Joonho Kwon

With the rapid proliferation of blockchain technology, the volume of stored data has increased dramatically. Existing blockchain systems typically employ a key–value storage model, which is efficient for single-key lookups but inadequate for complex queries such as value-based conditional searches and range queries. Although several studies have attempted to support complex queries by integrating external databases, such approaches inherently suffer from integrity and synchronization issues. To address these limitations, we propose and implement an LSM-Tree augmented with hierarchical, level-specific B-tree indexes (referred to as LSM HB-tree). The proposed architecture augments the conventional LSM-Tree hierarchy with level-specific B-tree indexes, thereby supporting composite-key indexing and improving the efficiency of data retrieval within on-chain storage. Index construction builds a B-tree index for SSTables at each level, thereby reducing disk access costs and significantly improving the performance of equality and range queries.We evaluate the system by varying the SSTable threshold from 2 MiB to 32 MiB and observe that an 8 MiB threshold provides the best trade-off between write latency and query efficiency. Under this configuration, experiments with equality and range queries under selectivity levels ranging from 0.01% to 100% demonstrate that LSM HB-tree substantially reduces query latency compared to the conventional LSM-Tree. Furthermore, multi-threaded experiments with up to 16 threads reveal that the best performance for both equality and range queries is achieved with four threads. Collectively, these results confirm that LSM HB-tree is a practical and effective index structure for supporting efficient complex queries entirely within the internal blockchain architecture.

Owing to the increasing use of permeable pavement, there is a growing need for studies that can improve its design and durability. One of the most important factors that can reduce the functionality of permeable pavement is the clogging issue. Field experiments for investigating the clogging potential are relatively expensive owing to the high-cost testing equipment and materials. Moreover, a lot of time is required for conducting real physical experiments to obtain physical properties for permeable pavement. In this paper, to overcome these limitations, we propose a three-dimensional microstructure reconstruction framework based on 3D-IDWGAN with an enhanced gradient penalty, which is an image-based computational system for clogging analysis in permeable pavement. Our proposed system first takes a two-dimensional image as an input and extracts latent features from the 2D image. Then, it generates a 3D microstructure image through the generative adversarial network part of our model with the enhanced gradient penalty. For checking the effectiveness of our system, we utilize the reconstructed 3D image combined with the numerical method for pavement microstructure analysis. Our results show improvements in the three-dimensional image generation of the microstructure, compared with other generative adversarial network methods, and the values of physical properties extracted from our model are similar to those obtained via real pavement samples.

Indoor location-based services have been widely investigated to take advantage of semantic trajectories for providing user oriented services in indoor environments. Although indoor semantic trajectories can provide seamless understanding to users regarding the provided location-based services, studies on the application of deep learning approaches for robust and valid semantic indoor localization are lacking. In this study, we combined a stacked denoising autoencoder and long short term memory technique with a rule-based refinement method applying a rule-based hidden Markov model (HMM) to perform robust and valid semantic trajectory extraction. In particular, our rule-based HMM approach incorporates a direct set of rules into HMM to resolve invalid movements of the extracted semantic trajectories and is extensible to various deep learning techniques. We compared the performance of our proposed approach with that of other cutting-edge deep learning approaches on two different real-world data sets. The experimental results demonstrate the feasibility of our proposed approach to produce more robust and valid semantic trajectories.

Trajectory analysis can be useful to understand pedestrian behaviour in indoor environments. Collecting real data however can be difficult and time consuming, and many publicly available data sets and trajectory generation methods focus on outdoor scenarios. We propose a method for generating realistic indoor trajectory data, taking into account the various restrictions of indoor environments. The result of our experiments, conducted on two museum floor plans, is a system which only requires a set of points of interest and a floor plan picture. A graph is automatically generated using Delaunay triangulation and trajectories can be obtained by simulating a person walking through the graph.

The growing number of connected Internet of Things (IoT) devices has increased the necessity for processing IoT data from multiple heterogeneous data stores. IoT data integration is a challenging problem owing to the heterogeneity of data stores in terms of their query language, data models, and schemas. In this paper, we propose a multi-store query system for IoT data called MusQ, where users can formulate join operation queries for heterogeneous data sources. To reconcile the heterogeneity between source schemas of IoT data stores, we extract a global schema from local source schemas semi-automatically by applying schema-matching and schema-mapping steps. In order to minimize the burden on the user to understand the finer details of various query languages, we define a unified query language called the multi-store query language (MQL), which follows a subset of the Datalog grammar. Thus, users can easily retrieve IoT data from multiple heterogeneous sources with MQL queries. As the three MQL query-processing join algorithms are based on a mediator–wrapper approach, MusQ performs efficient data integration over significant volumes of IoT data from multiple stores. We conduct extensive experiments to evaluate the performance of the MusQ system using a synthetic and large real IoT data set for three different types of data stores (RDBMS, NoSQL, and HDFS). The experimental results demonstrate that MusQ is suitable, scalable, and efficient query processing for multiple heterogeneous IoT data stores. Those advantages of MusQ are important in several areas that involve complex IoT systems, such as smart city, healthcare, and energy management.

