• Journal of the Korea Convergence Society
• /
• v.13 no.4
• /
• pp.53-61
• /
• 2022

Accidents are steadily occurring due to machine defects and carelessness during LNG storage operations. In previous studies, an environmental sensor module capable of measuring pressure, temperature, gas concentration, and flow to detect danger in advance was developed and the response speed according to the amount of leaked gas was measured. This paper proposes the development of a wired and wireless communication module that transmits data measured by the environmental sensor module to embedded devices connected to wired and wireless networks of SPI, UART, and LTE. First, a data communication module capable of interworking with an environmental sensor is designed. Design a protocol between devices in the Local Control Part and wired and wireless protocols in the Local Control Part and Remote Control Part. Ethernet, WiFi, and LTE communication modules were designed, and UART and SPI channels that can be linked with embedded controllers were designed. As a result, it was confirmed through a UI (User Interface) that each embedded device transmits data measured by the environmental sensor module while simultaneously communicating on a wired and wireless basis.

• Nuclear Engineering and Technology
• /
• v.54 no.1
• /
• pp.269-274
• /
• 2022

An artificial neural network (ANN) that identifies radionuclides from low-count gamma spectra of a NaI scintillator is proposed. The ANN was trained and tested using simulated spectra. 14 target nuclides were considered corresponding to the requisite radionuclide library of a radionuclide identification device mentioned in IEC 62327-2017. The network shows an average identification accuracy of 98.63% on the validation dataset, with the gross counts in each spectrum N_c = 100~10000 and the signal to noise ratio SNR = 0.05-1. Most of the false predictions come from nuclides with low branching ratio and/or similar decay energies. If the N_c>1000 and SNR>0.3, which is defined as the minimum identifiable condition, the averaged identification accuracy is 99.87%. Even when the source and the detector are covered with lead bricks and the response function of the detector thus varies, the ANN which was trained using non-shielding spectra still shows high accuracy as long as the minimum identifiable condition is satisfied. Among all the considered nuclides, only the identification accuracy of ²³⁵U is seriously affected by the shielding. Identification of other nuclides shows high accuracy even the shielding condition is changed, which indicates that the ANN has good generalization performance.

• Journal of the Society of Disaster Information
• /
• v.17 no.4
• /
• pp.802-816
• /
• 2021

Purpose: In this paper, we propose a direction of future research and development to be carried out in the passive tracking field by deriving a white space with enhanced search formula of patent analysis. Method: In this paper, we derive a white space by identifying the direction and the flow of technology change and by matrixing the object and solution through extensive patent search with enhanced search formula and analysis in the field of passive tracking technology. Result: By the proposed scheme, 'multi-target positioning and tracking' and '3D positioning technology' using artificial intelligence, adaptive/hybrid positioning technology, and radar/antenna were derived as white space technologies and confirmed with absence of any services or products. Conclusion: The derived white space technologies from this paper are the areas where patent applications are not active and there are not many prior patents, thus it is necessary to secure the rights through more active R&D and patent application activities.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.11
• /
• pp.13-18
• /
• 2022

In this paper, we proposed VW-FedAVG(Validation based Weighted FedAVG) which updates the global model by weighting according to performance verification from the models of each device participating in the training. The first method is designed to validate each local client model through validation dataset before updating the global model with a server side validation structure. The second is a client-side validation structure, which is designed in such a way that the validation data set is evenly distributed to each client and the global model is after validation. MNIST, CIFAR-10 is used, and the IID, Non-IID distribution for image classification obtained higher accuracy than previous studies.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.281-283
• /
• 2021

The representative companies mentioned in the recommendation service in the domestic OTT(Over-the-top media service) market are YouTube and Netflix. YouTube, through various methods, started personalized recommendations in earnest by introducing an algorithm to machine learning that records and uses users' viewing time from 2016. Netflix categorizes users by collecting information such as the user's selected video, viewing time zone, and video viewing device, and groups people with similar viewing patterns into the same group. It records and uses the information collected from the user and the tag information attached to the video. In this paper, we propose a method to improve video media recommendation by automatically generating metadata of video media that was written by hand.

• Information Systems Review
• /
• v.22 no.2
• /
• pp.77-99
• /
• 2020

Smart speaker is a device that provides an interactive voice-based service that can search and use various information and contents such as music, calendar, weather, and merchandise using artificial intelligence. Since AI technology provides more sophisticated and optimized services to users by accumulating data, early smart speaker manufacturers tried to build a platform through aggressive marketing. However, the frequency of using smart speakers is less than once a month, accounting for more than one third of the total, and user satisfaction is only 49%. Accordingly, the necessity of strengthening the user experience of smart speakers has emerged in order to acquire a large number of users and to enable continuous use. Therefore, this study analyzes the user experience of the smart speaker and proposes a method for enhancing the user experience of the smart speaker. Based on the analysis results in two stages, we propose ways to enhance the user experience of smart speakers by model. The existing research on the user experience of the smart speaker was mainly conducted by survey and interview-based research, whereas this study collected the actual review data written by the user. Also, this study interpreted the analysis result based on the smart speaker user experience dimension. There is an academic significance in interpreting the text mining results by developing the smart speaker user experience dimension. Based on the results of this study, we can suggest strategies for enhancing the user experience to smart speaker manufacturers.

