CAW-YOLO:Cross-Layer Fusion and Weighted Receptive Field-Based YOLO for Small Object Detection in Remote Sensing

In recent years,there has been extensive research on object detection methods applied to optical remote sensing images utilizing convolutional neural networks.Despite these efforts,the detection of small objects in remote sensing remains a formidable challenge.The deep network structure will bring about the loss of object features,resulting in the loss of object features and the near elimination of some subtle features associated with small objects in deep layers.Additionally,the features of small objects are susceptible to interference from background features contained within the image,leading to a decline in detection accuracy.Moreover,the sensitivity of small objects to the bounding box perturbation further increases the detection difficulty.In this paper,we introduce a novel approach,Cross-Layer Fusion and Weighted Receptive Field-based YOLO(CAW-YOLO),specifically designed for small object detection in remote sensing.To address feature loss in deep layers,we have devised a cross-layer attention fusion module.Background noise is effectively filtered through the incorporation of Bi-Level Routing Attention(BRA).To enhance the model’s capacity to perceive multi-scale objects,particularly small-scale objects,we introduce a weightedmulti-receptive field atrous spatial pyramid poolingmodule.Furthermore,wemitigate the sensitivity arising from bounding box perturbation by incorporating the joint Normalized Wasserstein Distance(NWD)and Efficient Intersection over Union(EIoU)losses.The efficacy of the proposedmodel in detecting small objects in remote sensing has been validated through experiments conducted on three publicly available datasets.The experimental results unequivocally demonstrate the model’s pronounced advantages in small object detection for remote sensing,surpassing the performance of current mainstream models.

Multi-Agent Deep Reinforcement Learning for Cross-Layer Scheduling in Mobile Ad-Hoc Networks

Due to the fading characteristics of wireless channels and the burstiness of data traffic,how to deal with congestion in Ad-hoc networks with effective algorithms is still open and challenging.In this paper,we focus on enabling congestion control to minimize network transmission delays through flexible power control.To effectively solve the congestion problem,we propose a distributed cross-layer scheduling algorithm,which is empowered by graph-based multi-agent deep reinforcement learning.The transmit power is adaptively adjusted in real-time by our algorithm based only on local information(i.e.,channel state information and queue length)and local communication(i.e.,information exchanged with neighbors).Moreover,the training complexity of the algorithm is low due to the regional cooperation based on the graph attention network.In the evaluation,we show that our algorithm can reduce the transmission delay of data flow under severe signal interference and drastically changing channel states,and demonstrate the adaptability and stability in different topologies.The method is general and can be extended to various types of topologies.

Novel E2E-QoE Metric for PHY Optimization:A Cross-Layered Framework

Existing systems use key performance indicators(KPIs)as metrics for physical layer(PHY)optimization,which suffers from the problem of overoptimization,because some unnecessary PHY enhancements are imperceptible to terminal users and thus induce additional cost and energy waste.Therefore,it is necessary to utilize directly the quality of experience(QoE)of user as a metric of optimization,which can achieve the global optimum of QoE under cost and energy constraints.However,QoE is still a metric of application layer that cannot be easily used to design and optimize the PHY.To address this problem,we in this paper propose a novel end-to-end QoE(E2E-QoE)based optimization architecture at the user-side for the first time.Specifically,a cross-layer parameterized model is proposed to establish the relationship between PHY and E2E-QoE.Based on this,an E2E-QoE oriented PHY anomaly diagnosis method is further designed to locate the time and root cause of anomalies.Finally,we investigate to optimize the PHY algorithm directly based on the E2E-QoE.The proposed frameworks and algorithms are all validated using the data from real fifth-generation(5G)mobile system,which show that using E2E-QoE as the metric of PHY optimization is feasible and can outperform existing schemes.

