• Journal of Information Processing Systems
• /
• v.20 no.2
• /
• pp.252-262
• /
• 2024

The multi-hop wireless sensor network (WSN) suffers from energy limitation and eavesdropping attacks. We propose a simple and energy-efficient convergecast mechanism using inter-flow random linear network coding that can provide confidentiality to the multi-hop WSN. Our scheme consists of two steps, constructing a logical tree of sensor nodes rooted at the sink node, with using the Bloom filter, and transmitting sensory data encoded by sensor nodes along the logical tree upward to the sink where the encoded data are decoded according to our proposed multi-hop network coding (MHNC) mechanism. We conducted simulations using OMNET++ CASTALIA-3.3 framework and validated that MHNC outperforms the conventional mechanism in terms of packet delivery ratio, data delivery time and energy efficiency.

• Journal of Korea Multimedia Society
• /
• v.23 no.10
• /
• pp.1236-1249
• /
• 2020

In a most recent object tracking research work, applying Convolutional Neural Network and Recurrent Neural Network-based strategies become relevant for resolving the noticeable challenges in it, like, occlusion, motion, object, and camera viewpoint variations, changing several targets, lighting variations. In this paper, the LSTM Network-based Tracking association method has proposed where the technique capable of real-time multi-object tracking by creating one of the useful LSTM networks that associated with tracking, which supports the long term tracking along with solving challenges. The LSTM network is a different neural network defined in Keras as a sequence of layers, where the Sequential classes would be a container for these layers. This purposing network structure builds with the integration of tracking association on Keras neural-network library. The tracking process has been associated with the LSTM Network feature learning output and obtained outstanding real-time detection and tracking performance. In this work, the main focus was learning trackable objects locations, appearance, and motion details, then predicting the feature location of objects on boxes according to their initial position. The performance of the joint object tracking system has shown that the LSTM network is more powerful and capable of working on a real-time multi-object tracking process.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.6 no.7
• /
• pp.1802-1814
• /
• 2012

In order to guide users to select the most optimal access network in heterogeneous wireless networks, a network selection algorithm is proposed which is designed based on multi-objective discrete particle swarm optimization (Multi-Objective Discrete Particle Swarm Optimization, MODPSO). The proposed algorithm keeps fast convergence speed and strong adaptability features of the particle swarm optimization. In addition, it updates an elite set to achieve multi-objective decision-making. Meanwhile, a mutation operator is adopted to make the algorithm converge to the global optimal. Simulation results show that compared to the single-objective algorithm, the proposed algorithm can obtain the optimal combination performance and take into account both the network state and the user preferences.

• Journal of Information Technology Services
• /
• v.11 no.4
• /
• pp.195-213
• /
• 2012

In ubiquitous environments, the Intelligent Transportation System (ITS) protocol is a typical service used to improve the quality of life for humans. The Vehicular Ad-hoc Network (VANET) protocol, a part of ITS, needs further study with regards to its support for high reliability, high speed mobility, data transmission efficiency, and so on. The IEEE 802.11 standard provides a high data rate channel, but it was designed for peer-to-peer network protocols. IEEE 802.11p also provides a high data rate channel, however, it only facilitates communication between roadside and on-board equipment. A VANET has characteristics that enable its topology to change rapidly; it can also be expanded to a multi-hop range network during communication. Therefore, the VANET protocol needs a way to infer the current topology information relating to VANET equipped vehicles. In this paper, we present the Multi-Beacon MAC Protocol, and propose a method to resolve the problem of beacon collisions in VANET through the use of this Multi-Beacon MAC protocol. Evaluation of the performance of Multi-Beacon MAC protocol by means of both mathematical analyses and simulation experiments indicate that the proposed method can effectively reduce beacon collisions and improve the throughput and the delay between vehicles in VANET systems.

