In this paper, we consider a synthetic aperture secure beamforming approach for a virtual multiple-input multiple-output (MIMO) broadcast channel in the presence of hybrid wiretapping environments. Our goal is to design the flight node deployment constructed by a single-antenna mobile autonomous aerial vehicle (AAV), corresponding transmission symbol strategy, transmit precoding, and received beamforming to maximize the system channel capacity. Leveraging the synthetic aperture beamforming, we aim to provide spatial gain along a predefined angle in free space while reducing it in others and thus enhance physical layer (PHY) security. To this end, we analyze the expression of the asymptotic channel eigenvalues to optimize the AAV flight node deployment. For the optimal precoding design, an energy-efficient method that minimizes the transmit power consumption is studied based on the given virtual MIMO channel, while meeting the quality of service (QoS) for the base station (BS), leakage tolerance of eavesdroppers (Eves), and per-node power constraints. The power minimization problem is a non-convex program, which is then reformulated as a tractable form after some mathematical manipulations. Moreover, we design the received beamforming by applying the linearly constrained minimum variance (LCMV) method such that the jamming can be effectively suppressed. Numerical results demonstrate the superiority of the proposed method in promoting capacity.

The autonomous and security are the crucial requirements in fields of the polar transportation. This paper proposes a newly iterative learning control framework for the autonomous surface vessels (ASV) to implement the path-following operation in the ice floes scenario. The proposed framework is divided into two parts: the guidance and control. For the former, the ice floes are firstly identified into threatening and non-threatening based on the size. Subsequently, the obstacle area of each threatening ice floe is programmed considering the underwater portion. Then the ice floes avoidance guidance with auto-select mechanism for ice-zone traversal mission is constructed by setting the hazard threshold and target point. For the latter, a robust adaptive iterative learning control (ILC) system is designed for the path-following mission, where the control accuracy increases with the number of iterations. The stability of the closed-loop control system is proved with utilization of the Lyapunov theorem. Finally, two numerical examples are provided to evaluate the advantages and accuracy of the proposed algorithm, where the ice floes are generated with irregular.

This article investigates an adaptive prescribed performance path-following control algorithm for rotor-assisted vehicles, incorporating reinforcement learning (RL) to execute energy-saving cruising missions. For obtaining a high-performance path-following controller, a concise prescribed performance control (PPC) algorithm is designed to tightly constrain the output errors within the defined boundaries, while a shifting function is introduced to solve the problem of initial condition restrictions. Furthermore, through integrating the Backstepping method and the optimal control technique, an improved RL with the form of actor-critic neural networks (AC-NNs) is proposed to offer an innovative approach to the challenges of the model uncertainties and external disturbances. In this approach, the actor NN is employed to create an appropriate control policy, while the critic NN is aimed at evaluating the cost-to-go function to modify the system action. Semi-global uniform ultimate bounded (SGUUB) stable properties of the proposed algorithm are guaranteed via the Lyapunov theory. Finally, the superiority and feasibility of the proposed algorithm are verified by two numerical experiments.

Recently, as one of the most popular covert communication technologies, generative steganography has received ever-increasing attention due to its promising performance against sophisticated steganalysis tools. However, it is quite difficult for the existing generative steganographic approaches to find a good tradeoff between hiding capacity and extraction accuracy, mainly due to the small capacity of their hiding spaces. To overcome this shortcoming, a Progressive Generative Steganography (PGS) network architecture is proposed to hide a secret message during the progressive image generation process to realize secure covert communication. Specifically, we first propose a robust Secret-to-Noise (S2N) mapping method to encode the secret message as a set of noise maps. Then, guided by these noise maps, a set of corresponding images ranging from low resolution to high resolution are progressively generated by the Single Generative Adversarial Networks (SINGAN). Consequently, a large-sized secret message can be hidden in the finally generated high-resolution image, since a set of high-capacity hiding spaces can be provided by the process of progressive image generation. Moreover, to improve the quality of image generation and the accuracy of secret message extraction, a Dense Secret-Feature Connection (DSFC) strategy is designed and integrated into the proposed PGS network architecture. Extensive experiments demonstrate that the proposed PGS outperforms the existing approaches in the aspects of both hiding capacity and message extraction, while maintaining promising anti-detectability and imperceptibility for covert communication.

