• KIISE Transactions on Computing Practices
• /
• v.21 no.8
• /
• pp.567-571
• /
• 2015

Transition-based dependency parsing requires much time and efforts to design and select features from a very large number of possible combinations. Recent studies have successfully applied Multi-Layer Perceptrons (MLP) to find solutions to this problem and to reduce the data sparseness. However, most of these methods have adopted greedy search and can only consider a limited amount of information from the context window. In this study, we use a Recurrent Neural Network to handle long dependencies between sub dependency trees of current state and current transition action. The results indicate that our method provided a higher accuracy (UAS) than an MLP based model.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.5 no.2
• /
• pp.269-286
• /
• 2011

In this paper, we study a problem that is concerning how to construct a delay-constrained multicast tree on a wireless mesh network (WMN) such that the number of serviced clients is maximized. In order to support high-quality and concurrent interference-free transmission streams, multiple radios are implemented in each mesh node in the WMNs. Instead of only orthogonal channels used for the multicast in the previous works, both orthogonal and partially overlapping channels are considered in this study. As a result, the number of links successfully allocated channels can be expected to be much larger than that of the approaches in which only orthogonal channels are considered. The number of serviced subscribers is then increased dramatically. Hence, the goal of this study is to find interference-free and delay-constrained multicast trees that can lead to the maximal number of serviced subscribers. This problem is referred as the MRDCM problem. Two heuristics, load-based greedy algorithm and load-based MCM algorithm, are developed for constructing multicast trees. Furthermore, two load-based channel assignment procedures are provided to allocate interference-free channels to the multicast trees. A set of experiments is designed to do performance, delay and efficiency comparisons for the multicast trees generated by all the approximation algorithms proposed in this study.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.6 no.12
• /
• pp.3219-3236
• /
• 2012

A tree routing structure is often adopted for many-to-one data gathering and aggregation in sensor networks. For real-time scenarios, considering lossy wireless links, it is an important issue how to construct a maximum-lifetime data gathering tree with delay constraint. In this work, we study the problem of lifetime-preserving and delay-constrained tree construction in unreliable sensor networks. We prove that the problem is NP-complete. A greedy approximation algorithm is proposed. We use expected transmissions count (ETX) as the link quality indicator, as well as a measure of delay. Our algorithm starts from an arbitrary least ETX tree, and iteratively adjusts the hierarchy of the tree to reduce the load on bottleneck nodes by pruning and grafting its sub-tree. The complexity of the proposed algorithm is $O(N^4)$. Finally, extensive simulations are carried out to verify our approach. Simulation results show that our algorithm provides longer lifetime in various situations compared to existing data gathering schemes.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.5
• /
• pp.1992-2008
• /
• 2018

Mobile opportunistic network is a kind of ad hoc networks, which implements the multi-hop routing communication with the help of contact opportunity brought about by the mobility of the nodes. It always uses opportunistic data transmission mode based on store-carry-forward to solve intermittent connect problem of link. Although many routing schemes have been proposed, most of them adopt the greedy transmission mode to pursue a higher delivery efficient, which result in unfairness extremely among nodes. While, this issue has not been paid enough attention up to now. In this paper, we analyzed the main factors that reflect fairness among nodes, modeled routing selection as a multiple attribute decision making problem, and proposed our Fairness-aware Routing Strategy, named FARS. To evaluate the performance of our FARS, extensive simulations and analysis have been done based on a real-life dataset and a synthetic dataset, respectively. The results show that, compared with other existing protocols, our FARS can greatly improve the fairness of the nodes when ensuring the overall delivery performance of the network.

• Journal of Korea Multimedia Society
• /
• v.17 no.10
• /
• pp.1160-1170
• /
• 2014

Clustering methods are very useful in many fields such as data mining, classification, and object recognition. Both the supervised and unsupervised grouping approaches can classify a series of sample data with a predefined or automatically assigned cluster number. However, there is no constraint on the number of elements for each cluster. Numbers of cluster members for each cluster obtained from clustering schemes are usually random. Thus, some clusters possess a large number of elements whereas others only have a few members. In some areas such as logistics management, a fixed number of members are preferred for each cluster or logistic center. Consequently, it is necessary to design a clustering method that can automatically adjust the number of group elements. In this paper, a k-means based clustering method with a fixed number of cluster members is proposed. In the proposed method, first, the data samples are clustered using the k-means algorithm. Then, the number of group elements is adjusted by employing a greedy strategy. Experimental results demonstrate that the proposed clustering scheme can classify data samples efficiently for a fixed number of cluster members.

• Journal of Information Processing Systems
• /
• v.10 no.2
• /
• pp.176-192
• /
• 2014

The realization of Wireless Multimedia Sensor Networks (WMSNs) has been fostered by the availability of low cost and low power CMOS devices. However, the transmission of bulk video data requires adequate bandwidth, which cannot be promised by single path communication on an intrinsically low resourced sensor network. Moreover, the distortion or artifacts in the video data and the adherence to delay threshold adds to the challenge. In this paper, we propose a two stage Quality of Service (QoS) guaranteeing scheme called Prioritized Multipath WMSN (PMW) for transmitting H.264 encoded video. Multipath selection based on QoS metrics is done in the first stage, while the second stage further prioritizes the paths for sending H.264 encoded video frames on the best available path. PMW uses two composite metrics that are comprised of hop-count, path energy, BER, and end-to-end delay. A color-coded assisted network maintenance and failure recovery scheme has also been proposed using (a) smart greedy mode, (b) walking back mode, and (c) path switchover. Moreover, feedback controlled adaptive video encoding can smartly tune the encoding parameters based on the perceived video quality. Computer simulation using OPNET validates that the proposed scheme significantly outperforms the conventional approaches on human eye perception and delay.

