Since securing data is essential in the field of artificial intelligence, the importance of data collection and purification is steadily increasing. On the other hand, there are typical problems arising in the process of collecting data, such as the black bias problem in COMPAS and the fairness problem that exists within the data, such as the facial recognition bias problem. Accordingly, by designing and implementing a system that corrects fairness by removing bias existing in the dataset itself, we tried to help research on artificial intelligence models. The 'Fairness Improvement Technology and Visualization Services for binary classification datasets collected on a batch basis' consists of a subset generator that separates the initial binary classification datasets with unique values, a bias remover that removes bias by comparing and verifying each subset, and a visualization module that visualizes the corrected data as a web service. In addition, the proposed system in this paper presents a data-level research method that eliminates bias in the data itself without modifying additional learning or algorithms, and confirms the potential of the proposed system using COMPAS Data[1], Adult Census Income Data[2] as validation data.

Similarity search tasks in big trajectory datasets often require tree-based indices to shorten the query time through early pruning of dissimilar trajectories early. However, tree-based indices have been outperformed by the learned index in skewed-distribution datasets of multidimensional point experimentally. The learned index performed faster because of its data distribution awareness and machine learning model-based prediction. Directly applying learned index to trajectories can lead to inefficient query performance due to repeating range queries according to the query trajectory length. Thus, we develop X-FIST, an extended Flood index to learn the Minimum Bounding Region of the trajectories and their sub-trajectories. In similarity search, X-FIST prunes dissimilar trajectories effectively independent to the query trajectory length. If the trajectory similarity distance function changes, X-FIST does not need to train new models of its Flood index. The experimental results on three real-world trajectory datasets demonstrate that our approach shortened query time in every distance function and produced better storage size reduction than the tree-based index and direct approach of learned index.

Learned indices can significantly shorten the query response time of k-Nearest Neighbor search of points data. However, extending the learned index for k-Nearest Neighbor search of trajectory data may return incorrect results (low recall) and require longer pruning time. Thus, we introduce an enhancement for trajectory learned index which is a pruning step for a learned index to retrieve the k-Nearest Neighbors correctly by learning the query workload. The pruning utilizes a predicted range query that covers the correct neighbors. We show that that our approach has the potential to work effectively in a large real-world trajectory dataset.

Early pruning of dissimilar trajectories is important in similar trajectory search on a big mobility data. R-trees can perform the pruning effectively, but the search and index size become inefficient due to numerous overlapping of minimum bounding regions in a dense and big dataset. Thus, we introduce the extended usage of learned index to learn the minimum bounding rectangles for trajectory similarity search. Our approach is designed to provide an effective pruning for trajectory similarity search with less storage size.

An indoor semantic trajectory is a sequence of timestamped semantic positions inside a building. However, its extraction depends on the erroneous indoor positioning. The error leads to an invalid trajectory that has distant consecutive positions. This invalid trajectory may lead to an issue of the non-sensical patterns when analyzing a big semantic trajectory data. To prevent extracting invalid trajectories, we apply the movement constraints to infer only close positions to the current position. We extend the constraints to several indoor positioning techniques, such as Hidden Markov Model, K-Nearest Neighbor, or Deep Neural Network. We show that our approach can effectively extract valid indoor semantic trajectories.

The rapid converging of big data and IoT (Internet of Things) technologies provides more opportunities in the area of road traffic applications. In this paper, we discuss a timeline visualization tool which enables us to better understand of traffic behaviors from road traffic big data.

Due to the increasing number of vehicles in recent years, traffic congestion problem is a common issue for residents of metropolises. For a better understanding of traffic congestion, the analyzed data from big data technology can be provided as timeline information. However, a scalability problem would occur when we convert raw traffic data into the timeline information due to the volume and complexity of traffic data. In this paper, we present two MapReduce-based approaches which extract the timeline information of road traffic data. By utilizing the distribute processing strategy, we can resolve the scalability problem. We propose an iterative approach of MapReduce as a baseline approach and a single iteration approach as an efficient solution. The single iteration easily extended to support various and/or complex analytic queries by providing proper codes at a reducer. We validate experimentally our MapReduce-based approaches on real traffic dataset from a Busan Intelligent Transport System (ITS) center.

