• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.3
• /
• pp.1100-1118
• /
• 2021

In a wide range of ML applications, the training data contains privacy-sensitive information that should be kept secure. Training the ML systems by privacy-sensitive data makes the ML model inherent to the data. As the structure of the model has been fine-tuned by training data, the model can be abused for accessing the data by the estimation in a reverse process called model inversion attack (MIA). Although, MIA has been applied to shallow neural network models of recognizers in literature and its threat in privacy violation has been approved, in the case of a deep learning (DL) model, its efficiency was under question. It was due to the complexity of a DL model structure, big number of DL model parameters, the huge size of training data, big number of registered users to a DL model and thereof big number of class labels. This research work first analyses the possibility of MIA on a deep learning model of a recognition system, namely a face recognizer. Second, despite the conventional MIA under the white box scenario of having partial access to the users' non-sensitive information in addition to the model structure, the MIA is implemented on a deep face recognition system by just having the model structure and parameters but not any user information. In this aspect, it is under a semi-white box scenario or in other words a gray-box scenario. The experimental results in targeting five registered users of a CNN-based face recognition system approve the possibility of regeneration of users' face images even for a deep model by MIA under a gray box scenario. Although, for some images the evaluation recognition score is low and the generated images are not easily recognizable, but for some other images the score is high and facial features of the targeted identities are observable. The objective and subjective evaluations demonstrate that privacy cyber-attack by MIA on a deep recognition system not only is feasible but also is a serious threat with increasing alert state in the future as there is considerable potential for integration more advanced ML techniques to MIA.

• The Journal of the Acoustical Society of Korea
• /
• v.42 no.4
• /
• pp.329-344
• /
• 2023

In this study, we comprehensively analyze the generalization performance of various deep learning-based active sonar target classifiers when applied to small and imbalanced active sonar datasets. To generate the active sonar datasets, we use data from two different oceanic experiments conducted at different times and ocean. Each sample in the active sonar datasets is a time-frequency domain image, which is extracted from audio signal of contact after the detection process. For the comprehensive analysis, we utilize 22 Convolutional Neural Networks (CNN) models. Two datasets are used as train/validation datasets and test datasets, alternatively. To calculate the variance in the output of the target classifiers, the train/validation/test datasets are repeated 10 times. Hyperparameters for training are optimized using Bayesian optimization. The results demonstrate that shallow CNN models show superior robustness and generalization performance compared to most of deep CNN models. The results from this paper can serve as a valuable reference for future research directions in deep learning-based active sonar target classification.

• The Journal of the Acoustical Society of Korea
• /
• v.39 no.4
• /
• pp.279-285
• /
• 2020

The study on the temporal and spatial monitoring of passing vessels is important in terms of protection and management the marine ecosystem in the coastal area. In this paper, we propose the automatic detection technique of passing vessel by utilizing an artificial intelligence technology and broadband striation patterns which are characteristic of broadband noise radiated by passing vessel. Acoustic measurements to collect underwater noise spectrum images and ship navigation information were conducted in the southern region of Jeju Island in South Korea for 12 days (2016.07.15-07.26). And the convolution neural network model is optimized through learning and validation processes based on the collected images. The automatic detection performance of passing vessel is evaluated by precision (0.936), recall (0.830), average precision (0.824), and accuracy (0.949). In conclusion, the possibility of the automatic detection technique of passing vessel is confirmed by using an artificial intelligence technology, and a future study is proposed from the results of this study.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.3
• /
• pp.237-246
• /
• 2019

In order to improve the accuracy of the rating prediction of the recommendation model, not only user-item rating data are used but also consider auxiliary information of item such as comments, tags, or descriptions. The traditional approaches use a word-level model of the bag-of-words for the auxiliary information. This model, however, cannot utilize the auxiliary information effectively, which leads to shallow understanding of auxiliary information. Convolution neural network (CNN) can capture and extract feature vector from auxiliary information effectively. Thus, this paper proposes character-level deep-Convolution Neural Network based matrix factorization (Char-DCNN-MF) that integrates deep CNN into matrix factorization for a novel recommendation model. Char-DCNN-MF can deeper understand auxiliary information and further enhance recommendation performance. Experiments are performed on three different real data sets, and the results show that Char-DCNN-MF performs significantly better than other comparative models.

