Vol. 43, No. 7,
Jul. 2016
Digital Library
FastIO: High Speed Launching of Smart TV Apps
Cheolhee Lee, Taeho Hwang, Youjip Won, Seongjin Lee
Smart TV uses Webkit as a web browser engine to provide contents such as web surfing, VOD watching, and games. Webkit uses web resources, such as HTML, CSS, JavaScript, and images, in order to run applications. At the start of an application, Webkit loads resources to the memory and creates DOM tree and render tree, which is a time consuming process. However, DOM tree and render tree created by the smart TV application do not change over time because the smart TV application uses web resources stored in a disk. If DOM tree and render tree can be stored and reused, it is possible to reduce loading time of an application. In this paper, we propose FastIO technique that selectively adds persistency to dynamically allocated memory. FastIO reduces overall application loading time by eliminating the process of loading resources from storage, parsing the HTML documents, and creating DOM tree and render tree. Comparison of the application resource loading times indicates that the web browser with FastIO is 7.9x, 44.8x, and 2.9x faster than the legacy web browser in an SSD, Ramdisk, and eMMC environment, respectively.
Dynamic Core Affinity for High-Performance I/O Devices Supporting Multiple Queues
Joong-Yeon Cho, Junyong Uhm, Hyun-Wook Jin, Sungin Jung
Several studies have reported the impact of core affinity on the network I/O performance of multi-core systems. As the network bandwidth increases significantly, it becomes more important to determine the effective core affinity. Although a framework for dynamic core affinity that considers both network and disk I/O has been suggested, the multiple queues provided by high-speed I/O devices are not properly supported. In this paper, we extend the existing framework of dynamic core affinity to efficiently support the multiple queues of high-speed I/O devices, such as 40 Gigabit Ethernet and NVM Express. Our experimental results show that the extended framework can improve the HDFS file upload throughput by up to 32%, and can provide improved scalability in terms of the number of cores. In addition, we analyze the impact of the assignment policy of multiple I/O queues across a number of cores.
Performance Analysis of Cloud-Backed File Systems with Various Object Sizes
Jiwon Kim, Kyungjun Lee, Sungtae Ryu, Hwansoo Han
Recent cloud infrastructures provide competitive performances and operation costs for many internet services through pay-per-use model. Particularly, object storages are highlighted, as they have unlimited file holding capacity and allow users to access the stored files anytime and anywhere. Several lines of research are based on cloud-backed file systems, which support traditional POSIX interface rather than RESTful APIs via HTTP. However, these existing file systems handle all files with uniform size backing objects. Consequently, the accesses to cloud object storages are likely to be inefficient. In our research, files are profiled according to characteristics, and appropriate backing unit sizes are determined. We experimentally verify that different backing unit sizes for the object storage improve the performance of cloud-backed file systems. In our comparative experiments with S3QL, our prototype cloud-backed file system shows faster performance by 18.6% on average.
The Present and Perspective of Quantum Machine Learning
This paper presents an overview of the emerging field of quantum machine learning which promises an innovative expedited performance of current classical machine learning algorithms by applying quantum theory. The approaches and technical details of recently developed quantum machine learning algorithms that have been able to substantially accelerate existing classical machine learning algorithms are presented. In addition, the quantum annealing algorithm behind the first commercial quantum computer is also discussed.
Sensing Model for Reducing Power Consumption for Indoor/Outdoor Context Transition
Deok-Ki Kim, Jae-Hyeon Park, Jung-Won Lee
With the spread of smartphones containing multiple on-board sensors, the market for context aware applications have grown. However, due to the limited power capacity of a smartphone, users feel discontented QoS. Additionally, context aware applications require the utilization of many forms of context and sensing information. If context transition has occurred, types of needed sensors must be changed and each sensor modules need to turn on/off. In addition, excessive sensing has been found when the context decision is ambiguous. In this paper, we focus on power consumption associated with the context transition that occurs during indoor/outdoor detection, modeling the activities of the sensor associated with these contexts. And we suggest a freezing algorithm that reduces power consumption in context transition. We experiment with a commercial application that service is indoor/outdoor location tracking, measure power consumption in context transition with and without the utilization of the proposed method. We find that proposed method reduces power consumption about 20% during context transition.
Korean Semantic Role Labeling Using Semantic Frames and Synonym Clusters
Soojong Lim, Joon-Ho Lim, Chung-Hee Lee, Hyun-Ki Kim
Semantic information and features are very important for Semantic Role Labeling(SRL) though many SRL systems based on machine learning mainly adopt lexical and syntactic features. Previous SRL research based on semantic information is very few because using semantic information is very restricted. We proposed the SRL system which adopts semantic information, such as named entity, word sense disambiguation, filtering adjunct role based on sense, synonym cluster, frame extension based on synonym dictionary and joint rule of syntactic-semantic information, and modified verb-specific numbered roles, etc. According to our experimentations, the proposed present method outperforms those of lexical-syntactic based research works by about 3.77 (Korean Propbank) to 8.05 (Exobrain Corpus) F1-scores.
