signals are often very effective for specific emotions, we propose an audio deep learning mechanism robust to the specific emotions. Finally, so-called emotion adaptive fusion is applied to enable synergy of multiple networks. The proposed network improves emotion classification performance by appropriately integrating existing supervised learning and semi-supervised learning networks. In the fifth attempt on the given test set in the EmotiW2017 challenge, the proposed method achieved a classification accuracy of 57.12%.

• International Journal of Internet, Broadcasting and Communication
• /
• v.12 no.2
• /
• pp.8-14
• /
• 2020

Recently, there was an increasing demand for an integrated access control system which is capable of user recognition, door control, and facility operations control for smart buildings automation. The market available door lock access control solutions need to be improved from the current level security of door locks operations where security is compromised when a password or digital keys are exposed to the strangers. At present, the access control system solution providers focusing on developing an automatic access control system using (RF) based technologies like bluetooth, WiFi, etc. All the existing automatic door access control technologies required an additional hardware interface and always vulnerable security threads. This paper proposes the user identification and authentication solution for automatic door lock control operations using camera based visible light communication (VLC) technology. This proposed approach use the cameras installed in building facility, user smart devices and IoT open source controller based LED light sensors installed in buildings infrastructure. The building facility installed IoT LED light sensors transmit the authorized user and facility information color grid code and the smart device camera decode the user informations and verify with stored user information then indicate the authentication status to the user and send authentication acknowledgement to facility door lock integrated camera to control the door lock operations. The camera based VLC receiver uses the artificial intelligence (AI) methods to decode VLC data to improve the VLC performance. This paper implements the testbed model using IoT open-source based LED light sensor with CCTV camera and user smartphone devices. The experiment results are verified with custom made convolutional neural network (CNN) based AI techniques for VLC deciding method on smart devices and PC based CCTV monitoring solutions. The archived experiment results confirm that proposed door access control solution is effective and robust for automatic door access control.

• Journal of Industrial Convergence
• /
• v.22 no.7
• /
• pp.1-13
• /
• 2024

Among e-government services, the intelligent CCTV control platform is a screening control service that utilizes artificial intelligence to display major objects such as people, cars, etc. to control personnel when they appear on CCTV. The operation of an intelligent CCTV control platform is expected to improve the quality of life of citizens by enabling rapid response in the event of an emergency and increasing the resolution of complaints. In this study, the benefits of the intelligent CCTV control platform, a non-market good, were estimated by applying the contingent valuation method (CVM), a choice experiment technique, to estimate the average willingness to pay per household and calculate the social benefits. As a result of the analysis, the average willingness to pay per household was estimated to be KRW 6,908 per year, and the economic benefits for the country as a whole were estimated to be about KRW 150.4 billion per year. This study is of academic significance as it extends the application of CVM to the field of intelligent e-Government services. The Intelligent CCTV control platforms is being actively discussed, this study has practical implications in that the benefits were estimated in monetary value.

• Journal of Korean Neurosurgical Society
• /
• v.62 no.4
• /
• pp.442-449
• /
• 2019

Objective : Bone mineral density (BMD) is an important consideration during fusion surgery. Although dual X-ray absorptiometry is considered as the gold standard for assessing BMD, quantitative computed tomography (QCT) provides more accurate data in spine osteoporosis. However, QCT has the disadvantage of additional radiation hazard and cost. The present study was to demonstrate the utility of artificial intelligence and machine learning algorithm for assessing osteoporosis using Hounsfield units (HU) of preoperative lumbar CT coupling with data of QCT. Methods : We reviewed 70 patients undergoing both QCT and conventional lumbar CT for spine surgery. The T-scores of 198 lumbar vertebra was assessed in QCT and the HU of vertebral body at the same level were measured in conventional CT by the picture archiving and communication system (PACS) system. A multiple regression algorithm was applied to predict the T-score using three independent variables (age, sex, and HU of vertebral body on conventional CT) coupling with T-score of QCT. Next, a logistic regression algorithm was applied to predict osteoporotic or non-osteoporotic vertebra. The Tensor flow and Python were used as the machine learning tools. The Tensor flow user interface developed in our institute was used for easy code generation. Results : The predictive model with multiple regression algorithm estimated similar T-scores with data of QCT. HU demonstrates the similar results as QCT without the discordance in only one non-osteoporotic vertebra that indicated osteoporosis. From the training set, the predictive model classified the lumbar vertebra into two groups (osteoporotic vs. non-osteoporotic spine) with 88.0% accuracy. In a test set of 40 vertebrae, classification accuracy was 92.5% when the learning rate was 0.0001 (precision, 0.939; recall, 0.969; F1 score, 0.954; area under the curve, 0.900). Conclusion : This study is a simple machine learning model applicable in the spine research field. The machine learning model can predict the T-score and osteoporotic vertebrae solely by measuring the HU of conventional CT, and this would help spine surgeons not to under-estimate the osteoporotic spine preoperatively. If applied to a bigger data set, we believe the predictive accuracy of our model will further increase. We propose that machine learning is an important modality of the medical research field.