Abstract The traditional foreground‐background segmentation models mainly depend on the low‐level features of the image, while ignoring the visual effect. Combining visual perception and local features, a top‐down segmentation model is proposed. This model regards foreground‐background segmentation as a reasoning problem based on visual perception, and calculates the association between two‐pixel blocks through Kullback–Leibler divergence, which solves the ill‐posed problem of traditional single‐pixel recognition. Meanwhile, local features are used to optimize the overall segmentation results in detail and improve the segmentation accuracy. The experimental results on the CMU‐Cornell iCoseg database and the BSDS500 database show that visual perception and local features can help improve the segmentation performance to a certain extent.

Abstract Multi-homed devices such as smartphones, tablets and laptops are enabled with multiple heterogeneous interfaces available for transmission. Those interfaces can be utilized for simultaneous transmission of a single TCP flow using Multipath TCP (MPTCP). MPTCP is a protocol that is designed to increase end-to-end throughput and reliability of communications by splitting data through multiple parallel paths. Although delay in MPTCP enhanced significantly in the recent years, high number of data transmissions remains an issue. In this paper, we reduce MPTCP delay by reducing the number of transmissions using Opportunistic Routing (OR) technique. OR is a routing model used to increase the delivery rate and reliability of data transmission in wireless networks by using the broadcasting method. This enables each subflow data to be delivered by multiple relays. We adapted OR on a number of MPTCP protocols namely, traditional MPTCP, Multipath TCP Traffic Splitting Control (MPTCP-TSC) and Redundant MPTCP (ReMP TCP) in an Internet of Things (IoT) environment. The results show that OR-based MPTCP schemes outperform existing schemes. We further compared the OR-based MPTCP protocols in terms of startup delay and energy efficiency. We found that ReMP TCP is better than other schemes in all scenarios.

Physical layer network coding (PNC) has been studied to serve wireless network MIMO systems with much lower backhaul load than approaches such as Cloud Radio Access Network (Cloud-RAN) and coordinated multipoint (CoMP). In this paper, we present a design guideline of engineering applicable PNC to fulfil the request of high user densities in 5G wireless RAN infrastructure. We show that the proposed design criteria guarantee that: 1) the whole system operates over binary system; 2) the PNC functions utilized at each access point overcome all singular fade states; and 3) the destination can unambiguously recover all source messages, while the overall backhaul load remains at the lowest level. We then develop a two-stage search algorithm to identify the optimum PNC mapping functions which greatly reduces the real-time computational complexity. The impact of estimated channel information and reduced number of singular fade states in different QAM modulation schemes are studied in this paper. Numerical results show that the proposed schemes achieve low outage probability with reduced backhaul load.

This paper presents a physical layer network coding (PNC) approach for network MIMO (N-MIMO) systems to release the heavy burden of backhaul load. The proposed PNC approach is applied for uplink scenario in binary systems, and the design guideline serves multiple mobile terminals (MTs) and guarantees unambiguous recovery of the message from each MT. We present a novel PNC design criterion first based on binary matrix theories, followed by an adaptive optimal mapping selection algorithm based on the proposed design criterion. In order to reduce the real-time computational complexity, a two-stage search algorithm for the optimal binary PNC mapping matrix is developed. Numerical results show that the proposed scheme achieves lower outage probability with reduced backhaul load compared to practical CoMP schemes which quantize the estimated symbols from a log-likelihood ratio (LLR) based multiuser detector into binary bits at each access point(AP).

In this paper, we consider joint antenna selection and optimal beamforming for energy efficient delay minimization. We assume multiple-input multi-output (MIMO) system with full duplex simultaneous wireless information and power transfer (FD-SWIPT) where each sensor is equipped with a power splitting (PS) system and can simultaneously receive both energy and information from the aggregator (AGG). We show that the antenna selection and beamforming power control policies are adaptive to the energy state information (ESI), the queue state information (QSI) and the channel state information (CSI). We develop an analytical framework for energy efficient delay-optimal control problem based on the theory of infinite horizon partially observable Markov decision process (POMDP). The infinite-horizon POMDP problem is transformed into an equivalent value Bellman program and solved by near-optimal point-based Heuristic Search Value Iteration (PB-HSVI) method under specific standard conditions. The proposed solution outcome is a set of sub-optimal antenna selection and beamforming control policies. Simulation results reveal an effective trade-off between the contradictory objectives (i.e. delay and power consumption) and show the enhancement in delay by using FD-SWIPT systems in comparison to Half Duplex (HD)-SWIPT systems.

