• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.9
• /
• pp.1224-1230
• /
• 2020

Since the spread of smart phones, interest in wearable devices has increased and diversified, and is closely related to the lives of users, and has been used as a method for providing personalized services. In this paper, we propose a method to detect the user's behavior by applying information from a 3-axis acceleration sensor and a 3-axis gyro sensor embedded in a smartphone to a convolutional neural network. Human behavior differs according to the size and range of motion, starting and ending time, including the duration of the signal data constituting the motion. Therefore, there is a performance problem for accuracy when applied to a convolutional neural network as it is. Therefore, we proposed a Time-Division Feature Fusion Convolutional Neural Network (TDFFCNN) that learns the characteristics of the sensor data segmented over time. The proposed method outperformed other classifiers such as SVM, IBk, convolutional neural network, and long-term memory circulatory neural network.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.1
• /
• pp.162-169
• /
• 2022

In a dynamically changing time-varying network environment, the optimal moving pattern of edge devices can be applied to distributing computing resources to edge cloud servers or deploying new edge servers in the FEC(Fog/Edge Computing) environment. In addition, this can be used to build an environment capable of efficient computation offloading to alleviate latency problems, which are disadvantages of cloud computing. This paper proposes an algorithm to extract the optimal moving pattern by analyzing the moving path of multiple edge devices requiring application services in an arbitrary spatio-temporal environment based on frequency. A comparative experiment with A^* and Dijkstra algorithms shows that the proposed algorithm uses a relatively fast execution time and less memory, and extracts a more accurate optimal path. Furthermore, it was deduced from the comparison result with the A^* algorithm that applying weights (preference, congestion, etc.) simultaneously with frequency can increase path extraction accuracy.

• Journal of the Economic Geographical Society of Korea
• /
• v.25 no.1
• /
• pp.171-181
• /
• 2022

The real estate price index plays key roles as quantitative data in real estate market analysis. International organizations including OECD publish the real estate price indexes by country, and the Korea Real Estate Board announces metropolitan-level and municipal-level indexes. However, when the index is set on the smaller spatial unit level than metropolitan and municipal-level, problems occur: missing values. As the spatial scope is narrowed down, there are cases where there are few or no transactions depending on the unit period, which lead index calculation difficult or even impossible. This study suggests a supervised learning-based machine learning model to compensate for missing values that may occur due to no transaction in a specific range and period. The models proposed in our research verify the accuracy of predicting the existing values and missing values.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.7
• /
• pp.101-108
• /
• 2022

We propose an intrusion detection model that detects denial-of-service(DoS) and distributed reflection denial-of-service(DRDoS) attacks, based on the empirical data of each internet of things(IoT) device by training system and network metrics that can be commonly collected from various IoT devices. First, we collect 37 system and network metrics from each IoT device considering IoT attack scenarios; further, we train them using six types of machine learning models to identify the most effective machine learning models as well as important metrics in detecting and distinguishing IoT attacks. Our experimental results show that the Random Forest model has the best performance with accuracy of over 96%, followed by the K-Nearest Neighbor model and Decision Tree model. Of the 37 metrics, we identified five types of CPU, memory, and network metrics that best imply the characteristics of the attacks in all the experimental scenarios. Furthermore, we found out that packets with higher transmission speeds than larger size packets represent the characteristics of DoS and DRDoS attacks more clearly in IoT networks.

• Journal of IKEEE
• /
• v.26 no.3
• /
• pp.364-372
• /
• 2022

This paper proposes the design and implementation results for human and object classification systems utilizing frequency modulated continuous wave (FMCW) radar sensor. Such a system requires the process of radar sensor signal processing for multi-target detection and the process of deep learning for the classification of human and object. Since deep learning requires such a great amount of computation and data processing, the lightweight process is utmost essential. Therefore, binary neural network (BNN) structure was adopted, operating convolution neural network (CNN) computation in a binary condition. In addition, for the real-time operation, a hardware accelerator was implemented and verified via FPGA platform. Based on performance evaluation and verified results, it is confirmed that the accuracy for multi-target classification of 90.5%, reduced memory usage by 96.87% compared to CNN and the run time of 5ms are achieved.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.1
• /
• pp.1-15
• /
• 2022

The MobileNetV3 is specially designed for mobile devices with limited memory and computing power. To reduce the network parameters and improve the network inference speed, a new lightweight network is proposed based on MobileNetV3. Firstly, to reduce the computation of residual blocks, a partial residual structure is designed by dividing the input feature maps into two parts. The designed partial residual structure is used to replace the residual block in MobileNetV3. Secondly, a dual-path feature extraction structure is designed to further reduce the computation of MobileNetV3. Different convolution kernel sizes are used in the two paths to extract feature maps with different sizes. Besides, a transition layer is also designed for fusing features to reduce the influence of the new structure on accuracy. The CIFAR-100 dataset and Image Net dataset are used to test the performance of the proposed partial residual structure. The ResNet based on the proposed partial residual structure has smaller parameters and FLOPs than the original ResNet. The performance of improved MobileNetV3 is tested on CIFAR-10, CIFAR-100 and ImageNet image classification task dataset. Comparing MobileNetV3, GhostNet and MobileNetV2, the improved MobileNetV3 has smaller parameters and FLOPs. Besides, the improved MobileNetV3 is also tested on CPU and Raspberry Pi. It is faster than other networks