• Journal of Intelligence and Information Systems
• /
• v.29 no.3
• /
• pp.167-183
• /
• 2023

In the recent field of recommendation systems, various studies have been conducted to model sparse data effectively. Among these, GLocal-K(Global and Local Kernels for Recommender Systems) is a research endeavor combining global and local kernels to provide personalized recommendations by considering global data patterns and individual user characteristics. However, due to its utilization of kernel tricks, GLocal-K exhibits diminished performance on highly sparse data and struggles to offer recommendations for new users or items due to the absence of side information. In this paper, to address these limitations of GLocal-K, we propose the GEase-K (Global and EASE kernels for Recommender Systems) model, incorporating the EASE(Embarrassingly Shallow Autoencoders for Sparse Data) model and leveraging side information. Initially, we substitute EASE for the local kernel in GLocal-K to enhance recommendation performance on highly sparse data. EASE, functioning as a simple linear operational structure, is an autoencoder that performs highly on extremely sparse data through regularization and learning item similarity. Additionally, we utilize side information to alleviate the cold-start problem. We enhance the understanding of user-item similarities by employing a conditional autoencoder structure during the training process to incorporate side information. In conclusion, GEase-K demonstrates resilience in highly sparse data and cold-start situations by combining linear and nonlinear structures and utilizing side information. Experimental results show that GEase-K outperforms GLocal-K based on the RMSE and MAE metrics on the highly sparse GoodReads and ModCloth datasets. Furthermore, in cold-start experiments divided into four groups using the GoodReads and ModCloth datasets, GEase-K denotes superior performance compared to GLocal-K.

• Journal of IKEEE
• /
• v.26 no.3
• /
• pp.408-415
• /
• 2022

In this paper, we propose a 3D point cloud reconstruction technique from 2D images using efficient feature map extraction network. The originality of the method proposed in this paper is as follows. First, we use a new feature map extraction network that is about 27% efficient than existing techniques in terms of memory. The proposed network does not reduce the size to the middle of the deep learning network, so important information required for 3D point cloud reconstruction is not lost. We solved the memory increase problem caused by the non-reduced image size by reducing the number of channels and by efficiently configuring the deep learning network to be shallow. Second, by preserving the high-resolution features of the 2D image, the accuracy can be further improved than that of the conventional technique. The feature map extracted from the non-reduced image contains more detailed information than the existing method, which can further improve the reconstruction accuracy of the 3D point cloud. Third, we use a divergence loss that does not require shooting information. The fact that not only the 2D image but also the shooting angle is required for learning, the dataset must contain detailed information and it is a disadvantage that makes it difficult to construct the dataset. In this paper, the accuracy of the reconstruction of the 3D point cloud can be increased by increasing the diversity of information through randomness without additional shooting information. In order to objectively evaluate the performance of the proposed method, using the ShapeNet dataset and using the same method as in the comparative papers, the CD value of the method proposed in this paper is 5.87, the EMD value is 5.81, and the FLOPs value is 2.9G. It was calculated. On the other hand, the lower the CD and EMD values, the better the accuracy of the reconstructed 3D point cloud approaches the original. In addition, the lower the number of FLOPs, the less memory is required for the deep learning network. Therefore, the CD, EMD, and FLOPs performance evaluation results of the proposed method showed about 27% improvement in memory and 6.3% in terms of accuracy compared to the methods in other papers, demonstrating objective performance.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.22 no.3
• /
• pp.15-30
• /
• 2019

Changpo Lake was created as a part of a land reclamation for refugee self-helping projects. It shows characteristics of a fresh water lake, and still retains the early appearance of reclamation that surrounding regions have not been developed into farm lands. Shallow wetland has formed around the lake, which provides great conditions for diverse lives, and surrounding earthiness is favorable for growth of vegetation and restoration of the ecosystem. However, as facilities of the Muan International Airport nearby Changpo Lake are expanding and barns are being constructed, artificialness is gradually increasing. Particularly, since pollution sources such as sport facilities, farm lands and barns are scattered around Changpo Lake, pollutants are flowing in constantly. Accordingly, the results for setting up management areas according to the spatial characteristics and creating natural ecological spaces near Changpo Lake, Taebongcheon stream and Hakgyecheon stream are as follows. First, the creation of a natural eco-friendly waterfront space should be promoted by securing the health of the aquatic ecosystem and restoring species and the ecosystem. In addition, a consultative body needs to be formed to lead local residents to participating in river investigation and monitoring, maintenance, and management through role sharing. Second, the basic direction of the spatial management plan is to keep the unique charm of Changpo Lake, maintain harmony with nature, create diverse waterfront areas, and secure the continuity of Changpo Lake and inflow streams. Moreover, the area should be divided into three zones such as a conservation zone, a restoration zone and a waterfront zone, and for each zone, the preservation of vegetation, the creation of ecological wetlands and restoration of the ecotone and ecological nature need to be promoted. Third, facilities and activity programs for each space of Changpo Lake should be operated for efficient management of protected areas. In order to suit the status of each space, biological habitats, water purification spaces, experiential and learning spaces, and convenience and rest spaces should be organized and designated as research, monitoring, education, and tourism areas. Accordingly, points of interest should be set up within the corresponding area. In this study, there are many parts that need to be supplemented for immediate implementation since the detailed plans and project costs for the promotion of programs by area are not calculated. Therefore, it is necessary to make detailed project plans and consider related projects such as water quality, restoration of habitats, nature learning and observation, and experience of ecological environments based on the categories such as research, monitoring, education and tourism in the future.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.5
• /
• pp.211-220
• /
• 2022

