Breast cancer is a highly complex disease that requires precise molecular subtyping to guide tailored treatment strategies. In this study, we employed a marker-based watershed segmentation technique on a breast cancer dataset, enabling the extraction of essential morphometric parameters. These included area, perimeter, circularity, maximal and minimal calipers, and eccentricity, along with hematoxylin and diaminobenzidine (DAB) staining characteristics for individual cells, nuclei, and cytoplasm. We utilized Support Vector Machine (SVM) and Random Forest (RF) models to classify molecular biomarker response scores to identify their molecular subtypes, leveraging these extracted features as discriminative factors. The dataset comprised whole-slide images (WSI) annotated with Progestin Receptors (PR) molecular biomarker response scores, categorizing cell regions into different classes: "other", "tumor: negative", "tumor: +1", "tumor: +2", and "tumor: +3". These detailed annotations enhanced the AI-driven classification of breast cancer molecular biomarkers response score detection on cell level. Performance evaluation of the proposed framework demonstrated substantial classification accuracy, with SVM achieving over 93% in precision, recall, F1-score, and overall accuracy, while RF exceeded 96% across these metrics. The study's findings highlight the efficacy of integrating marker-based watershed segmentation with morphometric and staining analysis for precise breast cancer molecular biomarkers response score classification. This approach provides deeper insights into tumor heterogeneity, reinforcing the importance of incorporating morphometric and staining parameters in molecular biomarkers response score classification and hence improved personalized treatment and prognosis.

Abstract The enhancement of Intrusion Detection Systems (IDS) is required to ensure protection of network resources and services. This is a hot research topic, especially in the presence of advanced intrusions and attacks. This paper provides a comparison between Distributed Cumulative Histogram (DCH) as a Feature Selection (FS) technique, Information Gain Ratio (IGR) FS and wrapper-based FS in terms of accuracy and Root Mean Square Error (RMSE). The utilization of DCH of the traffic instances in normal and attack cases allows us to compare the traffic charts. We can observe the difference between effective features and less effective ones. We verify the feasibility of using DCH as an FS technique in the field of anomaly detection with just six selected features giving more accurate results with most classifiers compared to the IGR and wrapper-based FS. We applied our experiments on the modern UNSW dataset with the WEKA simulation platform that contains a group of classification, feature reduction and selection techniques.

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.

Remote healthcare and telemedicine technology have witnessed a large and rapid development in the last decade with the large development of the Internet of Things (IoT) technology, where various types of medical sensors are aggregated for measuring medical parameters and transmitting them anywhere. Smart portable products can now be used to monitor different medical aspects to track human health. Also, they can be used in the prediagnosis of various diseases and in detecting abnormalities of organ functionality. In this article, we design and implement a multifunction and portable health monitoring system, which can help in daily medical inspections. The developed system monitors various medical aspects: heart rate (HR), blood oxygen saturation level (SpO2), body temperature, photoplethysmography (PPG) signal, electrocardiography (ECG) signal, room temperature, and room humidity. The obtained measurements are displayed on the built-in display or transmitted over Wi-Fi to either a mobile application, in the local mode, or to the cloud storage for remote monitoring. The developed system can be used to keep an eye on the people we need to care about, while keeping them in their normal daily life. The maximum error percentage of the proposed system is reported as 2.67%, 2.04%, and 1.58% for HR, SpO2, and body temperature, respectively, compared to commercial devices. In addition, statistical tests were performed and they showed a high level of agreement between the observed and the reference measurements. The results indicate the high accuracy and effectiveness of the proposed system to be used in daily medical applications.

Abstract Brain tumor is an acute cancerous disease that results from abnormal and uncontrollable cell division. Brain tumors are classified via biopsy, which is not normally done before the brain ultimate surgery. Recent advances and improvements in deep learning (DL) models helped the health industry in getting accurate diseases diagnosis. This article concentrates on the classification of magnetic resonance (MR) images. The objective is to differentiate between glioma tumors, meningioma tumors, pituitary tumors, and normal cases. Four deep convolutional neural networks are considered and compared in this article. These networks are inceptionresnetv2, inceptionv3, transfer learning, and BRAIN‐TUMOR‐net. A transfer‐learning strategy is considered to enhance the performance of pre‐trained models and save the time of training. The used dataset is the brain tumor magnetic resonance imaging dataset. It contains four classes including 826 MR images for glioma tumor, 822 MR images for meningioma tumor, 827 MR images for pituitary tumor, and 835 MR images for normal cases. Due to the limited number of images, we use the augmentation strategy to enlarge the size of the dataset. 75% of the data are considered for training and the other 25% are considered for testing. Segmentation of the classified results is performed. Simulation results prove that the DL model from scratch obtains the highest performance with the augmented data. In addition, a new practical implementation is presented for the proposed models.

In wireless radio communication systems, equalisation is one of the most important algorithms to improve the bit‐error‐rate performance. The linear zero‐forcing equalisers suffer from noise enhancement. The linear minimum mean square error equalisers suffer from large complexity and require the estimation of the signal‐to‐noise ratio to work properly. In this study, the authors propose a joint low‐complexity regularised zero‐forcing equaliser with successive interference cancellation (JLRZF–SIC) based on discrete cosine transform (DCT) for orthogonal frequency division multiplexing (OFDM) systems. The proposed JLRZF–SIC scheme jointly performs the equalisation and carrier frequency offset (CFO) compensation with lower‐complexity using the banded‐matrix approximation concept. Simulation results show the important role of the proposed JLRZF–SIC scheme is to improve the system performance compared to the other equalisation schemes.

