Digital Library[ Search Result ]
R-FLHE: Robust Federated Learning Framework Against Untargeted Model Poisoning Attacks in Hierarchical Edge Computing
http://doi.org/10.5626/JOK.2023.50.1.94
Federated learning is a server-client based distributed learning strategy that collects only trained model to guarantee data privacy and reduce communication costs. Recently, research is being conducted to prepare for the future IoT ecosystem by combining edge computing and federated learning. However, research considering vulnerabilities and threat is insufficient. In this paper, we propose Robust Federated Learning in Hierarchical Edge computing (R-FLHE), a federated learning framework for robust global model from untargeted model poisoning attacks. R-FLHE can aggregate models learned from clients, evaluate them on the edge server, and score them based on the calculated model’s loss. R-FLHE can maintain robustness of the global model by sending only the model of the edge server with the best score to the cloud server. The R-FLHE proposed in this paper shows robustness in maintaining constant performance for each federated learning round, with performance drop of only 0.81% and 1.88% on average even if attacks occur.
Deep k-Means Node Clustering Based on Graph Neural Networks
http://doi.org/10.5626/JOK.2023.50.12.1153
Recently, graph node clustering techniques using graph neural networks (GNNs) have been actively studied. Notably, most of these studies use a GNN to embed each node into a low-dimensional vector and then cluster the embedding vectors using the existing clustering algorithms. However, since this approach does not consider the final goal of clustering when training the GNN, it is difficult to say that it produces optimal clustering results. Therefore, in this paper, we propose a deep k-means clustering method that iteratively trains a GNN considering the final goal of k-means clustering and performs k-means clustering on the embedding vectors generated by the trained GNN. The proposed method considers both the similarity between nodes and the loss of k-means clustering when training a GNN. Experimental results using real datasets confirmed that the proposed method improves the quality of k-means clustering results compared to the existing methods.
Online Opinion Fraud Detection Using Graph Neural Network
Woochang Hyun, Insoo Lee, Bongwon Suh
http://doi.org/10.5626/JOK.2023.50.11.985
This study proposed a graph neural network model to detect opinion frauds that undermine the of information and hinder users" decision-making on online platforms. The proposed method uses methods on a graph of relationships between online reviews to produce relational representations, are then combined with the characteristics of the center nodes to predict fraud. Experimental results on a real-world dataset demonstrate that this approach is more accurate and faster than existing state-of-art methods, while also providing interpretability for key relations. With the help of this study, practitioners will be able to utilize the analytical results in decision-making and overcome the general drawback of neural network-based models" lack of explainability.
Improvement Study on Active Learning-based Cross-Project Defect Prediction System
http://doi.org/10.5626/JOK.2023.50.11.931
This study proposes a practical improvement method for an active learning-based system for cross-project defect prediction. A previous study applied active learning tech- niques to practically improve the performance of cross-project defect prediction, but it used a traditional machine learning model that used hand-made features as input for active learning target selection and defect prediction, therefore feature extraction was expensive and performance was limited. In addition, the problem of performance deviation according to the selection of the input project remained. In this study, the following methods were proposed to overcome these limitations. First, we used a deep learning model that can use the source code as an input to lower the model building cost and improve prediction performance. Second, a Bayesian convolutional neural network is applied to select an active learning target using a deep learning model. Third, instead of considering a single source project, we applied a method that automatically extracts a training data set from multiple projects. Applying the system proposed in this study to 7 open source projects improved the average prediction performance by 13.58% compared to the previous latest research.
A Quantitative Comparison of LIME and SHAP using Stamp-Based Distance Method on Image Data
http://doi.org/10.5626/JOK.2023.50.10.906
XAI(eXplainable AI), 인공신경망, MNIST, 도장 기반의 distance method, LIME, SHAP Abstract XAI, or eXplainable AI, is a technique used to explain artificial neural networks in a way that can be understood by humans. However, it is difficult to compare explanations and heat maps produced by XAI algorithms numerically as it is unclear how humans interpret them. This presents a challenge in determining which XAI algorithm is the most effective and accurate in providing explanations. Therefore, we introduced a stamp-based distance method to compare several XAI algorithms and identify the most accurate algorithm. The proposed method involves evaluating the quality of explanations generated by XAI algorithms applied to a deep learning model trained to detect the presence of stamps in the MNIST dataset. This evaluation was performed using statistical techniques to determine the effectiveness of each XAI algorithm. This paper evaluated performances of LIME and SHAP algorithms using the distance method, which compared explanations produced by each algorithm. Result revealed that LIME with the Felzenszwalb method provided more effective explanations than other LIME and SHAP algorithms.