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.9
• /
• pp.2991-3007
• /
• 2022

Two dimensional locality preserving projections (2D-LPP) is an improved algorithm of 2D image to solve the small sample size (SSS) problems which locality preserving projections (LPP) meets. It's able to find the low dimension manifold mapping that not only preserves local information but also detects manifold embedded in original data spaces. However, 2D-LPP is simple and elegant. So, inspired by the comparison experiments between two dimensional linear discriminant analysis (2D-LDA) and linear discriminant analysis (LDA) which indicated that matrix based methods don't always perform better even when training samples are limited, we surmise 2D-LPP may meet the same limitation as 2D-LDA and propose a novel matrix exponential method to enhance the performance of 2D-LPP. 2D-MELPP is equivalent to employing distance diffusion mapping to transform original images into a new space, and margins between labels are broadened, which is beneficial for solving classification problems. Nonetheless, the computational time complexity of 2D-MELPP is extremely high. In this paper, we replace some of matrix multiplications with multiple multiplications to save the memory cost and provide an efficient way for solving 2D-MELPP. We test it on public databases: random 3D data set, ORL, AR face database and Polyu Palmprint database and compare it with other 2D methods like 2D-LDA, 2D-LPP and 1D methods like LPP and exponential locality preserving projections (ELPP), finding it outperforms than others in recognition accuracy. We also compare different dimensions of projection vector and record the cost time on the ORL, AR face database and Polyu Palmprint database. The experiment results above proves that our advanced algorithm has a better performance on 3 independent public databases.

• Journal of IKEEE
• /
• v.26 no.4
• /
• pp.614-621
• /
• 2022

This paper proposes RIDS (Random Forest-Based Intrusion Detection), which is an intrusion detection system to detect hacking attack based on random forest. RIDS detects three typical attacks i.e. DoS (Denial of service) attack, fuzzing attack, and spoofing attack. It detects hacking attack based on four parameters, i.e. time interval between data frames, its deviation, Hamming distance between payloads, and its diviation. RIDS was designed in memory-centric architecture and node information is stored in memories. It was designed in scalable architecture where DoS attack, fuzzing attack, and spoofing attack can be all detected by adjusting number and depth of trees. Simulation results show that RIDS has 0.9835 accuracy and 0.9545 F1 score and it can detect three attack types effectively.

• Journal of the Korean Society of Systems Engineering
• /
• v.18 no.2
• /
• pp.94-107
• /
• 2022

Accidents prevention and mitigation is the highest priority of nuclear power plant (NPP) operation, particularly in the aftermath of the Fukushima Daiichi accident, which has reignited public anxieties and skepticism regarding nuclear energy usage. To deal with accident scenarios more effectively, operators must have ample and precise information about key safety parameters as well as their future trajectories. This work investigates the potential of machine learning in forecasting NPP response in real-time to provide an additional validation method and help reduce human error, especially in accident situations where operators are under a lot of stress. First, a base-case SGTR simulation is carried out by the best-estimate code RELAP5/MOD3.4 to confirm the validity of the model against results reported in the APR1400 Design Control Document (DCD). Then, uncertainty quantification is performed by coupling RELAP5/MOD3.4 and the statistical tool DAKOTA to generate a large enough dataset for the construction and training of neural-based machine learning (ML) models, namely LSTM, GRU, and hybrid CNN-LSTM. Finally, the accuracy and reliability of these models in forecasting system response are tested by their performance on fresh data. To facilitate and oversee the process of developing the ML models, a Systems Engineering (SE) methodology is used to ensure that the work is consistently in line with the originating mission statement and that the findings obtained at each subsequent phase are valid.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.117-127
• /
• 2022

Data anomalies seriously threaten the reliability of the bridge structural health monitoring system and may trigger system misjudgment. To overcome the above problem, an efficient and accurate data anomaly detection method is desiderated. Traditional anomaly detection methods extract various abnormal features as the key indicators to identify data anomalies. Then set thresholds artificially for various features to identify specific anomalies, which is the artificial experience method. However, limited by the poor generalization ability among sensors, this method often leads to high labor costs. Another approach to anomaly detection is a data-driven approach based on machine learning methods. Among these, the bidirectional long-short memory neural network (BiLSTM), as an effective classification method, excels at finding complex relationships in multivariate time series data. However, training unprocessed original signals often leads to low computation efficiency and poor convergence, for lacking appropriate feature selection. Therefore, this article combines the advantages of the two methods by proposing a deep learning method with manual experience statistical features fed into it. Experimental comparative studies illustrate that the BiLSTM model with appropriate feature input has an accuracy rate of over 87-94%. Meanwhile, this paper provides basic principles of data cleaning and discusses the typical features of various anomalies. Furthermore, the optimization strategies of the feature space selection based on artificial experience are also highlighted.