Vol. 43, No. 12,
Dec. 2016
Digital Library
Outdoor Swarm Flight System Based on RTK-GPS
SungTae Moon, YeonJu Choi, DoYoon Kim, Myeonghun Seung, HyeonCheol Gong
Recently, the increasing interest in drones has resulted in development of new related technologies. Attention has been focused toward research on swarm flight which controls drones simultaneously without collision. Thus, complicated missions can be completed rapidly through collaboration between drones. Due to low position accuracy, GPS is not appropriate for the outdoor mission involving accurate flight. In addition, the inaccurate position estimation of GPS gives rise to the serious problem of collision, since many drones are controlled in a narrow space. In this study, we increased the accuracy of position estimation through various sensors with Real-Time Kinematic-GPS (RTK-GPS). The mode switching algorithm was proposed to minimize the problem of sensor error. In addition, we introduced the outdoor swarm flight system based on the proposed position estimation.
Classifying Windows Executables using API-based Information and Machine Learning
DaeHee Cho, Kyeonghwan Lim, Seong-je Cho, Sangchul Han, Young-sup Hwang
Software classification has several applications such as copyright infringement detection, malware classification, and software automatic categorization in software repositories. It can be also employed by software filtering systems to prevent the transmission of illegal software. If illegal software is identified by measuring software similarity in software filtering systems, the average number of comparisons can be reduced by shrinking the search space. In this study, we focused on the classification of Windows executables using API call information and machine learning. We evaluated the classification performance of machine learning-based classifier according to the refinement method for API information and machine learning algorithm. The results showed that the classification success rate of SVM (Support Vector Machine) with PolyKernel was higher than other algorithms. Since the API call information can be extracted from binary executables and machine learning-based classifier can identify tampered executables, API call information and machine learning-based software classifiers are suitable for software filtering systems.
Bayesian Network-based Probabilistic Management of Software Metrics for Refactoring
In recent years, the importance of managing software defects in the implementation stage has emerged because of the rapid development and wide-range usage of intelligent smart devices. Even if not a few studies have been conducted on the prediction models for software defects, their outcomes have not been widely shared. This paper proposes an efficient probabilistic management model of software metrics based on the Bayesian network, to overcome limits such as binary defect prediction models. We expect the proposed model to configure the Bayesian network by taking advantage of various software metrics, which can help in identifying improvements for refactoring. Once the source code has improved through code refactoring, the measured related metric values will also change. The proposed model presents probability values reflecting the effects after defect removal, which can be achieved by improving metrics through refactoring. This model could cope with the conclusive binary predictions, and consequently secure flexibilities on decision making, using indeterminate probability values.
Coinductive Subtyping for Recursive and Union Types
Induction and coinduction are well-established proof principles, which are widely used in mathematics and computer science. In particular, induction is taught in most undergraduate programs and well understood in the field of computer science. In contrast, coinduction is not as widespread or well understood as induction. In this paper, we introduce coinduction by defining a subtype system for recursive and union types and proving the transitivity property of the system. This paper will help to promote familiarity with coinduction and provides a basis for a subtype system for recursive types with other advanced type constructors and connectives.
The Design of Object-of-Interest Extraction System Utilizing Metadata Filtering from Moving Object
Taewoo Kim, Hyungheon Kim, Pyeongkang Kim
The number of CCTV units is rapidly increasing annually, and the demand for intelligent video-analytics system is also increasing continuously for the effective monitoring of them. The existing analytics engines, however, require considerable computing resources and cannot provide a sufficient detection accuracy. For this paper, a light analytics engine was employed to analyze video and we collected metadata, such as an object’s location and size, and the dwell time from the engine. A further data analysis was then performed to filter out the target of interest; as a result, it was possible to verify that a light engine and the heavy data analytics of the metadata from that engine can reject an enormous amount of environmental noise to extract the target of interest effectively. The result of this research is expected to contribute to the development of active intelligent-monitoring systems for the future.
Repeated Cropping based on Deep Learning for Photo Re-composition
Eunbin Hong, Junho Jeon, Seungyong Lee
This paper proposes a novel aesthetic photo recomposition method using a deep convolutional neural network (DCNN). Previous recomposition approaches define the aesthetic score of photo composition based on the distribution of salient objects, and enhance the photo composition by maximizing the score. These methods suffer from heavy computational overheads, and often fail to enhance the composition because their optimization depends on the performance of existing salient object detection algorithms. Unlike previous approaches, we address the photo recomposition problem by utilizing DCNN, which shows remarkable performance in object detection and recognition. DCNN is used to iteratively predict cropping directions for a given photo, thus generating an aesthetically enhanced photo in terms of composition. Experimental results and user study show that the proposed framework can automatically crop the photo to follow specific composition guidelines, such as the rule of thirds.
