• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.232-234
• /
• 2022

Big data is widely used in customer relationship management, relationship marketing, financial business improvement, credit information and risk management. Moreover, as non-face-to-face financial transactions have become more active recently due to the COVID-19 virus, the use of financial big data is more demanded in terms of relationships with customers. In terms of customer relationship, financial big data has arrived at a time that requires an emotional rather than a technical approach. In relational marketing, it was necessary to emphasize the emotional aspect rather than the cognitive, rational, and rational aspects. Existing traditional financial data was collected and utilized through text-type customer transaction data, corporate financial information, and questionnaires. In this study, the customer's emotional image data, that is, atypical data based on the customer's cultural and leisure activities, is acquired through SNS and the customer's activity image is analyzed with an artificial intelligence CNN algorithm. Activity analysis is again applied to the annotated AI, and the AI big data model is designed to analyze the behavior model shown in the annotation.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.1
• /
• pp.31-40
• /
• 2024

In the realm of domestic online fashion platform industry the manual registration of product information by individual business owners leads to inconvenience and reliability issues, especially when dealing with simultaneous registrations of numerous product groups. Moreover, bias is significantly heightened due to the low quality of product images and an imbalance in data quantity. Therefore, this study proposes a ResNet50 model aimed at minimizing data bias through oversampling techniques and conducting multiple classifications for 13 fashion categories. Transfer learning is employed to optimize resource utilization and reduce prolonged learning times. The results indicate improved discrimination of up to 33.4% for data augmentation in classes with insufficient data compared to the basic convolution neural network (CNN) model. The reliability of all outcomes is underscored by precision and affirmed by the recall curve. This study is suggested to advance the development of the domestic online fashion platform industry to a higher echelon.

• Smart Media Journal
• /
• v.12 no.1
• /
• pp.9-16
• /
• 2023

Recently, a convolutional neural network (CNN) based system is being developed to overcome the limitations of human resources in the apple quality classification of farmhouse. However, since convolutional neural networks receive only images of the same size, preprocessing such as sampling may be required, and in the case of oversampling, information loss of the original image such as image quality degradation and blurring occurs. In this paper, in order to minimize the above problem, to generate a image patch based graph of an original image and propose a random walk-based positional encoding method to apply the graph transformer model. The above method continuously learns the position embedding information of patches which don't have a positional information based on the random walk algorithm, and finds the optimal graph structure by aggregating useful node information through the self-attention technique of graph transformer model. Therefore, it is robust and shows good performance even in a new graph structure of random node order and an arbitrary graph structure according to the location of an object in an image. As a result, when experimented with 5 apple quality datasets, the learning accuracy was higher than other GNN models by a minimum of 1.3% to a maximum of 4.7%, and the number of parameters was 3.59M, which was about 15% less than the 23.52M of the ResNet18 model. Therefore, it shows fast reasoning speed according to the reduction of the amount of computation and proves the effect.

• Journal of the Korean Geotechnical Society
• /
• v.40 no.4
• /
• pp.69-79
• /
• 2024

Field geotechnical data are obtained from various field and laboratory tests and are documented in geotechnical investigation reports. For efficient design and construction, digitizing these geotechnical parameters is essential. However, current practices involve manual data entry, which is time-consuming, labor-intensive, and prone to errors. Thus, this study proposes an automatic data extraction method from geotechnical investigation reports using image-based deep learning models and text-mining techniques. A deep-learning-based page classification model and a text-searching algorithm were employed to classify geotechnical investigation report pages with 100% accuracy. Computer vision algorithms were utilized to identify valid data regions within report pages, and text analysis was used to match and extract the corresponding geotechnical data. The proposed model was validated using a dataset of 205 geotechnical investigation reports, achieving an average data extraction accuracy of 93.0%. Finally, a user-interface-based program was developed to enhance the practical application of the extraction model. It allowed users to upload PDF files of geotechnical investigation reports, automatically analyze these reports, and extract and edit data. This approach is expected to improve the efficiency and accuracy of digitizing geotechnical investigation reports and building geotechnical databases.

