Abstract The prompt and accurate detection of brain tumours is essential for disease management and life‐saving. This paper introduces an efficient and robust completely automated system for classifying the three prominent types of brain tumour. The aim is to contribute for enhanced classification accuracy with minimum pre‐processing and less inference time. The power of deep networks is thoroughly investigated, with and without transfer learning. Fine‐tuned deep Residual Networks (ResNets) with depth up to 101 are introduced to manage the complex nature of brain images, and to capture their microstructural information. The proposed residual architectures with their in‐depth representations are evaluated and compared to other fine‐tuned networks (AlexNet, GoogLeNet and VGG16). A novel Convolutional Network (ConvNet) built and trained from scratch is also proposed for tumour type classification. Proven models are integrated by combining their decisions using majority voting to obtain the final classification accuracy. Results show that the residual architectures can be optimized efficiently, and a noticeable accuracy can be gained with them. Although ResNet models are deeper than VGG16, they show lower complexity. Results also indicate that building ensemble of models is a successful strategy to enhance the system performance. Each model in the ensemble learns specific patterns with certain filters. This stochastic nature boosts the classification accuracy. The accuracies obtained from ResNet18, ResNet101, and the proposed ConvNet are 98.91%, 97.39% and 95.43%, respectively. The accuracy based on decision fusion for the three networks is 99.57%, which is better than those of all state‐of‐the‐art techniques. The accuracy obtained with ResNet50 is 98.26%, and its fusion with ResNet18 and the designed network yields a 99.35% accuracy, which is also better than those of previous methods, meanwhile achieving minimum detection time requirements. Finally, visual representation of the learned features is provided to understand what the models have learned.

Quaternion algebra has been used to apply the fractional Fourier transform (FrFT) to color images in a comprehensive approach. However, the discrete fractional random transform (DFRNT) with adequate basic randomness remains to be examined. This paper presents a novel multistage privacy system for color medical images based on discrete quaternion fractional Fourier transform (DQFrFT) watermarking and three-dimensional chaotic logistic map (3D-CLM) encryption. First, we describe quaternion DFRNT (QDFRNT), which generalizes DFRNT to handle quaternion signals effectively, and then use QDFRNT to perform color medical image adaptive watermarking. To efficiently evaluate QDFRNT, this study derives the relationship between the QDFRNT of a quaternion signal and the four components of the DFRNT signal. Moreover, it uses the human vision system’s (HVS) masking qualities of edge, texture, and color tone immediately from the color host image to adaptively modify the watermark strength for each block in the color medical image using the QDFRNT-based adaptive watermarking and support vector machine (SVM) techniques. The limitations of watermark embedding are also explained to conserve watermarking energy. Second, 3D-CLM encryption is employed to improve the system’s security and efficiency, allowing it to be used as a multistage privacy system. The proposed security system is effective against many types of channel noise attacks, according to simulation results.

Non‐orthogonal multiple access (NOMA) has been integrated with beamspace multi‐input multi‐output (MIMO) to enhance system spectrum efficiency (SE) by serving more than one user per dedicated radio frequency (RF) chain. However, balancing the system performance with significant RF reduction is still challenging. In this study, the authors propose beamspace MIMO‐NOMA system based on signal alignment (SA) concept, where they will be able to tackle the issue of hardware complexity with a significant performance. Spectrum and energy efficiencies are analysed through two main stages. First, the excess degrees‐of‐freedom of beamspace MIMO‐NOMA are exploited by SA to suppress the inter‐beam/pair interference through designing user detection vectors and precoding matrix. Accordingly, a significant RF‐chains reduction is provided. Second, power allocation coefficients are evaluated upon the optimal SE in order to mitigate intra‐beam/pair interference. Moreover, the authors derive a tight closed formula for optimal SE based on Karush‐Kuhn‐Tucker analysis, which is validated by a heuristic‐based optimal solution. Simulation results show a superior performance gain over orthogonal multiple access technique. Furthermore, the Monte‐Carlo numerical solution depicts the marginal performance gap between the analytical and heuristic‐based optimisation approach. This confirms the accuracy and rigidity of the proposed system.