Cross-Layer Adaptive Resource Allocation Algorithm with Diverse QoS Requirements for Single-Cell OFDMA Systems

The orthogonal frequency division multiple access( OFDMA) based communication system has been considered as the main trend of next-Generation communication system. But the existing resource allocation algorithm designed for such system is always with high complexity thus hard to be realized. To solve such problem with the constraints of spectrum efficiency and buffer state,a novel cross-layer resource allocation algorithm( RAA) is proposed in this paper. The goal of our RAA is to maximize the system throughput while satisfying several practical constraints,such as fairness among services,head of line( Ho L) delay and diverse quality of service( Qo S) requirements. Due to these constraints,finding the optimal solution becomes a NPhard problem. Therefore in this paper a novel method to solve such problem with acceptable complexity is proposed within following steps: firstly,based on the link state we formulate the ideal subchannel allocation strategy as a convex optimization problem,which can be efficiently solved by our proposed lagrange multiplier technique subchannel allocation( LMTSA) algorithm; secondly,according to the obtained channel allocation matrix,a power allocation algorithm based on the water-filling power allocation( WPA) idea is deployed to get the optimal power allocation matrix combining with adaptive modulation and coding( AMC); finally,through a greedy algorithm,the ultimate subchannel and power allocation matrix can be obtained based on iterative method. The simulation results illustrate that we can achieve the higher throughput and better Qo S performance than the widely-used maximum throughput( MT) algorithm and round robin( RR) algorithm.

Features of fracture height propagation in cross-layer fracturing of shale oil reservoirs

Triaxial fracturing modeling experiments were carried out on whole diameter shale cores from different layers of Shahejie Formation in the Dongpu sag,Bohai Bay Basin to find out the vertical propagation shapes of hydraulic fractures in different reservoirs.A numerical simulation method of inserting global cohesive elements was adopted to build a pseudo-three-dimension fracture propagation model for multiple shale oil reservoirs considering interface strength,perforation location,and pump rate to research the features of hydraulic fracture(HF)penetrating through layers.The hydraulic fracture propagates in a cross pattern in tight sandstone layers,in a straight line in sandstone layers with natural fractures,forms ladder fracture in shale layers with beddings.The hydraulic fracture propagates in a stripe shape vertically in both sandstone and shale layers,but it spreads in the plane in shale layers after connecting beddings.Restricted by beddings,the hydraulic fractures in shale layers are smaller in height than those in sandstone layers.When a sandstone layer and a shale layer are fractured at the same time,the fracture extends the most in height after the two layers are connected.Perforating at positions where the sandstone-shale interface is higher in strength and increasing the pumping rate can enhance the fracture height,thus achieving the goal of increasing the production by cross-layer fracturing in multiple shale oil layers.

A CROSS-LAYER STRATEGY FOR COOPERATIVE DIVERSITY IN WIRELESS SENSOR NETWORKS

We investigate the problem of how to minimize the energy consumption in multi-hop Wireless Sensor Network (WSN),under the constraint of end-to-end reliability Quality of Seervice (QoS) requirement.Based on the investigation,we jointly consider the routing,relay selection and power allocation algorithm,and present a novel distributed cross-layer strategy using opportunistic relaying scheme for cooperative communication.The results show that under the same QoS requirement,the proposed cross-layer strategy performs better than other cross-layer cooperative communication algorithms in energy efficiency.We also investigated the impact of several parameters on the energy efficiency of the cooperative communication in WSNs,thus can be used to provide guidelines to decide when and how to apply cooperation for a given setup.

An Energy-Efficient Access Control Algorithm with Cross-Layer Optimization in Wireless Sensor Networks

This paper presents a wireless sensor network (WSN) access control algorithm designed to minimize WSN node energy consumption. Based on slotted ALOHA protocol, this algorithm incorporates the power control of physical layer, the transmitting probability of medium access control (MAC) layer, and the automatic repeat request (ARQ) of link layer. In this algorithm, a cross-layer optimization is preformed to minimizing the energy consuming per bit. Through theory deducing, the transmitting probability and transmitting power level is determined, and the relationship between energy consuming per bit and throughput per node is provided. Analytical results show that the cross-layer algorithm results in a significant energy savings relative to layered design subject to the same throughput per node, and the energy saving is extraordinary in the low throughput region.