In this paper, we investigate an unmanned aerial vehicle (UAV)-enabled secure communication scenario that a cluster of UAVs performs a virtual non-uniform linear array (NULA) to communicate with a base station (BS) in the presence of eavesdroppers (Eves). Our goal is to design the UAV topology, trajectory, and precoding to maximize the system channel capacity. To this end, we convert the original problem into equivalent two-stage problems. Specifically, we first try to maximize the channel gain by meticulously designing the UAV topology. We then study the joint optimization of the trajectory and precoding for total transmit power minimization while satisfying the constraints on providing quality of service (QoS) assurance to the BS, the leakage tolerance to Eves, the per-UAV transmit power, the initial/final locations, and the cylindrical no-fly zones. For the UAV topology design, we prove that the topology follows the Fekete-point distribution. The design of trajectory and precoding is formulated as a non-convex optimization problem which is generally intractable. Subsequently, the non-convex constraints are converted into convex terms, and a double-loop search algorithm is proposed to solve the transmit power minimization problem. Introduce random rotation offsets so as to perform a dynamic stochastic channel to enhance the security. Numerical results demonstrate the superiority of the proposed method in promoting capacity.

The goal of this paper is to address the physical layer (PHY) security problem for multi-user multi-input single-output (MU-MISO) Internet of Things (IoT) systems in the presence of passive eavesdroppers (Eves). To this end, we propose an artificial noise (AN)-aided rate-splitting (RS)-based secure beamforming scheme. Our design considers the dual use of common messages and places the research emphasis on hiding the private messages for secure communication. In particular, leveraging AN-aided RS-based beamforming, we aim to maximize the focused secrecy sum-rate (F-SSR) by jointly designing transmit information and AN beamforming while satisfying the desired received constraints for the private messages at IoT devices (IoDs), and per-antenna transmit power constraint at base station. Then, we proposed a two-stage algorithm to iteratively find the optimal solution. By transforming non-convex terms into linear terms, we first reformulate the original problem as a convex program. Next, we recast the optimization problem to an unconstrained problem to obtain the global optimal solutions. Utilizing the duality framework, we further develop an efficient algorithm based on a barrier interior point method to solve the reformulated problem. Simulation results validate the superior performance of our proposed schemes.

As a novel paradigm, Vehicular Edge Computing (VEC) can effectively support computation-intensive or delay-sensitive applications in the Internet of Vehicles era. Computation offloading and resource management strategies are key technologies that directly determine the system cost in VEC networks. However, due to vehicle mobility and stochastic arrival computation tasks, designing an optimal offloading and resource allocation policy is extremely challenging. To solve this issue, a deep reinforcement learning-based intelligent offloading and power allocation scheme is proposed for minimizing the total delay cost and energy consumption in dynamic heterogeneous VEC networks. Specifically, we first construct an end-edge-cloud offloading model in a bidirectional road scenario, taking into account stochastic task arrival, time-varying channel conditions, and vehicle mobility. With the objective of minimizing the long-term total cost composed of the energy consumption and task delay, the Markov Decision Process (MDP) can be employed to solve such optimization problems. Moreover, considering the high-dimensional continuity of the action space and the dynamics of task generation, we propose a deep deterministic policy gradient-based adaptive computation offloading and power allocation (DDPG-ACOPA) algorithm to solve the formulated MDP problem. Extensive simulation results demonstrate that the proposed DDPG-ACOPA algorithm performs better in the dynamic heterogeneous VEC environment, significantly outperforming the other four baseline schemes.

Directional modulation and artificial noise (AN)-based methods have been widely employed to achieve physical-layer security (PLS). However, these approaches can only achieve angle-dependent secure transmission. This paper presents an AN-aided decomposed and distributed directional modulation (D3M) scheme for secure wireless communications, which takes advantage of the spatial signatures to achieve an extra range-dimension security apart from the angles. Leveraging decomposed and distributed structure, each of modulated signal is represented by mutually orthogonal in-phase and quadrature branches, which are transmitted by two distributed transmitters to enhance PLS. In particular, we first aim to minimize transmit message power by integrated design of the transmit beamformers, subject to prescribed received signal-to-noise ratio (SNR) for the legitimate user (LU) and no inter-branch interference. This guarantees reliable and accurate transmission for the LU with the minimum transmit message power. Considering the leakage power on the sidelobes, AN is superimposed on the messages to try to mask the confidential information transmission. Simulation results demonstrate the security enhancement of our proposed D3M system.