This work proposes adaptive buffer-aided distributed space-time coding schemes and algorithms with feedback for wireless networks equipped with buffer-aided relays. The proposed schemes employ a maximum likelihood receiver at the destination, and adjustable codes subject to a power constraint with an amplify-and-forward cooperative strategy at the relays. The adjustable codes are part of the proposed space-time coding schemes and the codes are sent back to relays after being updated at the destination via feedback channels. Each relay is equipped with a buffer and is capable of storing blocks of received symbols and forwarding the data to the destination if selected. Different antenna configurations and wireless channels, such as static block fading channels, are considered. The effects of using buffer-aided relays to improve the bit error rate (BER) performance are also studied. Adjustable relay selection and optimization algorithms that exploit the extra degrees of freedom of relays equipped with buffers are developed to improve the BER performance. We also analyze the pairwise error probability and diversity of the system when using the proposed schemes and algorithms in a cooperative network. Simulation results show that the proposed schemes and algorithms obtain performance gains over previously reported techniques.

Adaptive power allocation (PA) algorithms with different criteria for a cooperative multiple‐input multiple‐output network equipped with distributed space‐time coding are proposed and evaluated. Joint constrained optimisation algorithms to determine the PA parameters and the receive filter are proposed for each transmitted symbol in each link, as well as the channel coefficients matrix. Linear receive filter and maximum‐likelihood detection are considered with amplify‐and‐forward and decode‐and‐forward cooperation strategies. In these proposed algorithms, the elements in the PA matrices are optimised at the destination node and then transmitted back to the relay nodes via a feedback channel. The effects of the feedback errors are considered. Linear minimum mean square error expressions and the PA matrices depend on each other and are updated iteratively. Stochastic gradient algorithms are developed with reduced computational complexity. Simulation results show that the proposed algorithms obtain significant performance gains as compared with existing PA schemes.

An adaptive distributed space-time coding (DSTC) scheme is proposed for two-hop cooperative MIMO networks. Linear minimum mean square error (MMSE) receive filters and adjustable matrices subject to a power constraint are considered with an amplify-and-forward (AF) cooperation strategy. In the proposed DSTC scheme, an adjustable matrix obtained by a feedback channel is employed to transform the space-time coded matrix at the relay node. Linear MMSE expressions of the adjustable code matrices based on the mean square error (MSE) and the maximum likelihood (ML) criteria are derived. The effects of the limited feedback and the feedback errors on the performance are considered. A stochastic gradient (SG) algorithm is also developed with reduced computational complexity. The simulation results show that the proposed algorithms obtain significant performance gains as compared to existing DSTC schemes.

An adaptive distributed space-time coding (DSTC) scheme is proposed for two-hop cooperative MIMO networks. Linear minimum mean square error (MMSE) receive filters and adjustable code matrices are considered subject to a power constraint with an amplify-and-forward (AF) cooperation strategy. In the proposed adaptive DSTC scheme, an adjustable code matrix obtained by a feedback channel is employed to transform the space-time coded matrix at the relay node. The effects of the limited feedback and the feedback errors are assessed. Linear MMSE expressions are devised to compute the parameters of the adjustable code matrix and the linear receive filters. Stochastic gradient (SG) and least-squares (LS) algorithms are also developed with reduced computational complexity. An upper bound on the pairwise error probability analysis is derived and indicates the advantage of employing the adjustable code matrices at the relay nodes. An alternative optimization algorithm for the adaptive DSTC scheme is also derived in order to eliminate the need for the feedback. The algorithm provides a fully distributed scheme for the adaptive DSTC at the relay node based on the minimization of the error probability. Simulation results show that the proposed algorithms obtain significant performance gains as compared to existing DSTC schemes.