Anomaly detection is critical across domains, from cybersecurity to fraud prevention. Graphs, adept at modeling intricate relationships, offer a flexible framework for capturing complex data structures. This paper proposes a novel anomaly detection approach, combining Graph Convolutional Networks (GCNs) and Density-Based Spatial Clustering of Applications with Noise (DBSCAN). GCNs, a specialized deep learning model for graph data, extracts meaningful node and edge representations by incorporating graph topology and attribute information. This facilitates learning expressive node embeddings capturing local and global structural patterns. For anomaly detection, DBSCAN, a density-based clustering algorithm effective in identifying clusters of varying densities amidst noise, is employed. By defining a minimum distance threshold and a minimum number of points within that distance, DBSCAN proficiently distinguishes normal graph elements from anomalies. Our approach involves training a GCN model on a labeled graph dataset, generating appropriately labeled node embeddings. These embeddings serve as input to DBSCAN, identifying clusters and isolating anomalies as noise points. The evaluation on benchmark datasets highlights the superior performance of our approach in anomaly detection compared to traditional methods. The fusion of GCNs and DBSCAN demonstrates a significant potential for accurate and efficient anomaly detection in graphs. This research contributes to advancing graph-based anomaly detection, with promising applications in domains where safeguarding data integrity and security is paramount.

Accurate detection and state analysis of traffic flows are essential for effectively reconstructing traffic flows and reducing the risk of severe injury and fatality. For this reason, several studies have proposed crowdsourcing to resolve traffic problems, in which drivers provide real-time traffic information using mobile devices to monitor traffic conditions. Using data collected via crowdsourcing for traffic event detection has advantages in terms of improved accuracy and reduced time and cost. In this paper, we propose a technique that employs crowdsourcing to collect traffic-related data for detecting events that influence traffic. The proposed technique uses various machine-learning methods to accurately identify events and location information. Therefore, it can resolve problems typically encountered with conventionally provided location information, such as broadly defined locations or inaccurate location information. The proposed technique has advantages in terms of reducing time and cost while increasing accuracy. Performance evaluations also demonstrated its validity and effectiveness.

Academic researchers publish their work in various formats, such as papers, patents, and research reports, on different academic sites. When searching for a particular researcher’s work, it can be challenging to pinpoint the right individual, especially when there are multiple researchers with the same name. In order to handle this issue, we propose a name disambiguation scheme for researchers with the same name based on heterogeneous academic sites. The proposed scheme collects and integrates research results from these varied academic sites, focusing on attributes crucial for disambiguation. It then employs clustering techniques to identify individuals who share the same name. Additionally, we implement the proposed rule-based algorithm name disambiguation method and the existing deep learning-based identification method. This approach allows for the selection of the most accurate disambiguation scheme, taking into account the metadata available in the academic sites, using a multi-classifier approach. We consider various researchers’ achievements and metadata of articles registered in various academic search sites. The proposed scheme showed an exceptionally high F1-measure value of 0.99. In this paper, we propose a multi-classifier that executes the most appropriate disambiguation scheme depending on the inputted metadata. The proposed multi-classifier shows the high F1-measure value of 0.67.

Road speed is an important indicator of traffic congestion. Therefore, the occurrence of traffic congestion can be reduced by predicting road speed because predicted road speed can be provided to users to distribute traffic. Traffic congestion prediction techniques can provide alternative routes to users in advance to help them avoid traffic jams. In this paper, we propose a machine-learning-based road speed prediction scheme using road environment data analysis. The proposed scheme uses not only the speed data of the target road, but also the speed data of neighboring roads that can affect the speed of the target road. Furthermore, the proposed scheme can accurately predict both the average road speed and rapidly changing road speeds. The proposed scheme uses historical average speed data from the target road organized by the day of the week and hour to reflect the average traffic flow on the road. Additionally, the proposed scheme analyzes speed changes in sections where the road speed changes rapidly to reflect traffic flows. Road speeds may change rapidly as a result of unexpected events such as accidents, disasters, and construction work. The proposed scheme predicts final road speeds by applying historical road speeds and events as weights for road speed prediction. It also considers weather conditions. The proposed scheme uses long short-term memory (LSTM), which is suitable for sequential data learning, as a machine learning algorithm for speed prediction. The proposed scheme can predict road speeds in 30 min by using weather data and speed data from the target and neighboring roads as input data. We demonstrate the capabilities of the proposed scheme through various performance evaluations.

In this study, we propose three k-nearest neighbor (k-NN) optimization techniques for a distributed, in-memory-based, high-dimensional indexing method to speed up content-based image retrieval. The proposed techniques perform distributed, in-memory, high-dimensional indexing-based k-NN query optimization: a density-based optimization technique that performs k-NN optimization using data distribution; a cost-based optimization technique using query processing cost statistics; and a learning-based optimization technique using a deep learning model, based on query logs. The proposed techniques were implemented on Spark, which supports a master/slave model for large-scale distributed processing. We showed the superiority and validity of the proposed techniques through various performance evaluations, based on high-dimensional data.

Recently, there has been active research on utilizing GPUs for the efficient processing of large-scale dynamic graphs. However, challenges arise due to the repeated transmission and processing of identical data during dynamic graph operations. This paper proposes an efficient processing scheme for large-scale dynamic graphs in GPU environments with limited memory, leveraging dynamic scheduling and operation reduction. The proposed scheme partitions the dynamic graph and schedules each partition based on active and tentative active vertices, optimizing GPU utilization. Additionally, snapshots are employed to capture graph changes, enabling the detection of redundant edge and vertex modifications. This reduces unnecessary computations, thereby minimizing GPU workloads and data transmission costs. The scheme significantly enhances performance by eliminating redundant operations on the same edges or vertices. Performance evaluations demonstrate an average improvement of 280% over existing static graph processing techniques and 108% over existing dynamic graph processing schemes.