• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권9호
• /
• pp.4572-4586
• /
• 2019

Mobile Edge Computing (MEC) and Information-Centric Networking (ICN) are essential network architectures for the future Internet. The advantages of MEC and ICN such as computation and storage capabilities at the edge of the network, in-network caching and named-data communication paradigm can greatly improve the quality of video streaming applications. However, the packet loss in wireless network environments still affects the video streaming performance and the existing loss recovery approaches in ICN does not exploit the capabilities of MEC. This paper proposes a Deep Learning based Loss Recovery Mechanism (DL-LRM) for video streaming over MEC based ICN. Different with existing approaches, the Forward Error Correction (FEC) packets are generated at the edge of the network, which dramatically reduces the workload of core network and backhaul. By monitoring network states, our proposed DL-LRM controls the FEC request rate by deep reinforcement learning algorithm. Considering the characteristics of video streaming and MEC, in this paper we develop content caching detection and fast retransmission algorithm to effectively utilize resources of MEC. Experimental results demonstrate that the DL-LRM is able to adaptively adjust and control the FEC request rate and achieve better video quality than the existing approaches.

• 한국통신학회논문지
• /
• 제41권7호
• /
• pp.750-753
• /
• 2016

Quorum sensing (QS) is a bacterium-to-bacterium cell communication mechanism allowing bio-cell network construction but such mechanism is not well defined yet. We construct a QS-based multiple access network (MAN) and then numerically analyse its average uplink channel capacity as well as BER performance over diffusion-based 3-D molecular communication channels.

• 한국농공학회:학술대회논문집
• /
• 한국농공학회 2001년도 학술발표회 발표논문집
• /
• pp.59-64
• /
• 2001

The objectives of the thesis are to propose a pattern classification method for remote sensing data using artificial neural network. First, we apply the error back propagation algorithm to classify the remote sensing data. In this case, the classification performance depends on a training data set. Using the training data set and the error back propagation algorithm, a layered neural network is trained such that the training pattern are classified with a specified accuracy. After training the neural network, some pixels are deleted from the original training data set if they are incorrectly classified and a new training data set is built up. Once training is complete, a testing data set is classified by using the trained neural network. The classification results of Landsat TM data show that this approach produces excellent results which are more realistic and noiseless compared with a conventional Bayesian method.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2002년도 Proceedings of International Symposium on Remote Sensing
• /
• pp.709-714
• /
• 2002

This paper discussed and analyzed results of different classification algorithms for land use classification in arid and semiarid areas using CBERS-1 image, which in case of our study is Shihezi Municipality, Xinjiang Province. Three types of classifiers are included in our experiment, including the Maximum Likelihood classifier, BP neural network classifier and Fuzzy-ARTMAP neural network classifier. The classification results showed that the classification accuracy of Fuzzy-ARTMAP was the best among three classifiers, increased by 10.69% and 6.84% than Maximum likelihood and BP neural network, respectively. Meanwhile, the result also confirmed the practicability of CBERS-1 image in land use survey.

• Structural Engineering and Mechanics
• /
• 제15권3호
• /
• pp.285-297
• /
• 2003

Complementing recent advances made in the field of structural health monitoring and damage detection, the concept of a wireless sensing network with distributed computational power is proposed. The fundamental building block of the proposed sensing network is a wireless sensing unit capable of acquiring measurement data, interrogating the data and transmitting the data in real time. The computational core of a prototype wireless sensing unit can potentially be utilized for execution of embedded engineering analyses such as damage detection and system identification. To illustrate the computational capabilities of the proposed wireless sensing unit, the fast Fourier transform and auto-regressive time-series modeling are locally executed by the unit. Fast Fourier transforms and auto-regressive models are two important techniques that have been previously used for the identification of damage in structural systems. Their embedment illustrates the computational capabilities of the prototype wireless sensing unit and suggests strong potential for unit installation in automated structural health monitoring systems.

• Journal of Communications and Networks
• /
• 제11권2호
• /
• pp.115-121
• /
• 2009

In cognitive radio (CR) systems, cognitive users can use the frequency bands when the primary users are not present. Hence, reliable detection of available spectrum is foundation of cognitive radio technology. To ensure unimpaired operation of primary users, cooperative spectrum sensing is needed. To reduce the network overhead of cooperative spectrum sensing, a novel cooperative spectrum sensing algorithm based on credibility is proposed. In particular, the close-form expressions for probability of detection and false-alarm are derived for the novel algorithm, and expression for the average overhead used for cooperation is given. The thresholds design method for the algorithm is also discussed. The conclusion is proved by computer simulations.