Recently, research on smart factories triggered by the 4th industrial revolution is being actively conducted. Accordingly, the manufacturing industry is conducting various studies to improve productivity and quality based on deep learning technology with robust performance. This paper is a study on the method of detecting tire surface defects in the visual inspection stage of the tire manufacturing process, and introduces a tire surface defect detection method using a depth image acquired through a 3D camera. The tire surface depth image dealt with in this study has the problem of low contrast caused by the shallow depth of the tire surface and the difference in the reference depth value due to the data acquisition environment. And due to the nature of the manufacturing industry, algorithms with performance that can be processed in real time along with detection performance is required. Therefore, in this paper, we studied a method to normalize the depth image through relatively simple methods so that the tire surface defect detection algorithm does not consist of a complex algorithm pipeline. and conducted a comparative experiment between the general normalization method and the normalization method suggested in this paper using YOLO V3, which could satisfy both detection performance and speed. As a result of the experiment, it is confirmed that the normalization method proposed in this paper improved performance by about 7% based on mAP 0.5, and the method proposed in this paper is effective.

• Journal of the Korean Geotechnical Society
• /
• v.15 no.1
• /
• pp.99-112
• /
• 1999

By using 92 values of lateral earth pressure coefficient(K) measured in Korea, the tendency of K with varying depth is analyzed and compared with the range of K defined by Hoek and Brown. The horizontal stress is generally larger than the vertical stress in Korea : About 84 % of K values are above 1. In this study, the theory of elasto-plasticity is applied to analyze the variation of K values, and the results are compared with those of numerical analysis. This reveals that the erosion, sedimentation and weathering of earth crust are important factors in the determination of K values. Surface erosion, large lateral pressure and good rock mass increase the K values, but sedimentation decreases the K values. This study enable us to analyze the effects of geological processes on the K values, especially at shallow depth where underground excavation takes place. A neural network expert system using multi-layer back-propagation algorithm is developed to predict the K values. The neural network model has a correlation coefficient above 0.996 when it is compared with measured data. The comparison with 9 measured data which are not included in the back-propagation learning has shown an average inference error of 20% and the correlation coefficient above 0.95. The expert system developed in this study can be used for reliable determination of K values.

• Korean Journal of Remote Sensing
• /
• v.35 no.2
• /
• pp.299-316
• /
• 2019

The purpose of this study was to analyze landslide susceptibility in the Pyeongchang area using Weight of Evidence (WOE) and Evidential Belief Function (EBF) as probability models and Artificial Neural Networks (ANN) as a machine learning model in a geographic information system (GIS). This study examined the widespread shallow landslides triggered by heavy rainfall during Typhoon Ewiniar in 2006, which caused serious property damage and significant loss of life. For the landslide susceptibility mapping, 3,955 landslide occurrences were detected using aerial photographs, and environmental spatial data such as terrain, geology, soil, forest, and land use were collected and constructed in a spatial database. Seventeen factors that could affect landsliding were extracted from the spatial database. All landslides were randomly separated into two datasets, a training set (50%) and validation set (50%), to establish and validate the EBF, WOE, and ANN models. According to the validation results of the area under the curve (AUC) method, the accuracy was 74.73%, 75.03%, and 70.87% for WOE, EBF, and ANN, respectively. The EBF model had the highest accuracy. However, all models had predictive accuracy exceeding 70%, the level that is effective for landslide susceptibility mapping. These models can be applied to predict landslide susceptibility in an area where landslides have not occurred previously based on the relationships between landslide and environmental factors. This susceptibility map can help reduce landslide risk, provide guidance for policy and land use development, and save time and expense for landslide hazard prevention. In the future, more generalized models should be developed by applying landslide susceptibility mapping in various areas.