Vol. 44, No. 7,
Jul. 2017
Digital Library
Implementation of Intra-Partition Communication in Layered ARINC 653 for Drone Flight-Control Program
Joo-Kwang Park, Jooho Kim, Hyun-Chul Jo, Hyun-Wook Jin
http://doi.org/10.5626/JOK.2017.44.7.649
As the type and purpose of drones become diverse and the number of additional functions is increasing, the role of the corresponding software has increased. Through partitioning and an efficient solving of SWaP(size, weight and power) problems, ARINC 653 can provide reliable software reuse and consolidation regarding avionic systems. ARINC 653 can be more effectively applied to drones, a small unmanned aerial vehicle, in addition to its application with large-scale aircraft. In this paper, to exploit ARINC 653 for a drone flight-control program, an intra-partition communication system is implemented through an extension of the layered ARINC 653 and applied to a real drone system. The experiment results show that the overheads of the intra-partition communication are low, while the resources that are assigned to the drone flight-control program are guaranteed through the partitioning.
Design and Implementation of an In-Memory File System Cache with Selective Compression
http://doi.org/10.5626/JOK.2017.44.7.658
The demand for large-scale storage systems has continued to grow due to the emergence of multimedia, social-network, and big-data services. In order to improve the response time and reduce the load of such large-scale storage systems, DRAM-based in-memory cache systems are becoming popular. However, the high cost of DRAM severely restricts their capacity. While the method of compressing cache entries has been proposed to deal with the capacity limitation issue, compression and decompression, which are technically difficult to parallelize, induce significant processing overhead and in turn retard the response time. A selective compression scheme is proposed in this paper for in-memory file system caches that rapidly estimates the compression ratio of incoming cache entries with their Shannon entropies and compresses cache entries with low compression ratio. In addition, a description is provided of the design and implementation of an in-kernel in-memory file system cache with the proposed selective compression scheme. The evaluation showed that the proposed scheme reduced the execution time of benchmarks by approximately 18% in comparison to the conventional non-compressing in-memory cache scheme. It also provided a cache hit ratio similar to the all-compressing counterpart and reduced 7.5% of the execution time by reducing the compression overhead. In addition, it was shown that the selective compression scheme can reduce the CPU time used for compression by 28% compared to the case of the all-compressing scheme.
Searching Effective Network Parameters to Construct Convolutional Neural Networks for Object Detection
Nuri Kim, Donghoon Lee, Songhwai Oh
http://doi.org/10.5626/JOK.2017.44.7.668
Deep neural networks have shown remarkable performance in various fields of pattern recognition such as voice recognition, image recognition and object detection. However, underlying mechanisms of the network have not been fully revealed. In this paper, we focused on empirical analysis of the network parameters. The Faster R-CNN(region-based convolutional neural network) was used as a baseline network of our work and three important parameters were analyzed: the dropout ratio which prevents the overfitting of the neural network, the size of the anchor boxes and the activation function. We also compared the performance of dropout and batch normalization. The network performed favorably when the dropout ratio was 0.3 and the size of the anchor box had not shown notable relation to the performance of the network. The result showed that batch normalization can’t entirely substitute the dropout method. The used leaky ReLU(rectified linear unit) with a negative domain slope of 0.02 showed comparably good performance.
Title Generation Model for which Sequence-to-Sequence RNNs with Attention and Copying Mechanisms are used
http://doi.org/10.5626/JOK.2017.44.7.674
In big-data environments wherein large amounts of text documents are produced daily, titles are very important clues that enable a prompt catching of the key ideas in documents; however, titles are absent for numerous document types such as blog articles and social-media messages. In this paper, a title-generation model for which sequence-to-sequence RNNs with attention and copying mechanisms are employed is proposed. For the proposed model, input sentences are encoded based on bi-directional GRU (gated recurrent unit) networks, and the title words are generated through a decoding of the encoded sentences with keywords that are automatically selected from the input sentences. Regarding the experiments with 93631 training-data documents and 500 test-data documents, the attention-mechanism performances are more effective (ROUGE-1: 0.1935, ROUGE-2: 0.0364, ROUGE-L: 0.1555) than those of the copying mechanism; in addition, the qualitative-evaluation radiative performance of the former is higher.