Novel Optimized Cross-Layer Design with Maximum Weighted Capacity Based Resource Allocation for AMC/HARQ Wireless Networks

To provide quality-of service (QoS) guarantees for heterogeneous applications, most recent wireless communications technologies and standards combine the error-correcting capability of hybrid automatic repeat request (HARQ) schemes at the data link layer (DLL) with the adaptation ability of the adaptive modulation and coding (AMC) modes at the physical layer (PHY) layer. This paper aims to investigate the aggregated system capacity as well as the breakdown of this capacity for different ACM modes in each HARQ scheme. This investigation was done by using maximum weighted capacity (MWC) resource allocation at the PHY layer in conjunction with a novel packet error rate (PER)-based scheduling at the medium access control (MAC) layer. As a result, the dominant AMC mode corresponding to channel SNR was available.

Delivering audiovisual content with MPEG-21-enabled cross-layer QoS adaptation

Future multimedia communication systems have to support the user’s needs, the terminal capabilities, the content specification and the underlying networking technologies. The related protocols and applications must be designed from this integration perspective in a cross-layer centric manner. In this paper, we propose an implementation of a streaming service (e.g., Television over IP service) with a unified QoS management concept that enables an IP driven integration of different system components (terminal, user, content, and network). The MPEG-21 framework is used to provide a common support for imple- menting and managing the end-to-end QoS. The main focus of this paper is on the architecture design, protocols specification and implementation evaluation. Performance evaluations using PSNR and SSIM objective video quality metrics show the benefit of the proposed MPEG-21-enabled cross-layer adaptation.

Cross-layer design of combining AMC with HARQ in cooperative relay system with perfect and imperfect CSI

A cross-layer design which combines adaptive modulation and coding (AMC) at the physical layer with a hybrid automatic repeat request (HARQ) protocol at the data link layer (LL) is presented, in cooperative relay system over Nakagami-m fading channels with perfect and imperfect channel state information (CSI). In order to maximize spectral efficiency (SE) under delay and packet error rate (PER) performance constraints, a state transition model and an optimization framework with perfect CSI are presented. Then the framework is extended to cooperative relay system with imperfect CSI. The numerical results show that the scheme can achieve maximum SE while satisfying transmitting delay requirements. Compared with the imperfect CSI, the average PER with perfect CSI is much lower and the spectral efficiency is much higher.

Network-adaptive HD MPEG-2 video streaming with cross-layered channel monitoring in WLAN

In this paper, we propose a practical design and implementation of network-adaptive high definition (HD) MPEG-2 video streaming combined with cross-layered channel monitoring (CLM) over the IEEE 802.11a wireless local area network (WLAN). For wireless channel monitoring, we adopt a cross-layered approach, where an access point (AP) periodically measures lower layers such as medium access control (MAC) and physical (PHY) transmission information (e.g., MAC layer loss rate) and then sends the monitored information to the streaming server application. The adaptive streaming server with the CLM scheme reacts more quickly and efficiently to the fluctuating wireless channel than the end-to-end application-layer monitoring (E2EM) scheme. The streaming server dynamically performs priority-based frame dropping to adjust the sending rate according to the measured wireless channel condition. For this purpose, the proposed streaming system nicely provides frame-based prioritized packetization by using a real-time stream parsing module. Various evaluation results over an IEEE 802.11a WLAN testbed are provided to verify the intended Quality of Service (QoS) adaptation capability. Experimental results showed that the proposed system can mitigate the quality degradation of video streaming due to the fluctuations of time-varying channel.

Performance of Cross-Layer Design with Power Allocation in Space-Time Coded MIMO Systems

A cross-layer design(CLD)scheme with combination of power allocation,adaptive modulation(AM)and automatic repeat request(ARQ)is presented for space-time coded MIMO system under imperfect feedback,and the corresponding system performance is investigated in a Rayleigh fading channel.Based on imperfect feedback information,a suboptimal power allocation(PA)scheme is derived to maximize the average spectral efficiency(SE)of the system.The scheme is based on a so-called compressed SNR criterion,and has a closed-form expression for positive power allocation,thus being computationally efficient.Moreover,it can improve SE of the presented CLD.Besides,due to better approximation,it obtains the performance close to the existing optimal approach which requires numerical search.Simulation results show that the proposed CLD with PA can achieve higher SE than the conventional CLD with equal power allocation scheme,and has almost the same performance as CLD with optimal PA.However,it has lower calculation complexity.