In future cellular 5G, the network operators have recognised the spectrum scarcity as one of the major problems. Therefore, expanding or even re‐utilising the current bandwidth requires an advanced technique to accommodate the enormous communicating devices. In this paper, energy efficiency (EE) maximization is jointly carried out with respect to the following design parameters: base station density, number of users, number of attached antennas, and power control coefficient based on analytical channel estimates and feasible pilot reuse. Although dense network performance is restricted to the accumulation of both user and inter‐cell interferences, the reasons of mutual selection among the optimal design parameters will be clearly discussed to discover their effects on mitigating interference. Simulation results validate that the diversity of the design parameters achieves the maximum EE given a predefined quality of service constraints. Also, the study of hardware distortion will expose the relevant influence on the optimised EE. Moreover, the results will be extended to study the energy consumption in terms of optimised design variables. Finally, our results will be confirmed through a fair comparison with the alternating optimisation based on Monte Carlo simulation, wherein, our proposal shows a reality and fast convergence.

The authors propose efficient hybrid error resilience and error concealment (ER‐EC) algorithms for H.264 3D video‐plus‐depth (3DV + D) transmission over error‐prone channels. At the encoder, content‐adaptive pre‐processing ER mechanisms are implemented by applying the context adaptive variable length coding (CAVLC), the slice structured coding, and the explicit flexible macro‐block ordering. At the decoder, a post‐processing EC algorithm with multi‐proposition schemes is implemented to recover the lost 3DV colour frames. The convenient EC hypothesis is adopted based on the lost macro‐blocks size mode, the faulty view, and the frame types. For the recovery of the lost 3DV depth frames, an encoder‐independent decoder‐dependent depth‐assisted EC algorithm is suggested. It exploits the previously estimated colour disparity vectors (DVs) and motion vectors (MVs) to estimate more additional depth‐assisted MVs and DVs. After that, the optimum colour‐plus‐depth DVs and MVs are accurately selected by employing the directional interpolation EC algorithm and the decoder MV estimation algorithm. Finally, a weighted overlapping block motion and disparity compensation scheme is utilised to reinforce the performance of the proposed hybrid ER‐EC algorithms. Experimental results on standard 3DV + D sequences show that the proposed hybrid algorithms have superior objective and subjective performance indices.

The high efficiency video coding (HEVC) partial encryption (PE) technique depends on encrypting the highly sensitive data on the video bit stream. The HEVC PE technique should keep the video format compliance, should be of the same bit rate, and ensure real-time constraints. The paper suggests an effective RC6 HEVC PE technique which encrypts sensible video data bits with low complexity overhead, fast encoding time for real-time applications, and fixed HEVC bitrate. These features result from using the low computational complexity RC6 block cipher for encrypting the selective video bins. The proposed RC6 HEVC PE encrypts the discrete cosine transform (DCT) coefficients sign bit, the DCT remaining absolute values suffixes that are binarized by Exp-Golomb (EGk) order zero, the motion vector difference (MVD) sign bits, and MVD absolute values suffixes that are binarized by EGk order one. Also, this paper introduces experimental results that compare between the proposed RC6 HEVC PE and HEVC PE algorithms that use the Advanced Encryption Standard in different operation modes. This paper presents more details about the security analysis of RC6 HEVC PE including encryption quality test, key space test, statistical analysis such as histogram and correlation coefficient analysis, and sensitivity analysis such as the key sensitivity analysis. The achieved test results ensured and confirmed the security, reliability, and robustness of RC6 HEVC PE technique.

This study investigates the performance of multicarrier delay diversity modulation (MDDM) systems with both cyclic delay diversity and space–time Trellis code (STTC) techniques and compares its performance with conventional MDDM systems. Deploying STTCs can allow cost efficient and flexible system deployment compared with classical MDDM systems with multiple cyclic delays. In this study, the authors’ propose MDDM systems with both cyclic delay and STTCs. The MDDM system is modelled for two and four transmit antennas. In this study, they compare the performance of the proposed MDDM systems with quadrature phase shift keying (QPSK), 8 phase shift keying (8PSK) and 16 quadrature amplitude modulation (16QAM) STTCs and compare its results with conventional MDDM systems. The noise variance of the received signals at the MDDM receiver is mathematically derived. The minimum mean square error technique for channel estimation is applied to the proposed MDDM systems. Simulation results demonstrate that the proposed MDDM systems enhance the performance of classical MDDM systems and give large coding gains compared with the classical case.