• The Korean Journal of Archival Studies
• /
• no.79
• /
• pp.5-32
• /
• 2024

The Korean government ranked 3rd among 193 UN member countries in the UN's 2022 e-Government Development Index. Korea, which has consistently been evaluated as a top country, can clearly be said to be a leading country in the world of e-government. The lubricant of e-government is data. Data itself is neither information nor a record, but it is a source of information and records and a resource of knowledge. Since administrative actions through electronic systems have become widespread, the production and technology of data-based records have naturally expanded and evolved. Technology may seem value-neutral, but in fact, technology itself reflects a specific worldview. The digital order of new technologies, armed with hyper-connectivity and super-intelligence, not only has a profound influence on traditional power structures, but also has an a similar influence on existing information and knowledge transmission media. Moreover, new technologies and media, including data-based generative artificial intelligence, are by far the hot topic. It can be seen that the all-round growth and spread of digital technology has led to the augmentation of human capabilities and the outsourcing of thinking. This also involves a variety of problems, ranging from deep fakes and other fake images, auto profiling, AI lies hallucination that creates them as if they were real, and copyright infringement of machine learning data. Moreover, radical connectivity capabilities enable the instantaneous sharing of vast amounts of data and rely on the technological unconscious to generate actions without awareness. Another irony of the digital world and online network, which is based on immaterial distribution and logical existence, is that access and contact can only be made through physical tools. Digital information is a logical object, but digital resources cannot be read or utilized without some type of device to relay it. In that respect, machines in today's technological society have gone beyond the level of simple assistance, and there are points at which it is difficult to say that the entry of machines into human society is a natural change pattern due to advanced technological development. This is because perspectives on machines will change over time. Important is the social and cultural implications of changes in the way records are produced as a result of communication and actions through machines. Even in the archive field, what problems will a data-based archive society face due to technological changes toward a hyper-intelligence and hyper-connected society, and who will prove the continuous activity of records and data and what will be the main drivers of media change? It is time to research whether this will happen. This study began with the need to recognize that archives are not only records that are the result of actions, but also data as strategic assets. Through this, author considered how to expand traditional boundaries and achieves reterritorialization in a data-driven society.

• Journal of the Korean Society of Safety
• /
• v.35 no.5
• /
• pp.74-85
• /
• 2020

Smart phone zombie or Smombie means pedestrians who walk without attention to their surroundings because they are focused upon their smart phone. Because the traffic accidents and injuries caused by Smombie have been increased rapidly in recent years, the social attention and policies are needed to prevent it. This study was conducted to analyze Smombie's current status and some solutions used before and to propose new improved method through the latest ICT trend. In this study, we did the field survey to check Smombies at several places in Seoul through people counting, and found that a lot of pedestrians still use the smart phone while walking. And we analyzed many case studies about some solutions to prevent Smombies previously. The case studies include legal regulations, government policies, smart phone app services and facilities that are used before. We studied them through internet searches and reference studies and we also checked the current operating situation as visiting several places that the solutions actually has been operated. Therefore, we found there are some limitations in previous solutions in terms of effectiveness and management. To consider new solution that can be expected to overcome the limitations, we analyzed the latest ICT trends focused on features to utilize the Smombie prevention, especially video recognition and digital signage. In these days, video recognition has been developed rapidly with assistance of AI technology and it can recognize the specific pedestrian's characteristics such as holding smart phone as well as hair style, clothes, backpack and etc. On the other hands, the digital signage is the convergence device that includes big display, network connection and various IoT sensors. It can be used as public media in many places for public services as well as advertising. Through these analysis results, we show the requirements and the user scenario for the improved method to prevent Smombie. Finally, we propose to develop R&D technology to recognize Smombie exactly as pedestrian attributes and to spread creative contents to increase pedestrian's interest and engagement for Smombie prevention through digital signage.

• Journal of Internet Computing and Services
• /
• v.24 no.6
• /
• pp.91-98
• /
• 2023

Recently, according to development of artificial intelligence, a wide range of industry being automatic and optimized. Also we can find out some research of using supervised learning for deteceting defect of railway in domestic rail industry. However, there are structures other than rails on the track, and the fastener is a device that binds the rail to other structures, and periodic inspections are required to prevent safety accidents. In this paper, we present a method of reducing cost for labeling using semi-supervised and transfer model trained on rail fastener data. We use Resnet50 as the backbone network pretrained on ImageNet. At first we randomly take training data from unlabeled data and then labeled that data to train model. After predict unlabeled data by trained model, we adopted a method of adding the data with the highest probability for each class to the training data by a predetermined size. Futhermore, we also conducted some experiments to investigate the influence of the number of initially labeled data. As a result of the experiment, model reaches 92% accuracy which has a performance difference of around 5% compared to supervised learning. This is expected to improve the performance of the classifier by using relatively few labels without additional labeling processes through the proposed method.

• KIPS Transactions on Computer and Communication Systems
• /
• v.11 no.2
• /
• pp.67-72
• /
• 2022

Recently, various intelligent application services using artificial intelligence are being actively developed. In particular, research on artificial intelligence-based real-time prediction services is being actively conducted in the manufacturing industry, and the demand for artificial intelligence services that can detect and predict fire and odors is very high. However, most of the existing detection and prediction systems do not predict the occurrence of fires and odors, but rather provide detection services after occurrence. This is because AI-based prediction service technology is not applied in existing systems. In addition, fire prediction, odor detection and odor level prediction services are services with ultra-low delay characteristics. Therefore, in order to provide ultra-low-latency prediction service, edge computing technology is combined with artificial intelligence models, so that faster inference results can be applied to the field faster than the cloud is being developed. Therefore, in this paper, we propose an LSTM algorithm-based learning model that can be used for fire prediction and odor detection/prediction, which are most required in the manufacturing industry. In addition, the proposed learning model is designed to be implemented in edge devices, and it is proposed to receive real-time sensor data from the IoT terminal and apply this data to the inference model to predict fire and odor conditions in real time. The proposed model evaluated the prediction accuracy of the learning model through three performance indicators, and the evaluation result showed an average performance of over 90%.