In this paper, we consider the physical layer (PHY) security problem for hybrid wiretapping wireless systems in millimeter wave transmission, where active eavesdroppers (AEs) and passive eavesdroppers (PEs) coexist to intercept the confidential messages and emit jamming signals. To achieve secure and reliable transmission, we propose an artificial noise (AN)-aided robust multi-beam array transceiver scheme. Leveraging beamforming, we aim to minimize transmit power by jointly designing the information and AN beamforming, while satisfying valid reception for legitimate users (LUs), per-antenna power constraints for transmitter, as well as all interception power constraints for eavesdroppers (Eves). In particular, the interception power formulation is taken into account for protecting the information against hybrid Eves with imperfect AE channel state information (CSI) and no PE CSI. In light of the intractability of the problem, we reformulate the considered problem by replacing non-convex constraints with tractable forms. Afterwards, a two-stage algorithm is developed to obtain the optimal solution. Additionally, we design the received beamforming weights by means of minimum variance distortionless response, such that the jamming caused by AEs can be effectively suppressed. Simulation results demonstrate the superiority of our proposed scheme in terms of energy efficiency and security.

Medical imaging denoising faces great challenges, yet is in great demand. With its distinctive characteristics, medical imaging denoising in the image domain requires innovative deep learning strategies. In this study, we propose a simple yet effective strategy, the content-noise complementary learning (CNCL) strategy, in which two deep learning predictors are used to learn the respective content and noise of the image dataset complementarily. A medical image denoising pipeline based on the CNCL strategy is presented, and is implemented as a generative adversarial network, where various representative networks (including U-Net, DnCNN, and SRDenseNet) are investigated as the predictors. The performance of these implemented models has been validated on medical imaging datasets including CT, MR, and PET. The results show that this strategy outperforms state-of-the-art denoising algorithms in terms of visual quality and quantitative metrics, and the strategy demonstrates a robust generalization capability. These findings validate that this simple yet effective strategy demonstrates promising potential for medical image denoising tasks, which could exert a clinical impact in the future. Code is available at: https://github.com/gengmufeng/CNCL-denoising.

Optical coherence tomography (OCT) is a widely-used modality in clinical imaging, which suffers from the speckle noise inevitably. Deep learning has proven its superior capability in OCT image denoising, while the difficulty of acquiring a large number of well-registered OCT image pairs limits the developments of paired learning methods. To solve this problem, some unpaired learning methods have been proposed, where the denoising networks can be trained with unpaired OCT data. However, majority of them are modified from the cycleGAN framework. These cycleGAN-based methods train at least two generators and two discriminators, while only one generator is needed for the inference. The dual-generator and dual-discriminator structures of cycleGAN-based methods demand a large amount of computing resource, which may be redundant for OCT denoising tasks. In this work, we propose a novel triplet cross-fusion learning (TCFL) strategy for unpaired OCT image denoising. The model complexity of our strategy is much lower than those of the cycleGAN-based methods. During training, the clean components and the noise components from the triplet of three unpaired images are cross-fused, helping the network extract more speckle noise information to improve the denoising accuracy. Furthermore, the TCFL-based network which is trained with triplets can deal with limited training data scenarios. The results demonstrate that the TCFL strategy outperforms state-of-the-art unpaired methods both qualitatively and quantitatively, and even achieves denoising performance comparable with paired methods. Code is available at: https://github.com/gengmufeng/TCFL-OCT.

In large-scale online service systems, software changes are inevitable and frequent. Due to importing new code or configurations, changes are likely to incur incidents and destroy user experience. Thus it is essential for engineers to identify bad software changes, so as to reduce the influence of incidents and improve system re- liability. To better understand bad software changes, we perform the first empirical study based on large-scale real-world data from a large commercial bank. Our quantitative analyses indicate that about 50.4% of incidents are caused by bad changes, mainly be- cause of code defect, configuration error, resource contention, and software version. Besides, our qualitative analyses show that the current practice of detecting bad software changes performs not well to handle heterogeneous multi-source data involved in soft- ware changes. Based on the findings and motivation obtained from the empirical study, we propose a novel approach named SCWarn aiming to identify bad changes and produce interpretable alerts accurately and timely. The key idea of SCWarn is drawing support from multimodal learning to identify anomalies from heterogeneous multi-source data. An extensive study on two datasets with various bad software changes demonstrates our approach significantly outperforms all the compared approaches, achieving 0.95 F1-score on average and reducing MTTD (mean time to detect) by 20.4%∼60.7%. In particular, we shared some success stories and lessons learned from the practical usage.