Orthogonal frequency division multiplexing (OFDM) is a method of encoding digital data on multiple carrier frequencies. OFDM has developed into a popular scheme for wide‐band digital communication. Despite its advantages, it has a major drawback of its high peak‐to‐average power ratio (PAPR) value which degrades its efficiency and increases its cost. In this study, two proposed systems are discussed to reduce the PAPR value. They depend on a signal conversion to an approximated triangle signal by means of a proposed Wizard amplitude shaping encoder. The whole characteristics mathematical analysis are presented for the proposed systems. In addition, the complexity evaluations, reliability, in‐band distortion; in terms of error vector magnitude, time and frequency domain behaviours are explained. The two proposed systems are compared with the conventional OFDM system in terms of PAPR and bit error rate under additive white Gaussian noise channel and multipath fading channels. Furthermore, the impacts of the proposed schemes design parameters, are studied.

This paper presents an efficient technique for sharpening of Misrsat-1 data using superresolution (SR) methods and fusion methods. Due to the difference in spectral characteristics between bands 1 and 3 and the panchromatic (PAN) band of Misrsat-1, we implement SR on high details of these bands and use the resulting image to sharpen the bands of the multispectral (MS) image. Several SR methods are tested and compared in this paper for this purpose. The first class of methods uses spatial-domain SR, in which SR is performed on the high-pass details extracted from bands 1 and 3 and the PAN band. The superresolved high-pass details are used after that to enhance the spatial resolution of the MS data using the high-pass filter fusion method. The second class of methods depends on the interpolation of coefficients in the high-frequency subbands of a multiscale representation of bands 1 and 3 and the PAN band and an additive fusion method to add the high-frequency subband coefficients to different bands of the MS image. A comparison study between different SR methods belonging to the aforementioned classes such as nonuniform interpolation (NUI), projection onto convex sets (POCS), iterative back projection (IBP), structure-adaptive normalized convolution (SANC), and adaptive steering kernel regression (ASKR) is presented. The simulation results show that iterative SR methods such as IBP and POCS produce more noise than interpolation methods such as NUI, SANC, and ASKR. The results also reveal that combining the ASKR with a multiscale decomposition enhances the signal-to-noise ratio.

Cognitive Radio (CR) technology is one of the strong candidate technologies to solve the spectrum scarcity problems. In this paper, we tackle the problem of secure data transmission between a secondary user transmitter and receiver through a relay in the presence of an eavesdropper in a cognitive radio network. The proposed scheme selects the best Decode-and-Forward relay among different relays to assist the transmitter, and to maximize the achievable secrecy rate without harming the primary user. Simulation results show that the secrecy capacity of the network using this scheme will almost be double the capacity when selecting the conventional scheme of relay selection.

In this study, the physical layer security for cognitive radio network (CRN) will be investigated in which a secondary user transmitter (SU-Tx) sends confidential information to a SU receiver (SU-Rx) on the same frequency band of a primary user (PU) in the presence of an eavesdropper receiver. Moreover, relay selection scheme is proposed for the security constrained CRNs with single eavesdropper, multiple eavesdroppers and PUs. The proposed scheme selects a trusted decode and forward relay to assist the SU-Tx and maximise the achievable secrecy rate that is subjected to the interference power constraints at the PUs for the different number of eavesdroppers and PUs under available channel knowledge. The SU cooperates with relays only when a high secrecy rate is achieved. Secrecy rate and secrecy outage probability are the two performance metrics that are used to verify the effectiveness of the proposed scheme although asymptotic approximations of the secrecy outage probability are also derived. Simulation and analytical results demonstrate that the performance improvement of the proposed scheme reaches to the double relative to the conventional scheme for the secrecy capacity.