• Journal of electromagnetic engineering and science
• /
• 제12권1호
• /
• pp.1-7
• /
• 2012

In this paper, we investigated the throughput of a cognitive radio network where two primary frequency channels (PCs) are sensed and opportunistically accessed by N secondary users. The sharing sensing member (SSM) protocol is introduced to sense both PCs simultaneously. According to the SSM protocol, N SUs (Secondary User) are divided into two groups, which allows for the simultaneous sensing of two PCs. With a frame structure, after determining whether the PCs are idle or active during a sensing slot, the SUs may use the remaining time to transmit their own data. The throughput of the network is formulated as a convex optimization problem. We then evaluated an iterative algorithm to allocate the optimal sensing time, fusion rule and the number of members in each group. The computer simulation and numerical results show that the proposed optimal allocation improves the throughput of the SU under a misdetection constraint to protect the PCs. If not, its initial date of receipt shall be nullified.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권6호
• /
• pp.3029-3045
• /
• 2017

The main processes of a cognitive radio system include spectrum sensing, spectrum decision, spectrum sharing, and spectrum conversion. Experimental results show that these stages introduce a time delay that affects the spectrum sensing accuracy, reducing its efficiency. To reduce the time delay, the frequency spectrum prediction was proposed to alleviate the burden on the spectrum sensing. In this paper, the deep recurrent neural network (DRNN) was proposed to predict the spectrum of multiple time slots, since the existing methods only predict the spectrum of one time slot. The continuous state of a channel is divided into a many time slots, forming a time series of the channel state. Since there are more hidden layers in the DRNN than in the RNN, the DRNN has fading memory in its bottom layer as well as in the past input. In addition, the extended Kalman filter was used to train the DRNN, which overcomes the problem of slow convergence and the vanishing gradient of the gradient descent method. The spectrum prediction based on the DRNN was verified with a WiFi signal, and the error of the prediction was analyzed. The simulation results proved that the multiple slot spectrum prediction improved the spectrum efficiency and reduced the energy consumption of spectrum sensing.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권1호
• /
• pp.159-177
• /
• 2018

Participatory sensing is becoming popular and has shown its great potential in data acquisition for ambient assisted living. In this paper, we propose an incentive mechanism in participatory sensing for ambient assisted living, which benefits both the platform and the mobile devices that participated in the sensing task. Firstly, we analyze the profit of participant and platform, and a Stackelberg game model is formulated. The model takes privacy, reputation, power state and quality of data into consideration, and aims at maximizing the profit for both participant and publisher. The discussion of properties of the game show that there exists an unique Stackelberg equilibrium. Secondly, two algorithms are given: one describes how to reach the Stackelberg equilibrium and the other presents the procedures of employing the incentive strategy. Finally, we conduct simulations to evaluate the properties and effectiveness of the proposed mechanism. Simulation results show that the proposed incentive mechanism works well, and the participants and the publisher will be benefitted from it. With the mechanism, the total amount of sensory data can be maximized and the quality of the data can be guaranteed effectively.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제10권4호
• /
• pp.1555-1570
• /
• 2016

For monitoring forest fires, a real-time system to prevent fires in wider areas should be supported consistently. However, there has still been a lack of the support for real-time system related to forest fire monitoring. In addition, the 'real-time' processing in a forest fire detection system can lead to excessive consumption of energy. To solve these problems, the intelligent data acquisition of sensing nodes is required, and the maximum energy savings as well as rapid and accurate detection by flame sensors need to be done. In this regard, this paper proposes a node built-in filter algorithm for intelligent data collection of sensing nodes for the rapid detection of forest fires with focus on reducing the power consumption of the remote sensing nodes and providing efficient wireless sensor network-based forest environment monitoring in terms of data transmission, network stability and data acquisition. The experimental result showed that battery life can be extended through the intelligent sampling of remote sensing nodes, and the average accuracy of the measurement of flame detection based on the distance is 44%.