Vol. 43, No. 1,
Jan. 2016
Digital Library
PathSavanna: Realistic Packet Routing using GPGPU on the Xen-based Virtual Router
Geun-Yeong Park, Chiyoung Lee, Chuck Yoo
As the need for a flexible Internet grows, research for software and virtual routers has increased. Although software routers and virtual routers provide Internet flexibility, they have low performance compared with existing hardware routers. In addition, the low performance problem is intensified in virtual routers because they have virtualization overheads. GPU routing is one method of improving the performance of software routers. However, previous GPU routing is based on native software routers, which are not virtualized, and presents experimental simulation results only. In this paper, we examine the effect of GPU routing on a virtual router using PathSavanna. Our GPU routing is implemented on the virtual router and forwards real packets to another machine, which is connected by a network.
Optimal Acoustic Sound Localization System Based on a Tetrahedron-Shaped Microphone Array
This paper proposes a new sound localization algorithm that can improve localization performance based on a tetrahedron-shaped microphone array. Sound localization system estimates directional information of sound source based on the time delay of arrival(TDOA) information between the microphone pairs in a microphone array. In order to obtain directional information of the sound source in three dimensions, the system requires at least three microphones. If one of the microphones fails to detect proper signal level, the system cannot produce a reliable estimate. This paper proposes a tetrahedron- shaped sound localization system with a coordinate transform method by adding one microphone to the previously known triangular-shaped system providing more robust and reliable sound localization. To verify the performance of the proposed algorithm, a real time simulation was conducted, and the results were compared to the previously known triangular-shaped system. From the simulation results, the proposed tetrahedron-shaped sound localization system is superior to the triangular-shaped system by more than 46% for maximum sound source detection.
Improving Performance of I/O Virtualization Framework based on Multi-queue SSD
Tae Yong Kim, Dong Hyun Kang, Young Ik Eom
Virtualization has become one of the most helpful techniques in computing systems, and today it is prevalent in several computing environments including desktops, data-centers, and enterprises. However, since I/O layers are implemented to be oblivious to the I/O behaviors on virtual machines (VM), there still exists an I/O scalability issue in virtualized systems. In particular, when a multi-queue solid state drive (SSD) is used as a secondary storage, each system reveals a semantic gap that degrades the overall performance of the VM. This is due to two key problems, accelerated lock contentions and the I/O parallelism issue. In this paper, we propose a novel approach, including the design of virtual CPU (vCPU)-dedicated queues and I/O threads, which efficiently distributes the lock contentions and addresses the parallelism issue of Virtio-blk-data-plane in virtualized environments. Our approach is based on the above principle, which allocates a dedicated queue and an I/O thread for each vCPU to reduce the semantic gap. Our experimental results with various I/O traces clearly show that our design improves the I/O operations per second (IOPS) in virtualized environments by up to 155% over existing QEMU-based systems.
Optimizing Constant Value Generation in Just-in-time Compiler for 64-bit JavaScript Engine
JavaScript is widely used in web pages with HTML. Many JavaScript engines adopt Just-in-time compilers to accelerate the execution of JavaScript programs. Recently, many newly introduced devices are adopting 64-bit CPUs instead of 32-bit and Just-in-time compilers for 64-bit CPU are slowly being introduced in JavaScript engines. However, there are many inefficiencies in the currently available Just-in-time compilers for 64-bit devices. Especially, the size of code is significantly increased compared to 32-bit devices, mainly due to 64-bit wide addresses in 64-bit devices. In this paper, we are going to address the inefficiencies introduced by 64-bit wide addresses and values in the Just-in-time compiler for the V8 JavaScript engine and propose more efficient ways of generating constant values and addresses to reduce the size of code. We implemented the proposed optimization in the V8 JavaScript engine and measured the size of code as well as performance improvements with Octane and SunSpider benchmarks. We observed a 3.6% performance gain and 0.7% code size reduction in Octane and a 0.32% performance gain and 2.8% code size reduction in SunSpider.