Optical coherence tomography angiography (OCTA) is a promising imaging modality for microvasculature studies. Deep learning networks have been widely applied in the field of OCTA reconstruction, benefiting from its powerful mapping capability among images. However, these existing deep learning-based methods depend on high-quality labels, which are hard to acquire considering imaging hardware limitations and practical data acquisition conditions. In this article, we proposed an unprecedented weakly supervised deep learning-based pipeline for OCTA reconstruction task, in the absence of high-quality training labels. The proposed pipeline was investigated on an in vivo animal dataset and a human eye dataset by a cross-validation strategy. Compared with supervised learning approaches, the proposed approach demonstrated similar or even better performance in the OCTA reconstruction task. These investigations indicate that the proposed weakly supervised learning strategy is well capable of performing OCTA reconstruction, and has a certain potential towards clinical applications.

In this paper, an efficient multi-beam transmission scheme that uses symbol-level precoding based on frequency diverse array (FDA) is proposed to enhance the physical layer security (PLS). Unlike the usual maximization of secrecy rate, we assume that the position information of passive eavesdropper (Eve) is not available at transmitter, which is a more realistic assumption. We use a minimum transmission message power criterion to design the precoder, subject to constraint on received signals at symbol level for per legitimate user (LU). This guarantees the valid reception of LUs to obtain the corresponding symbols under transmission messages power minimization. Then, after accurate calculation of the transmission message power, the remaining power can be allocated to artificial noise (AN), which deteriorates the quality of received signals at other regions. Numerical simulations show the validity and effectiveness of the proposed scheme.

In this paper, we research a synthesis scheme for secure wireless communication in the broadcasting multiusers directional modulation system, which consists of multiple legitimate users (LUs) receiving the same confidential messages and multiple eavesdroppers (Eves) intercepting the confidential messages. We propose a new type of array antennas, termed random frequency diverse arrays (RFDA), to enhance the security of confidential messages due to its angle-range dependent beam patterns. Based on RFDA, we put forward a synthesis scheme to achieve multiobjective secure wireless communication. First, with known locations of Eves, the beamforming vector is designed to minimize Eves’ receiving power of confidential message (Min-ERP) while satisfying the power requirement of LUs. Furthermore, we research a more practical scenario, where locations of Eves are unknown. Unlike the scenario of known locations of Eves, the beamforming vector is designed to maximize the sum received power of LUs (Max-LRP) while satisfying a minimum received power constraint at each LU. Second, the artificial-noise projection matrix (ANPM) is calculated to reduce artificial-noise (AN) impact on LUs and enhance the interference on Eves. Numerical results verify the superior secure performance of the proposed schemes in the broadcasting multiusers system.

In this paper, we research synthesis scheme for secure wireless communication in multibeam directional modulation (MBDM) system, which consists of multiple legitimate users (LUs) receiving their own individual confidential messages, respectively, and multiple eavesdroppers (Eves) intercepting confidential messages. We propose a new type of array antennas, termed frequency diverse arrays (FDA), to enhance security of confidential messages. Leveraging FDA technology and artificial noise (AN) technology, we aim to address the PHY security problem for MBDM by jointly optimizing the frequency offsets, the precoding matrix and the AN projection matrix. In the first stage, with known locations of Eves, precoding matrix is designed to minimize Eve’s receiving power of confidential message (Min-ERP), while satisfying power requirement of LUs. And then artificial-noise projection matrix (ANPM) is calculated to enhance AN impact on Eves without influencing LUs. Furthermore, we research a more practical scenario, where locations of Eves are unknown. Unlike the scenario of the known locations of Eves, precoding matrix is designed to maximize AN transmit power (Max-ATP), while satisfying each LU’s requirement received power of confidential message. In the second stage, we analyze and further optimize secrecy capacity. The problem is solved by optimizing frequency offsets through modified artificial bee colony (M-ABC) algorithm. Numerical results show that the proposed scheme can achieve a secure transmission in MBDM system.