• International conference on construction engineering and project management
• /
• 2024.07a
• /
• pp.1307-1307
• /
• 2024

Recent research on heavy equipment has been conducted for the purposes of enhanced safety, productivity improvement, and carbon neutrality at construction sites. A sensor-based approach is being explored to monitor the location and movements of heavy equipment in real time. However, it poses significant challenges in terms of time and cost as multiple sensors should be installed on numerous heavy equipment at construction sites. In addition, there is a limitation in identifying the collaboration or interference between two or more heavy equipment. In light of this, a vision-based deep learning approach is being actively conducted to effectively respond to various working conditions and dynamic environments. To enhance the performance of a vision-based activity recognition model, it is essential to secure a sufficient amount of training datasets (i.e., video datasets collected from actual construction sites). However, due to safety and security issues at construction sites, there are limitations in adequately collecting training dataset under various situations and environmental conditions. In addition, the videos feature a sequence of multiple activities of heavy equipment, making it challenging to clearly distinguish the boundaries between preceding and subsequent activities. To address these challenges, this study proposed a domain adaptation in vision-based transfer learning for automated excavator activity recognition utilizing 3D ResNet (residual deep neural network). Particularly, this study aimed to identify the optimal depth of 3D ResNet (i.e., the number of layers of the feature extractor) suitable for domain adaptation via fine-tuning process. To achieve this, this study sought to evaluate the activity recognition performance of five 3D ResNet models with 18, 34, 50, 101, and 152 layers, which used two consecutive videos with multiple activities (5 mins, 33 secs and 10 mins, 6 secs) collected from actual construction sites. First, pretrained weights from large-scale datasets (i.e., Kinetic-700 and Moment in Time (MiT)) in other domains (e.g., humans, animals, natural phenomena) were utilized. Second, five 3D ResNet models were fine-tuned using a customized dataset (14,185 clips, 60,606 secs). As an evaluation index for activity recognition model, the F1 score showed 0.881, 0.689, 0.74, 0.684, and 0.569 for the five 3D ResNet models, with the 18-layer model performing the best. This result indicated that the activity recognition models with fewer layers could be advantageous in deriving the optimal weights for the target domain (i.e., excavator activities) when fine-tuning with a limited dataset. Consequently, this study identified the optimal depth of 3D ResNet that can maintain a reliable performance in dynamic and complex construction sites, even with a limited dataset. The proposed approach is expected to contribute to the development of decision-support systems capable of systematically managing enhanced safety, productivity improvement, and carbon neutrality in the construction industry.

• Journal of Broadcast Engineering
• /
• v.23 no.6
• /
• pp.855-865
• /
• 2018

Sound event detection is one of the research areas to model human auditory cognitive characteristics by recognizing events in an environment with multiple acoustic events and determining the onset and offset time for each event. DCASE, a research group on acoustic scene classification and sound event detection, is proceeding challenges to encourage participation of researchers and to activate sound event detection research. However, the size of the dataset provided by the DCASE Challenge is relatively small compared to ImageNet, which is a representative dataset for visual object recognition, and there are not many open sources for the acoustic dataset. In this study, the sound events that can occur in indoor and outdoor are collected on a larger scale and annotated for dataset construction. Furthermore, to improve the performance of the sound event detection task, we developed a dual CNN structured sound event detection system by adding a supplementary neural network to a convolutional neural network to determine the presence of sound events. Finally, we conducted a comparative experiment with both baseline systems of the DCASE 2016 and 2017.