Social networking site (SNS) messages can contain subjective traffic information, including congestion-related expressions such as “bad traffic” or “traffic is crazy”. Moreover, they also contain heterogeneous levels of location information, such as a point (latitude, longitude), a road, or an area name, which complicates the process of collecting related traffic information. This paper aims to use SNS messages for monitoring traffic conditions on a road by computing the traffic congestion degree. The process begins by classifying those SNS messages that are related to a road in terms of location information and constructing an initial graph structure to store each message. Because of the heterogeneous location types, we need to combine the initial graph structures based on their spatial references. We can then measure the subjective congestion by computing an expression score using our rule-based approach.

In vehicular localization, there is an increasing interest in the fusion algorithm between the relative local sensing estimate (LSE) of ranging sensors and the absolute remote sensing estimate (RSE) of a GPS receiver. A challenging issues of the fusion algorithm is to find a matched pair corresponding to the same vehicle between two sets of estimates. To aim this, we present a greedy data matching (GDM) that finds an optimal set of pairs, consisting of a sensing estimate and a GPS estimate, based on the closeness of these estimates. To represent the closeness in spatial domain, we employ the Mahalanobis distance metric based on the position and the speed estimates. To cope with the temporal randomness of these estimates, we also present a moving-average weighting factor which can provide a robustness to the random error of the estimates. From the numerical results, we show that the GDM outperforms the existing schemes in terms of the correct matching probability.

High-performance radio-frequency identification (RFID) is a challenging issue for large-scale enterprises. As a key component of an RFID system, RFID middleware is an important factor to measure the performance of the system. To evaluate the feasibility of an RFID middleware, the performance of the RFID middleware should be carefully evaluated in various RFID-enabled business environments. However, the construction of an RFID testbed requires a lot of time, money, and human resources because it involves numerous tagged items and a large number of deployed readers. We must provide a meaningful input tag stream representing various business activities, rather than random data. This paper presents a novel simulation model for the virtual construction of RFID testbeds. To ensure the semantic validity of the input tag stream, the proposed RFID simulation network (RSN) extends Petri nets by including sets of functions that represent unique characteristics of RFID environments such as the uncertainty of communications and tag movement patterns. By configuring appropriate functions, the RSN automatically generates an input tag stream that matches the distribution of real data. We demonstrate that the RSN model correctly reflects data from real-world environments by comparing input tag streams from real RFID equipment and from the RSN model.

XML-enabled publish-subscribe (pub-sub) systems have emerged as an increasingly important tool for e-commerce and Internet applications. In a typical pub-sub system, subscribed users specify their interests in a profile expressed in the XPath language. Each new data content is then matched against the user profiles so that the content is delivered only to the interested subscribers. As the number of subscribed users and their profiles can grow very large, the scalability of the service is critical to the success of pub-sub systems. In this article, we propose a novel scalable filtering system called iFiST that transforms user profiles of a twig pattern expressed in XPath into sequences using the Prüfer's method. Consequently, instead of breaking a twig pattern into multiple linear paths and matching them separately, FiST performs holistic matching of twig patterns with each incoming document in a bottom-up fashion. FiST organizes the sequences into a dynamic hash-based index for efficient filtering, and exploits the commonality among user profiles to enable shared processing during the filtering phase. We demonstrate that the holistic matching approach reduces filtering cost and memory consumption, thereby improving the scalability of FiST.

Web services composition search systems have received a great deal of attention recently. However, current solutions have limitations of inefficiency and including redundant Web services in the results. In this paper, we proposed a redundant-free Web services composition search based on a two phase algorithm. In the forward phase, the candidate composition will be found efficiently by searching the link Index. In the backward phase, redundant-free Web services compositions are generated from the candidate composition by using the concepts of tokens. Experimental results demonstrate the performance benefits of our proposed techniques compared to state-of-the-art composition approaches.

Web services search and discovery systems have received a great deal of attention recently. However, little attention has been given to a Web services filtering system. In this paper, we propose a design and architecture of a semantic Web services filtering system called SWFilter. SWFilter uses Prufer sequences transformed from Web services and user queries. The filtering process is performed in a bottom-up manner. Ontology information and compositions of Web services are also considered in the filtering process.

In recent years, the Web services composition has received much attention. By Web services composition, we mean taking advantage of currently existing Web services to provide a new service that does not exist on the repository. In this paper, we propose a new system called PSR for Web services composition search using a relational database. We also propose algorithms for pre-computing Web services composition using joins and indices. We demonstrated that our pre-computing Web services composition approach in RDBMS yields lower execution time and good scalability when handling a large number of Web services and user queries.