Event Cognition-based Daily Activity Prediction Using Wearable Sensors
Chung-Yeon Lee, Dong Hyun Kwak, Beom-Jin Lee, Byoung-Tak Zhang
Learning from human behaviors in the real world is essential for human-aware intelligent systems such as smart assistants and autonomous robots. Most of research focuses on correlations between sensory patterns and a label for each activity. However, human activity is a combination of several event contexts and is a narrative story in and of itself. We propose a novel approach of human activity prediction based on event cognition. Egocentric multi-sensor data are collected from an individual’s daily life by using a wearable device and smartphone. Event contexts about location, scene and activities are then recognized, and finally the users’’ daily activities are predicted from a decision rule based on the event contexts. The proposed method has been evaluated on a wearable sensor data collected from the real world over 2 weeks by 2 people. Experimental results showed improved recognition accuracies when using the proposed method comparing to results directly using sensory features.
Member Organization-based Service Recommendation for User Groups in Internet of Things Environments
Recommender systems can be used to assist users in selecting required services for their tasks in Internet of Things (IoT) environments in which diverse services can be provided by utilizing IoT devices. Traditional research on recommendation mainly focuses on predicting preferences of individual users. However, in IoT environments, not only individual users but also groups of users can access services in the environments. In this study, we analyzed user groups" preferences on services and developed service recommendation approach for new groups that do not have a history of accessing IoT-services in a certain place. Our approach extends the traditional user-based collaborative filtering by considering the similarity between user groups based on their member organization. We conducted experiments with a real-world dataset collected from IoT testbed environments. The results demonstrate that the proposed approach is effective to recommend services to new user groups in IoT environments.
Active Vision from Image-Text Multimodal System Learning
In image classification, recent CNNs compete with human performance. However, there are limitations in more general recognition. Herein we deal with indoor images that contain too much information to be directly processed and require information reduction before recognition. To reduce the amount of data processing, typically variational inference or variational Bayesian methods are suggested for object detection. However, these methods suffer from the difficulty of marginalizing over the given space. In this study, we propose an image-text integrated recognition system using active vision based on Spatial Transformer Networks. The system attempts to efficiently sample a partial region of a given image for a given language information. Our experimental results demonstrate a significant improvement over traditional approaches. We also discuss the results of qualitative analysis of sampled images, model characteristics, and its limitations.
Dynamic Decision Making for Self-Adaptive Systems Considering Environment Information
Misoo Kim, Hohyeon Jeong, Eunseok Lee
Self-adaptive systems (SASs) can change their goals and behaviors to achieve its ultimate goal in a dynamic execution environment. Existing approaches have designed, at the design time, utility functions to evaluate and predict the goal satisfaction, and set policies that are crucial to achieve each goal. The systems can be adapted to various runtime environments by utilizing the pre-defined utility functions and policies. These approaches, however, may or may not guarantee the proper adaptability, because system designers cannot assume and predict all system environment perfectly at the design time. To cope with this problem, this paper proposes a new method of dynamic decision making, which takes the following steps: firstly we design a Dynamic Decision Network (DDN) with environmental data and goal model that reflect system contexts; secondly, the goal satisfaction is evaluated and predicted with the designed DDN and real-time environmental information. We furthermore propose a dynamic reflection method that changes the model by using newly generated data in real-time. The proposed method was actually applied to ROBOCODE, and verified its effectiveness by comparing to conventional static decision making.
Topological Analysis of the Feasibility and Initial-value Assignment of Image Segmentation
This paper introduces and analyzes the theoretical basis and method of the conventional initial-value assignment problem and feasibility of image segmentation. The paper presents topological evidence and a method of appropriate initial-value assignment based on topology theory. Subsequently, the paper shows minimum conditions for feasibility of image segmentation based on separation axiom theory of topology and a validation method of effectiveness for image modeling. As a summary, this paper shows image segmentation with its mathematical validity based on topological analysis rather than statistical analysis. Finally, the paper applies the theory and methods to conventional Gaussian random field model and examines effectiveness of GRF modeling.
External Merge Sorting in Tajo with Variable Server Configuration
Jongbaeg Lee, Woon-hak Kang, Sang-won Lee
There is a growing requirement for big data processing which extracts valuable information from a large amount of data. The Hadoop system employs the MapReduce framework to process big data. However, MapReduce has limitations such as inflexible and slow data processing. To overcome these drawbacks, SQL query processing techniques known as SQL-on-Hadoop were developed. Apache Tajo, one of the SQL-on-Hadoop techniques, was developed by a Korean development group. External merge sort is one of the heavily used algorithms in Tajo for query processing. The performance of external merge sort in Tajo is influenced by two parameters, sort buffer size and fanout. In this paper, we analyzed the performance of external merge sort in Tajo with various sort buffer sizes and fanouts. In addition, we figured out that there are two major causes of differences in the performance of external merge sort: CPU cache misses which increase as the sort buffer size grows; and the number of merge passes determined by fanout.
TCP-aware Segment Scheduling Method for HTTP Adaptive Streaming
HTTP Adaptive Streaming (HAS) is a technique that adapts its video quality to network conditions for providing Quality of Experience. In the HAS approach, a video content is encoded at multiple bitrates and the encoded video content is divided into several video segments. A HAS player estimates the network bandwidth and adjusts the video bitrate based on estimated bandwidth. However, the segment scheduler in the conventional HAS player requests video segments periodically without considering TCP. If the waiting duration for the next segment request is quite long, the TCP connection can be initialized and it restarts slow-start. Slow-start causes the reduction in TCP throughput and consequentially leads to low-quality video streaming. In this study, we propose a TCP-aware segment scheduling scheme to improve performance of HAS service. The proposed scheme adjusts request time for the next video request to prevent initialization of TCP connection and also considers the point of scheduling time. The simulation proves that our scheme improves the Quality of Service of the HAS service without buffer underflow issue.
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