High reliable disjoint path set selection in mobile
            <i>ad-hoc</i>
            network using Hopfield neural network

Sheikhan, Mansour; Hemmati, Ehsan

doi:10.1049/iet-com.2010.0680

Cited by 14 publications

(8 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…First, we suggest that we put the sum of phased-inboundedges I sum n in (15) into two parts as follows:…”

Section: A Indirect Greedy and Nongreedy Algorithms For L ≥mentioning

confidence: 99%

“…A special case of the CHNN, the real HNN [9], [10], has been one of the most well-known and widely used neural networks in optimization since the 1980s. Its applications varied from associative memory system design problems (see [6], [11]- [13]) to radio resource optimization in wireless networks (see [15], [18]), from combinatorial optimization (see [16]- [19]) to image restoration, from robotics to system identification to analog-to-digital conversion (see [14]), and so on.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Shadow-Cuts Minimization/Maximization and Complex Hopfield Neural Networks

Uykan

2021

IEEE Trans. Neural Netw. Learning Syst.

View full text Add to dashboard Cite

In this article, we continue our very recent work by extending it to the complex case. Having been inspired by the real Hopfield neural network (HNN) results, our investigations here yield various novel results, some of which are as follows. First, extending the "biased pseudo-cut" concept to the complex HNN (CHNN) case, we introduce a "shadowcut" that is defined as the sum of intercluster phased edges. Second, while the discrete-time real HNN strictly minimizes the "biased pseudo-cut" in each neuron state change, the CHNN "tends" to minimize the shadow-cut (as the CHNN energy function is minimized). Third, these definitions pose a novel L-phased graph clustering (partitioning) problem in which the sum of the shadow-cuts is minimized (or maximized) for the Hermitian complex and the directed graphs whose edges are (possibly arbitrary positive/negative) complex numbers. Finally, combining the CHNN and the pioneering algorithm GADIA of Babadi and Tarokh and their modified versions, we propose simple indirect algorithms to solve the defined shadow-cuts minimization/maximization problem. The proposed algorithms naturally include the CHNN as well as the GADIA as its special cases. The computer simulations confirm the findings. Index Terms-Associative memory, clustering, complex Hopfield neural networks (CHNNs), GADIA, graphs with (positive and negative) complex edges, L-phased partitioning problem. I. INTRODUCTION AND MOTIVATION C OMPLEX-VALUED neural networks are becoming an emergent and rapidly developing field because they recently widened the scope of their applications to machine learning, imaging, remote sensing, optoelectronics, quantum neural systems, physiological neural systems, and artificial neural information processing [33], [34]. Complex-valued neural networks are as follows. 1) They are highly suitable not only for representing graphs with complex edges but also for processing the amplitude and phase. This is one of the core concepts in physical systems dealing with electromagnetic, light, and ultrasonic waves, as well as quantum waves [33]. 2) They utilize complex arithmetic, showing specific dynamic characteristics in their learning, self-organizing, and processing [33], [34]. These facts bring critical advantages to representing and modeling complicated relations among the nodes in complex graphs for solving various machine learning problems. In addition, they bring critical advantages in analyzing and processing Manuscript

show abstract

“…First, we suggest that we put the sum of phased-inboundedges I sum n in (15) into two parts as follows:…”

Section: A Indirect Greedy and Nongreedy Algorithms For L ≥mentioning

confidence: 99%

mentioning

confidence: 99%

Shadow-Cuts Minimization/Maximization and Complex Hopfield Neural Networks

Uykan

2021

IEEE Trans. Neural Netw. Learning Syst.

View full text Add to dashboard Cite

show abstract

“…Each flow s travels along either a single path or two paths from a source to a destination which is calculated in advance by a routing protocol, for example, load-balancing routing protocol for multi-radio mesh network (LBM) [24], link expiration time (LET) [25], multi-radio link-quality source routing (MR-LQSR) [26], multi-radio ad-hoc on-demand distance vector routing (MR-AODV) [27,28], and given as input to our problem. For a flow s with two paths, TCP packets are scheduled between these two paths according to our proposed path selection algorithm.…”

Section: Traffic Routing and Flow Schedulingmentioning

confidence: 99%

TCP with hop-oriented network coding in multi-radio multi-channel wireless mesh networks

Liu

2012

IET Networks

View full text Add to dashboard Cite

In multi-radio multi-channel wireless mesh networks (MRMC WMNs), the performance of transmission control protocol (TCP) significantly deteriorates when non-congestion packet losses occur. TCP-hop-oriented network Coding (HONC) is proposed in this study to improve the performance of TCP with hop-oriented network coding in MRMC WMNs. It combines a block of inter-and intra-flow packets that share a same next-hop node by random linear network coding, and then it forwards and acknowledges these blocks hop by hop. Distributed rate control and path selection algorithm is introduced to effectively utilise network resources and balance load from congested paths to non-congested ones. The simulations show that TCP-HONC achieves a significant throughput gain. Meanwhile, the end-to-end delay and delay jitter of TCP-HONC are relatively small even with a high loss rate. TCP-HONC outperforms TCP/NC end-to-end by 236% and TCP/NC hop-by-hop by 143% in throughput and reduces the average end-to-end delay to 27 and 90%, when the packet loss rate on each link is 35%. Moreover, the resource is fairly allocated to different flows. TCP-HONC is also capable of balancing load among different paths and the queue length on bottleneck links is stable. The throughput gain achieved by TCP-HONC is the result of re-encoding data at intermediate nodes and the derived delay reduction benefits from the one-hop ACK and retransmission scheme.

show abstract

“…The continuous-time HNN has been successfully applied to various radio resource management problems in cellular radio systems (e.g., [10] and [11]) and mobile ad-hoc networks (e.g., [12] and [13]), all of which are NP-complete problems. The VLSI implementation of the HNN has the capacity to find suboptimal solutions in a few microseconds [11], which is fast enough to establish a new resource allocation on a frame-by-frame basis in current wireless communication systems for relatively low mobile speeds (i.e.…”

Section: Introductionmentioning

confidence: 99%

Continuous-time Hopfield neural network-based optimized solution to 2-channel allocation problem

Uykan

2015

Turk J Elec Eng & Comp Sci

View full text Add to dashboard Cite

Abstract:The channel allocation problem in cellular radio systems is NP-complete, and thus its general solution is not known for even the 2-channel case. It is well known that the link gain system matrix (or received-signal power system matrix) of the radio network is (and may be highly) asymmetric, and that as the Hopfield neural network is applied to optimization problems, its weight matrix should be symmetric. The main contribution of this paper is as follows: turning the channel allocation problem into a maxCut graph partitioning problem, we propose a simple and effective continuous-time Hopfield neural network-based solution by determining its symmetric weight matrix from the asymmetric received-signal-power-system matrix. Computer simulations confirm the effectiveness and superiority of the proposed solution as compared to standard algorithms for various illustrative cellular radio scenarios for the 2-channel case.

show abstract

High reliable disjoint path set selection in mobile ad-hoc network using Hopfield neural network

Cited by 14 publications

References 20 publications

Shadow-Cuts Minimization/Maximization and Complex Hopfield Neural Networks

Shadow-Cuts Minimization/Maximization and Complex Hopfield Neural Networks

TCP with hop-oriented network coding in multi-radio multi-channel wireless mesh networks

Continuous-time Hopfield neural network-based optimized solution to 2-channel allocation problem

Contact Info

Product

Resources

About