Initial Small Data Reveal Rumor Traits via Recurrent Neural Networks
http://doi.org/10.5626/JOK.2017.44.7.680
The emergence of online media and their data has enabled data-driven methods to solve challenging and complex tasks such as rumor classification problems. Recently, deep learning based models have been shown as one of the fastest and the most accurate algorithms to solve such problems. These new models, however, either rely on complete data or several days-worth of data, limiting their applicability in real time. In this study, we go beyond this limit and test the possibility of super early rumor detection via recurrent neural networks (RNNs). Our model takes in social media streams as time series input, along with basic meta-information about the rumongers including the follower count and the psycholinguistic traits of rumor content itself. Based on analyzing millions of social media posts on 498 real rumors and 494 non-rumor events, our RNN-based model detected rumors with only 30 initial posts (i.e., within a few hours of rumor circulation) with remarkable F1 score of 0.74. This finding widens the scope of new possibilities for building a fast and efficient rumor detection system.
A Fusion Method of Co-training and Label Propagation for Prediction of Bank Telemarketing
http://doi.org/10.5626/JOK.2017.44.7.686
Telemarketing has become the center of marketing action of the industry in the information society. Recently, machine learning has emerged in many areas, especially, financial prediction. Financial data consists of lots of unlabeled data in most parts, and therefore, it is difficult for humans to perform their labeling. In this paper, we propose a fusion method of semi-supervised learning for automatic labeling of unlabeled data to predict telemarketing. Specifically, we integrate labeling results of label propagation and co-training with a decision tree. The data with lower reliabilities are removed, and the data are extracted that have consistent label from two labeling methods. After adding them to the training set, a decision tree is learned with all of them. To confirm the usefulness of the proposed method, we conduct the experiments with a real telemarketing dataset in a Portugal bank. Accuracy of the proposed method is 83.39%, which is 1.82% higher than that of the conventional method, and precision of the proposed method is 19.37%, which is 2.67% higher than that of the conventional method. As a result, we have shown that the proposed method has a better performance as assessed by the t-test.
Face Detection using Orientation(In-Plane Rotation) Invariant Facial Region Segmentation and Local Binary Patterns(LBP)
Hee-Jae Lee, Ha-Young Kim, David Lee, Sang-Goog Lee
http://doi.org/10.5626/JOK.2017.44.7.692
Face detection using the LBP based feature descriptor has issues in that it can not represent spatial information between facial shape and facial components such as eyes, nose and mouth. To address these issues, in previous research, a facial image was divided into a number of square sub-regions. However, since the sub-regions are divided into different numbers and sizes, the division criteria of the sub-region suitable for the database used in the experiment is ambiguous, the dimension of the LBP histogram increases in proportion to the number of sub-regions and as the number of sub-regions increases, the sensitivity to facial orientation rotation increases significantly. In this paper, we present a novel facial region segmentation method that can solve in-plane rotation issues associated with LBP based feature descriptors and the number of dimensions of feature descriptors. As a result, the proposed method showed detection accuracy of 99.0278% from a single facial image rotated in orientation.
Efficient Authentication of Aggregation Queries for Outsourced Databases
http://doi.org/10.5626/JOK.2017.44.7.703
Outsourcing databases is to offload storage and computationally intensive tasks to the third party server. Therefore, data owners can manage big data, and handle queries from clients, without building a costly infrastructure. However, because of the insecurity of network systems, the third-party server may be untrusted, thus the query results from the server may be tampered with. This problem has motivated significant research efforts on authenticating various queries such as range query, kNN query, function query, etc. Although aggregation queries play a key role in analyzing big data, authenticating aggregation queries has not been extensively studied, and the previous works are not efficient for data with high dimension or a large number of distinct values. In this paper, we propose the AMR-tree that is a data structure, applied to authenticate aggregation queries. We also propose an efficient proof construction method and a verification method with the AMR-tree. Furthermore, we validate the performance of the proposed algorithm by conducting various experiments through changing parameters such as the number of distinct values, the number of records, and the dimension of data.