• Journal of Advanced Navigation Technology
• /
• v.26 no.4
• /
• pp.211-218
• /
• 2022

Continuous wave (CW) radar has the advantage of reliability and accuracy compared to other sensors such as camera and lidar. In addition, binarized neural network (BNN) has a characteristic that dramatically reduces memory usage and complexity compared to other deep learning networks. Therefore, this paper proposes binarized neural network based human identification and motion classification system using CW radar. After receiving a signal from CW radar, a spectrogram is generated through a short-time Fourier transform (STFT). Based on this spectrogram, we propose an algorithm that detects whether a person approaches a radar. Also, we designed an optimized BNN model that can support the accuracy of 90.0% for human identification and 98.3% for motion classification. In order to accelerate BNN operation, we designed BNN hardware accelerator on field programmable gate array (FPGA). The accelerator was implemented with 1,030 logics, 836 registers, and 334.904 Kbit block memory, and it was confirmed that the real-time operation was possible with a total calculation time of 6 ms from inference to transferring result.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.4 no.4
• /
• pp.277-286
• /
• 2002

Most of the problems in dealing with the tunnel construction are the uncertainties and complexities of the stress conditions and rock strengths in ahead of the tunnel excavation. The limitations on the investigation technology, inaccessibility of borehole test in mountain area and public hatred also restrict our knowledge on the geologic conditions on the mountainous tunneling area. Nevertheless an extensive and superior geophysical exploration data is possibly acquired deep within the mountain area, with up to the tunnel locations in the case of alternative design or turn-key base projects. An appealing claim in the use of artificial neural networks (ANN) is that they give a more trustworthy results on our data based on identifying relevant input variables such as a little geotechnical information and biological learning principles. In this study, error back-propagation algorithm that is one of the teaching techniques of ANN is applied to presupposition on Rock Mass Ratings (RMR) for unknown tunnel area. In order to verify the applicability of this model, a 4km railway tunnel's field data are verified and used as input parameters for the prediction of RMR, with the learned pattern by error back propagation logics. ANN is one of basic methods in solving the geotechnical uncertainties and helpful in solving the problems with data consistency, but needs some modification on the technical problems and we hope our study to be developed in the future design work.

• Korean Journal of Remote Sensing
• /
• v.33 no.5_2
• /
• pp.631-640
• /
• 2017

The estimation of rice yield affects the income of farmers as well as the fields related to agriculture. Moreover, it has an important effect on the government's policy making including the control of supply demand and the price estimation. Thus, it is necessary to build the crop yield estimation model and from the past, many studies utilizing empirical statistical models or artificial neural network algorithms have been conducted through climatic and satellite data. Presently, scientists have achieved successful results with deep learning algorithms in the field of pattern recognition, computer vision, speech recognition, etc. Among deep learning algorithms, the SSAE (Stacked Sparse AutoEncoder) algorithm has been confirmed to be applicable in the field of forecasting through time series data and in this study, SSAE was utilized to estimate the rice yield in South Korea. The climatic and satellite data were used as the input variables and different types of input data were constructed according to the period of rice growth in South Korea. As a result, the combination of the satellite data from May to September and the climatic data using the 16 day average value showed the best performance with showing average annual %RMSE (percent Root Mean Square Error) and region %RMSE of 7.43% and 7.16% that the applicability of the SSAE algorithm could be proved in the field of rice yield estimation.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.12 no.6
• /
• pp.629-635
• /
• 2019

In Deep Learning models derivative is implemented by error back-propagation which enables the model to learn the error and update parameters. It can find the global (or local) optimal points of parameters even in the complex models taking advantage of a huge improvement in computing power. However, deliberately generated data points can 'fool' models and degrade the performance such as prediction accuracy. Not only these adversarial examples reduce the performance but also these examples are not easily detectable with human's eyes. In this work, we propose the method to detect adversarial datasets with random noise addition. We exploit the fact that when random noise is added, prediction accuracy of non-adversarial dataset remains almost unchanged, but that of adversarial dataset changes. We set attack methods (FGSM, Saliency Map) and noise level (0-19 with max pixel value 255) as independent variables and difference of prediction accuracy when noise was added as dependent variable in a simulation experiment. We have succeeded in extracting the threshold that separates non-adversarial and adversarial dataset. We detected the adversarial dataset using this threshold.