Ontology-Based Dynamic Context Management and Spatio-Temporal Reasoning for Intelligent Service Robots
Jonghoon Kim, Seokjun Lee, Dongha Kim, Incheol Kim
One of the most important capabilities for autonomous service robots working in living environments is to recognize and understand the correct context in dynamically changing environment. To generate high-level context knowledge for decision-making from multiple sensory data streams, many technical problems such as multi-modal sensory data fusion, uncertainty handling, symbolic knowledge grounding, time dependency, dynamics, and time-constrained spatio-temporal reasoning should be solved. Considering these problems, this paper proposes an effective dynamic context management and spatio-temporal reasoning method for intelligent service robots. In order to guarantee efficient context management and reasoning, our algorithm was designed to generate low-level context knowledge reactively for every input sensory or perception data, while postponing high-level context knowledge generation until it was demanded by the decision-making module. When high-level context knowledge is demanded, it is derived through backward spatio-temporal reasoning. In experiments with Turtlebot using Kinect visual sensor, the dynamic context management and spatio-temporal reasoning system based on the proposed method showed high performance.
Korean Semantic Role Labeling Using Case Frame Dictionary and Subcategorization
Computers require analytic and processing capability for all possibilities of human expression in order to process sentences like human beings. Linguistic information processing thus forms the initial basis. When analyzing a sentence syntactically, it is necessary to divide the sentence into components, find obligatory arguments focusing on predicates, identify the sentence core, and understand semantic relations between the arguments and predicates. In this study, the method applied a case frame dictionary based on The Korean Standard Dictionary of The National Institute of the Korean Language; in addition, we used a CRF Model that constructed subcategorization of predicates as featured in Korean Lexical Semantic Network (UWordMap) for semantic role labeling. Automatically tagged semantic roles based on the CRF model, which established the information of words, predicates, the case-frame dictionary and hypernyms of words as features, were used. This method demonstrated higher performance in comparison with the existing method, with accuracy rate of 83.13% as compared to 81.2%, respectively.
Performance Comparison of PostgreSQL and MongoDB using YCSB
In the era of Big Data, NoSQL databases provide solutions for problems, circumventing the limitations of traditional relational databases by using new architectures and data model. Contrary to relational database products, the range of the features architectures, and limitations of NoSQL databases is very broad. Thus, choosing the right database products requires more considerations and difficulties. The advent of NoSQL does not only promote the abundance of NoSQL products, but also stimulates the relational database realm to expand their features beyond the relational model. In order to understand NoSQL trends more accurately, here we discuss and compare NoSQL databases with relational databases. We also present the newest features associated with NoSQL in one of the most advanced open-source relational databases, PostgreSQL. To discuss future directions for PostgreSQL we analyzed the performance of NoSQL and PostgreSQL by conducting experiments using the NoSQL benchmark tool (YCSB).
Application of an Adaptive Incremental Classifier for Streaming Data
In streaming data analysis where underlying data distribution may be changed or the concept of interest can drift with the progress of time, the ability to adapt to concept drift can be very powerful especially in the process of incremental learning. In this paper, we develop a general framework for an adaptive incremental classifier on data stream with concept drift. A distribution, representing the performance pattern of a classifier, is constructed by utilizing the distance between the confidence score of a classifier and a class indicator vector. A hypothesis test is then performed for concept drift detection. Based on the estimated p-value, the weight of outdated data is set automatically in updating the classifier. We apply our proposed method for two types of linear discriminant classifiers. The experimental results on streaming data with concept drift demonstrate that the proposed adaptive incremental learning method improves the prediction accuracy of an incremental classifier highly.
LISP based IP Address Virtualization Technique for Resource Utilization on Virtualized SDN
Youngkeun Go, Gyeongsik Yang, Bong-yeol Yu, Chuck Yoo
Network virtualization is a technique that abstracts the physical network to provide multiple virtual networks to users. Virtualized network has the advantage to offer flexible services and improve resource utilization. In SDN architecture, network hypervisor serves to virtualize the network through address virtualization, topology virtualization and policy virtualization. Among them, address virtualization refers to the technique that provides an independent address space for each virtual network. Previous work divided the physical address space, and assigned an individual division to each virtual network. Each virtual address is then mapped one-to-one to a physical address. However, this approach requires a lot of flow entries, thus making it disadvantageous. Since SDN switches use TCAM (Ternary Contents Addressable Memory) for the flow table, it is very important to reduce the number of flow entries in the aspect of cost and scalability. In this paper, we propose a LISP based address virtualization, which separates address spaces for the physical and virtual addresses and transmits packet through tunneling, in order to resolve the limitation of the previous studies. By implementing a prototype, we show that the proposed scheme provides better scalability.