The Application and Integration of an Improvement Technique for Layers of NETCONF
Modern networks consisting of various heterogeneous equipment are often installed in a distributed manner. Thus the NETCONF standard was established to manage networks centrally and efficiently. In this paper, we present a method that integrates each NETCONF layer into a single system based on the results of previous studies. In the RPC Layer, an asynchronous communication channel and parallel processes are possible using multi-threading. In the Operation Layer, operational efficiency is increased by using a data group with dependencies between the equipment configuration data and by improving the data structure, enabling efficiently processing of XML queries even with multiple managers. The data modeling techniques and grouping methods in the Content Layer are presented in detail for interoperability between the Operation Layer and the Content Layer. Finally, the GUI program was implemented and its implementation is reported. We performed an experiment comparing the improved NETCONF with the standard NETCONF to measure factors, such as query processing ratio, query processing speed, and CPU utilization. The improved NETCONF demonstrated excellent query processing ratio and query processing speed, whereas the standard NETCONF had excellent CPU utilization.
Improvement of Korean Homograph Disambiguation using Korean Lexical Semantic Network (UWordMap)
Joon-Choul Shin, Cheol-Young Ock
Disambiguation of homographs is an important job in Korean semantic processing and has been researched for long time. Recently, machine learning approaches have demonstrated good results in accuracy and speed. Other knowledge-based approaches are being researched for untrained words. This paper proposes a hybrid method based on the machine learning approach that uses a lexical semantic network. The use of a hybrid approach creates an additional corpus from subcategorization information and trains this additional corpus. A homograph tagging phase uses the hypernym of the homograph and an additional corpus. Experimentation with the Sejong Corpus and UWordMap demonstrates the hybrid method is to be effective with an increase in accuracy from 96.51% to 96.52%.
A Sensing Node Selection Scheme for Energy-Efficient Cooperative Spectrum Sensing in Cognitive Radio Sensor Networks
Fanhua Kong, Zilong Jin, Jinsung Cho
Cognitive radio technology can allow secondary users (SUs) to access unused licensed spectrums in an opportunistic manner without interfering with primary users (PUs). Spectrum sensing is a key technology for cognitive radio (CR). However, few studies have examined energy-efficient spectrum sensing in cognitive radio sensor networks (CRSNs). In this paper, we propose an energy-efficient cooperative spectrum sensing nodes selection scheme for cluster-based cognitive radio sensor networks. In our proposed scheme, false alarm probability and energy consumption are considered to minimize the number of spectrum sensing nodes in a cluster. Simulation results show that by applying the proposed scheme, spectrum sensing efficiency is improved with a decreased number of spectrum sensing nodes. Furthermore, network energy efficiency is guaranteed and network lifetime is substantially prolonged.
Energy-aware Selective Compression Scheme for Solar-powered Wireless Sensor Networks
Min Jae Kang, Semi Jeong, Dong Kun Noh
Data compression involves a trade-off between delay time and data size. Greater delay times require smaller data sizes and vice versa. There have been many studies performed in the field of wireless sensor networks on increasing network life cycle durations by reducing data size to minimize energy consumption; however, reductions in data size result in increases of delay time due to the added processing time required for data compression. Meanwhile, as energy generation occurs periodically in solar energy-based wireless sensor networks, redundant energy is often generated in amounts sufficient to run a node. In this study, this excess energy is used to reduce the delay time between nodes in a sensor network consisting of solar energy-based nodes. The energy threshold value is determined by a formula based on the residual energy and charging speed. Nodes with residual energy below the threshold transfer data compressed to reduce energy consumption, and nodes with residual energy above the threshold transfer data without compression to reduce the delay time between nodes. Simulation based performance verifications show that the technique proposed in this study exhibits optimal performance in terms of both energy and delay time compared with traditional methods.
Cluster-based Energy-aware Data Sharing Scheme to Support a Mobile Sink in Solar-Powered Wireless Sensor Networks
Hong Seob Lee, Jun Min Yi, Jaeung Kim, Dong Kun Noh
In contrast with battery-based wireless sensor networks (WSNs), solar-powered WSNs can operate for a longtime assuming that there is no hardware fault. Meanwhile, a mobile sink can save the energy consumption of WSN, but its ineffective movement may incur so much energy waste of not only itself but also an entire network. To solve this problem, many approaches, in which a mobile sink visits only on clustering-head nodes, have been proposed. But, the clustering scheme also has its own problems such as energy imbalance and data instability. In this study, therefore, a cluster-based energy-aware data-sharing scheme (CE-DSS) is proposed to effectively support a mobile sink in a solar-powered WSN. By utilizing the redundant energy efficiently, CE-DSS shares the gathered data among cluster-heads, while minimizing the unexpected black-out time. The simulation results show that CE-DSS increases the data reliability as well as conserves the energy of the mobile sink.
Search
Journal of KIISE
- ISSN : 2383-630X(Print)
- ISSN : 2383-6296(Electronic)
- KCI Accredited Journal
Editorial Office
- Tel. +82-2-588-9240
- Fax. +82-2-521-1352
- E-mail. chwoo@kiise.or.kr