PM2.5 is an important indicator of the severity of air pollution and its level can be predicted through hazy photographs caused by its degradation. Image-based PM2.5 estimation is thus extensively employed in various multimedia applications but is challenging because of its ill-posed property. In this paper, we convert it to the problem of estimating the PM2.5-relevant haze transmission and propose a learning model called the transmission filtering network. Different from most methods that generate a transmission map directly from a hazy image, our model takes the coarse transmission map derived from the dark channel prior as the input. To obtain a transmission map that satisfies the local smoothness constraint without regional boundary degradation, our model performs the edge-preserving smoothing filtering as the refinement on the map. Moreover, we introduce the attention mechanism to the network architecture for more efficient feature extraction and smoothing effects in the transmission estimation. Experimental results prove that our model performs favorably against the state-of-the-art dehazing methods in a variety of hazy scenes.

Abstract Single image rain removal is a challenging ill‐posed problem due to various shapes and densities of rain streaks. We present a novel incremental randomly wired network (IRWN) for single image deraining. Different from previous methods, most structures of modules in IRWN are generated by a stochastic network generator based on the random graph theory, which ease the burden of manual design and further help to characterize more complex rain streaks. To decrease network parameters and extract more details efficiently, the image pyramid is fused via the multi‐scale network structure. An incremental rectified loss is proposed to better remove rain streaks in different rain conditions and recover the texture information of target objects. Extensive experiments on synthetic and real‐world datasets demonstrate that the proposed method outperforms the state‐of‐the‐art methods significantly. In addition, an ablation study is conducted to illustrate the improvements obtained by different modules and loss items in IRWN.

In this study, the authors propose a novel progressive dehazing network to address the single image haze removal problem based on a new mean progressive scattering model. Different from methods that learn atmosphere light and transmission maps with different networks, these two variables are optimised in a unified network. Following the methodology of traditional prior‐based methods that estimate a coarse transmission map first, a progressive refinement branch in the decoder has been designed to restore the fine‐scale transmission map. To improve the prediction accuracy of the transmission map, a novel binomial truncated loss that assigns weights to error values according to the probabilities of error occurrences has been proposed. An ablation study is conducted to verify the effectiveness of the components in the proposed method. Experiments in the synthetic datasets and real images demonstrate that the proposed method outperforms other state‐of‐the‐art methods.

In this paper, a frequency diverse array-based directional modulation with artificial noise synthesis scheme is proposed to enhance the physical layer security of wireless communications. We aim to optimize the secrecy performance by jointly optimizing the frequency offsets, the beamforming vector, and the artificial-noise projection matrix (ANPM). Specifically, we address the physical layer security problems for known locations of proximal eavesdropper (Eve) and legitimate user (LU). The beamforming vector and frequency offsets are designed to preserve the signal power at LU. The ANPM is calculated to minimize the effect of AN on LU. Furthermore, we extend our approach to the case of multi-LUs with unknown Eve locations. Being different from the case of a single LU, the frequency offsets across array antennas are optimized to equally allocate transmitted power to each LU. The numerical results show that the proposed method can provide a higher secrecy performance than conventional DM methods. In the case of multi-LUs with unknown Eve locations, the proposed method can provide a high secrecy capacity while achieving almost equal achievable capacity to each LU.

Frequency diverse array- (FDA-) based directional modulation (DM) is a promising technique for physical layer security, due to its angle-range dependent transmit beampattern. However, the existing schemes are not suitable for the broadcasting scenario, where there are multiple legitimate users (LUs) to receive the confidential message. In this paper, we propose a novel random frequency diverse array- (RFDA-) based DM scheme to realize the point to multi-point broadcasting secure transmission in both angle and range dimension. In the first stage, the beamforming vector is designed to maximize the artificial noise (AN) power, while satisfying the power requirement of LUs for transmitting the confidential message simultaneously. In the second stage, the AN projection matrix is obtained by maximizing signal-to-interference-plus-noise ratio (SINR) at the LUs. The proposed scheme only broadcasts the confidential message to the locations of LUs while the other regions are covered by AN, which promotes the security of the wireless broadcasting system. Moreover, it is energy efficient since the power of each LU is under accurate control. Numerical simulations are presented to validate the performance of the proposed scheme.