Cross-layer Enhancement to Multi-hop Routing in Sensor Networks: an Empirical Study

Lossy link is one of the unique characteristics in random-deployed sensor networks. We envision that robustness and reliability of routing cannot be ensured purely in network layer. Our idea is to enhance the performance of routing protocol by cross-layer interaction. We modified mint protocol, a routing protocol in TinyOS and proposed an enhanced version of mint called PA-mint. A transmission power control interface is added to network layer in PA-mint. When routing performance of the current network is not satisfied, PA-mint monotonically increases the transmission power via the interface we added. PA-mint is able to connect orphan nodes and robust to node mobility or key nodes failure. In the case that automatic request retransmission is employed, the number of retransmissions can be reduced by PA-mint. Results from experiments show that PA-mint increases the reliability and robustness of routing protocol by cross-layer interaction.

Cross-Layer Design Based Optimized Link State Routing Protocol for Wireless Mesh Networks

A proactive routing protocol CL-OLSR （cross-layer based optimized link state routing） by using a brand-new routing metric CLM （cross-layer metric） is proposed. CL-OLSR takes into account four link quality impact factors in route calculation through the cross-layer operation mechanism： the node available bandwidth, the node load, the link delivery rate, and the link interference, and thus the effect of route selection is optimized greatly. The simulation results show that the proposed CL-OLSR protocol can not only improve the network throughput to a large extent, but also reduce the end-to-end delay, while achieving load balance route results.

Cross-Layer Design for EH Systems with Finite Buffer Constraints

Energy harvesting(EH)technology in wireless communication is a promising approach to extend the lifetime of future wireless networks.A cross-layer optimal adaptation policy for a point-to-point energy harvesting(EH)wireless communication system with finite buffer constraints over a Rayleigh fading channel based on a Semi-Markov Decision Process(SMDP)is investigated.Most adaptation strategies in the literature are based on channeldependent adaptation.However,besides considering the channel,the state of the energy capacitor and the data buffer are also involved when proposing a dynamic modulation policy for EH wireless networks.Unlike the channeldependent policy,which is a physical layer-based optimization,the proposed cross-layer dynamic modulation policy is a guarantee to meet the overflow requirements of the upper layer by maximizing the throughput while optimizing the transmission power and minimizing the dropping packets.Based on the states of the channel conditions,data buffer,and energy capacitor,the scheduler selects a particular action corresponding to the selected modulation constellation.Moreover,the packets are modulated into symbols according to the selected modulation type to be ready for transmission over the Rayleigh fading channel.Simulations are used to test the performance of the proposed cross-layer policy scheme,which shows that it significantly outperforms the physical layer channel-dependent policy scheme in terms of throughput only.

A NOVEL CROSS-LAYER STRATEGY OF VIDEO TRANSMISSION TO SOLVE PERFORMANCE ANOMALY IN MULTI-RATE IEEE 802.11 NETWORKS

When wireless hosts use different rates to transmit data in IEEE 802.11 networks, it will take on the state of performance anomaly which will severely decrease the throughputs of all the higher rate hosts. Hence, it is bad for video service transmission. Considering that video is very sensitive to packet delivery delay but can tolerate some packet losses, we propose a novel cross-layer scheme which takes these two characteristics into consideration. Firstly, the maximum number of retransmissions for a video Medium Access Control (MAC) frame is computed in MAC layer according to video frame rate requirement of application layer and current access delay of MAC layer. Secondly, within the margin of the tolerant Packet Loss Rate (PLR) of application layer, several video MAC frames are allowed to drop so that we can adaptively select the transmission rate as high as possible for the rest of video MAC frames in terms of current channel quality and the maximum number of retransmissions. Experiment results show that the proposed method can reduce the delay and jitter of video service and improve the throughputs of fast hosts. Therefore, it increases the quality of reconstructed video to a certain extent and relieves the performance anomaly of network effectively.