• The Journal of Korea Robotics Society
• /
• v.16 no.2
• /
• pp.137-146
• /
• 2021

When controlling manipulator, degree of freedom is lost in singularity so specific joint velocity does not propagate to the end effector. In addition, control problem occurs because jacobian inverse matrix can not be calculated. To avoid singularity, we apply Deep Deterministic Policy Gradient(DDPG), algorithm of reinforcement learning that rewards behavior according to actions then determines high-reward actions in simulation. DDPG uses off-policy that uses 𝝐-greedy policy for selecting action of current time step and greed policy for the next step. In the simulation, learning is given by negative reward when moving near singulairty, and positive reward when moving away from the singularity and moving to target point. The reward equation consists of distance to target point and singularity, manipulability, and arrival flag. Dual arm manipulators hold long rod at the same time and conduct experiments to avoid singularity by simulated path. In the learning process, if object to be avoided is set as a space rather than point, it is expected that avoidance of obstacles will be possible in future research.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.42 no.1
• /
• pp.8-20
• /
• 2019

The vehicle routing problem is one of the vibrant research problems for half a century. Many studies have extensively studied the vehicle routing problem in order to deal with practical decision-making issues in logistics. However, developments of new logistics strategies have inevitably required investigations on solution methods for solving the problem because of computational complexity and inherent constraints in the problem. For this reason, this paper suggests a simulated annealing (SA) algorithm for a variant of vehicle routing problem introduced by a previous study. The vehicle routing problem is a multi-depot and multi-trip vehicle routing problem with multiple heterogeneous vehicles restricted by the maximum permitted weight and the number of compartments. The SA algorithm generates an initial solution through a greedy-type algorithm and improves it using an enhanced SA procedure with three local search methods. A series of computational experiments are performed to evaluate the performance of the heuristic and several managerial findings are further discussed through scenario analyses. Experiment results show that the proposed SA algorithm can obtain good solutions within a reasonable computation time and scenario analyses show that a transportation system visiting non-dedicated factories shows better performance in truck management in terms of the numbers of vehicles used and trips for serving customer orders than another system visiting only dedicated factories.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.43 no.4
• /
• pp.150-160
• /
• 2020

In this paper, we introduce a pilot's scheduling model which is able to maintain and balance their capabilities for each relevant skill level in military helicopter squadron. Flight scheduler has to consider many factors related pilot's flight information and spends a lot of times and efforts for flight planning without scientific process depending on his/her own capability and experience. This model reflected overall characteristics that include pilot's progression by basis monthly and cumulative flight hours, operational recent flight data and quickly find out a pinpoint areas of concern with respect to their mission subjects etc. There also include essential several constraints, such as personnel qualifications, and Army helicopter training policy's constraints such as regulations and guidelines. We presented binary Integer Programming (IP) mathematical formulation for optimization and demonstrated its effectiveness by comparisons of real schedule versus model's solution to several cases experimental scenarios and greedy random simulation model. The model made the schedule in less than 30 minutes, including the data preprocessing process, and the results of the allocation were more equal than the actual one. This makes it possible to reduce the workload of the scheduler and effectively manages the pilot's skills. We expect to set up and improve better flight planning and combat readiness in Korea Army aviation.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2013.05a
• /
• pp.395-398
• /
• 2013

최근 VANET 라우팅 프로토콜에 관한 연구가 증가하는 이유는 차량에 통신장비를 장착하여 차량 간 또는 기간통신망 간에 통신수요 증가가 가까운 미래에 활성화 될 것으로 예상되어 국제적으로 현실에 적용이 가능한 VANET 라우팅 프로토콜에 관심과 중요성이 높아지고 있다. VANET 라우팅 프로토콜에서 주요한 성능을 결정하는 사항은 패킷처리율, 패킷전송지연 그리고 오버헤드이다. 이러한 조건을 만족시키는 VANET 라우팅 프로토콜로 DGRP(Directional Greedy Routing Protocol)이 있다. DGRP는 위치기반 라우팅 프로토콜로 GPSR보다 높은 패킷처리율, 낮은 패킷전송지연과 오버헤드를 갖는다. 이러한 장점을 통해서 본 논문에서는 우리는 DGRP를 개선한 WDGRP를 제안하고자 한다. WDGRP는 기존의 VANET 라우팅의 프로토콜의 장점을 포함하고 있으며 알고리즘을 개선함으로써 DGRP보다 높은 성능을 갖는다. 본 논문에서는 기존의 라우팅 프로토콜인 GPSR, DGRP 라우팅 프로토콜을 WDGRP와 함께 각각 성능비교를 하였다. 그 결과 WDGRP은 다른 라우팅 프로토콜보다 패킷전달율이 증가하였고 오버헤드와 패킷전송지연은 감소하였다.