Wireless local area networks (WLANs) offer a promising role in the fourth-generation heterogeneous wireless networks. This requires efficient and timely switching of a mobile node's connection (called vertical handover) from cellular network to WLAN. Existing methods to initiate vertical handover do not fully utilize the WLAN potential and result in switching to cellular networks even when a WLAN network is available. We propose a hybrid approach to determine vertical handover timing with a goal to maximize the utilization of WLAN resources, while maintaining a low probability of handover failure. Simulation results indicate the proposed technique showing better performance in terms of number of ping-pong events and handover dropping probability as compared to existing techniques which are based on mean RSS, FFT and adaptive threshold.

A geometric features-based filtering technique, named as the adaptive geometric features based filtering technique (AGFF), is presented for removal of impulse noise in corrupted color images. In contrast with the traditional noise detection techniques where only 1-D statistical information is used for noise detection and estimation, a novel noise detection method is proposed based on geometric characteristics and features (i.e., the 2-D information) of the corrupted pixel or the pixel region, leading to effective and efficient noise detection and estimation outcomes. A progressive restoration mechanism is devised using multipass nonlinear operations which adapt to the intensity and the types of the noise. Extensive experiments conducted using a wide range of test color images have shown that the AGFF is superior to a number of existing well-known benchmark techniques, in terms of standard image restoration performance criteria, including objective measurements, the visual image quality, and the computational complexity.

An Adaptive geometric features based filtering (AGFF) technique with a low computational complexity is proposed for removal of impulse noise in corrupted color images. The effective and efficient detection is based on geometric characteristics and features of the corrupted pixel and/or the pixel region. A progressive restoration mechanism is devised using multi-pass non-linear operations. Through extensive experiments conducted using a wide range of test color images, the proposed filtering technique has demonstrated superior performance to that of well-known benchmark techniques, in terms of objective measurements, the visual image quality and the computational complexity.

Soft handoff in WCDMA systems allows multi connection between the user and base stations during handoff, in contrast to single connection in hard handoff. But multi connection flexibility leads to a trade-off between quality of service for the user and the system downlink capacity. The heterogeneous wireless networks consist of WCDMA and WLAN systems, which operate at different frequency with no direct interference. Therefore, a vertical soft handoff between downlink shared channels from WCDMA and WLAN will not suffer similar side effects as the horizontal soft handoff in WCDMA systems. In this paper, we present an analytical framework for vertical soft handoff and propose a context-aware vertical soft handoff algorithm (CAVSH) for heterogeneous wireless networks. CAVSH considers four user and system context parameters such as user required bandwidth, user traffic cost, access network utilization, and signal to interference-and-noise ratio (SINR). The results show that the proposed CAVSH can provide the system with lower dropping probability, lower average cost to the user and higher throughput, as compared with vertical hard handoff.

Next generation heterogeneous wireless networks offer the end users with assurance of QoS inside each access network as well as during vertical handoff between them. For guaranteed QoS, the vertical handoff algorithm must be QoS aware, which cannot be achieved with the use of traditional RSS as the vertical handoff criteria. In this paper, we propose a novel vertical handoff algorithm which uses received SINR from various access networks as the handoff criteria. This algorithm consider the combined effects of SINR from different access networks with SINR value from one network being converted to equivalent SINR value to the target network, so the handoff algorithm can have the knowledge of achievable bandwidths from both access networks to make handoff decisions with QoS consideration. Analytical results confirm that the new SINR based vertical handoff algorithm can consistently offer the end user with maximum available bandwidth during vertical handoff contrary to the RSS based vertical handoff, whose performance differs under different network conditions. System level simulations also reveal the improvement of overall system throughputs using SINR based vertical handoff, comparing with the RSS based vertical handoff.

In the next generation multimedia wireless network environment that consists of heterogeneous access technologies, we need to offer the end user with multimedia QoS inside each access network as well as during vertical handoff between them. The vertical handoff algorithm have to be QoS aware, which cannot be achieved by using the traditional RSS as the vertical handoff criteria. In this paper, we propose a new vertical handoff algorithm using the receiving SINR from various access networks as the handoff criteria. By converting the different receiving SINR values, the handoff algorithm can have the knowledge of achievable bandwidths from both access networks, and make handoff decisions with multimedia QoS consideration. Analysis results confirms that the new SINR based vertical handoff algorithm is able to consistently offer the end user with maximum available bandwidth during vertical handoff comparing with the RSS based vertical handoff, whose performance differs under different network conditions.