An Efficient Clustering Algorithm for Massive GPS Trajectory Data
Taeyong Kim, Bokuk Park, Jinkwan Park, Hwan-Gue Cho
Digital road map generation is primarily based on artificial satellite photographing or in-site manual survey work. Therefore, these map generation procedures require a lot of time and a large budget to create and update road maps. Consequently, people have tried to develop automated map generation systems using GPS trajectory data sets obtained by public vehicles. A fundamental problem in this road generation procedure involves the extraction of representative trajectory such as main roads. Extracting a representative trajectory requires the base data set of piecewise line segments(GPS-trajectories), which have close starting and ending points. So, geometrically similar trajectories are selected for clustering before extracting one representative trajectory from among them. This paper proposes a new divide- and-conquer approach by partitioning the whole map region into regular grid sub-spaces. We then try to find similar trajectories by sweeping. Also, we applied the Fréchet distance measure to compute the similarity between a pair of trajectories. We conducted experiments using a set of real GPS data with more than 500 vehicle trajectories obtained from Gangnam-gu, Seoul. The experiment shows that our grid partitioning approach is fast and stable and can be used in real applications for vehicle trajectory clustering.
Automatic Tagging for Social Images using Convolution Neural Networks
While the Internet develops rapidly, a huge amount of image data collected from smart phones, digital cameras and black boxes are being shared through social media sites. Generally, social images are handled by tagging them with information. Due to the ease of sharing multimedia and the explosive increase in the amount of tag information, it may be considered too much hassle by some users to put the tags on images. Image retrieval is likely to be less accurate when tags are absent or mislabeled. In this paper, we suggest a method of extracting tags from social images by using image content. In this method, CNN(Convolutional Neural Network) is trained using ImageNet images with labels in the training set, and it extracts labels from instagram images. We use the extracted labels for automatic image tagging. The experimental results show that the accuracy is higher than that of instagram retrievals.
Feature-based Gene Classification and Region Clustering using Gene Expression Grid Data in Mouse Hippocampal Region
Mi-Sun Kang, HyeRyun Kim, Sukchan Lee, Myoung-Hee Kim
Brain gene expression information is closely related to the structural and functional characteristics of the brain. Thus, extensive research has been carried out on the relationship between gene expression patterns and the brain’s structural organization. In this study, Principal Component Analysis was used to extract features of gene expression patterns, and genes were automatically classified by spatial distribution. Voxels were then clustered with classified specific region expressed genes. Finally, we visualized the clustering results for mouse hippocampal region gene expression with the Allen Brain Atlas. This experiment allowed us to classify the region-specific gene expression of the mouse hippocampal region and provided visualization of clustering results and a brain atlas in an integrated manner. This study has the potential to allow neuroscientists to search for experimental groups of genes more quickly and design an effective test according to the new form of data. It is also expected that it will enable the discovery of a more specific sub-region beyond the current known anatomical regions of the brain.
Scalable Ontology Reasoning Using GPU Cluster Approach
JinYung Hong, MyungJoong Jeon, YoungTack Park
In recent years, there has been a need for techniques for large-scale ontology inference in order to infer new knowledge from existing knowledge at a high speed, and for a diversity of semantic services. With the recent advances in distributed computing, developments of ontology inference engines have mostly been studied based on Hadoop or Spark frameworks on large clusters. Parallel programming techniques using GPGPU, which utilizes many cores when compared with CPU, is also used for ontology inference. In this paper, by combining the advantages of both techniques, we propose a new method for reasoning large RDFS ontology data using a Spark in-memory framework and inferencing distributed data at a high speed using GPGPU. Using GPGPU, ontology reasoning over high-capacity data can be performed as a low cost with higher efficiency over conventional inference methods. In addition, we show that GPGPU can reduce the data workload on each node through the Spark cluster. In order to evaluate our approach, we used LUBM ranging from 10 to 120. Our experimental results showed that our proposed reasoning engine performs 7 times faster than a conventional approach which uses a Spark in-memory inference engine.
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%.
Effective Korean Speech-act Classification Using the Classification Priority Application and a Post-correction Rules
Namhoon Song, Kyoungman Bae, Youngjoong Ko
A speech-act is a behavior intended by users in an utterance. Speech-act classification is important in a dialogue system. The machine learning and rule-based methods have mainly been used for speech-act classification. In this paper, we propose a speech-act classification method based on the combination of support vector machine (SVM) and transformation-based learning (TBL). The user"s utterance is first classified by SVM that is preferentially applied to categories with a low utterance rate in training data. Next, when an utterance has negative scores throughout the whole of the categories, the utterance is applied to the correction phase by rules. The results from our method were higher performance over the baseline system long with error-reduction.