Efficient Spectrum Sensing for Cognitive Radio Sensor Networks via Optimization of Sensing Time
In cognitive radio sensor networks (CRSNs), secondary users (SUs) can occupy licensed bands opportunistically without causing interferences to primary users (PUs). SUs perform spectrum sensing to detect the presence of PUs. Sensing time is a critical parameter for spectrum sensing that can yield a tradeoff between sensing performance and secondary throughput. In this study, we investigate new approaches for spectrum sensing by exploring the tradeoff from a) spectrum sensing for PU detection (SSPD) and b) spectrum sensing for secondary throughput (SSST). In the proposed scheme, the first sensing result of the current frame determines the dynamic performance of the second spectrum sensing. Energy constraint in CRSNs leads to maximized network energy efficiency via optimization of sensing time. Simulation results show that the proposed scheme of SSPD and SSST improves network performance in terms of energy efficiency and secondary throughput, respectively.
Network Intelligence based on Network State Information for Connected Vehicles Utilizing Fog Computing
This paper proposes a method taking advantage of Fog computing and SDN in the connected vehicle environment which is having an unstable communication channel and a dynamic topology. For this purpose, the controller should understand the current state of the overall network by maintaining recent network topology, especially, the mobility information of mobile nodes. These are managed by the controller, and are important in unstable conditions in the mobile environment. The mobility levels are divided into 3 categories. We can efficiently exploit that information. By utilizing network state information, we suggest two outcomes. First, we reduce the control message overhead by adjusting the period of beacon messages. Second, we propose a recovery process to prepare the communication failure. We can efficiently recover connection failure through mobility information. Furthermore, we suggest a path recovery by decoupling the cloud level and the fog level in accordance with application data types. The simulation results show that the control message overhead and the connection failure time are decreased by approximately 55% and 5%, respectively in comparison to the existing method.
Local Grid-based Multipath Routing Protocol for Mobile Sink in Wireless Sensor Networks
Taehun Yang, Sangdae Kim, Hyunchong Cho, Cheonyong Kim, Sang-Ha Kim
A multipath routing in wireless sensor networks (WSNs) provides advantage such as reliability improvement and load balancing by transmitting data through divided paths. For these reasons, existing multipath routing protocols divide path appropriately or create independent paths efficiently. However, when the sink node moves to avoid hotspot problem or satisfy the requirement of the applications, the existing protocols have to reconstruct multipath or exploit foot-print chaining mechanism. As a result, the existing protocols will shorten the lifetime of a network due to excessive energy consumption, and lose the advantage of multipath routing due to the merging of paths. To solve this problem, we propose a multipath creation and maintenance scheme to support the mobile sink node. The proposed protocol can be used to construct local grid structure with restricted area and exploit grid structure for constructing the multipath. The grid structure can also be extended depending on the movement of the sink node. In addition, the multipath can be partially reconstructed to prevent merging paths. Simulation results show that the proposed protocol is superior to the existing protocols in terms of energy efficiency and packet delivery ratio.
kNN Query Processing Algorithm based on the Encrypted Index for Hiding Data Access Patterns
Hyeong-Il Kim, Hyeong-Jin Kim, Youngsung Shin, Jae-woo Chang
In outsourced databases, the cloud provides an authorized user with querying services on the outsourced database. However, sensitive data, such as financial or medical records, should be encrypted before being outsourced to the cloud. Meanwhile, k-Nearest Neighbor (kNN) query is the typical query type which is widely used in many fields and the result of the kNN query is closely related to the interest and preference of the user. Therefore, studies on secure kNN query processing algorithms that preserve both the data privacy and the query privacy have been proposed. However, existing algorithms either suffer from high computation cost or leak data access patterns because retrieved index nodes and query results are disclosed. To solve these problems, in this paper we propose a new kNN query processing algorithm on the encrypted database. Our algorithm preserves both data privacy and query privacy. It also hides data access patterns while supporting efficient query processing. To achieve this, we devise an encrypted index search scheme which can perform data filtering without revealing data access patterns. Through the performance analysis, we verify that our proposed algorithm shows better performance than the existing algorithms in terms of query processing times.
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