In this paper, we discuss the issue of delay-throughput tradeoff from providing end-to-end delay guarantee multicast service in wireless ad hoc network. Efforts are made to develop a Delay Constraint Multicast (DCM) routing protocol, focused on constructing a delay based multicast tree, which is able to provide soft end-to-end delay guarantees for all multicast receivers. Forwarding decisions are made based on local access delay and QoS information from a source node, resulting in a high ratio of timely delivered packets. Based on simulation results, DCM is able to deliver data packets with average latency right below the delay constraint while keeping communication overhead at minimum.

A robust structure-adaptive hybrid vector filter is proposed for digital color image restoration in this paper. At each pixel location, the image vector (i.e., pixel) is first classified into several different signal activity categories by applying a modified quadtree decomposition to luminance component (image) of the input color image. A weight-adaptive vector filtering operation with an optimal window is then activated to achieve the best tradeoff between noise suppression and detail preservation. Through extensive simulation experiments conducted using a wide range of test color images, the filter has demonstrated superior performance to that of a number of well known benchmark techniques, in terms of both standard objective measurements and perceived image quality, in suppressing several distinct types of noise commonly considered in color image restoration, including Gaussian noise, impulse noise, and mixed noise.

A novel window adaptive hybrid filter for the removal of different types of noise which contaminate color images is proposed. At each pixel location, the image vector is first classified into several different signal activity areas through a modified quadtree decomposition on the luminance of the input image, with only one empirical parameter required to be controlled. Then, an optimal window and weight adaptive vector filtering operation is activated for the best tradeoff between noise suppression and detail preservation. The proposed filter has demonstrated superior performance in suppressing several distinctive types of color image noise, which include Gaussian, impulse, and mixed noise. Significant improvements have been achieved in terms of standard objective measurements as well as the perceived image quality.

In this paper we present a robust and efficient switch-based filtering technique that makes use of a multiple window noise detection scheme. The proposed method performs exceptionally well for both impulse and Gaussian type noise, with a minimum amount of computational expense incurred. All parameters required for the MWC detection are trained off-line using a maximum-likelihood estimator, so no a prior knowledge of the noise type or image characteristics are required. As the results show, the new technique demonstrates a marked performance gain over existing state of the art methods.

Traffic predictions have been demonstrated with the capability to improve network efficiency and QoS in broadband ATM networks. Recent research shows that fuzzy logic prediction outperforms conventional autoregression predictions. The application of fuzzy logic also has a potential to control traffic more effectively. In this paper, we propose the use of the fuzzy logic prediction on connection admission control (CAC) and congestion control on high speed networks. We first modeled traffic characteristics using an on-line fuzzy logic predictor on CAC. Simulation results show that fuzzy logic prediction improves the efficiency of both conventional and measurement-based CAC. In addition, the measurement-based approach incorporating fuzzy logic inference and using fuzzy logic prediction is shown to achieve higher network utilization while maintaining QoS. We then applied the fuzzy logic predictor to congestion control in which the ABR queue is estimated one round-trip in advance. Simulation results show that the fuzzy logic control scheme significantly reduces convergence time and overall buffer requirements as compared with conventional schemes.

This paper presents some studies on the Internet TCP/IP traffic over ATM unspecified bit rate (UBR) and available bit rate (ABR) classes of service. In both cases, fuzzy logic prediction has been used to improve the efficiency and fairness of traffic throughput. For TCP/IP over UBR, a novel fuzzy logic based cell dropping scheme is presented. This is referred to as fuzzy logic selective cell drop (FSCD). A key feature of the scheme is its ability to accept or drop a new incoming packet dynamically based on the predicted future buffer condition in the switch. This is achieved by using fuzzy logic prediction for the production of a drop factor. The packet dropping decision is then based on this drop factor and a predefined threshold value. Simulation results show that the proposed scheme significantly improves the TCP efficiency and fairness. To study TCP/IP over ABR, we applied the fuzzy logic ABR service buffer management scheme from our previous work to both approximate and exact fair rate computation ER switch algorithms. We then compared the performance of the fuzzy logic control with conventional schemes. Simulation results show that on zero TCP packet loss, the fuzzy logic control scheme achieves maximum efficiency and perfect fairness with a smaller buffer size. When mixed with VBR traffic, the fuzzy logic control scheme achieves a higher efficiency with lower cell loss.