Efficient Shortest Path Techniques on a Summarized Graph based on the Relationships
Hyunwook Kim, HoJin Seo, Young-Koo Lee
http://doi.org/10.5626/JOK.2017.44.7.710
As graphs are becoming increasingly large, the costs for storing and managing data are increasing continuously. Shortest path discovery over a large graph requires long running time due to frequent disk I/Os and high complexity of the graph data. Recently, graph summarization techniques have been studied, which reduce the size of graph data and disk I/Os by representing highly dense subgraphs as a single super-node. Decompressing should be minimized for efficient shortest path discovery over the summarized graph. In this paper, we analyze the decompression performance of a summarized graph and propose an approximate technique that discovers the shortest path quickly with a minimum error ratio. We also propose an exact technique that efficiently discovered the shortest path by exploiting an index built on paths containing super-nodes. In our experiments, we showed that the proposed technique based on the summarized graph can reduce the running time by up to 70% compared with the existing techniques performed on the original graph.
A Markov Approximation-Based Approach for Network Service Chain Embedding
Pham Chuan, Minh N. H. Nguyen, Choong Seon Hong
http://doi.org/10.5626/JOK.2017.44.7.719
To reduce management costs and improve performance, the European Telecommunication Standards Institute (ETSI) introduced the concept of network function virtualization (NFV), which can implement network functions (NFs) on cloud/datacenters. Within the NFV architecture, NFs can share physical resources by hosting NFs on physical nodes (commodity servers). For network service providers who support NFV architectures, an efficient resource allocation method finds utility in being able to reduce operating expenses (OPEX) and capital expenses (CAPEX). Thus, in this paper, we analyzed the network service chain embedding problem via an optimization formulation and found a close-optimal solution based on the Markov approximation framework. Our simulation results show that our approach could increases on average CPU utilization by up to 73% and link utilization up to 53%.
Cooperative Detection of Moving Source Signals in Sensor Networks
Minh N. H. Nguyen, Pham Chuan, Choong Seon Hong
http://doi.org/10.5626/JOK.2017.44.7.726
In practical distributed sensing and prediction applications over wireless sensor networks (WSN), environmental sensing activities are highly dynamic because of noisy sensory information from moving source signals. The recent distributed online convex optimization frameworks have been developed as promising approaches for solving approximately stochastic learning problems over network of sensors in a distributed manner. Negligence of mobility consequence in the original distributed saddle point algorithm (DSPA) could strongly affect the convergence rate and stability of learning results. In this paper, we propose an integrated sliding windows mechanism in order to stabilize predictions and achieve better convergence rates in cooperative detection of a moving source signal scenario.
Performance Analysis of LoRa(Long Range) according to the Distances in Indoor and Outdoor Spaces
Junyeong Lim, Jaemin Lee, Donghyun Kim, Jongdeok Kim
http://doi.org/10.5626/JOK.2017.44.7.733
LPWAN(Low Power Wide Area Network) technology is M2M (Machine to Machine) networking technology for the Internet of Things. The technology is designed to support low-power, long-distance and low-speed communications that are typical of LoRaWAN(Long Range Wide Area Network). To exchange inter-object information using a LoRaWAN, the link performances for various environments must be known. however, active performance analysis research that is based on an empirical environment is nonexistent. Therefore, this paper empirically evaluates the performance of the LoRa (Long Range) link, a physical communication technology of the LoRaWAN for various variables that may affect the link quality in indoor and outdoor environments. To achieve this, a physical performance monitoring system was designed and implemented. A communication experiment environment was subsequently constructed based on the indoor and outdoor conditions. The SNR(Signal to Noise Ratio), RSSI(Received Signal Strength Indication), and the PDR(Packet Delivery Ratio) were evaluated.
Categorization of Korean News Articles Based on Convolutional Neural Network Using Doc2Vec and Word2Vec
http://doi.org/10.5626/JOK.2017.44.7.742
In this paper, we propose a novel approach to improve the performance of the Convolutional Neural Network(CNN) word embedding model on top of word2vec with the result of performing like doc2vec in conducting a document classification task. The Word Piece Model(WPM) is empirically proven to outperform other tokenization methods such as the phrase unit, a part-of-speech tagger with substantial experimental evidence (classification rate: 79.5%). Further, we conducted an experiment to classify ten categories of news articles written in Korean by feeding words and document vectors generated by an application of WPM to the baseline and the proposed model. From the results of the experiment, we report the model we proposed showed a higher classification rate (89.88%) than its counterpart model (86.89%), achieving a 22.80% improvement. Throughout this research, it is demonstrated that applying doc2vec in the document classification task yields more effective results because doc2vec generates similar document vector representation for documents belonging to the same category.
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