Indoor positioning techniques, owing to received signal strength indicator (RSSI)-based sensors, can provide useful trajectory-based services. These services include user movement analytics, next-to-visit recommendation, and hotspot detection. However, the value of RSSI is often disturbed due to obstacles in indoor environment, such as doors, walls, and furnitures. Therefore, many indoor positioning techniques still extract an invalid trajectory from the disturbed RSSI. An invalid trajectory contains distant or impossible consecutive positions within a short time, which is unlikely in a real-world scenario. In this study, we enhanced indoor positioning techniques with movement constraints on BLE (Bluetooth Low Energy) RSSI data to prevent an invalid semantic indoor trajectory. The movement constraints ensure that a predicted semantic position cannot be far apart from the previous position. Furthermore, we can extend any indoor positioning technique using these movement constraints. We conducted comprehensive experimental studies on real BLE RSSI datasets from various indoor environment scenarios. The experimental results demonstrated that the proposed approach effectively extracts valid indoor semantic trajectories from the RSSI data.

The new standard oneM2M (one machine-to-machine) aims to standardize the architecture and protocols of Internet of Things (IoT) middleware for better interoperability. Although the standard seems promising, it lacks several features for efficiently searching and retrieving IoT data which satisfy users’ intentions. In this paper, we design and develop a oneM2M-based query engine, called OMQ, that provides a real-time processing over IoT data streams. For this purpose, we define a query language which enables users to retrieve IoT data from data sources using JavaScript Object Notation (JSON). We also propose efficient query processing algorithms which utilizes the oneM2M architecture consisting of two nodes: (1) the IoT node and (2) the infrastructure node. IoT nodes of OMQ are mainly sensor devices execute user queries the aggregate, transform and filter operators, whereas the infrastructure node handles the join operator of user queries. Since the query processing algorithms are implemented as the hybrid infrastructure-edge processing, user queries can be executed efficiently in each IoT node rather than only in the infrastructure node. Thus, our OMQ system reduces the query processing time and the network bandwidth. We conducted a comprehensive evaluation of OMQ using a real and a synthetic data set. Experimental results demonstrate the feasibility and efficiency of OMQ system for executing queries and transferring data from each IoT node.

In this paper, we are interested in computing ZIP code proximity from two perspectives, proximity between two ZIP codes (Ad-Hoc) and neighborhood proximity (Top-K). Such a computation can be used for ZIP code-based target marketing as one of the smart city applications. A naïve approach to this computation is the usage of the distance between ZIP codes. We redefine a distance metric combining the centroid distance with the intersecting road network between ZIP codes by using a weighted sum method. Furthermore, we prove that the results of our combined approach conform to the characteristics of distance measurement. We have proposed a general and heuristic approach for computing Ad-Hoc proximity, while for computing Top-K proximity, we have proposed a general approach only. Our experimental results indicate that our approaches are verifiable and effective in reducing the execution time and search space.

One of the crucial problems for taxi drivers is to efficiently locate passengers in order to increase profits. The rapid advancement and ubiquitous penetration of Internet of Things (IoT) technology into transportation industries enables us to provide taxi drivers with locations that have more potential passengers (more profitable areas) by analyzing and querying taxi trip data. In this paper, we propose a query processing system, called Distributed Profitable-Area Query (DISPAQ) which efficiently identifies profitable areas by exploiting the Apache Software Foundation’s Spark framework and a MongoDB database. DISPAQ first maintains a profitable-area query index (PQ-index) by extracting area summaries and route summaries from raw taxi trip data. It then identifies candidate profitable areas by searching the PQ-index during query processing. Then, it exploits a Z-Skyline algorithm, which is an extension of skyline processing with a Z-order space filling curve, to quickly refine the candidate profitable areas. To improve the performance of distributed query processing, we also propose local Z-Skyline optimization, which reduces the number of dominant tests by distributing killer profitable areas to each cluster node. Through extensive evaluation with real datasets, we demonstrate that our DISPAQ system provides a scalable and efficient solution for processing profitable-area queries from huge amounts of big taxi trip data.