Spark based Scalable RDFS Ontology Reasoning over Big Triples with Confidence Values
Hyun-Kyu Park, Wan-Gon Lee, Batselem Jagvaral, Young-Tack Park
Recently, due to the development of the Internet and electronic devices, there has been an enormous increase in the amount of available knowledge and information. As this growth has proceeded, studies on large-scale ontological reasoning have been actively carried out. In general, a machine learning program or knowledge engineer measures and provides a degree of confidence for each triple in a large ontology. Yet, the collected ontology data contains specific uncertainty and reasoning such data can cause vagueness in reasoning results. In order to solve the uncertainty issue, we propose an RDFS reasoning approach that utilizes confidence values indicating degrees of uncertainty in the collected data. Unlike conventional reasoning approaches that have not taken into account data uncertainty, by using the in-memory based cluster computing framework Spark, our approach computes confidence values in the data inferred through RDFS-based reasoning by applying methods for uncertainty estimating. As a result, the computed confidence values represent the uncertainty in the inferred data. To evaluate our approach, ontology reasoning was carried out over the LUBM standard benchmark data set with addition arbitrary confidence values to ontology triples. Experimental results indicated that the proposed system is capable of running over the largest data set LUBM3000 in 1179 seconds inferring 350K triples.
User Reputation Management Method Based on Analysis of User Activities on Social Media
Jinkyung Yun, Jiwon Jeong, Suji Lee, Jongtae Lim, Kyungsoo Bok, Jaesoo Yoo
Recently, social network services have changed by moving towards an open platform where, as well as simply allowing the building of relationships among users, various types of information can be generated and shared. Since existing user reputation management methods evaluate user reliability based on user profiles, explicit relations, and evaluation, they are not suitable for determining user reliability on social media due to few explicit evaluation. In this paper, we analyze social activities on social media and propose a new user reputation management method that considers implicit evaluation as well as explicit evaluation. The proposed method derives positive and negative implicit evaluation from social activities, and generates user reputation information by field in order to consider user expertise. It also considers the number of users that participate in evaluation in order to measure user influence. As a result, it generates the reputation information of users who have no explicit evaluation and creates user reputation information that is more suitable for social media.
Trust Evaluation Scheme of Web Data Based on Provenance in Social Semantic Web Environments
Sangwon Yoon, Kitae Choi, Jaeyeol Park, Jongtae Lim, Kyoungsoo Bok, Jaesoo Yoo
Recently, as the generation and sharing of web data have increased, the importance of a social semantic web that combines the semantic web and the social web has also been increasing. In this paper, we propose a trust evaluation scheme based on provenance by extending the PROV model in the social semantic web environment. The proposed scheme manages the provenance of web data and adds the necessary elements for trust evaluation in the PROV model of W3C. The extended PROV model supports data management and provenance tracing. The proposed trust evaluation scheme considers various parameters such as user trust, original data trust, and user evaluation. The evaluated trust is managed as provenance. When processing a query, the proposed scheme generates a result by considering the trust. Therefore, the proposed scheme can manage the provenance of web data and compute data trust correctly by using such various parameters. The evaluated trust becomes a criterion to determine whether the query result can be trusted or not. In order to show the validity of the proposed scheme, we verify its performance using SPARQL queries.
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.
Human Visual System-Aware Optimal Power-Saving Color Transformation for Mobile OLED Devices
Jae-Hyeok Lee, Eun-Sil Kim, Young-Jin Kim
Due to the merits of OLED displays such as fast responsiveness, wide view angle, and power efficiency, their use has increased. However, despite the power efficiency of OLED displays, the portion of their power consumption among the total power consumption is still high since user interaction-based applications such as instant messaging, video play, and games are frequently used. Their power consumption varies significantly depending on the display contents and thus color transformation is one of the low-power techniques used in OLED displays. Prior low-power color transformation techniques have not been rigorously studied in terms of satisfaction of the human visual system, and have not considered optimal visual satisfaction and power consumption at the same time in relation to color transformation. In this paper, we propose a novel low-power color transformation technique which strictly considers human visual system-awareness as well as optimization of both visual satisfaction and power consumption in a balanced way. Experimental results show that the proposed technique achieves better human visual satisfaction in terms of visuality and also shows on average 13.4% and 22.4% improvement over a prior one in terms of power saving.
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