The possibility of terahertz imaging in medical applications is investigated by the design and implementation of an electromagnetic system. Numerical analysis based on the transmission line matrix method is used to obtain the shape or form of the biological object. The effect of different discretization parameters on the convergence of the transmission line matrix method is studied in detail. Exact and efficient dielectric profile image reconstructions of three dimension lossy scatterers from different complex cross sections using synthetic scattered field data are presented. The influence of antenna spacing and the suitability of the simplified transmission line matrix model for system evaluation are examined.

Cognitive radio (CR) has been proposed for spectral efficiency improvement while avoiding interference with licensed users. The offset quadrature amplitude modulation‐based filter bank multicarrier (OQAM‐FBMC) modulation is a promising candidate for CR‐based systems. Although it behaves better in many aspects than orthogonal frequency division multiplexing (OFDM), the application of some techniques with FBMC becomes more challenging due to the imaginary interference, as in the case of multiple‐input multiple‐output (MIMO) technique. Here, the authors first propose a new MIMO‐based FBMC transceiver structure for CR systems. The proposed structure is based on QAM transmission to handle the interference presented in conventional OQAM‐FBMC systems. The authors also introduce two different methods to satisfy the orthogonality conditions and cancel the residual interference in QAM‐FBMC systems. Both methods are based on discrete cosine transform (DCT) to achieve superior spectrum confinement and hence better spectral efficiency. Moreover, the authors present a resource allocation algorithm for the proposed structure. Simulation results demonstrate that the proposed structure outperforms the conventional FBMC‐based MIMO techniques in terms of bit error rate (BER) and computational complexity. The results also show that the spectral efficiency of the proposed structure could be further improved by applying the proposed resource allocation algorithm.

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.

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.

Due to their noise amplification, conventional Zero-Forcing (ZF) equalizers are not suited for interference-limited environments such as the Single-Carrier Frequency Division Multiple Access (SC-FDMA) in the presence of Carrier-Frequency Offsets (CFOs) . Moreover, they suffer increasing complexity with the number of subcarriers and in particular with Multiple-Input Multiple-Output (MIMO) systems. In this letter, we propose a Joint Low-Complexity Regularized ZF (JLRZF) equalizer for MIMO SC-FDMA systems to cope with these problems. The main objective of this equalizer is to avoid the direct matrix inversion by performing it in two steps to reduce the complexity. We add a regularization term in the second step to avoid the noise amplification. From the obtained simulation results, the proposed scheme is able to enhance the system performance with lower complexity and sufficient robustness to estimation errors.

Similar to the orthogonal frequency division multiple access (OFDMA) system, the single-carrier frequency division multiple access (SC-FDMA) system also suffers from frequency mismatches between the transmitter and the receiver. As a result, in this system, the carrier frequency offsets (CFOs) disrupt the orthogonality between subcarriers and give rise to inter-carrier interference (ICI) and multiple access interference (MAI) among users. The authors present a new minimum mean square error (MMSE) equaliser, which jointly performs equalisation and carrier frequency offsets (CFOs) compensation. The mathematical expression of this equaliser has been derived taking into account the MAI and the channel noise. A low complexity implementation of the proposed equalisation scheme using a banded matrix approximation is presented here. From the obtained simulation results, the proposed equalisation scheme is able to enhance the performance of the SC-FDMA system, even in the presence of estimation errors.

Single-carrier frequency division multiple access (SC-FDMA) has been adopted as a possible air interface for future wireless networks. It combines most of the advantages of orthogonal frequency division multiple access (OFDMA) and the low peak-to-average-power ratio (PAPR) of single-carrier transmission. This study proposes a new transceiver scheme for SC-FDMA systems implementing the wavelet transform to decompose the transmitted signal into approximation and detail components. The approximation component can be clipped or companded whereas the detail component is left unchanged because of its sensitivity to noise. Wavelet filter banks at the transmitter and the receiver demonstrate the ability to reduce the distortion in the reconstructed signal while retaining all the significant features present in the signal. The performance of the proposed scheme is investigated with different PAPR reduction methods. Simulation results show that the proposed scheme with the hybrid clipping and companding method provides a significant performance enhancement when compared with the conventional SC-FDMA system, while the complexity of the system is slightly increased.

A hybrid receiver scheme for downlink code division multiple access (CDMA) systems over frequency selective channels is proposed. The proposed receiver combines a linear regularised zero forcing (RZF) equaliser and a parallel interference cancellation scheme with a tanh decision function (TPIC). It is called the RZF-TPIC receiver. The RAKE receiver is used to reduce the channel effects and obtain an initial estimate of the data. Multi-stages of TPIC are then employed to mitigate the multiple access interference (MAI). At the final stage, the RZF equaliser is used to provide a better estimate of the desired user's data. The effect of the decision function used for symbol estimation in the PIC stage is investigated. The performance of the proposed scheme is evaluated and compared with the traditional RAKE receiver by computer simulations. It is found that the proposed scheme offers significant gains, even with a large number of interfering users.

The selective mapping (SLM) scheme is one of the most popular peak-to-average power ratio (PAPR) reduction techniques proposed for multi-input multi-output orthogonal frequency division multiplexing (MIMO-OFDM) systems. One of the major disadvantages of this scheme is the need for the transmission of side information (SI) bits to enable the receiver to recover the transmitted data. The authors present a small overhead SLM (s-SLM) scheme for space–time block coded (STBC) MIMO-OFDM systems. This proposed scheme improves the system bandwidth efficiency and achieves a significantly lower bit error rate (BER) than the individual SLM (i-SLM) and direct SLM (d-SLM) schemes. In addition, approximate expressions for the complementary cumulative distribution function (CCDF) of the PAPR and the average BER of the proposed s-SLM scheme are derived. The simulation results show that the proposed s-SLM scheme improves the detection probability of the SI bits and hence gives a better performance than the i-SLM and the d-SLM schemes.