A novel method is proposed for image interpolation. It is assumed that the pixel correlation between local regions across scales would remain similar. In addition, this a priori similarity could be extracted from a set of available image data that have the same content but different resolutions. A simple architecture is devised to estimate the correlation efficiently, which is then used to predict the unknown pixel values in a high-resolution image. Evaluation shows a promising performance of the proposed algorithm.

This paper presents a novel measurement-based connection admission control (CAC) which uses fuzzy set and fuzzy logic theory. Unlike conventional CAC, the proposed CAC does not use complicated analytical models or a priori traffic descriptors. Instead, traffic parameters are predicted by an on-line fuzzy logic predictor (Qiu et al. 1999). QoS requirements are targeted indirectly by an adaptive weight factor. This weight factor is generated by a fuzzy logic inference system which is based on arrival traffic, queue occupancy and link load. Admission decisions are then based on real-time measurement of aggregate traffic statistics with the fuzzy logic adaptive weight factor as well as the predicted traffic parameters. Both homogeneous and heterogeneous traffic were used in the simulation. Fuzzy logic prediction improves the efficiency of both conventional and measurement-based CAC. In addition, the measurement-based approach incorporating fuzzy logic inference and using fuzzy logic prediction is shown to achieve higher network utilization while maintaining QoS.

This paper proposes a novel postprocessing technique for reducing blocking artifacts in low-bit-rate transform-coded images. The proposed approach works in the transform domain to alleviate the accuracy loss of transform coefficients, which is introduced by the quantization process. The masking effect in the human visual system (HVS) is considered, and an adaptive weighting mechanism is then integrated into the postfiltering. In low-activity areas, since blocking artifacts appear to be perceptually more detectable, a large window is used to efficiently smooth out the artifacts. In order to preserve image details, a small mask, as well as a large central weight, is employed for processing those high-activity blocks, where blocking artifacts are less noticeable due to the masking ability of local background. The quantization constraint is finally applied to the postfiltered coefficients. Experimental results show that the proposed technique provides satisfactory performance as compared to other postfilters in both objective and subjective image quality.

This paper presents a novel closed-loop traffic controller which is based on fuzzy set and fuzzy logic theory. The proposed controller has stable and robust operations under long round-trip delays and it does not use complicated analytical methods. A key feature of the controller is its ability to target link utilization dynamically based on the predicted future buffer condition in the switch. This is achieved by using fuzzy logic target utilization and fuzzy logic prediction. The prediction estimates the queue length one round-trip delay ahead. The predicted queue length, together with the queue growth rate and current queue length are used to produce a target utilization factor. The proposed fuzzy logic traffic control scheme is applied to both approximate and exact fair rate computation switch algorithms. The performance of fuzzy logic traffic control scheme is then compared with conventional schemes. Simulation results show that the fuzzy logic control scheme significantly reduces convergence time and overall buffer size requirements. It also exhibits lower queueing delay, delay variation and cell loss ratio.

A fuzzy logic based scheme aimed at the provision and maintenance of optimum queue length for the ABR class buffer is proposed and analysed. The investigation is focused under conditions of heavy offered load and long propagation delays which exist in MAN and WAN. A fuzzy logic predictor is proposed for an ATM switch to estimate the output queue length. This information together with the current queue length and growth rate is provided to a fuzzy inference system that generates an additional traffic rate factor. This factor can be used alone to increase/decrease ABR source delivery rate, or in conjunction with other congestion avoidance and control algorithms such as explicit rate indication for congestion avoidance (ERICA) to calculate ABR traffic bandwidth allocation and the explicit rate (ER) field in backward RM (BRM) cells. Simulation results indicate that this scheme improves the QoS performance of ABR and other real-time service classes. Since the fuzzy systems involved are all instantaneously functional, there is no need for lengthy training process like some neural network systems and the scheme is not affected by different classes and class combinations of traffic. With the implementation of this algorithm, both the efficiency and QoS can be improved for heavily loaded metropolitan/wide area network.

The design of a neural network configuration for object recognition is described. Recognition is achieved by determining the type and angle of orientation of the scene object. Supervised networks configured as a conventional classifier and three variations of a fuzzy classifier are investigated. Their performances are evaluated with the reference of correlation coefficients. Results demonstrate the superiority of the fuzzy neural network designs for predictive accuracy compared to the conventional neural network classifier. All network configurations yielded correct object angles.>