• International Journal of Computer Science & Network Security
• /
• v.23 no.11
• /
• pp.21-31
• /
• 2023

In this paper, we focused on the problem of evaluating multi-class classification accuracy and simulation of multiple classifier performance metrics. Multi-class classifiers for sentiment analysis involved many challenges, whereas previous research narrowed to the binary classification model since it provides higher accuracy when dealing with text data. Thus, we take inspiration from the non-linear Support Vector Machine to modify the algorithm by embedding dynamic hyperplanes representing multiple class labels. Then we analyzed the performance of multi-class classifiers using macro-accuracy, micro-accuracy and several other metrics to justify the significance of our algorithm enhancement. Furthermore, we hybridized Enhanced Convolution Neural Network (ECNN) with Dynamic Support Vector Machine (DSVM) to demonstrate the effectiveness and efficiency of the classifier towards multi-class text data. We performed experiments on three hybrid classifiers, which are ECNN with Binary SVM (ECNN-BSVM), and ECNN with linear Multi-Class SVM (ECNN-MCSVM) and our proposed algorithm (ECNNDSVM). Comparative experiments of hybrid algorithms yielded 85.12 % for single metric accuracy; 86.95 % for multiple metrics on average. As for our modified algorithm of the ECNN-DSVM classifier, we reached 98.29 % micro-accuracy results with an f-score value of 98 % at most. For the future direction of this research, we are aiming for hyperplane optimization analysis.

• Korean Management Science Review
• /
• v.18 no.2
• /
• pp.25-38
• /
• 2001

The well-known back-propagation algorithm for multi-layered neural network has successfully been applied to pattern c1assification problems with remarkable flexibility. Recently. the multi-layered neural network is used as a powerful data mining tool. Nevertheless, in many cases with complex boundary of classification, the successful learning is not guaranteed and the problems of long learning time and local minimum attraction restrict the field application. In this paper, an Improved learning procedure of multi-layered neural network is proposed. The procedure is based on the generalized delta rule but it is particular in the point that the architecture of network is not fixed but enlarged during learning. That is, the number of hidden nodes or hidden layers are increased to help finding the classification boundary and such procedure is controlled by entropy evaluation. The learning speed and the pattern classification performance are analyzed and compared with the back-propagation algorithm.

• Journal of Communications and Networks
• /
• v.17 no.2
• /
• pp.110-117
• /
• 2015

In mobile social network, it is a critical challenge to select an optimal set of devices to supply high quality service constantly under dynamic network topology and the limit of device capacity in mobile ad-hoc network (MANET). In this paper, a multi-devices composition and maintenance problem is proposed with ubiquitous service model and network model. In addition, a multi-devices composition and maintenance approach with dynamic planning is proposed to deal with this problem, consisting of service discovery, service composition, service monitor and service recover. At last, the simulation is implemented with OPNET and MATLAB and the result shows this mechanism is better applied to support complex ubiquitous service.

• Proceedings of the KIEE Conference
• /
• 2009.07a
• /
• pp.4_5
• /
• 2009

A new protection coordination algorithm in Multi-Agent based distribution automation system is proposed in this paper. Distribution network protection coordination is acted by normal state distribution operation. But, in more and more complex distribution network structure, it has a big problem that central server processed all measurement data, coordination setting and controls for operation. So, a algorithm to change coordination setting is proposed automatically in terminal devices which Recloser and OCR to include Multi-Agent concepts in distribution network.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2019.05a
• /
• pp.129-132
• /
• 2019

This paper explains the design idea of a multi-Hop network for LoRaWAN. First, the existing LoRaWAN communication method(Single-Hop) will be described based on the standard specification. It then discusses technical considerations when converting from LoRaWAN to a multi-hop network. Finally, we introduce our ideas in this paper.

• Proceedings of the KIEE Conference
• /
• 2004.11c
• /
• pp.240-242
• /
• 2004

A channel allocation algorithm of multi-user OFDM(orthogonal frequency division multiplexing) system is presented. The proposed algorithm is to reduce the complexity of the system, using the GNN(gradual neural network) with gradual expansion scheme and the algorithm attempts to allocate channel with good channel gain to each user. The method has lower computational complexity and less iteration than other algorithms.