QUALITY-AWARE CROSS-LAYER SCHEDULING FOR ROBUST VIDEO STREAMING OVER WIRELESS CHANNELS

In the case of video streaming over wireless channels, burst errors may lead to serious video quality degradation. By jointly exploiting the scheduling mechanism on different communication layers, this paper proposes a quality-aware cross-layer scheduling scheme to achieve unequal error control for each Latency-constraint Frame Set (LFS) of a video stream. After a network-layer agent at base station firstly utilizes the network-layer packet scheduling to provide packet-granularity importance classifi-cation for the current LFS, a link-layer agent at base station further utilizes the Radio-Link-Unit (RLU) scheduling to implement finer selective retransmission of the current LFS. Under scheduling delay and bandwidth constraints, the proposed scheme can be aware of the application-layer quality and time-varying channel conditions, and hence burst errors can simply be shifted to lower-priority transmission units in the current LFS. Simulation results demonstrate that the proposed scheme has strong robustness against burst errors, and thus improves the overall received quality of the video stream over wireless channels.

A Novel Cross-Layer Scheduling Algorithm for OFDMA-Based WiMAX Networks

IEEE 802.16e based WiMAX networks promise a desirable available quality of service for mobile users and scheduling algorithms provide the best effective use of network resources in it. In this paper, we propose a novel cross-layer scheduling algorithm for OFDMA-based WiMAX networks. Our scheme employs a priority function at the MAC layer and a slot allocation policy at physical layer and by interaction between these two layers specifies the best allocation for each connection. Simulation results show performance of proposed scheme in comparison with two other well-known scheduling algorithms, MAX-SNR scheduling and Proportional Fairness (PF) scheduling. Our proposed cross-layer algorithm outperforms the other algorithms in delay and packet loss rate values for real-time services.

An efficient cross-layer buffer management optimization scheme for 5G protocol stack

It is extremely challenging for the 5G User Equipment(UE)to meet the requirement of low-latency data transmission with higher achievable data rates.And user plane processing of 5G protocol stack(PS)is one of the dominating components for end-to-end data transmission in the network system.In this paper,a cross-layer buffer management scheme(CLBM)is proposed.CLBM adopts a zero-copy technique for protocol data unit(PDU)processing between protocol layers and allows to improve the memory operation efficiency significantly with reduced processing latency and CPU usage.Moreover,the PS performance profiling(PSperf)tool,a general evaluation framework for the performance measurement and analysis of PS,is implemented based on the OpenAirInterface(OAI)5G platform.The evaluation result shows that compared with the PS of OAI the CLBM strategy reduces the CPU usage of RLC,PDCP,and MAC layer processing significantly up to 20.6%,63.4%,and 38.8%,respectively.In result,the processing delay of the whole user plane of PS also has been reduced distinctly at various offered traffic load.

Performance Study of a Cross-Layer Based Multipath Routing Protocol for IEEE 802.11e Mobile Ad Hoc Networks

Communication over wireless links identifies significant challenges for routing protocols operating. This paper proposes a Cross-layer design based Multipath Routing Protocol (CMRP) for mobile ad hoc networks, by means of the node energy signal from the physical layer. The purpose is to optimize routing decision and path quality. The nodes’ mobility behavior is predicted using a notion of “Signal Fading Degree, SFD”. Especially, in combination of the IEEE 802.11e standard at the MAC layer, we determine that the IEEE 802.11e makes a significant contribution to performance improvement of CMRP. Performance evaluation of AODV in legacy 802.11 and CMRP in IEEE 802.11e shows that, as a function of speed of node mobility, a tremendous reduction achieved, in metrics such as the average end-to-end delay, route overhead, route discovery frequency, normalized routing load - almost more than 80%, 40%, 40%, and 40%. In the case of varying number of sessions, the reduction for route discovery frequency and normalized routing load are up to 70% and 80%.